Personalized health system and method of use

Abstract

A personalized health system for a non-human subject, such as a companion animal, is provided herein that utilizes a machine learning model to analyze genetic and phenotypic data of the non-human subject and make product or behavioral recommendations for the non-human subject based at least in part on the analysis. A personalized health system may include an application (App) or website for use by a guardian or health care professional of a non-human subject to monitor health and welfare of a non-human animal and receive notifications regarding recommended products or behavioral corrections. The machine learning model may also analyze environmental data, behavioral data, clinical data, and activity data to generate new recommendations for non-human subjects or improve existing recommendations.

Description

Cross-references

[0001] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 513,589, filed July 14, 2023, and U.S. Provisional Application Serial No. 63 / 608,543, filed December 11, 2023, each of which is incorporated herein by reference in its entirety. Summary of the Invention

[0002] This document provides methods, systems, and computer-readable media for using machine learning to assess one or more conditions in non-human subjects (e.g., companion animals, farm animals). Machine learning models can be applied to a genotype-phenotype profile comprised of genetic and phenotypic data of the non-human subject to identify the presence of one or more conditions in the non-human subject, or the risk of one or more conditions occurring in the non-human subject. The genetic data may include data from at least one genomic locus from a plurality of genomic loci, such as genetic variants (e.g., single nucleotide polymorphisms) that may be associated with one or more conditions. The phenotypic data may include data from at least one phenotype from a plurality of phenotypes that may be associated with one or more conditions. Data relating to other parameters, including the non-human subject's environment, behavioral traits, clinical information, etc., may also be input into the machine learning model. In some embodiments, the methods and systems of this disclosure provide recommendations for products or behavioral changes to improve, mitigate, or prevent one or more conditions in the non-human subject. The products may be nutritional products, such as food, supplements, or snacks, or any combination thereof. In some embodiments, the system disclosed herein is a computer-implemented system including a graphical user interface (GUI) configured to deliver the recommendation communication to a user of a personal electronic device, such as a guardian or healthcare professional of the non-human object, via an application (App).

[0003] The aspects disclosed herein provide a method for identifying nutritional products recommended for non-human animal subjects, the method comprising: (a) receiving genetic data at multiple genomic loci of the non-human animal subject, wherein at least one of the multiple genomic loci is associated with a first condition; (b) receiving phenotypic data associated with multiple phenotypes of the non-human animal subject, wherein at least one of the multiple phenotypes is associated with a second condition; (c) generating a genotype-phenotype profile of the non-human animal subject by processing a dataset including the genetic data and the phenotypic data to determine qualitative or quantitative measurements of the at least one of the multiple genomic loci and qualitative or quantitative measurements of at least one of the multiple phenotypes; and (d) [the method is not specified in the original text]. A machine learning predictive model is applied to the genotype-phenotype profile of the non-human animal subject to identify the recommended nutritional product for the non-human animal subject based at least in part on the probability that the non-human animal subject has: (i) a first condition or the risk of having the first condition; and (ii) a second condition or the risk of having the second condition; (e) ranking the first condition relative to the second condition at least in part based on the severity of the first and second conditions to identify the highest-ranked condition among the first and second conditions; and (f) manufacturing the nutritional product, wherein the nutritional product improves, mitigates, or prevents at least the highest-ranked condition or the risk of having at least the highest-ranked condition in the non-human animal subject. In some embodiments, the first condition or the second condition includes: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human animal subject is a feline, canine, or farm animal. In some embodiments, the non-human animal subject is a companion animal. In some embodiments, the genetic data is determined by: (i) obtaining or having obtained a biological sample from the non-human animal subject; and (ii) performing or having performed genotyping on the biological sample. In some embodiments, the method further includes receiving the genetic data from a nucleic acid sequencing device, wherein the nucleic acid sequencing device includes a whole-genome sequencer, a skim sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the at least one genomic locus includes one or more polymorphisms associated with the first condition. In some embodiments, the method further includes receiving the phenotypic data from the guardian of the non-human animal subject, the veterinarian of the non-human animal subject, or a combination thereof. In some embodiments, the multiple phenotypes include any combination of the non-human animal subject's weight, body mass index, sex, age, or breed.In some embodiments, the method further includes: receiving activity data of the non-human animal subject; updating the genotype-phenotype profile with the activity data to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the activity data includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the method further includes: receiving environmental data of the non-human animal subject; updating the genotype-phenotype profile with the environmental data to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the environmental data includes: urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of climbing stairs, or any combination thereof. In some embodiments, the method further includes: receiving biomarker data from the non-human animal object, wherein the biomarker data includes the presence or level of one or more biomarkers detected in biological samples obtained from the non-human animal object, wherein the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, minerals, or any combination thereof; updating the genotype-phenotype profile with the biomarker data to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the machine learning prediction model includes clustering algorithms, decision tree algorithms, statistical algorithms, gradient boosting machines (GBM), or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based clustering algorithm. In some embodiments, the machine learning prediction model is a genome-optimal linear unbiased prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human animal objects belonging to the same species that have the first or second condition. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human animal objects belonging to the same species. In some implementations, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein at least one of the multiple genomic loci is associated with the first condition; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human animal subjects, wherein at least one of the multiple phenotypes is associated with the second condition.In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human animal subject, wherein the notification includes: (i) the first condition or risk of the first condition and the second condition or risk of the second condition in the non-human animal subject; (ii) the genotype-phenotype profile of the non-human animal subject; (iii) recommended nutritional products for the non-human animal subject; (iv) recommendations for behavioral modification of the non-human animal subject; (v) prescriptions for therapeutic or preventative interventions for the non-human animal subject; or (vi) any combination of (i) to (v). In some embodiments, the behavioral modification includes increasing, decreasing, or avoiding one or more activities, wherein the one or more activities (i) increase or decrease the risk of the non-human animal subject developing the first condition or the second condition, or (ii) worsen or improve the first condition or the second condition in the non-human animal subject. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting the type or quantity of the nutritional product, wherein the nutritional product includes food, supplements, or snacks; (iii) exposure to the product; (iv) use of the product; or (v) any combination of (i) to (iv). In some embodiments, the method further includes: performing (a) to (b) at multiple time points to obtain new genotype data or new phenotype data; updating the genotype-phenotype profile at the multiple time points with the new genotype data, the new phenotype data, or a combination thereof to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human animal at one or more of the plurality of time points, wherein the notification includes: (i) the first condition or risk of the first condition and the second condition or risk of the second condition in the non-human animal; (ii) an updated spectrum of the non-human animal; (iii) recommendations for products, behavior modification, or any combination thereof for the non-human animal; (iv) prescriptions for therapeutic or preventative interventions for the non-human animal; or (v) any combination of (i) to (iv).In some embodiments, the method further includes: receiving biomarker data, activity data, environmental data, behavioral data, or clinical data of the non-human animal subject; generating an updated genotype-phenotype profile of the non-human animal subject by processing the biomarker data, the activity data, the environmental data, the behavioral data, or the clinical data, or a combination thereof, to determine quantitative or qualitative measurements; and applying the machine learning prediction model to the updated genotype-phenotype profile of the non-human animal subject to identify: a new nutritional product or a new amount of the nutritional product recommended for the non-human animal subject; or behavioral modification of the non-human animal subject. In some embodiments, clinical information includes the medical history of the non-human animal subject or the medical history of the biological relatives of the non-human animal subject. In some embodiments, one or more behavioral data include chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the nutritional product includes food, supplements, or snacks, or any combination thereof.

[0004] The aspects disclosed herein provide a system configured to identify recommended nutritional products for non-human animal subjects, the system comprising: a computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program including instructions executable by the computing device to create an application, the application comprising: (a) a first module configured by the at least one processor to receive genetic data at multiple genomic loci of the non-human animal subject, wherein at least one of the multiple genomic loci is associated with a first condition; (b) a second module configured by the at least one processor to receive phenotypic data associated with multiple phenotypes of the non-human animal subject, wherein at least one of the multiple phenotypes is associated with a second condition; and (c) a third module configured to determine qualitative or quantitative measurements of at least one of the multiple genomic loci and qualitative values ​​of at least one of the multiple phenotypes by processing the genetic data and the phenotypic data by the at least one processor. (d) A fourth module, configured by the at least one processor to apply a machine learning prediction model to the genotype-phenotype profile of the non-human animal object to identify the nutritional product recommended for the non-human animal object based at least in part on the probability that the non-human animal object has: (i) the first condition or the risk of the first condition; and (ii) the second condition or the risk of the second condition; (e) a fifth module, configured by the at least one processor to rank the first condition relative to the second condition based at least in part on the severity of the first condition and the second condition to identify the highest-ranked condition among the first condition and the second condition; and (f) a sixth module, configured by the at least one processor to identify the nutritional product for manufacture, wherein the nutritional product improves, mitigates, or prevents at least the highest-ranked condition or the risk of the highest-ranked condition in the non-human animal object. In some embodiments, the first condition or the second condition includes: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human animal object is a feline, canine, or farm animal. In some embodiments, the non-human animal object is a companion animal. In some embodiments, the genetic data is determined by obtaining or acquiring biological samples from the non-human animal object.In some embodiments, the first module is configured to receive the genetic data from a nucleic acid sequencing device, wherein the nucleic acid sequencing device includes a whole-genome sequencer, a skim sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the at least one genomic locus includes one or more polymorphisms associated with the first condition. In some embodiments, the second module is configured to receive the phenotypic data from the guardian of the non-human animal subject, the veterinarian of the non-human animal subject, or a combination thereof. In some embodiments, the multiple phenotypes include any combination of the non-human animal subject's weight, body mass index, sex, age, or breed. In some embodiments, the system further includes a module configured to receive activity data of the non-human animal subject; wherein the third module is further configured to update the genotype-phenotype profile with the activity data to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile. In some embodiments, the activity data includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the system further includes a module configured to receive environmental data from the non-human animal object; wherein the third module is further configured to update the genotype-phenotype profile with the environmental data to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the system further includes a module configured to receive biomarker data from the non-human animal object, wherein the biomarker data includes the presence or level of one or more biomarkers detected in biological samples obtained from the non-human animal object, wherein the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, minerals, or any combination thereof; wherein the third module is further configured to update the genotype-phenotype profile with the biomarker data to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile. In some embodiments, the machine learning prediction model includes clustering algorithms, decision tree algorithms, statistical algorithms, gradient boosting machines (GBM), or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based clustering algorithm. In some embodiments, the machine learning prediction model is a genome best linear unbiased prediction (GBLUP) or a Bayesian variable selection model.In some embodiments, the machine learning prediction model is validated using samples from a validation cohort of non-human animal subjects belonging to the same species and exhibiting either the first or second condition. In some embodiments, the machine learning prediction model is trained using samples from a training cohort of non-human animal subjects belonging to the same species. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein at least one of the multiple genomic loci is associated with the first condition; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human animal subjects, wherein at least one of the multiple phenotypes is associated with the second condition. In some embodiments, the system further includes a module configured to transmit recommended nutritional products for the non-human animal subjects to a graphical user interface (GUI) on a user's personal electronic device. In some embodiments, the GUI is configured to display a notification to the user, wherein the user is the guardian or veterinarian of the non-human animal subject. In some embodiments, the system further includes the user's personal electronic device. In some embodiments, the notification includes: (i) the first condition or risk of the first condition and the second condition or risk of the second condition in the non-human animal subject; (ii) the genotype-phenotype profile of the non-human animal subject; (iii) a recommended nutritional product for the non-human animal subject; (iv) a recommendation for behavior modification of the non-human animal subject; (v) a prescription for a therapeutic or preventative intervention for the non-human animal subject; or (vi) any combination of (i) to (v). In some embodiments, the behavior modification includes increasing, decreasing, or avoiding one or more activities, wherein the one or more activities (i) increase or decrease the risk of the non-human animal subject developing the first condition or the second condition, or (ii) worsen or improve the first condition or the second condition in the non-human animal subject. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting the type or quantity of the nutritional product, wherein the nutritional product includes food, supplements, or snacks; (iii) exposure to the product; (iv) use of the product; or (v) any combination of (i) to (iv). In some implementations, the first and second modules are further configured to receive the gene data and the phenotypic data at multiple time points to obtain new genotype data or new phenotypic data; wherein the third module is further configured to update the genotype-phenotype profile with the new genotype data, the new phenotypic data or a combination thereof at the multiple time points to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile.In some embodiments, the system further includes a module configured to transmit recommended nutritional products for the non-human animal object to a graphical user interface (GUI) on a user's personal electronic device. In some embodiments, the GUI is configured to display a notification to the user, wherein the user is the guardian or veterinarian of the non-human animal object. In some embodiments, the notification includes: (i) the first condition or risk of the first condition and the second condition or risk of the second condition in the non-human animal object; (ii) the updated spectrum of the non-human animal object; (iii) recommendations for products, behavior modification, or any combination thereof for the non-human animal object; (iv) prescriptions for therapeutic or preventative interventions for the non-human animal object; or (v) any combination of (i) to (iv). In some embodiments, the system further includes: a module configured to receive biomarker data, activity data, environmental data, behavioral data, or clinical data of the non-human animal subject; wherein the third module is further configured to generate an updated genotype-phenotype profile of the non-human animal subject by processing the biomarker data, the activity data, the environmental data, the behavioral data, or the clinical data, or a combination thereof, to determine quantitative or qualitative measurements thereof; and wherein the fourth module is further configured to apply the machine learning prediction model to the updated genotype-phenotype profile of the non-human animal subject to identify: a new nutritional product or a new amount of the nutritional product recommended for the non-human animal subject; or behavioral correction for the non-human animal subject. In some embodiments, the clinical data includes the medical history of the non-human animal subject or the medical history of the biological relatives of the non-human animal subject. In some embodiments, the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the nutritional product includes food, supplements, or snacks, or any combination thereof.

[0005] The aspects disclosed herein provide a non-transitory computer-readable medium including machine-executable code that, when executed by one or more computer processors, implements a method for identifying a recommended nutritional product for a non-human animal subject, the method comprising: (a) receiving genetic data at a plurality of genomic loci of the non-human animal subject, wherein at least one of the plurality of genomic loci is associated with a first condition; (b) receiving phenotypic data associated with a plurality of phenotypes of the non-human animal subject, wherein at least one of the plurality of phenotypes is associated with a second condition; and (c) generating the non-human subject by processing the genetic data and the phenotypic data to determine qualitative or quantitative measurements of the at least one of the plurality of genomic loci and qualitative or quantitative measurements of the at least one of the plurality of phenotypes. (d) Applying a machine learning prediction model to the genotype-phenotype profile of the non-human animal object to identify the nutritional product recommended for the non-human animal object based at least in part on the probability that the non-human animal object has: (i) a first condition or the risk of having the first condition; and (ii) a second condition or the risk of having the second condition; (e) ranking the first condition relative to the second condition based at least in part on the severity of the first and second conditions to identify the highest-ranked condition among the first and second conditions; and (f) identifying a nutritional product recommended for manufacture for the non-human animal object, wherein the nutritional product at least improves, alleviates, or prevents the highest-ranked condition or the risk of having the highest-ranked condition in the non-human animal object. In some embodiments, the first condition or the second condition includes: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human animal object is a feline, canine, or farm animal. In some embodiments, the non-human animal object is a companion animal. In some embodiments, the genetic data is determined by: (i) obtaining or having obtained a biological sample from the non-human animal subject; and (ii) performing or having performed genotyping on the biological sample. In some embodiments, the method further includes receiving the genetic data from a nucleic acid sequencing device, wherein the nucleic acid sequencing device includes a whole-genome sequencer, a skim sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the at least one genomic locus includes one or more polymorphisms associated with the first condition. In some embodiments, the method further includes receiving the phenotypic data from the guardian of the non-human animal subject, the veterinarian of the non-human animal subject, or any combination thereof.In some embodiments, the multiple phenotypes include any combination of the non-human animal subject's weight, body mass index, sex, age, or breed. In some embodiments, the method further includes receiving activity data from the non-human animal subject; updating the genotype-phenotype profile with the activity data to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the activity data includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the method further includes receiving environmental data from the non-human animal subject; updating the genotype-phenotype profile with the environmental data to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the method further includes receiving biomarker data from the non-human animal object, wherein the biomarker data includes the presence or level of one or more biomarkers detected in biological samples obtained from the non-human animal object, wherein the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, minerals, or any combination thereof; updating the genotype-phenotype profile with the biomarker data to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the machine learning prediction model includes clustering algorithms, decision tree algorithms, statistical algorithms, gradient boosting machines (GBM), or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based clustering algorithm. In some embodiments, the machine learning prediction model is a genome best linear unbiased prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human animal objects belonging to the same species that have the first condition or the second condition. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human animal objects belonging to the same species. In some implementations, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein at least one of the multiple genomic loci is associated with the first condition; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human animal subjects, wherein at least one of the multiple phenotypes is associated with the second condition.In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human animal subject, wherein the notification includes: (i) the first condition or risk of the first condition and the second condition or risk of the second condition in the non-human animal subject; (ii) the genotype-phenotype profile of the non-human animal subject; (iii) recommended nutritional products for the non-human animal subject; (iv) recommendations for behavioral modification of the non-human animal subject; (v) prescriptions for therapeutic or preventative interventions for the non-human animal subject; or (vi) any combination of (i) to (v). In some embodiments, the behavioral modification includes increasing, decreasing, or avoiding one or more activities, wherein the one or more activities (i) increase or decrease the risk of the non-human animal subject developing the first condition or the second condition, or (ii) worsen or improve the first condition or the second condition in the non-human animal subject. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting the type or quantity of the nutritional product, wherein the nutritional product includes food, supplements, or snacks; (iii) exposure to the product; (iv) use of the product; or (v) any combination of (i) to (iv). In some embodiments, the method further includes performing (a) to (b) at multiple time points to obtain new genotype data or new phenotype data; updating the genotype-phenotype profile at the multiple time points with the new genotype data, the new phenotype data, or a combination thereof to generate an updated profile; and applying the machine learning prediction model to the updated profile. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human animal at one or more of the plurality of time points, wherein the notification includes: (i) the first condition or risk of the first condition and the second condition or risk of the second condition in the non-human animal; (ii) the updated spectrum of the non-human animal; (iii) recommendations for products, behavior modification or any combination thereof for the non-human animal; (iv) prescriptions for therapeutic or preventive interventions for the non-human animal; or (v) any combination of (i) to (iv).In some embodiments, the method further includes: receiving biomarker data, activity data, environmental data, behavioral data, or clinical data of the non-human animal subject; generating an updated genotype-phenotype profile of the non-human animal subject by processing the biomarker data, the activity data, the environmental data, the behavioral data, or the clinical data, or a combination thereof, to determine quantitative or qualitative measurements; and applying the machine learning prediction model to the updated genotype-phenotype profile of the non-human animal subject to identify: a new nutritional product or a new amount of the nutritional product recommended for the non-human animal subject; or behavioral modification of the non-human animal subject. In some embodiments, clinical information includes the medical history of the non-human animal subject or the medical history of the biological relatives of the non-human animal subject. In some embodiments, one or more behavioral data include chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the nutritional product includes food, supplements, or snacks, or any combination thereof.

[0006] The aspects disclosed herein provide a method for identifying one or more conditions in a non-human object, the method comprising: (a) receiving genetic data at multiple genomic loci of the non-human animal object, wherein the multiple genomic loci are associated with one or more conditions; (b) receiving phenotypic data associated with multiple phenotypes of the non-human object; (c) generating a genotype-phenotype profile of the non-human object by processing the dataset to determine qualitative or quantitative measurements of at least one genomic locus of the multiple genomic loci and qualitative or quantitative measurements of at least one phenotype of the multiple phenotypes; and (d) applying a machine learning prediction model to the genotype-phenotype profile of the non-human object to identify the non-human object as having or at risk of having the one or more conditions. In some embodiments, the method further comprises determining a wellness probability score (WPS) from the genotype-phenotype profile. In some embodiments, the WPS is a numerical value indicating the probability that the non-human object has or is at risk of having the one or more conditions. In some embodiments, the method includes identifying the non-human subject as having multiple of the one or more conditions or a risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human subject is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the genetic data is determined by: (i) obtaining or having obtained a biological sample from the non-human subject; and (ii) performing or having performed genotyping on the biological sample. In some embodiments, performing or having performed the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, the analysis of the multiple DNA molecules includes whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or analysis using a DNA microarray. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions (indels).In some embodiments, the plurality of genomic loci include at least eight distinct loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an application (App) or website from which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical characteristics. In some embodiments, the physical characteristics include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the method further includes receiving clinical data from the non-human animal subject, wherein the clinical data includes a medical history or family history. In some embodiments, the medical history or family history includes: a diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes a diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the method further includes receiving behavioral data of the non-human animal subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes receiving activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an application (App) or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the method further includes receiving environmental data of the non-human subject. In some implementations, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of climbing stairs, or any combination thereof.In some embodiments, the environmental data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the guardian or veterinarian of the non-human subject. In some embodiments, the method further includes receiving biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes K-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model.In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are related to the one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting a specific food, vitamin, or supplement; (iii) ingesting a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplement, snack, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (c) at multiple time points during the lifespan of the non-human subject.In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0007] The aspects disclosed herein provide a computer-implemented system for identifying one or more conditions in a non-human object, the computer-implemented system comprising: a computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program including instructions executable by the computing device to create an application, the application comprising: (a) a first software module configured to receive one or more datasets, the datasets comprising: (i) genetic data at multiple genomic loci of the non-human object, wherein the multiple genomic loci are associated with one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the non-human object; (b) a second software module configured to generate a genotype-phenotype profile of the non-human object by processing the datasets to determine qualitative or quantitative measurements of at least one genomic locus among the multiple genomic loci and qualitative or quantitative measurements of at least one phenotype among the multiple phenotypes; and (c) a third software module configured to apply a machine learning predictive model to the genotype-phenotype profile of the non-human object to generate a WPS, wherein the WPS indicates whether the non-human object has one or more conditions or the risk of having one or more conditions. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human object has or is at risk of having one or more of the conditions. In some embodiments, the third software module is further configured to identify the non-human object as having or at risk of having multiple of the conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the computer-implemented system further includes a genotyping device configured to acquire the genetic data from a biological sample from the non-human object. In some embodiments, the genotyping device includes a sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the plurality of genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci.In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is entered into an app or website by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical characteristics. In some embodiments, physical characteristics include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the first software module is configured to receive clinical data of the non-human animal subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the first software module is configured to receive behavioral data of the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the first software module is configured to receive environmental data of the non-human animal object, wherein the environmental data includes: geographic location, home environment, activity level, frequency of activities performed, or any combination thereof. In some embodiments, the first software module is further configured to receive activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some implementations, the first software module is further configured to receive environmental data from the non-human object.In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the first software module is further configured to receive biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes: tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model is validated using biopsies from a cohort of non-human subjects that have been analyzed and interpreted as corresponding to one or more conditions predicted by the machine learning prediction model.In some embodiments, the machine learning predictive model is trained using samples from a training cohort of non-human subjects belonging to the same species. Training the machine learning predictive model involves assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, where each cluster is assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the computer-implemented system further includes a display module communicatively coupled to the computing device, wherein the display module is configured to provide notifications to a user, including a guardian or veterinarian of the non-human subject, wherein the notifications include: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is displayed to the user via a graphical user interface (GUI) of the computing device. In some embodiments, the notification is an electronic report visible to the user on the GUI. In some embodiments, the notification includes a recommendation for the behavior modification. In some embodiments, the behavior modification is related to one or more conditions. In some embodiments, the behavior modification related to one or more conditions includes increasing, decreasing, or avoiding one or more activities. In some embodiments, the activities include: (i) engaging in physical exercise; (ii) consuming specific foods, vitamins, or supplements; (iii) consuming specific amounts of the food, vitamin, or supplement; (iv) exposure to a product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation for the product, wherein the product includes nutritional products. In some embodiments, the nutritional products include foods, supplements, snacks, or any combination thereof. In some embodiments, the first software module, the second software module, and the third software module are further configured to analyze new datasets of the non-human objects at multiple time points to provide updated WPS.In some embodiments, the display module is further configured to provide the user with another notification, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human object or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human object; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human object; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a K-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model.

[0008] The aspects disclosed herein provide a method for identifying one or more conditions in a non-human subject, the method comprising: a method for implementing a personalized health system for a non-human subject, the method comprising: providing recommendations to the non-human subject at least in part based on a Health Probability Score (WPS) of the non-human subject, wherein the WPS is determined by: (a) applying a machine learning predictive model to one or more datasets comprising: (i) genetic data at multiple genomic loci of the non-human subject, and (ii) phenotypic data associated with multiple phenotypes of the non-human subject; (b) generating a genotype-phenotype profile of the non-human subject by processing the dataset to determine qualitative or quantitative measurements of at least one genomic locus among the multiple genomic loci and qualitative or quantitative measurements of at least one phenotype among the multiple phenotypes; and (c) applying a machine learning predictive model to the genotype-phenotype profile of the non-human subject to generate a WPS of the non-human subject, wherein the WPS indicates whether the non-human subject has the one or more conditions or has a risk of having the one or more conditions. In some embodiments, the WPS is a numerical value indicating the probability that the non-human subject has the one or more conditions or the risk of having the one or more conditions. In some embodiments, the recommendation includes products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human subject is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the genetic data is determined by: (a) obtaining or having obtained a biological sample from the non-human subject; and (b) performing or having performed genotyping on the biological sample. In some embodiments, performing or having performed the genotyping assay includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms.In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website from which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical fitness. In some embodiments, physical fitness includes weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the method further includes receiving clinical data from the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, diet sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family medical history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the method further includes receiving behavioral data of the non-human subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes receiving activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the method further includes receiving environmental data from the non-human object. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of climbing stairs, or any combination thereof.In some embodiments, the environmental data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the guardian or veterinarian of the non-human subject. In some embodiments, the method further includes receiving biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes: tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes K-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model.In some embodiments, the machine learning prediction model is validated using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the machine learning prediction model is trained using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort of non-human subjects, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the genetic data and phenotypic data of the training dataset are stored in a network-managed database, the network being configured to transform the raw data into a data structure suitable for input into the machine learning prediction model. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are related to the one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation for the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplement, snack, or any combination thereof. In some embodiments, the method further includes delivering a second nutritional product to the non-human subject at least in part based on an updated Health Probability Score (WPS) of the non-human subject, wherein the updated WPS is determined by iteratively performing (a) to (c) at multiple time points during the non-human subject's lifespan.In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0009] The aspects disclosed herein provide a method for identifying one or more conditions in a non-human subject, the method comprising: a method for implementing a personalized health system for a non-human subject, the method comprising: (a) determining whether the non-human subject has one or more conditions or is at risk of developing the one or more conditions by: (i) obtaining or having obtained a biological sample from the non-human subject; (ii) performing or having performed genotyping on the biological sample to generate genetic data; (iii) receiving phenotypic data of the non-human subject; and (iv) applying a machine learning predictive model to a dataset including the genetic data and the phenotypic data to determine whether the non-human subject has the one or more conditions or is at risk of developing the one or more conditions; and (b) if the non-human subject has the one or more conditions or is at risk of developing the one or more conditions, providing the non-human subject with recommendations to remedy the one or more conditions or the risk of developing the one or more conditions, and if the non-human subject does not have the one or more conditions or is at risk of developing the one or more conditions, providing the subject with another recommendation not to remedy the one or more conditions or the risk of developing the one or more conditions. In some embodiments, the method further includes calculating a Health Probability Score (WPS) based at least in part on the genetic and phenotypic data of the non-human subject. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having or experiencing one or more of the conditions. In some embodiments, the recommendation includes products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by or in any combination thereof by the non-human subject. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, another recommendation includes products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by or in any combination thereof by the non-human subject. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the method further includes identifying the non-human subject as being at risk of having or experiencing multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health status conditions, one or more dermatological conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal.In some embodiments, the companion animal is a feline or canine. In some embodiments, performing the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website from which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the dataset further includes receiving clinical data from the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the dataset further includes receiving behavioral data from the non-human subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the dataset further includes activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar.In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the dataset further includes environmental data of the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the dataset further includes biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring biological samples from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof.In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes K-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, wherein each cluster is assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are associated with the one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplements, snacks, or any combination thereof.In some embodiments, the method further includes iteratively performing (a) to (b) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0010] The aspects disclosed herein provide a method for training a machine learning model, the method comprising: (a) receiving by the machine learning model multiple training spectra obtained for a variety of non-human animals, wherein the machine learning model includes one or more parameters, wherein the multiple training spectra are associated with the genotypes and phenotypes of non-human animals among the multiple non-human animals; (b) providing recommendations indicating that the non-human animal is at risk of having one or more conditions or of having said one or more conditions; (c) receiving updated recommendations at the machine learning model; and (d) adjusting said one or more parameters of the machine learning model based on said updated recommendations, thereby training the machine learning model. In some embodiments, the method further comprises calculating a Health Probability Score (WPS) based at least in part on the genetic data and phenotypic data of the non-human object. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human object has said one or more conditions or of having said one or more conditions. In some embodiments, the recommendations include products, behavior modifications, or any combination thereof for the non-human object. In some embodiments, the products are consumed or used by the non-human object or any combination thereof. In some embodiments, the consumed products are nutritional products, supplements, snacks, or drugs. In some embodiments, another recommendation includes products, behavior modifications, or any combination thereof targeting the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the method further includes identifying the non-human subject as having multiple of the one or more conditions or at risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human subject is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, performing genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms.In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight distinct loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website from which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical fitness. In some embodiments, physical fitness includes weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the dataset further includes receiving clinical data from the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family medical history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the dataset further includes receiving behavioral data of the non-human subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the dataset further includes activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some implementations, the dataset further includes environmental data of the non-human object. In some implementations, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of climbing stairs, or any combination thereof.In some embodiments, the environmental data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the guardian or veterinarian of the non-human subject. In some embodiments, the dataset further includes biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring biological samples from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes K-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model.In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are related to the one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting a specific food, vitamin, or supplement; (iii) ingesting a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplement, snack, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (b) at multiple time points during the lifespan of the non-human subject.In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0011] The aspects disclosed herein provide a method for identifying one or more conditions in a non-human animal object, the method comprising: (a) receiving a dataset comprising: (i) genetic data at multiple genomic loci of the non-human animal object, wherein at least one of the multiple genomic loci is associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the non-human animal object; (b) generating a genotype-phenotype profile of the non-human animal object by processing the dataset to determine qualitative or quantitative measurements of the at least one genomic locus of the multiple genomic loci and qualitative or quantitative measurements of at least one phenotype of the multiple phenotypes; and (c) applying a machine learning prediction model to the genotype-phenotype profile of the non-human animal object to identify the non-human object as having or at risk of having the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human animal is a feline, canine, or farm animal. In some embodiments, the non-human animal object is a companion animal. In some embodiments, the genetic data is determined by: (i) obtaining or having obtained a biological sample from the non-human animal object; and (ii) performing or having performed genotyping on the biological sample. In some embodiments, the method further includes receiving the genetic data from a nucleic acid sequencing device, wherein the nucleic acid sequencing device includes a whole-genome sequencer, a skim sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the at least one genomic locus includes one or more polymorphisms. In some embodiments, the method further includes receiving the phenotypic data from the guardian of the non-human animal object, the veterinarian of the non-human animal object, or a combination thereof. In some embodiments, the phenotypic data includes one or more physical qualities. In some embodiments, one or more physical qualities include the non-human animal object's weight, body mass index, sex, age, or breed. In some embodiments, the method further includes: (d) receiving clinical data from the non-human animal object; (e) updating the dataset with the clinical data to generate an updated dataset; and (f) applying the machine learning model to the updated dataset. In some implementations, the clinical data includes the medical history of the non-human animal subject or the medical history of a biological relative of the non-human animal subject.In some embodiments, the method further includes: (d) receiving behavioral data of the non-human animal object; (e) updating the dataset with the behavioral data to generate an updated dataset; and (f) applying the machine learning model to the updated dataset. In some embodiments, the one or more behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes: (d) receiving activity data of the non-human animal object; (e) updating the dataset with the activity data to generate an updated dataset; and (f) applying the machine learning model to the updated dataset. In some embodiments, the activity data includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the method further includes: (d) receiving environmental data of the non-human animal object; (e) updating the dataset with the environmental data to generate an updated dataset; and (f) applying the machine learning model to the updated dataset. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the method further includes: (d) receiving biomarker data from the non-human animal object, wherein the biomarker data includes the presence or level of one or more biomarkers detected in biological samples obtained from the non-human animal object, wherein the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or minerals, or any combination thereof; (e) updating the dataset with the biomarker data to generate an updated dataset; and (f) applying the machine learning model to the updated dataset. In some embodiments, the machine learning prediction model includes clustering algorithms, decision tree algorithms, statistical algorithms, gradient boosting machines (GBM), or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based clustering algorithm. In some embodiments, the statistical prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human animal subjects belonging to the same species and exhibiting one or more of the aforementioned conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human animal subjects belonging to the same species.In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human animal subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human animal subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the behavior modification includes increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) the type or quantity of food, supplements, or snacks ingested; (iii) exposure to the product; (iv) use of the product; or (v) any combination of (i) to (iv). In some embodiments, the product is a food, supplement, or snack manufactured to improve, mitigate, or prevent one or more conditions in the non-human animal subject. In some embodiments, the method further includes: (d) iteratively performing (a) through (c) at multiple time points during the lifespan of the non-human animal subject using biomarker data, environmental data, activity data, or phenotypic data to generate an updated dataset; and (e) applying the machine learning predictive model to the updated dataset to identify the non-human subject as having or at risk of having the one or more conditions. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human animal subject at one or more of the multiple time points, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of having the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) through (iv).

[0012] The aspects disclosed herein provide a method for updating nutritional recommendations for non-human animal subjects, the method comprising: (a) providing a spectrum of the non-human animal subject on a graphical user interface (GUI) of a personal electronic device of a guardian of the non-human animal subject, wherein the spectrum includes the genotype of the non-human animal subject, wherein the genotype is associated with one or more conditions; (b) generating recommendations for nutritional products by a processor based at least in part on the spectrum in (a) to mitigate, prevent, or maintain the one or more conditions in the non-human animal subject; (c) transmitting the recommendations by the processor to the personal electronic device of the guardian of the non-human animal subject; and (d) receiving by the processor a biological analysis of the non-human animal subject. The method includes: (a) obtaining biomarker data from the sample, wherein the biomarker data includes the concentration of the analyte detected in the biological sample compared with a reference concentration of the analyte in one or more control subjects, wherein the analyte includes proteins, metabolites, sugars, lipids, hormones, vitamins, cell counts, electrolytes, or minerals; (e) automatically modifying the recommendation based on the received biomarker data to generate an updated recommendation, wherein the updated recommendation includes a number or frequency of nutritional products different from or different from the number or frequency of the nutritional products recommended in (b); and (f) transmitting the updated recommendation by the processor to the personal electronic device for viewing on the GUI by the guardian of the non-human animal subject. In some embodiments, the method further includes determining a health probability score (WPS) from the genotype-phenotype profile. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having or being ... In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the genetic data is determined by: (a) obtaining or having obtained a biological sample from the non-human object; and (b) performing or having performed genotyping on the biological sample.In some embodiments, performing or having performed the genotyping assay includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human animal, or a combination thereof. In some embodiments, the phenotypic data is received from an application (App) or website from which data is added by the guardian of the non-human subject or the veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human object determined by measuring the methylation of DNA in a biological sample obtained from the non-human object. In some embodiments, the method further includes receiving clinical data from the non-human animal object, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergic reactions, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes a diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes a prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the method further includes receiving behavioral data from the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes receiving activity information from the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar.In some embodiments, the activity data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the activity data is entered into an application (App) or website by the guardian or veterinarian of the non-human subject. In some embodiments, the method further includes receiving environmental data of the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the environmental data is entered into an App or website by the guardian or veterinarian of the non-human subject. In some embodiments, the method further includes receiving biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof.In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes k-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are associated with one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes nutritional products.In some embodiments, the nutritional product includes food, supplements, snacks, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (c) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0013] The aspects disclosed herein provide a computer-implemented system configured to update nutritional recommendations for non-human animal subjects. The computer-implemented system includes: a computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program. The computer program includes instructions executable by the computing device to create an application program, the application program including: (a) a first software module configured to provide a spectrum of the non-human animal subject on a graphical user interface (GUI) of a personal electronic device of the guardian of the non-human animal subject, wherein the spectrum includes the genotype of the non-human animal subject, the genotype being associated with one or more conditions; (b) a second software module configured by the at least one processor to generate recommendations for nutritional products based at least partially on the spectrum in (a) to mitigate, prevent, or maintain the one or more conditions in the non-human animal subject; and (c) a third software module configured by the at least one processor to transmit the recommendations to a... The system comprises: (d) a personal electronic device for the guardian of the non-human animal subject; (e) a fourth software module configured by the at least one processor to receive biomarker data obtained from analyzing a biological sample of the non-human animal subject, wherein the biomarker data includes the concentration of the analyte detected in the biological sample compared to a reference concentration of the analyte in one or more control subjects, wherein the analyte includes proteins, metabolites, sugars, lipids, hormones, vitamins, cell counts, electrolytes, or minerals; (f) a fifth software module configured to automatically modify the recommendations based on the received biomarker data to generate updated recommendations, wherein the updated recommendations include the number or frequency of the nutritional products different from those recommended in (b); and (c) a sixth software module configured by the at least one processor to transmit the updated recommendations to the personal electronic device for the guardian of the non-human animal subject to view on the GUI. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having one or more of the conditions. In some embodiments, the third software module is further configured to identify the non-human object as having multiple of the one or more conditions, or a risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal.In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the computer-implemented system further includes a genotyping device configured to acquire the genetic data from a biological sample of the non-human subject. In some embodiments, the genotyping device includes a sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the plurality of genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is entered into an app or website by the guardian of the non-human subject or the veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human object determined by measuring the methylation of DNA in a biological sample obtained from the non-human object. In some embodiments, the first software module is configured to receive clinical data of the non-human animal object, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergic reactions, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the first software module is configured to receive behavioral data of the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the first software module is configured to receive environmental data of the non-human animal object, wherein the environmental data includes geographic location, home environment, activity level, frequency of activities performed, or any combination thereof. In some embodiments, the first software module is further configured to receive activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof.In some implementations, the activity data includes information obtained from an activity tracking device. In some implementations, the activity tracking device includes a smart device. In some implementations, the tracking device includes a GPS-connected dog collar. In some implementations, the activity data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some implementations, the activity data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some implementations, the first software module is further configured to receive environmental data of the non-human object. In some implementations, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some implementations, the environmental data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some implementations, the environmental data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the first software module is further configured to receive biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine.In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsies, peripheral blood, capillary blood, fecal samples, urine samples, buccal swabs, or any combination thereof. In some embodiments, the machine learning prediction model is validated using biopsies from a cohort of non-human subjects that have been analyzed and interpreted as corresponding to one or more conditions predicted by the machine learning prediction model. In some embodiments, the machine learning prediction model is trained using samples from a training cohort of non-human subjects belonging to the same species, wherein training the machine learning prediction model includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the computer-implemented system further includes a display module communicatively coupled to a computing device, wherein the display module is configured to provide notifications to a user, wherein the user includes a guardian or veterinarian of the non-human object, wherein the notifications include: (i) the one or more conditions of the non-human object or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human object; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human object; (iv) prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the notifications are displayed to the user via a graphical user interface (GUI) of the computing device. In some embodiments, the notifications are electronic reports visible to the user on the GUI. In some embodiments, the notifications include recommendations for behavior modifications. In some embodiments, the behavior modifications are related to the one or more conditions. In some embodiments, behavior modifications related to the one or more conditions include increasing, decreasing, or avoiding one or more activities. In some embodiments, the activity includes: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes nutritional products. In some embodiments, the nutritional product includes food, supplements, snacks, or any combination thereof.In some embodiments, the first, second, and third software modules are further configured to analyze new datasets of the non-human subjects at multiple time points to provide updated WPS. In some embodiments, the display module is further configured to provide the user with another notification, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subjects or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subjects; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human subjects; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human subjects; or (v) any combination of (i) to (iv). In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a K-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some implementations, the statistical prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some implementations, the Bayesian variable selection model is a single-step BayesC model.

[0014] The aspects disclosed herein provide a non-transitory computer-readable medium including machine-executable code that, when executed by one or more computer processors, implements a method for updating nutritional recommendations for a non-human animal object, the method comprising: (a) providing a spectrum of the non-human animal object on a graphical user interface (GUI) of a personal electronic device of a guardian of the non-human animal object, wherein the spectrum includes the genotype of the non-human animal object, wherein the genotype is associated with one or more conditions; (b) generating recommendations for nutritional products by a processor, at least in part, based on the spectrum in (a), to mitigate, prevent, or maintain the one or more conditions in the non-human animal object; and (c) transmitting the recommendations by the processor to a personal electronic device of the guardian of the non-human animal object. (d) The processor receives biomarker data obtained from analyzing a biological sample of the non-human animal subject, wherein the biomarker data includes the concentration of the analyte detected in the biological sample compared to a reference concentration of the analyte in one or more control subjects, wherein the analyte includes proteins, metabolites, sugars, lipids, hormones, vitamins, cell counts, electrolytes, or minerals; (e) The processor automatically modifies the recommendations based on the received biomarker data to generate updated recommendations, wherein the updated recommendations include a number or frequency of nutritional products different from or different from the number or frequency of nutritional products recommended in (b); and (f) The processor transmits the updated recommendations to the personal electronic device for viewing on the GUI by the guardian of the non-human animal subject. In some embodiments, the method further includes calculating a Health Probability Score (WPS) based at least in part on the genetic data and phenotypic data of the non-human subject. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having one or more conditions. In some embodiments, the recommendations include products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the other recommendation includes a product, behavior modification, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the method further includes identifying the non-human subject as having multiple of the one or more conditions or at risk of having multiple of the one or more conditions.In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, performing the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website where data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the dataset further includes receiving clinical data from the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, diet sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the dataset further includes receiving behavioral data of the non-human object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof.In some embodiments, the dataset further includes activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the dataset further includes environmental data of the non-human object. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of climbing stairs, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the dataset further includes biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring biological samples from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum alanine aminotransferase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins.In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolites are urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolytes include sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a K-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) a recommendation for a product, behavior modification, or any combination thereof for the non-human subject; (iv) a prescription for a therapeutic or preventative intervention for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes a recommendation for the behavior modification. In some embodiments, the behavior modification is related to the one or more conditions. In some embodiments, the behavior modification includes increasing, decreasing, or avoiding one or more activities.In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting a specific food, vitamin, or supplement; (iii) ingesting a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplement, snack, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (b) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0015] The aspects disclosed herein provide a method for generating nutritional product recommendations for non-human animal subjects, the method comprising: (a) receiving genotype data of the non-human animal subject by a processor, wherein the genotype data includes: (i) DNA methylation detected at one or more genomic loci in a biological sample of the non-human animal subject; (ii) the presence of one or more genetic risk factors detected at one or more genomic loci in the biological sample, wherein the one or more genetic risk factors are associated with one or more conditions; (b) analyzing the DNA methylation by the processor to estimate the biological age of the non-human animal subject; (c) obtaining, by the processor, the probability that the non-human animal subject has or will have the one or more conditions based at least in part on the presence of the one or more genetic risk factors; and (d) generating a recommendation for a nutritional product by the processor based at least in part on the biological age of the non-human animal subject and the probability that the non-human animal subject has or will have the one or more conditions. In some embodiments, the method further comprises determining a health probability score (WPS) from the genotype-phenotype profile. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having the one or more conditions. In some embodiments, the method includes identifying the non-human subject as having multiple of the one or more conditions or a risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human subject is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the genetic data is determined by: (a) obtaining or having obtained a biological sample from the non-human subject; and (b) performing or having performed genotyping on the biological sample. In some embodiments, performing or having performed the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms.In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight distinct loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an application (App) or website in which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical fitness. In some embodiments, physical fitness includes weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the method further includes receiving clinical data from the non-human animal subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, diet sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family medical history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the method further includes receiving behavioral data of the non-human animal subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes receiving activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an application (App) or website by the guardian or veterinarian of the non-human object. In some embodiments, the method further includes receiving environmental data of the non-human object.In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the method further includes receiving biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes K-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model.In some embodiments, the statistical prediction model is a genome-best linear unbiased prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, wherein each cluster is assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) a recommendation for a product, behavior modification, or any combination thereof for the non-human subject; (iv) a prescription for a therapeutic or preventative intervention for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes a personal health system for the non-human subject. In some embodiments, the notification includes a recommendation for the behavior modification. In some embodiments, the behavior modification is related to the one or more conditions. In some embodiments, the behavior modification includes increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting a specific food, vitamin, or supplement; (iii) ingesting a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplement, snack, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (c) at multiple time points during the lifespan of the non-human subject.In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0016] The aspects disclosed herein provide a computer-implemented system configured to generate nutritional product recommendations for non-human animal subjects. The computer-implemented system includes: a computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program. The computer program includes instructions executable by the computing device to create an application program, the application program including: (a) a first module configured to receive genotype data of the non-human animal subject by the at least one processor, wherein the genotype data includes: (i) DNA methylation detected at one or more genomic loci in a biological sample of the non-human animal subject; (ii) one or more genetic markers detected at one or more genomic loci in the biological sample. The at least one processor is configured to: (a) analyze the DNA methylation of the non-human animal subject to estimate its biological age; (b) obtain, by the at least one processor, the probability that the non-human animal subject has or will have the one or more conditions based at least partially on the presence of the one or more genetic risk factors; and (d) generate a recommendation for a nutritional product based at least partially on the biological age of the non-human animal subject and the probability that the non-human animal subject has or will have the one or more conditions. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or will have the one or more conditions. In some embodiments, the third software module is further configured to identify the non-human subject as having or being at risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the computer-implemented system further includes a genotyping device configured to acquire the genetic data from a biological sample of the non-human object. In some embodiments, the genotyping device includes a sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the plurality of genomic loci include one or more polymorphisms.In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is entered into an app or website by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical fitness. In some embodiments, physical fitness includes weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the first software module is configured to receive clinical data of the non-human animal subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, diet sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family medical history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the first software module is configured to receive behavioral data of the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the first software module is configured to receive environmental data of the non-human animal object, wherein the environmental data includes geographic location, home environment, activity level, frequency of activities performed, or any combination thereof. In some embodiments, the first software module is further configured to receive activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some implementations, the activity data includes information obtained from the guardian of the non-human object, the veterinarian of the non-human object, or a combination thereof. In some implementations, the activity data is entered into an app or website by the guardian or veterinarian of the non-human object.In some embodiments, the first software module is further configured to receive environmental data from the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the first software module is further configured to receive biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsies, peripheral blood, capillary blood, fecal samples, urine samples, buccal swabs, or any combination thereof. In some embodiments, the machine learning prediction model is validated using biopsies from a cohort of non-human subjects that have been analyzed and interpreted as corresponding to one or more conditions predicted by the machine learning prediction model.In some embodiments, the machine learning predictive model is trained using samples from a training cohort of non-human subjects belonging to the same species. Training the machine learning predictive model involves assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the computer-implemented system further includes a display module communicatively coupled to the computing device, wherein the display module is configured to provide notifications to a user, including a guardian or veterinarian of the non-human subject, wherein the notifications include: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is displayed to the user via a graphical user interface (GUI) of the computing device. In some embodiments, the notification is an electronic report visible to the user on the GUI. In some embodiments, the notification includes a recommendation for the behavior modification. In some embodiments, the behavior modification is related to one or more conditions. In some embodiments, the behavior modification related to one or more conditions includes increasing, decreasing, or avoiding one or more activities. In some embodiments, the activities include: (i) engaging in physical exercise; (ii) consuming specific foods, vitamins, or supplements; (iii) consuming specific amounts of the food, vitamin, or supplement; (iv) exposure to a product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation for the product, wherein the product includes nutritional products. In some embodiments, the nutritional products include foods, supplements, snacks, or any combination thereof. In some embodiments, the first software module, the second software module, and the third software module are further configured to analyze new datasets of the non-human objects at multiple time points to provide updated WPS.In some embodiments, the display module is further configured to provide the user with another notification, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human object or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human object; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human object; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a K-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model.

[0017] The aspects disclosed herein provide a non-transitory computer-readable medium including machine-executable code that, when executed by one or more computer processors, implements a method for generating nutritional product recommendations for non-human animal subjects, the method comprising: (a) receiving genotype data of the non-human animal subject by the processor, wherein the genotype data includes: (i) DNA methylation detected at one or more genomic loci in a biological sample of the non-human animal subject; (ii) the presence of one or more genetic risk factors detected at one or more genomic loci in the biological sample, wherein the one or more genetic risk factors are associated with one or more conditions; (b) analyzing the DNA methylation by the processor to estimate the biological age of the non-human animal subject; (c) obtaining, at least in part, a probability by the processor that the non-human animal subject has or will have the one or more conditions based on the presence of the one or more genetic risk factors; and (d) generating a recommendation for a nutritional product by the processor at least in part based on the biological age of the non-human animal subject and the probability by which the non-human animal subject has or will have the one or more conditions. In some embodiments, the method further comprises calculating a Health Probability Score (WPS) at least in part based on the genetic data and the phenotypic data of the non-human subject. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having or experiencing one or more of the conditions. In some embodiments, the recommendation includes products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by or in any combination thereof by the non-human subject. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, another recommendation includes products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by or in any combination thereof by the non-human subject. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the method further includes identifying the non-human subject as being at risk of having or experiencing multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human subject is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine.In some embodiments, performing the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website where data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the dataset further includes receiving clinical data from the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the dataset further includes receiving behavioral data from the non-human subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the dataset further includes activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar.In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the dataset further includes environmental data of the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the dataset further includes biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring biological samples from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof.In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes K-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, wherein each cluster is assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes a personal health system for the non-human subject. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are associated with the one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplements, snacks, or any combination thereof.In some embodiments, the method further includes iteratively performing (a) to (b) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0018] The aspects disclosed herein provide a method for generating nutritional product recommendations for non-human animal subjects, the method comprising: (a) receiving phenotypic data of the non-human animal subject by a processor, wherein the phenotypic data includes the non-human animal subject's weight or body mass index (BMI), age, species, and breed; (b) determining, by the processor, that the non-human animal subject is overweight based at least in part on the non-human animal subject's weight or BMI, age, and breed; and (c) receiving genotype data by the processor indicating the presence of one or more genetic risk factors detected at one or more genomic loci in a biological sample of the non-human animal subject, wherein the one or more genetic risk factors are related to the non-human animal subject's... The method is associated with one or more conditions related to weight or BMI; (d) receiving by the processor: (i) environmental data of the non-human animal subject, wherein the environmental data indicates that the non-human animal subject lives in an urban or rural environment; or (ii) the lifestyle of the non-human animal subject, wherein the lifestyle includes a sedentary lifestyle or an active lifestyle; (e) generating recommendations by the processor to manage the weight or BMI of the non-human animal subject based at least in part on the phenotypic data and the genetic data, wherein the recommendations for the nutritional products are optimized according to the environmental data, the lifestyle, or a combination thereof of the non-human animal subject; and (f) transmitting the recommendations by the processor to a personal electronic device of the guardian of the non-human animal subject. In some embodiments, the method further includes determining a Health Probability Score (WPS) from the genotype-phenotype profile. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has one or more conditions or is at risk of having one or more conditions. In some embodiments, the method includes identifying the non-human subject as being at risk of having multiple of the one or more conditions or having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the genetic data is determined by: (a) obtaining or having obtained a biological sample from the non-human object; and (b) performing or having performed genotyping on the biological sample.In some embodiments, performing or having performed the genotyping assay includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an application (App) or website from which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human object determined by measuring the methylation of DNA in a biological sample obtained from the non-human object. In some embodiments, the method further includes receiving clinical data from the non-human animal object, wherein the clinical data includes a medical history or family history. In some embodiments, the medical history or family history includes: a diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes a diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes a prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the method further includes receiving behavioral data from the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes receiving activity information from the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar.In some embodiments, the activity data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the activity data is entered into an application (App) or website by the guardian or veterinarian of the non-human subject. In some embodiments, the method further includes receiving environmental data of the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the environmental data is entered into an App or website by the guardian or veterinarian of the non-human subject. In some embodiments, the method further includes receiving biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof.In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes k-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are associated with the one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes nutritional products.In some embodiments, the nutritional product includes food, supplements, snacks, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (c) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0019] The aspects disclosed herein provide a computer-implemented system configured to generate nutritional product recommendations for non-human animal subjects. The computer-implemented system includes: a computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program. The computer program includes instructions executable by the computing device to create an application program, the application program including: (a) a first module configured to receive phenotypic data of the non-human animal subject by the at least one processor, wherein the phenotypic data includes the non-human animal subject's weight or body mass index (BMI), age, species, and breed; (b) a second module configured to determine, by the at least one processor, that the non-human animal subject is overweight based at least in part on the non-human animal subject's weight or BMI, age, and breed; and (c) a third module configured to receive genotype data by the at least one processor, the genotype data indicating the detection of one or more genomic loci in a biological sample of the non-human animal subject. The at least one processor receives: (i) environmental data of the non-human animal subject, wherein the environmental data indicates that the non-human animal subject lives in an urban or rural environment; or (ii) the lifestyle of the non-human animal subject, wherein the lifestyle includes a sedentary lifestyle or an active lifestyle; (e) a fifth module configured by the at least one processor to generate recommendations for managing the weight or BMI of the non-human animal subject, at least in part based on the phenotypic data and the genotypic data, wherein the recommendations for nutritional products are optimized based on the environmental data, the lifestyle, or a combination thereof of the non-human animal subject; and (f) a sixth module configured by the at least one processor to transmit the recommendations to a personal electronic device of the guardian of the non-human animal subject. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has the one or more conditions or is at risk of having the one or more conditions. In some embodiments, the third software module is further configured to identify the non-human object as having multiple of the one or more conditions, or a risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal.In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the computer-implemented system further includes a genotyping device configured to acquire the genetic data from a biological sample of the non-human subject. In some embodiments, the genotyping device includes a sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the plurality of genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is entered into an app or website by the guardian of the non-human subject or the veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human object determined by measuring the methylation of DNA in a biological sample obtained from the non-human object. In some embodiments, the first software module is configured to receive clinical data of the non-human animal object, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergic reactions, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the first software module is configured to receive behavioral data of the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the first software module is configured to receive environmental data of the non-human animal object, wherein the environmental data includes geographic location, home environment, activity level, activities performed, or frequency of activities, or any combination thereof. In some embodiments, the first software module is further configured to receive activity information of the non-human animal object.In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the first software module is further configured to receive environmental data of the non-human object. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the first software module is further configured to receive biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof.In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model is validated using biopsies from a cohort of non-human subjects that have been analyzed and interpreted as corresponding to one or more conditions predicted by the machine learning prediction model. In some embodiments, the machine learning prediction model is trained using samples from a training cohort of non-human subjects belonging to the same species, wherein training the machine learning prediction model includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the computer-implemented system further includes a display module communicatively coupled to the computing device, wherein the display module is configured to provide notifications to a user, wherein the user includes a guardian or veterinarian of the non-human object, wherein the notifications include: (i) the one or more conditions of the non-human object or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human object; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human object; (iv) prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the notifications are displayed to the user via a graphical user interface (GUI) of the computing device. In some embodiments, the notifications are electronic reports visible to the user on the GUI. In some embodiments, the notifications include recommendations for behavior modifications. In some embodiments, the behavior modifications are related to the one or more conditions. In some embodiments, behavior modifications related to the one or more conditions include increasing, decreasing, or avoiding one or more activities. In some embodiments, the activity includes: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes nutritional products. In some embodiments, the nutritional product includes food, supplements, snacks, or any combination thereof.In some embodiments, the first, second, and third software modules are further configured to analyze new datasets of the non-human subjects at multiple time points to provide updated WPS. In some embodiments, the display module is further configured to provide the user with another notification, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or the risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a k-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some implementations, the statistical prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some implementations, the Bayesian variable selection model is a single-step BayesC model.

[0020] The aspects disclosed herein provide a non-transitory computer-readable medium including machine-executable code that, when executed by one or more computer processors, implements a method for generating nutritional product recommendations for non-human animal subjects, the method comprising: (a) receiving phenotypic data of the non-human animal subject by the processor, wherein the phenotypic data includes the non-human animal subject's weight or body mass index (BMI), age, species, and breed; (b) determining, by the processor, that the non-human animal subject is overweight based at least in part on the non-human animal subject's weight or BMI, age, and breed; and (c) receiving genotype data by the processor indicating the presence of one or more genetic risk factors detected at one or more genomic loci in a biological sample of the non-human animal subject, wherein the... The method includes: (d) receiving, by the processor: (i) environmental data of the non-human animal subject, wherein the environmental data indicates that the non-human animal subject lives in an urban or rural environment; or (ii) the lifestyle of the non-human animal subject, wherein the lifestyle includes a sedentary lifestyle or an active lifestyle; (e) generating recommendations by the processor, at least in part, based on the phenotypic data and the genetic data, to manage the weight or BMI of the non-human animal subject, wherein the recommendations for nutritional products are optimized based on the environmental data, the lifestyle, or a combination thereof of the non-human animal subject; and (f) transmitting the recommendations by the processor to a personal electronic device of the guardian of the non-human animal subject. In some embodiments, the method further includes calculating a Health Probability Score (WPS) at least in part based on the genetic data and the phenotypic data of the non-human subject. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having the one or more conditions. In some embodiments, the recommendations include products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the other recommendation includes products, behavior modifications, or any combination thereof targeting the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the method further includes identifying the non-human subject as having multiple of the one or more conditions or at risk of having multiple of the one or more conditions.In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, performing the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website where data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the dataset further includes receiving clinical data from the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, diet sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the dataset further includes receiving behavioral data of the non-human object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof.In some embodiments, the dataset further includes activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the dataset further includes environmental data of the non-human object. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of climbing stairs, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the dataset further includes biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring biological samples from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins.In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolites are urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolytes include sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a k-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) a recommendation for a product, behavior modification, or any combination thereof for the non-human subject; (iv) a prescription for a therapeutic or preventative intervention for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes a recommendation for the behavior modification. In some embodiments, the behavior modification is related to the one or more conditions. In some embodiments, the behavior modification includes increasing, decreasing, or avoiding one or more activities.In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting a specific food, vitamin, or supplement; (iii) ingesting a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplement, snack, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (b) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0021] The aspects disclosed herein provide a method for identifying a nutritional product recommended for a non-human animal subject, the method comprising: (a) receiving genetic data at multiple genomic loci of the non-human animal subject, wherein at least one of the multiple genomic loci is associated with one or more conditions; (b) receiving phenotypic data associated with multiple phenotypes of the non-human animal subject; (c) generating a genotype-phenotype profile of the non-human animal subject by processing a dataset including the genetic data and the phenotypic data to determine qualitative or quantitative measurements of the at least one of the multiple genomic loci and at least one of the multiple phenotypes; and (d) applying a machine learning prediction model to the genotype-phenotype profile of the non-human animal subject to identify the nutritional product recommended for the non-human subject based at least in part on the probability that the non-human animal subject has: (i) one or more conditions, or (ii) a risk of having one or more conditions. In some embodiments, the method further comprises providing the nutritional product to the non-human animal subject. In some embodiments, the method further comprises determining a health probability score (WPS) from the genotype-phenotype profile. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human object has or is at risk of having or experiencing one or more of the conditions. In some embodiments, the method includes identifying the non-human object as having or at risk of having multiple of the conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the genetic data is determined by: (a) obtaining or having obtained a biological sample from the non-human object; and (b) performing or having performed genotyping on the biological sample. In some embodiments, performing or having performed the genotyping assay includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis.In some embodiments, the plurality of genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an application (App) or website in which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical characteristics. In some embodiments, physical characteristics include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the method further includes receiving clinical data of the non-human animal subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: a diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family history includes a prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the method further includes receiving behavioral data of the non-human animal subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes receiving activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the guardian of the non-human object, the veterinarian of the non-human object, or a combination thereof. In some embodiments, the activity data is entered into an application (App) or website by the guardian or veterinarian of the non-human object. In some embodiments, the method further includes receiving environmental data of the non-human object.In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the method further includes receiving biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes k-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model.In some embodiments, the statistical prediction model is a genome-best linear unbiased prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, wherein each cluster is assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) a recommendation for a product, behavior modification, or any combination thereof for the non-human subject; (iv) a prescription for a therapeutic or preventative intervention for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes a recommendation for the behavior modification. In some embodiments, the behavior modification is related to the one or more conditions. In some embodiments, the behavior modification includes increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) ingesting a specific food, vitamin, or supplement; (iii) ingesting a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplement, snack, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (c) at multiple time points during the lifespan of the non-human subject.In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0022] The aspects disclosed herein provide a computer-implemented system configured to identify recommended nutritional products for non-human animal subjects. The computer-implemented system includes: a computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program. The computer program includes instructions executable by the computing device to create an application program, the application program including: (a) a first module configured to receive, by the at least one processor, genetic data at multiple genomic loci of the non-human animal subject, wherein at least one of the multiple genomic loci is associated with one or more conditions; and (b) a second module configured to receive, by the at least one processor, phenotypes associated with multiple phenotypes of the non-human animal subject. The data; (c) a third module configured by the at least one processor to generate a genotype-phenotype profile of the non-human animal object by processing a dataset including the genetic data and the phenotypic data to determine qualitative or quantitative measurements of at least one genomic locus among the plurality of genomic loci and qualitative or quantitative measurements of at least one phenotype among the plurality of phenotypes; and (d) a fourth module configured by the at least one processor to apply a machine learning prediction model to the genotype-phenotype profile of the non-human animal object to identify the recommended nutritional product for the non-human animal object based at least in part on the probability that the non-human animal object has: (i) one or more of the conditions, or (ii) the risk of having one or more of the conditions. In some embodiments, the method further includes providing the nutritional product to the non-human animal object. In some embodiments, the WPS is a numerical value indicating the probability that the non-human object has one or more of the conditions or the risk of having one or more of the conditions. In some embodiments, the third software module is further configured to identify the non-human object as having multiple of the one or more conditions or the risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the computer-implemented system further includes a genotyping device configured to acquire the genetic data from a biological sample of the non-human object.In some embodiments, the genotyping device includes a sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the plurality of genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is entered into an app or website by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical characteristics. In some embodiments, physical characteristics include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the first software module is configured to receive clinical data of the non-human animal subject, wherein the clinical data includes medical history or family medical history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family history includes a prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the first software module is configured to receive behavioral data of the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the first software module is configured to receive environmental data of the non-human animal object, wherein the environmental data includes geographic location, home environment, activity level, frequency of activities performed, or any combination thereof. In some embodiments, the first software module is further configured to receive activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar.In some implementations, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some implementations, the activity data is entered into an app or website by the non-human subject's guardian or veterinarian. In some implementations, the first software module is further configured to receive environmental data of the non-human subject. In some implementations, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some implementations, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some implementations, the environmental data is entered into an app or website by the non-human subject's guardian or veterinarian. In some implementations, the first software module is further configured to receive biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes a fat-soluble vitamin or a water-soluble vitamin. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolites are urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolytes include sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof.In some embodiments, the machine learning prediction model is validated using biopsies from a cohort of non-human subjects that have been analyzed and interpreted as corresponding to one or more conditions predicted by the machine learning prediction model. In some embodiments, the machine learning prediction model is trained using samples from a training cohort of non-human subjects belonging to the same species, wherein training the machine learning prediction model includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the computer-implemented system further includes a display module communicatively coupled to the computing device, wherein the display module is configured to provide notifications to a user, wherein the user includes a guardian or veterinarian of the non-human object, wherein the notifications include: (i) the one or more conditions of the non-human object or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human object; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human object; (iv) prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the notifications are displayed to the user via a graphical user interface (GUI) of the computing device. In some embodiments, the notifications are electronic reports visible to the user on the GUI. In some embodiments, the notifications include recommendations for behavior modifications. In some embodiments, the behavior modifications are related to the one or more conditions. In some embodiments, behavior modifications related to the one or more conditions include increasing, decreasing, or avoiding one or more activities. In some implementations, the activity includes: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some implementations, the notification includes a recommendation for the product, wherein the product includes a nutritional product. In some implementations, the nutritional product includes food, supplements, snacks, or any combination thereof. In some implementations, the first software module, the second software module, and the third software module are further configured to analyze new datasets of the non-human objects at multiple time points to provide updated WPS.In some embodiments, the display module is further configured to provide the user with another notification, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human object or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human object; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human object; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a k-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model.

[0023] The aspects disclosed herein provide a non-transitory computer-readable medium including machine-executable code that, when executed by one or more computer processors, implements a method for identifying a nutritional product recommended for a non-human animal object, the method comprising: (a) receiving genetic data at a plurality of genomic loci of the non-human animal object, wherein at least one of the plurality of genomic loci is associated with one or more conditions; (b) receiving phenotypic data associated with multiple phenotypes of the non-human animal object; (c) generating a genotype-phenotype profile of the non-human animal object by processing a dataset including the genetic data and the phenotypic data to determine qualitative or quantitative measurements of the at least one of the plurality of genomic loci and at least one of the plurality of phenotypes; and (d) applying a machine learning prediction model to the genotype-phenotype profile of the non-human animal object to identify the nutritional product recommended for the non-human object based at least in part on the probability that the non-human animal object has: (i) one or more conditions, or (ii) a risk of having one or more conditions. In some embodiments, the method further comprises providing the nutritional product to the non-human animal object. In some embodiments, the method further includes calculating a Health Probability Score (WPS) based at least in part on the genetic and phenotypic data of the non-human subject. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having or experiencing one or more of the conditions. In some embodiments, the recommendation includes products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by or in any combination thereof by the non-human subject. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, another recommendation includes products, behavior modifications, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by or in any combination thereof by the non-human subject. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the method further includes identifying the non-human subject as being at risk of having or experiencing multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health status conditions, one or more dermatological conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal.In some embodiments, the companion animal is a feline or canine. In some embodiments, performing the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website from which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the dataset further includes receiving clinical data from the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family history includes the diagnosis of one or more diseases or conditions. In some embodiments, the medical history or family history includes the prognosis of one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the dataset further includes receiving behavioral data from the non-human subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the dataset further includes activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar.In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the dataset further includes environmental data of the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoors, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the dataset further includes biomarker data of the non-human subject, wherein the biomarker data is obtained by measuring biological samples from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble vitamins or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof.In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes k-means clustering. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, wherein each cluster is assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system. In some embodiments, the notification includes recommendations for the behavior modifications. In some embodiments, the behavior modifications are associated with the one or more conditions. In some embodiments, the behavior modifications include increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to the product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation of the product, wherein the product includes a nutritional product. In some embodiments, the nutritional product includes food, supplements, snacks, or any combination thereof.In some embodiments, the method further includes iteratively performing (a) to (b) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0024] The aspects disclosed herein provide a method for identifying nutritional products recommended for non-human animal subjects, the method comprising: (a) obtaining a biological sample from the non-human animal subject; (b) performing genotyping on the first biological sample of the non-human animal subject to generate genetic data at multiple genomic loci of the non-human animal subject, wherein at least one of the multiple genomic loci is associated with one or more conditions; (c) receiving phenotypic data associated with multiple phenotypes of the non-human animal subject; (d) receiving biomarker data, activity data, environmental data, behavioral data, or clinical data of the non-human animal subject; and (e) generating a genotype-phenotype profile of the non-human animal subject by processing one or more datasets to determine qualitative or quantitative measurements of: (i) the multiple phenotypes of the non-human animal subject; (ii) at least one genomic locus of the genomic loci, (iii) at least one phenotype of the multiple phenotypes, and (iv) at least one of the biomarker data, the activity data, the environmental data, the behavioral data, and the clinical data; the one or more datasets include the genetic data, the phenotypic data, and one or more of the following: the biomarker data, the activity data, the environmental data, the behavioral data, and the clinical data; and (f) applying a machine learning predictive model to the genotype-phenotype profile of the non-human animal object to identify the recommended nutritional product for the non-human animal object based at least in part on the probability that the non-human animal object has: (i) one or more of the conditions, or (ii) the risk of having one or more of the conditions. In some embodiments, the method further includes: (g) iteratively performing (c) through (d) at multiple time points to obtain a new dataset, the new dataset including new phenotypic data and at least one of the following: new biomarker data, new activity data, new environmental data, new behavioral data, or new clinical data; (h) updating the genotype-phenotype profile with the new dataset to generate an updated genotype-phenotype profile; and (i) applying the machine learning prediction model to the updated genotype-phenotype profile to modify the amount or type of the nutritional product recommended for the non-human animal subject. In some embodiments, the method further includes determining a health probability score (WPS) from the genotype-phenotype profile. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having or being ...In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the genetic data is determined by: (a) obtaining or having obtained a biological sample from the non-human object; and (b) performing or having performed genotyping on the biological sample. In some embodiments, performing or having performed genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight distinct loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an application (App) or website in which data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical fitness. In some embodiments, physical fitness includes weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the method further includes receiving clinical data from the non-human animal subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, diet sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family medical history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions.In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the method further includes receiving behavioral data of the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the method further includes receiving activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an application (App) or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the method further includes receiving environmental data of the non-human object. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the method further includes receiving biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein. In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols.In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a k-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is a genome-best linear unbiased prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC. In some embodiments, the method further includes validating the machine learning prediction model using samples from a validation cohort of non-human subjects belonging to the same species who have the one or more conditions. In some embodiments, the method further includes training the machine learning prediction model using samples from a training cohort of non-human subjects belonging to the same species, wherein the training includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, wherein each cluster is assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the method further includes providing notification to the guardian or veterinarian of the non-human subject, wherein the notification includes: (i) the one or more conditions in the non-human subject or the risk of developing the one or more conditions; (ii) the genotype-phenotype profile of the non-human subject; (iii) recommendations for products, behavior modification, or any combination thereof for the non-human subject; (iv) prescriptions for therapeutic or preventative interventions for the non-human subject; or (v) any combination of (i) to (iv). In some embodiments, the notification is an electronic report. In some embodiments, the notification further includes the non-human subject's personal health system.In some embodiments, the notification includes a recommendation for the behavior modification. In some embodiments, the behavior modification is related to the one or more conditions. In some embodiments, the behavior modification includes increasing, decreasing, or avoiding one or more activities. In some embodiments, the one or more activities include: (i) engaging in physical exercise; (ii) consuming a specific food, vitamin, or supplement; (iii) consuming a specific amount of the food, vitamin, or supplement; (iv) exposure to a product; (v) use of the product; or (vi) any combination of (i) to (v). In some embodiments, the notification includes a recommendation for the product, wherein the product includes nutritional products. In some embodiments, the nutritional products include food, supplements, snacks, or any combination thereof. In some embodiments, the method further includes iteratively performing (a) to (c) at multiple time points during the lifespan of the non-human subject. In some embodiments, the method further includes providing another notification to the guardian of the non-human subject, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human subject or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human subject; (iii) an updated recommendation for products, behavior modification, or any combination thereof for the non-human subject; (iv) an updated prescription for therapeutic or preventive interventions for the non-human subject; or (v) any combination of (i) to (iv).

[0025] The aspects disclosed herein provide a computer-implemented system configured to identify recommended nutritional products for non-human animal subjects. The computer-implemented system includes: a computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program. The computer program includes instructions executable by the computing device to create an application program, the application program including: (a) a first module configured by the at least one processor to receive genetic data at multiple genomic loci of the non-human animal subject, wherein at least one of the multiple genomic loci is associated with one or more conditions; (b) a second module configured by the at least one processor to receive phenotypic data associated with multiple phenotypes of the non-human animal subject; (c) a third module configured by the at least one processor to receive biomarker data, activity data, environmental data, behavioral data, or clinical data of the non-human animal subject; and (d) a fourth module configured to, through the at least one processor, receive genetic data at multiple phenotypic sites of the non-human animal subject. The at least one processor processes one or more datasets to determine qualitative or quantitative measurements of the following to generate a genotype-phenotype profile of the non-human animal object: (i) at least one genomic locus of the plurality of genomic loci, (ii) at least one phenotype of the plurality of phenotypes, and (iii) at least one of the biomarker data, the activity data, the environmental data, the behavioral data, and the clinical data, wherein the one or more datasets include: the genetic data, the phenotypic data, and one or more of the following: the biomarker data, the activity data, the environmental data, the behavioral data, and the clinical data; and (e) a fifth module configured by the at least one processor to apply a machine learning predictive model to the genotype-phenotype profile of the non-human animal object to identify the recommended nutritional product for the non-human object based at least in part on the probability that the non-human animal object has: (i) one or more conditions, or (ii) the risk of having one or more conditions. In some implementations, the system further includes: (f) a sixth module configured to be executed iteratively by the at least one processor at multiple time points from (b) to (c) to obtain a new dataset, the new dataset including new phenotypic data and at least one of the following: new biomarker data, new activity data, new environmental data, new behavioral data, or new clinical data; (g) a seventh module configured to be executed by the at least one processor to update the genotype-phenotype profile with the new dataset to generate an updated genotype-phenotype profile; and (h) an eighth module configured to be executed by the at least one processor to apply the machine learning prediction model to the updated genotype-phenotype profile to modify the amount or type of the nutritional product recommended for the non-human animal subjects.In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human object has or is at risk of having or experiencing one or more of the conditions. In some embodiments, the third software module is further configured to identify the non-human object as having or at risk of having multiple of the conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human object is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, the computer-implemented system further includes a genotyping device configured to acquire the genetic data from a biological sample of the non-human object. In some embodiments, the genotyping device includes a sequencer, a quantitative PCR (qPCR) device, or a DNA microarray. In some embodiments, the plurality of genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the plurality of genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is entered into an app or website by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical fitness. In some embodiments, physical fitness includes weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the first software module is configured to receive clinical data of the non-human animal subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, dietary sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof. In some embodiments, the medical history or family medical history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions.In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the first software module is configured to receive behavioral data of the non-human animal object, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the first software module is configured to receive environmental data of the non-human animal object, wherein the environmental data includes geographic location, home environment, activity level, frequency of activities performed, or any combination thereof. In some embodiments, the first software module is further configured to receive activity information of the non-human object. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human object's guardian, the non-human object's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human object's guardian or the non-human object's veterinarian. In some embodiments, the first software module is further configured to receive environmental data from the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of stair climbing, or any combination thereof. In some embodiments, the environmental data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the environmental data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the first software module is further configured to receive biomarker data from the non-human subject, wherein the biomarker data is obtained by measuring a biological sample from the non-human subject under conditions sufficient to detect the amount or presence of one or more biomarkers, wherein the one or more biomarkers are associated with the one or more conditions. In some embodiments, the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, or any combination thereof. In some embodiments, the protein is an enzyme. In some embodiments, the enzyme is a digestive enzyme or a metabolic enzyme. In some embodiments, the digestive enzyme is a lipase or an amylase. In some embodiments, the metabolic enzyme is lactate dehydrogenase, creatine phosphokinase, gamma-glutamyl transpeptidase, serum glutamate-pyruvate transaminase, or alkaline phosphatase. In some embodiments, the protein includes total protein.In some embodiments, the protein is albumin, globulin, or lipoprotein. In some embodiments, the lipoprotein is low-density lipoprotein or high-density lipoprotein. In some embodiments, the sugar includes glucose. In some embodiments, the lipid includes fatty acids. In some embodiments, the lipid includes sterols. In some embodiments, the sterol is cholesterol. In some embodiments, the hormone is cortisol or a thyroid hormone. In some embodiments, the thyroid hormone is triiodothyronine or thyroxine. In some embodiments, the vitamin includes fat-soluble or water-soluble vitamins. In some embodiments, the cells include red blood cells, white blood cells, platelets, or any combination thereof. In some embodiments, the metabolite is urea nitrogen, total bilirubin, or creatinine. In some embodiments, the electrolyte includes sodium, potassium, chloride, calcium, phosphorus, or any combination thereof. In some embodiments, the biological sample includes tissue biopsy, peripheral blood, capillary blood, fecal sample, urine sample, buccal swab, or any combination thereof. In some embodiments, the machine learning prediction model is validated using biopsies from a cohort of non-human subjects that have been analyzed and interpreted as corresponding to one or more conditions predicted by the machine learning prediction model. In some embodiments, the machine learning prediction model is trained using samples from a training cohort of non-human subjects belonging to the same species, wherein training the machine learning prediction model includes assigning one or more labels to a training dataset obtained from the training cohort using a classification algorithm to generate multiple clusters, each cluster being assigned a different label. In some embodiments, the training dataset includes: (i) genetic data at multiple genomic loci of the training cohort, wherein the multiple genomic loci are associated with the one or more conditions; and (ii) phenotypic data associated with multiple phenotypes of the training cohort of non-human subjects. In some embodiments, the computer-implemented system further includes a display module communicatively coupled to the computing device, wherein the display module is configured to provide notifications to a user, wherein the user includes a guardian or veterinarian of the non-human object, wherein the notifications include: (i) the one or more conditions of the non-human object or the risk of the occurrence of the one or more conditions; (ii) the genotype-phenotype profile of the non-human object; (iii) recommendations for products, behavior modifications, or any combination thereof for the non-human object; (iv) prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the notifications are displayed to the user via a graphical user interface (GUI) of the computing device. In some embodiments, the notifications are electronic reports visible to the user on the GUI. In some embodiments, the notifications include recommendations for behavior modifications.In some implementations, the behavior modification is associated with one or more of the conditions. In some implementations, behavior modification associated with one or more of the conditions includes increasing, decreasing, or avoiding one or more activities. In some implementations, the activities include: (i) engaging in physical exercise; (ii) consuming specific foods, vitamins, or supplements; (iii) consuming specific amounts of the food, vitamin, or supplement; (iv) exposure to a product; (v) use of the product; or (vi) any combination of (i) to (v). In some implementations, the notification includes a recommendation for the product, wherein the product includes nutritional products. In some implementations, the nutritional products include foods, supplements, snacks, or any combination thereof. In some implementations, the first software module, the second software module, and the third software module are further configured to analyze new datasets of the non-human subjects at multiple time points to provide updated WPS. In some embodiments, the display module is further configured to provide the user with another notification, wherein the other notification includes: (i) a new condition of the one or more conditions in the non-human object or a risk of the occurrence of the new condition; (ii) an updated genotype-phenotype profile of the non-human object; (iii) updated recommendations for products, behavior modification, or any combination thereof for the non-human object; (iv) updated prescriptions for therapeutic or preventative interventions for the non-human object; or (v) any combination of (i) to (iv). In some embodiments, the machine learning prediction model includes clustering algorithms, statistical algorithms, or any combination thereof. In some embodiments, the clustering algorithm is a centroid-based algorithm, a hierarchical clustering algorithm, or a spectral clustering algorithm. In some embodiments, the centroid-based algorithm includes a k-means clustering algorithm. In some embodiments, the statistical algorithm is a genome-wide prediction algorithm or a statistical prediction model. In some embodiments, the statistical prediction model is Genome Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model. In some embodiments, the Bayesian variable selection model is a single-step BayesC model.

[0026] The aspects disclosed herein provide a non-transitory computer-readable medium including machine-executable code that, when executed by one or more computer processors, implements a method for identifying a nutritional product recommended for a non-human animal subject, the method comprising: (a) obtaining a biological sample from the non-human animal subject; (b) genotyping the first biological sample of the non-human animal subject to generate genetic data at multiple genomic loci of the non-human animal subject, wherein at least one of the multiple genomic loci is associated with one or more conditions; (c) receiving phenotypic data associated with multiple phenotypes of the non-human animal subject; (d) receiving biomarker data, activity data, environmental data, behavioral data, or clinical data of the non-human animal subject; and (e) determining qualitative or quantitative measurements of the following by processing one or more datasets. The genotype-phenotype profile of the non-human animal subject is generated based on: (i) at least one genomic locus of the plurality of genomic loci, (ii) at least one phenotype of the plurality of phenotypes, and (iii) at least one of the biomarker data, the activity data, the environmental data, the behavioral data, and the clinical data, wherein the dataset includes the genetic data, the phenotypic data, and one or more of the following: the biomarker data, the activity data, the environmental data, the behavioral data, and the clinical data; and (f) applying a machine learning prediction model to the genotype-phenotype profile of the non-human animal subject to identify the recommended nutritional product for the non-human subject based at least in part on the probability that the non-human animal subject has: (i) one or more of the conditions, or (ii) the risk of having one or more of the conditions. In some embodiments, the method further includes: (g) iteratively performing (c) through (d) at multiple time points to obtain a new dataset, the new dataset including new phenotypic data and at least one of the following: new biomarker data, new activity data, new environmental data, new behavioral data, or new clinical data; (h) updating the genotype-phenotype profile with the new dataset to generate an updated genotype-phenotype profile; and (i) applying the machine learning prediction model to the updated genotype-phenotype profile to modify the amount or type of the nutritional product recommended for the non-human animal subject. In some embodiments, the method further includes calculating a Health Probability Score (WPS) based at least in part on the genetic data and phenotypic data of the non-human subject. In some embodiments, the WPS is a numerical value indicating the likelihood that the non-human subject has or is at risk of having the one or more conditions. In some embodiments, the recommendation includes a product, behavior modification, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof.In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the other recommendation includes a product, behavior modification, or any combination thereof for the non-human subject. In some embodiments, the product is consumed or used by the non-human subject, or any combination thereof. In some embodiments, the consumed product is a nutritional product, supplement, snack, or medication. In some embodiments, the method further includes identifying the non-human subject as having or at risk of having multiple of the one or more conditions. In some embodiments, the one or more conditions include: one or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof. In some embodiments, the non-human subject is a mammal. In some embodiments, the mammal is a feline, canine, or farm animal. In some embodiments, the mammal is a companion animal. In some embodiments, the companion animal is a feline or canine. In some embodiments, performing the genotyping includes: (i) subjecting the biological sample to conditions sufficient to isolate, enrich, or extract multiple DNA molecules from the biological sample; and (ii) analyzing the multiple DNA molecules to generate the genetic data. In some embodiments, analyzing the multiple DNA molecules includes performing whole-genome sequencing, skimming sequencing, quantitative PCR (qPCR), or using DNA microarray analysis. In some embodiments, the multiple genomic loci include one or more polymorphisms. In some embodiments, the one or more polymorphisms include single nucleotide polymorphisms (SNPs) or insertions / deletions. In some embodiments, the multiple genomic loci include at least eight different loci. In some embodiments, the phenotypic data includes information obtained from the guardian of the non-human subject, the veterinarian of the non-human subject, or a combination thereof. In some embodiments, the phenotypic data is received from an app or website where data is added by the guardian or veterinarian of the non-human subject. In some embodiments, the phenotypic data includes physical attributes. In some embodiments, physical attributes include weight, sex, age, or breed. In some embodiments, the age is the biological age of the non-human subject determined by measuring the methylation of DNA in a biological sample obtained from the non-human subject. In some embodiments, the dataset further includes clinical data of the non-human subject, wherein the clinical data includes medical history or family history. In some embodiments, the medical history or family history includes: diagnosis or prognosis of one or more diseases or conditions, diet sensitivities, lameness, allergies, activity levels, exercise intolerance, reproductive status, pre-existing conditions, known adverse life events, or any combination thereof.In some embodiments, the medical history or family medical history includes a diagnosis of the one or more diseases or conditions. In some embodiments, the medical history or family medical history includes the prognosis of the one or more diseases or conditions. In some embodiments, the one or more diseases or conditions are dental diseases or conditions. In some embodiments, the dataset further includes receiving behavioral data of the non-human subject, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy levels, or any combination thereof. In some embodiments, the dataset further includes activity information of the non-human subject. In some embodiments, the activity information includes activity level, activity type, calories burned, sleep duration, or any combination thereof. In some embodiments, the activity data includes information obtained from an activity tracking device. In some embodiments, the activity tracking device includes a smart device. In some embodiments, the tracking device includes a GPS-connected dog collar. In some embodiments, the activity data includes information obtained from the non-human subject's guardian, the non-human subject's veterinarian, or a combination thereof. In some embodiments, the activity data is entered into an app or website by the non-human subject's guardian or the non-human subject's veterinarian. In some embodiments, the dataset further includes environmental data of the non-human subject. In some embodiments, the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, ti...

Claims

1. A method for identifying nutritional products recommended for non-human animal subjects, the method comprising: (a) Receive genetic data at multiple genomic loci of the non-human animal object, wherein at least one of the multiple genomic loci is associated with a first condition; (b) Receive phenotypic data relating to multiple phenotypic traits of the non-human animal object, wherein at least one of the multiple phenotypic traits is associated with a second condition; (c) Genotype-phenotype profiles of the non-human animal subjects are generated by processing a dataset including the genetic data and the phenotypic data to determine qualitative or quantitative measurements of at least one of the plurality of genomic loci and qualitative or quantitative measurements of at least one of the plurality of phenotypes. (d) Applying a machine learning prediction model to the genotype-phenotype profile of the non-human animal subject to identify the nutritional product recommended for the non-human subject based at least in part on the probability that the non-human animal subject has the following: (i) the first situation or the risk of the first situation occurring; and (ii) The second situation or the risk of the second situation occurring; (e) The first situation is ranked relative to the second situation, at least in part, based on the severity of the first situation and the second situation, to identify the situation with the highest ranking among the first situation and the second situation; and (f) Manufacturing the nutritional product, wherein the nutritional product improves, mitigates or prevents at least the highest-ranking condition or the risk of the occurrence of at least the highest-ranking condition in the non-human animal subject.

2. The method of claim 1, wherein the first state or the second state comprises: One or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof.

3. The method of claim 1, wherein the non-human animal object is a feline, canine, or farm animal.

4. The method of claim 3, wherein the non-human animal object is a companion animal.

5. The method of claim 1, wherein the genetic data is determined by: Biological samples obtained from or already obtained from the non-human animal object; and Genotyping of the biological sample has been performed or is being performed.

6. The method of claim 1, further comprising receiving the gene data from a nucleic acid sequencing device, wherein the nucleic acid sequencing device includes a whole genome sequencer, a skim sequencer, a quantitative PCR (qPCR) device, or a DNA microarray.

7. The method of claim 1, wherein the at least one genomic locus includes one or more polymorphisms associated with the first condition.

8. The method of claim 1, further comprising receiving the phenotypic data from the guardian of the non-human animal object, the veterinarian of the non-human animal object, or a combination thereof.

9. The method of claim 1, wherein the plurality of phenotypes includes any combination of the weight, body mass index, sex, age, or breed of the non-human animal subject.

10. The method of claim 1, further comprising: Receive activity data from the non-human animal object; The genotype-phenotype profile is updated using the activity data to generate an updated profile; and The machine learning prediction model is applied to the updated spectrum.

11. The method of claim 10, wherein the activity data includes activity level, activity type, calories burned, sleep duration, or any combination thereof.

12. The method of claim 10, wherein the activity data includes information obtained from the activity tracking device.

13. The method of claim 1, further comprising: Receive environmental data from the non-human animal object; The genotype-phenotype profile is updated using the environmental data to generate an updated profile; and The machine learning prediction model is applied to the updated spectrum.

14. The method of claim 13, wherein the environmental data comprises: Urban environment, rural environment, residential location, presence of allergens, time spent indoors / outdoor, frequency of climbing stairs, or any combination thereof.

15. The method of claim 1, further comprising: Receive biomarker data of the non-human animal object, wherein the biomarker data includes the presence or level of one or more biomarkers detected in biological samples obtained from the non-human animal object, wherein the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, minerals or any combination thereof. The genotype-phenotype profile is updated using the biomarker data to generate an updated profile; and The machine learning prediction model is applied to the updated spectrum.

16. The method of claim 1, wherein the machine learning prediction model comprises clustering algorithms, decision tree algorithms, statistical algorithms, gradient boosting machines (GBM), or any combination thereof.

17. The method of claim 16, wherein the clustering algorithm is a centroid-based clustering algorithm.

18. The method of claim 16, wherein the machine learning prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model.

19. The method of claim 1, further comprising using samples from a validation cohort of non-human animal subjects belonging to the same species and having the first condition or the second condition to validate the machine learning prediction model.

20. The method of claim 1, further comprising training the machine learning prediction model using samples from a training cohort of non-human animal objects belonging to the same species.

21. The method of claim 20, wherein the training dataset comprises: (i) Gene data at multiple genomic loci of the training queue, wherein at least one of the multiple genomic loci is associated with the first condition; and (ii) Phenotypic data associated with multiple phenotypes of the training cohort of non-human animal subjects, wherein at least one of the multiple phenotypes is associated with the second condition.

22. The method of claim 1, further comprising providing notification to the guardian of the non-human animal or the veterinarian of the non-human animal, wherein the notification includes: (i) the first condition or the risk of the first condition occurring and the second condition or the risk of the second condition occurring in the non-human animal object; (ii) The genotype-phenotype profile of the non-human animal subjects; (iii) The nutritional products recommended for non-human animal subjects; (iv) Recommendations for behavioral correction of the aforementioned non-human animal subjects; (v) A prescription for a therapeutic or preventative intervention on the aforementioned non-human animal subject; or Any combination of (vi)(i) to (v).

23. The method of claim 22, wherein the behavior modification includes increasing, decreasing or avoiding one or more activities, wherein the one or more activities (i) increase or decrease the risk that the non-human animal subject will exhibit the first condition or the second condition, or (ii) worsen or improve the first condition or the second condition in the non-human animal subject.

24. The method of claim 23, wherein one or more of the activities include: (i) Engage in physical exercise; (ii) Ingesting the type or quantity of the nutritional product, wherein the nutritional product includes food, supplements or snacks; (iii) Exposure to the product; (iv) Use of the product; or Any combination of (v)(i) to (iv).

25. The method of claim 1, further comprising: Perform (a) through (b) at multiple time points to obtain new genotype or phenotype data; The genotype-phenotype profile is updated at the multiple time points using the new genotype data, the new phenotype data, or a combination thereof to generate an updated profile; and The machine learning prediction model is applied to the updated spectrum.

26. The method of claim 25, further comprising providing notification to the guardian of the non-human animal or the veterinarian of the non-human animal at one or more of the plurality of time points, wherein the notification includes: (i) the first condition in the non-human animal object or the risk of the first and second conditions or the risk of the second condition; (ii) the updated spectrum of the non-human animal object; (iii) Recommendations of products, behavior modification, or any combination thereof for the non-human animal subjects; (iv) A prescription for a therapeutic or preventative intervention for the aforementioned non-human animal subject; or Any combination of (v)(i) to (iv).

27. The method of claim 1, further comprising: Receive biomarker data, activity data, environmental data, behavioral data, or clinical data from the non-human animal subjects; An updated genotype-phenotype profile of the non-human animal subjects is generated by processing the biomarker data, the activity data, the environmental data, the behavioral data, or the clinical data, or a combination thereof, to determine their quantitative or qualitative measurements. and The machine learning prediction model was applied to the updated genotype-phenotype profile of the non-human animal subjects for identification: New nutritional products or new amounts of said nutritional products recommended for the non-human animal subjects; or Behavior correction of non-human animal subjects.

28. The method of claim 27, wherein the clinical information includes the medical history of the non-human animal subject or the medical history of a biological relative of the non-human animal subject.

29. The method of claim 27, wherein one or more behavioral traits include chewing, itching, aggression, neurosis, anxiety, energy level, or any combination thereof.

30. The method of claim 1, wherein the nutritional product comprises food, supplement, or snack, or any combination thereof.

31. A system configured to identify a nutritional product recommended for a non-human animal subject, the system comprising: A computing device including at least one processor, an operating system configured to execute executable instructions, memory, and a computer program, the computer program including instructions executable by the computing device to create an application, the application including: (a) A first module, configured to receive genetic data at multiple genomic loci of the non-human animal object by the at least one processor, wherein at least one of the multiple genomic loci is associated with a first condition; (b) A second module, the second module being configured to receive phenotypic data associated with multiple phenotypic traits of the non-human animal object by the at least one processor, wherein at least one of the multiple phenotypic traits is associated with a second condition; (c) A third module configured to generate a genotype-phenotype profile of the non-human animal object by processing the gene data and the phenotypic data by the at least one processor to determine qualitative or quantitative measurements of at least one of the plurality of genomic loci and qualitative or quantitative measurements of at least one of the plurality of phenotypes; (d) A fourth module, the fourth module being configured to apply a machine learning prediction model by the at least one processor to the genotype-phenotype profile of the non-human animal object to identify the nutritional product recommended for the non-human animal object based at least in part on the probability that the non-human animal object has: (i) the first situation or the risk of the first situation occurring; and (ii) The second situation or the risk of the second situation occurring; (e) A fifth module, configured by the at least one processor to rank the first situation relative to the second situation at least in part based on the severity of the first situation and the second situation to identify the situation with the highest ranking among the first and second situations; and (f) A sixth module, the sixth module being configured to identify the nutritional product for manufacture by the at least one processor, wherein the nutritional product improves, mitigates or prevents at least the highest-ranking condition or the risk of the occurrence of at least the highest-ranking condition in the non-human animal subject.

32. The system of claim 31, wherein the first condition or the second condition comprises: One or more genetic conditions, one or more nutritional conditions, one or more clinical conditions, one or more health conditions, one or more skin conditions, or one or more allergic conditions, or any combination thereof.

33. The system of claim 31, wherein the non-human animal object is a feline, canine, or farm animal.

34. The system of claim 31, wherein the non-human animal object is a companion animal.

35. The system of claim 31, wherein the genetic data is determined by obtaining or acquiring biological samples from the non-human animal object.

36. The system of claim 31, wherein the one or more processors are further configured to configure the first module to receive the gene data from a nucleic acid sequencing device, wherein the nucleic acid sequencing device includes a whole genome sequencer, a skim sequencer, a quantitative PCR (qPCR) device, or a DNA microarray.

37. The system of claim 31, wherein the at least one genomic locus includes one or more polymorphisms associated with the first condition.

38. The system of claim 31, wherein the one or more processors are further configured to cause the second module to be configured to receive the phenotypic data from the guardian of the non-human animal object, the veterinarian of the non-human animal object, or a combination thereof.

39. The system of claim 31, wherein the plurality of phenotypes includes any combination of the weight, body mass index, sex, age, or breed of the non-human animal object.

40. The system of claim 31, wherein the one or more processors are further configured to configure a module to receive activity data of the non-human animal object; wherein the third module is further configured to update the genotype-phenotype profile with the activity data to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile.

41. The system of claim 40, wherein the activity data includes activity level, activity type, calories burned, sleep duration, or any combination thereof.

42. The system of claim 40, wherein the activity data includes information obtained from the activity tracking device.

43. The system of claim 31, wherein the one or more processors are further configured to configure a module to receive environmental data of the non-human animal object; wherein the third module is further configured to update the genotype-phenotype profile with the environmental data to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile.

44. The system of claim 43, wherein the environmental data includes urban environment, rural environment, residential geographic location, presence of allergens, time spent indoors / outdoor, frequency of climbing stairs, or any combination thereof.

45. The system of claim 31, wherein the one or more processors are further configured to configure a module to receive biomarker data of the non-human animal object, wherein the biomarker data includes the presence or level of one or more biomarkers detected in a biological sample obtained from the non-human animal object, wherein the one or more biomarkers include proteins, sugars, lipids, hormones, vitamins, cells, metabolites, electrolytes, minerals, or any combination thereof; wherein the third module is further configured to update the genotype-phenotype profile with the biomarker data to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile.

46. ​​The system of claim 31, wherein the machine learning prediction model comprises clustering algorithms, decision tree algorithms, statistical algorithms, gradient boosting machines (GBM), or any combination thereof.

47. The system of claim 46, wherein the clustering algorithm is a centroid-based clustering algorithm.

48. The system of claim 46, wherein the machine learning prediction model is Genomic Best Linear Unbiased Prediction (GBLUP) or a Bayesian variable selection model.

49. The system of claim 31, wherein the machine learning prediction model is validated using samples from a validation cohort of non-human animal objects belonging to the same species that have the first condition or the second condition.

50. The system of claim 31, wherein the machine learning prediction model is trained using samples from a training cohort of non-human animal objects belonging to the same species.

51. The system of claim 50, wherein the training data set comprises: (i) Gene data at multiple genomic loci of the training queue, wherein at least one of the multiple genomic loci is associated with the first condition; (ii) Phenotypic data associated with multiple phenotypes of the training cohort of non-human animal subjects, wherein at least one of the multiple phenotypes is associated with the second condition.

52. The system of claim 31, wherein the one or more processors are further configured to configure the module to transmit the nutritional product recommended for the non-human animal object to a graphical user interface (GUI) on a user's personal electronic device.

53. The system of claim 52, wherein the GUI is configured to display a notification to the user, wherein the user is the guardian of the non-human animal object or the veterinarian of the non-human animal object.

54. The system of claim 52, wherein the system further comprises the user's personal electronic device.

55. The system of claim 31, wherein the notification includes: (i) the first condition or the risk of the first condition occurring and the second condition or the risk of the second condition occurring in the non-human animal object; (ii) The genotype-phenotype profile of the non-human animal subjects; (iii) The nutritional products recommended for non-human animal subjects; (iv) Recommendations for behavioral correction of the aforementioned non-human animal subjects; (v) A prescription for a therapeutic or preventative intervention on the non-human animal subject; or Any combination of (vi)(i) to (v).

56. The system of claim 55, wherein the behavior modification includes increasing, decreasing or avoiding one or more activities, wherein the one or more activities (i) increase or decrease the risk that the non-human animal subject will exhibit the first condition or the second condition, or (ii) worsen or improve the first condition or the second condition in the non-human animal subject.

57. The system of claim 56, wherein one or more of the activities include: (i) Engage in physical exercise; (ii) Ingesting the type or quantity of the nutritional product, wherein the nutritional product includes food, supplements or snacks; (iii) Exposure to the product; (iv) Use of the product; or Any combination of (v)(i) to (iv).

58. The system of claim 31, wherein the one or more processors are further configured to cause the first module and the second module to be further configured to receive the gene data and the phenotypic data at multiple time points to obtain new genotype data or new phenotypic data; wherein the third module is further configured to update the genotype-phenotype profile with the new genotype data, the new phenotypic data or a combination thereof at the multiple time points to generate an updated profile, and the fourth module is further configured to apply the machine learning prediction model to the updated profile.

59. The system of claim 58, wherein the one or more processors are further configured to configure the module to transmit the nutritional product recommended for the non-human animal object to a graphical user interface (GUI) on a user's personal electronic device.

60. The system of claim 59, wherein the GUI is configured to display a notification to the user, wherein the user is the guardian of the non-human animal object or the veterinarian of the non-human animal object.

61. The system of claim 58, wherein the notification includes: (i) the first condition or the risk of the first condition occurring and the second condition or the risk of the second condition occurring in the non-human animal object; (ii) the updated spectrum of the non-human animal object; (iii) Recommendations of products, behavior modification, or any combination thereof for the non-human animal subjects; (iv) A prescription for a therapeutic or preventative intervention for the aforementioned non-human animal subject; or Any combination of (v)(i) to (iv).

62. The system of claim 31, wherein the one or more processors are further configured to: a module is configured to receive biomarker data, activity data, environmental data, behavioral data, or clinical data of the non-human animal object; wherein the third module is further configured to generate an updated genotype-phenotype profile of the non-human animal object by processing the biomarker data, the activity data, the environmental data, the behavioral data, or the clinical data, or a combination thereof, to determine quantitative or qualitative measurements thereof; and wherein the fourth module is further configured to apply the machine learning prediction model to the updated genotype-phenotype profile of the non-human animal object to identify: a new nutritional product or a new amount of the nutritional product recommended for the non-human animal object; or behavioral correction for the non-human animal object.

63. The system of claim 62, wherein the clinical data includes the medical history of the non-human animal subject or the medical history of a biological relative of the non-human animal subject.

64. The system of claim 62, wherein the behavioral data includes chewing, itching, aggression, neurosis, anxiety, energy level, or any combination thereof.

65. The system of claim 31, wherein the nutritional product comprises food, supplements, or snacks, or any combination thereof.

66. A non-transitory computer-readable medium comprising machine-executable code, which, when executed by one or more computer processors, implements a method for identifying a nutritional product recommended for a non-human animal subject, the method being provided in any one of claims 1-30.

Images