Organic Molecular Exposomics

Abstract

This specification presents and describes methods for detecting, collecting, and analyzing the exposomics of target organic molecular signatures.

Description

[Technical Field]

[0001] cross reference This application claims the benefits of U.S. Provisional Patent Application No. 63 / 487,150, filed on 27 February 2023, which is incorporated herein by reference in its entirety. [Background technology]

[0002] Organic molecules play crucial roles in many biological processes that have structural and functional importance in human metabolic, physiological, and / or molecular pathways. Changes in the concentration of the organic molecules in question may be influenced by diet, intake of pharmaceutical compounds, exposure to the environment, and / or the progression or presence of disease.

[0003] Therefore, there is an unmet need for systems and devices that can rapidly and non-invasively assess rich datasets of target organic molecular signatures and classify one or more target molecules and / or biological phenotypes. [Overview of the project]

[0004] Aspects of the disclosure provided herein include a method for classifying the phenotype of a subject, comprising acquiring or collecting one or more organic molecular signatures from a plurality of locations along a biological sample of the subject, and determining the phenotype of the subject from the one or more organic molecular signatures of the subject. In some embodiments, the one or more organic molecular signatures include molecular signatures of molecules having a mass-to-charge ratio of at least 50 Daltons (Da). In some embodiments, the one or more organic molecular signatures include one or more time-resolved organic molecular signatures. In some embodiments, a light source is used to acquire or collect one or more organic molecular signatures from a plurality of locations along a biological sample. In some embodiments, the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof. In some embodiments, the phenotype of the subject includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more up-controlled or down-controlled physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof. In some embodiments, the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis (ALS), or any combination thereof. In some embodiments, the exogenous compound includes nicotine, melamine, or any combination thereof. In some embodiments, the endogenous compound includes an endogenous metabolite, a signaling molecule, or any combination thereof. In some embodiments, the signaling molecule includes hypotaurine. In some embodiments, the endogenous metabolite includes creatinine. In some embodiments, the dietary supplement includes agmatine. In some embodiments, the pharmaceutical includes a pharmaceutical for treating heartburn, acid reflux, peptic ulcer, or any combination thereof. In some embodiments, the pharmaceutical includes betasol. In some embodiments, the exposure phenotype includes the subject's exposure to environmental chemicals. In some embodiments, the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.In some embodiments, acquisition or collection involves performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assays, or any combination thereof on a biological sample. In some embodiments, the subject is administered or ingested a drug, dietary supplement, or combination thereof to treat a disease of the subject, and the subject's phenotype includes a response to the drug, dietary supplement, or combination thereof. In some embodiments, the phenotype is used to determine the modification of the drug, dietary supplement, or combination thereof to alleviate the disease of the subject. In some embodiments, the modification of the drug, dietary supplement, or combination thereof includes administering an improved or novel drug, dietary supplement, or combination thereof. In some embodiments, one or more organic molecule signatures include the temporal concentration of one or more organic molecules acquired or collected from a biological sample of the subject. In some embodiments, determining the phenotype of a target includes training a predictive model using one or more organic molecule signatures and associated phenotype labels of a set of targets different from the target, and providing one or more organic molecule signatures of the target to the trained predictive model to output the phenotype of the target.

[0005] Aspects of the disclosure provided herein include a method for classifying the phenotype of a subject, comprising: placing one or more probes on a biological sample of the subject; obtaining or collecting one or more molecular signatures from the biological sample of molecules having a mass-to-charge ratio of at least 50 Da; and determining the phenotype of the subject from the one or more molecular signatures of the subject. In some embodiments, the one or more molecular signatures include one or more organic molecular signatures. In some embodiments, a light source is used to obtain or collect one or more molecular signatures from one or more probes placed on a biological sample. In some embodiments, the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof. In some embodiments, the phenotype of the subject includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more up-controlled or down-controlled physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof. In some embodiments, the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis (ALS), or any combination thereof. In some embodiments, the exogenous compound includes nicotine, melamine, or any combination thereof. In some embodiments, the endogenous compound includes an endogenous metabolite, a signaling molecule, or any combination thereof. In some embodiments, the signaling molecule includes hypotaurine. In some embodiments, the endogenous metabolite includes creatinine. In some embodiments, the dietary supplement includes agmatine. In some embodiments, the pharmaceutical includes a pharmaceutical for treating heartburn, acid reflux, peptic ulcer, or any combination thereof. In some embodiments, the pharmaceutical includes betasol. In some embodiments, the betasol exposure phenotype includes exposure of the subject to environmental chemicals. In some embodiments, the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof. In some embodiments, acquisition or collection includes performing a protein fluorescence assay using one or more probes.In some embodiments, the subject is administered or ingested a drug, dietary supplement, or combination thereof to treat the disease of the subject, and the subject's phenotype includes a response to the drug, dietary supplement, or combination thereof. In some embodiments, the phenotype is used to determine the modification of the drug, dietary supplement, or combination thereof to alleviate the disease of the subject. In some embodiments, the modification of the drug, dietary supplement, or combination thereof includes administering an improved or novel drug, dietary supplement, or combination thereof. In some embodiments, determining the subject's phenotype includes training a predictive model with one or more molecular signatures and associated phenotypic labels of a set of subjects different from the subject, and providing one or more molecular signatures of the subject to the trained predictive model to output the subject's phenotype.

[0006] Aspects of the disclosure provided herein include a system for classifying the phenotype of a subject, comprising one or more processors and a memory for storing one or more programs to be executed by the one or more processors, wherein the one or more programs include instructions for (i) acquiring or collecting one or more organic molecular signatures of a biological sample from a plurality of locations along the biological sample of a subject, and (ii) determining the phenotype of the subject from the one or more organic molecular signatures of the subject. In some embodiments, the one or more organic molecular signatures include molecular signatures of molecules having a mass-to-charge ratio of at least 50 Daltons (Da). In some embodiments, the one or more organic molecular signatures include one or more time-resolved organic molecular signatures. In some embodiments, a light source is used to acquire or collect one or more organic molecular signatures from a plurality of locations along the biological sample. In some embodiments, the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof. In some embodiments, the phenotype of interest includes molecular phenotype, physiological phenotype, behavioral phenotype, disease phenotype, healthy phenotype, exposure phenotype, one or more upregulated or downregulated physiological pathways, response to pharmaceuticals, response to dietary supplements, presence of exogenous compounds, presence of endogenous compounds, presence of inflammation, or any combination thereof. In some embodiments, the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis (ALS), or any combination thereof. In some embodiments, the exogenous compound includes nicotine, melamine, or any combination thereof. In some embodiments, the endogenous compound includes endogenous metabolites, signaling molecules, or any combination thereof. In some embodiments, the signaling molecule includes hypotaurine. In some embodiments, the endogenous metabolite includes creatinine. In some embodiments, the dietary supplement includes agmatine. In some embodiments, the pharmaceutical includes pharmaceuticals for treating heartburn, acid reflux, peptic ulcers, or any combination thereof. In some embodiments, the pharmaceutical product includes betasol.In some embodiments, the exposure phenotype includes the subject's exposure to environmental chemicals. In some embodiments, the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof. In some embodiments, acquisition or collection includes performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof on the biological sample. In some embodiments, the subject is administered or ingested a drug, dietary supplement, or combination thereof to treat a disease of the subject, and the subject's phenotype includes a reaction to the drug, dietary supplement, or combination thereof. In some embodiments, the phenotype is used to determine the modification of a drug, dietary supplement, or combination thereof to alleviate a disease of the subject. In some embodiments, the modification of a drug, dietary supplement, or combination thereof includes administering an improved or novel drug, dietary supplement, or combination thereof. In some embodiments, one or more organic molecule signatures include the temporal concentration of one or more organic molecules acquired or collected from the biological sample of the subject. In some embodiments, determining the phenotype of a target includes training a predictive model using one or more organic molecule signatures and associated phenotype labels of a set of targets different from the target, and providing one or more organic molecule signatures of the target to the trained predictive model to output the phenotype of the target.

[0007] Aspects of the disclosure provided herein include a system for classifying the phenotype of a subject, comprising one or more processors and a memory for storing one or more programs to be executed by the one or more processors, the one or more programs including instructions for (i) obtaining or collecting one or more molecular signatures from a biological sample having a mass-to-charge ratio of at least 50 Da when one or more probes are placed on the biological sample of the subject, and (ii) determining the phenotype of the subject from the one or more molecular signatures of the subject. In some embodiments, the one or more molecular signatures include one or more organic molecular signatures. In some embodiments, a light source is used to obtain or collect one or more molecular signatures from the biological sample. In some embodiments, the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof. In some embodiments, the phenotype of interest includes molecular phenotype, physiological phenotype, behavioral phenotype, disease phenotype, healthy phenotype, exposure phenotype, one or more upregulated or downregulated physiological pathways, response to pharmaceuticals, response to dietary supplements, presence of exogenous compounds, presence of endogenous compounds, presence of inflammation, or any combination thereof. In some embodiments, the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis (ALS), or any combination thereof. In some embodiments, the exogenous compound includes nicotine, melamine, or any combination thereof. In some embodiments, the endogenous compound includes endogenous metabolites, signaling molecules, or any combination thereof. In some embodiments, the signaling molecule includes hypotaurine. In some embodiments, the endogenous metabolite includes creatinine. In some embodiments, the dietary supplement includes agmatine. In some embodiments, the pharmaceutical includes pharmaceuticals for treating heartburn, acid reflux, peptic ulcers, or any combination thereof. In some embodiments, the pharmaceutical product comprises betasol. In some embodiments, the exposure phenotype comprises exposure of the subject to environmental chemicals.In some embodiments, the biological sample includes samples of hair, teeth, fingernails, toenails, or any combination thereof. In some embodiments, the instruction to acquire or collect includes performing a protein fluorescence assay using one or more probes. In some embodiments, the subject is administered or ingested a drug, dietary supplement, or combination thereof to treat the disease of the subject, and the subject's phenotype includes a response to the drug, dietary supplement, or combination thereof. In some embodiments, the phenotype is used to determine the modification of the drug, dietary supplement, or combination thereof to alleviate the disease of the subject. In some embodiments, the modification of the drug, dietary supplement, or combination thereof includes administering an improved or novel drug, dietary supplement, or combination thereof. In some embodiments, the instruction to determine the subject's phenotype includes training a predictive model with one or more molecular signatures and associated phenotypic labels of a set of subjects different from the subject, and providing one or more molecular signatures of the subject to the trained predictive model to output the subject's phenotype.

[0008] Aspects of the disclosure provided herein include a method for training an untrained or partially untrained machine learning algorithm or predictive model, comprising: collecting or acquiring one or more organic molecular signatures of a plurality of biological samples to be trained, in a computer system having one or more processors and memory for storing one or more programs to be executed by the one or more processors, wherein a first subset of the plurality of trained samples has a first phenotype associated with one or more organic molecular signatures, and a second subset of the plurality of trained samples has a second phenotype associated with one or more organic molecular signatures; and training an untrained or partially untrained machine learning algorithm or predictive model using one or more organic molecular signatures of the plurality of trained samples and the corresponding first and second phenotypes associated with one or more organic molecular signatures, thereby creating or generating a trained predictive model. In some embodiments, one or more organic molecular signatures include one or more organic molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da. In some embodiments, one or more organic molecular signatures include one or more time-resolved organic molecular signatures. In some embodiments, a light source is used to acquire or collect one or more organic molecular signatures from multiple biological samples under training. In some embodiments, the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof. In some embodiments, the first or second phenotype includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more up-controlled or down-controlled physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof. In some embodiments, the disease phenotype includes autism spectrum disorder (ASD), attention deficit hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof. In some embodiments, the exogenous compound includes nicotine, melamine, or any combination thereof.In some embodiments, the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof. In some embodiments, the signaling molecule comprises hypotaurine. In some embodiments, the endogenous metabolite comprises creatinine. In some embodiments, the dietary supplement comprises agmatine. In some embodiments, the pharmaceutical comprises a pharmaceutical for treating heartburn, acid reflux, peptic ulcers, or any combination thereof. In some embodiments, the pharmaceutical comprises betasol. In some embodiments, the exposure phenotype comprises the subject's exposure to environmental chemicals. In some embodiments, the biological sample comprises a sample of hair, teeth, fingernails, toenails, or any combination thereof. In some embodiments, acquisition or collection comprises performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof on the biological sample. In some embodiments, multiple training subjects are administered or ingested pharmaceuticals, dietary supplements, or combinations thereof to treat diseases of the multiple training subjects, and a first or second phenotype of the multiple training subjects includes a response to the pharmaceuticals, dietary supplements, or combinations thereof. In some embodiments, the first or second phenotype is used to determine the modification of the pharmaceuticals, dietary supplements, or combinations thereof to alleviate the disease of the subject. In some embodiments, the modification of the pharmaceuticals, dietary supplements, or combinations thereof includes administering improved or novel pharmaceuticals, dietary supplements, or combinations thereof. In some embodiments, one or more organic molecular signatures include the temporal concentration of one or more organic molecular signatures obtained or collected from biological samples of the multiple training subjects. [Brief explanation of the drawing]

[0009] Novel features of the present invention are specifically described in the appended claims. For a better understanding of the features and advantages of the present invention, please refer to the following detailed description and the appended drawings, which describe exemplary embodiments in which the principles of the present invention are used.

[0010] [Figure 1] Figure 1 shows a flowchart of a method for determining a target phenotype from one or more organic molecular signatures, as described in some embodiments of this specification. [Figure 2] Figure 2 shows a flowchart of a method for determining a target phenotype from one or more molecular signatures, as described in some embodiments of this specification. [Figure 3A] Figures 3A and 3B show representative concentrations of the hypotaurine organic molecular signature collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 3A), as well as a comparison of mean hypotaurine concentrations across a control group and an autism spectrum disorder group (Figure 3B). [Figure 3B] Figures 3A and 3B show representative concentrations of the hypotaurine organic molecular signature collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 3A), as well as a comparison of mean hypotaurine concentrations across a control group and an autism spectrum disorder group (Figure 3B). [Figure 4A] Figures 4A and 4B show representative concentrations of melamine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 4A), as well as comparisons of mean melamine concentrations across a control group and an autism spectrum disorder group (Figure 4B). [Figure 4B]Figures 4A and 4B show representative concentrations of melamine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 4A), as well as comparisons of mean melamine concentrations across a control group and an autism spectrum disorder group (Figure 4B). [Figure 5A] Figures 5A and 5B show representative concentrations of agmatine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 5A), as well as comparisons of mean agmatine concentrations across a control group and an autism spectrum disorder group (Figure 5B). [Figure 5B] Figures 5A and 5B show representative concentrations of agmatine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 5A), as well as comparisons of mean agmatine concentrations across a control group and an autism spectrum disorder group (Figure 5B). [Figure 6A] Figures 6A and 6B show representative concentrations of betasol organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 6A), as well as comparisons of mean betasol concentrations across a control group and an autism spectrum disorder group (Figure 6B). [Figure 6B] Figures 6A and 6B show representative concentrations of betasol organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 6A), as well as comparisons of mean betasol concentrations across a control group and an autism spectrum disorder group (Figure 6B). [Figure 7A]Figures 7A and 7B show representative concentrations of creatinine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 7A), as well as comparisons of mean creatinine concentrations across a control group and an autism spectrum disorder group (Figure 7B). [Figure 7B] Figures 7A and 7B show representative concentrations of creatinine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 7A), as well as comparisons of mean creatinine concentrations across a control group and an autism spectrum disorder group (Figure 7B). [Figure 8A] Figures 8A and 8B show representative concentrations of nicotine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 8A), and a comparison of average nicotine concentrations across non-smokers and smokers (Figure 8B). [Figure 8B] Figures 8A and 8B show representative concentrations of nicotine organic molecular signatures collected across biological samples using the methods, devices, and / or systems described herein, as described in some embodiments herein (Figure 8A), and a comparison of average nicotine concentrations across non-smokers and smokers (Figure 8B). [Figure 9] Figure 9 shows the receiver operating feature curve and corresponding area under curve performance of a predictive model trained with one or more organic molecular signatures when classifying subjects with autism spectrum disorder, as described in some embodiments of this specification. [Figure 10A] Figures 10A and 10B show a composite index (Figure 10A) derived from multiple organic molecules between a control and a subject with autism spectrum disorder, as described in some embodiments herein, and the importance of associated features for each of the multiple organic molecules considered in the composite index (Figure 10B). [Figure 10B] Figures 10A-10B show a composite index derived from a plurality of organic molecules between a control and a subject with an autism spectrum disorder (Figure 10A), and the importance of associated features for each of the plurality of organic molecules considered in the composite index (Figure 10B), as described in some embodiments of this specification. [Figure 11A] Figures 11A-11B show a composite index derived from a plurality of organic molecules between a control and a subject with amyotrophic lateral sclerosis (Figure 11A), and the importance of associated features for each of the plurality of organic molecules considered in the composite index (Figure 11B), as described in some embodiments of this specification. [Figure 11B] Figures 11A-11B show a composite index derived from a plurality of organic molecules between a control and a subject with amyotrophic lateral sclerosis (Figure 11A), and the importance of associated features for each of the plurality of organic molecules considered in the composite index (Figure 11B), as described in some embodiments of this specification. [Figure 12] Figure 12 shows a computer system configured to implement the method of the present disclosure, as described in some embodiments of this specification. **DETAILED DESCRIPTION OF THE INVENTION**

[0011] Throughout this application, various embodiments may be presented in a range format. The description in range format is merely for convenience and brevity and should not be construed as an immutable limitation on the scope of the present disclosure. It should be understood that the description of a range should be considered as specifically disclosing any possible sub-ranges as well as individual numerical values within that range. For example, a description of a range such as 1-6 should be considered as specifically disclosing sub-ranges such as 1-3, 1-4, 1-5, 2-4, 2-6, 3-6, etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0012] As used herein and in the claims, the singular forms "a," "an," and "the" include plural references unless the context explicitly indicates otherwise. For example, the term "sample" includes multiple samples, as well as mixtures thereof.

[0013] The terms “determining,” “measuring,” “evaluating,” “assessing,” and “analyzing” are often used interchangeably herein to refer to forms of measurement. These terms include determining whether an element is present or not (e.g., detection). Such terms may include quantitative, qualitative, or both quantitative and qualitative determinations. Assessments may be relative or absolute. “Detecting the presence of ~” may include determining the quantity of something that is present, in addition to determining whether something is present or not, depending on the context.

[0014] The terms “subject,” “individual,” and “patient” are often used interchangeably herein. A “subject” may be a biological entity containing expressed genetic material. A biological entity may be a plant, animal, or microorganism, including, for example, bacteria, viruses, fungi, and protists. A subject may be a tissue, cell, or offspring of a biological entity obtained in vivo or cultured in vitro. A subject may be a mammal. A mammal may be a human. A subject may be diagnosed or suspected of being at high risk for a disease. In some cases, a subject may not necessarily be diagnosed or suspected of being at high risk for a disease. In some cases, a subject may comprise a set or group of one or more subjects.

[0015] The term "in vivo" is used to describe events that occur within the body of a subject.

[0016] The term "ex vivo" is used to describe events that occur outside the body of the subject. Ex vivo assays are not performed on the subject; rather, the assay is performed on a sample separate from the subject. An example of an ex vivo assay performed on a sample is an "in vitro" assay.

[0017] The term "in vitro" is used to describe events that occur when experimental reagents are contained within a container for holding experimental reagents, as they are separated from the biological source from which the material is obtained. In vitro assays may include cell-based assays that use live or dead cells. In vitro assays may also include cell-free assays that do not use intact cells.

[0018] As used herein, a number preceded by the term "approximately" refers to a number plus or minus 10% of that number. A range preceded by the term "approximately" refers to a range of minus 10% of its lowest value and plus 10% of its highest value.

[0019] As used herein, the terms “treatment” or “treating” are used in reference to a medical or other interventional regimen for obtaining a beneficial or desired outcome in a recipient. Beneficial or desired outcomes include, but are not limited to, therapeutic benefits and / or preventive benefits. Therapeutic benefits may also refer to the eradication or alleviation of the symptom or underlying condition being treated. Furthermore, therapeutic benefits can be achieved by eradicating or alleviating one or more physiological symptoms associated with an underlying condition, thereby resulting in improvement in the subject, even though the subject may still suffer from the underlying condition. Preventive effects include delaying, preventing, or eliminating the onset of a disease or illness; delaying or eliminating the onset of symptoms of a disease or illness; slowing, stopping, or reversing the progression of a disease or illness, or any combination thereof. For preventive benefits, subjects at risk of developing a particular disease, or subjects reporting one or more physiological symptoms of a disease, even if they have not been diagnosed with the disease, may be treated.

[0020] The methods and / or systems described herein measure, detect, and / or acquire one or more molecular signatures (e.g., one or more organic molecular signatures) of one or more biological samples of one or more subjects. In some cases, the one or more molecular signatures may include the concentrations of one or more molecules (e.g., one or more organic molecules). In some cases, the methods and / or systems described herein may non-invasively measure, detect, and / or acquire the concentrations of one or more molecular signatures. The one or more molecular signatures may be used as features for classifying and / or predicting the phenotype of a subject. In some cases, the phenotype of a subject may include a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof. In some cases, the disease phenotype may include autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis (ALS), cancer, or any combination thereof. In some cases, the exogenous compound may include nicotine, melamine, or any combination thereof. In some cases, the endogenous compound may include metabolites, signaling molecules, or any combination thereof. The signaling molecule may include hypotaurine. In some cases, the endogenous metabolite may include creatinine. In some cases, the dietary supplement may include agmatine. In some cases, the drug may include medication for treating heartburn, acid reflux, peptic ulcers, or any combination thereof. In some cases, the drug may include betasol. In some cases, the exposure phenotype may include the subject's exposure to environmental chemicals.

[0021] In some cases, the subject's phenotype may be used to determine the subject's response to a drug and / or supplement administered to it. In some cases, the subject's phenotype may be used to indicate methods of adjustment, such as completely changing a drug and / or supplement, adding a drug and / or supplement, identifying a new drug and / or supplement to administer to the subject, changing a drug and / or supplement administration regimen, or any combination thereof. In some cases, the administered drug and / or supplement may alleviate the disease of the subject, or one or more symptoms of the disease and / or illness.

[0022] In some cases, the biological sample may include biological tissue, a biopsy of a living tissue, a fluid biopsy, or any combination thereof. In some cases, the biological tissue may include fingernails, toenails, hair, teeth, or any combination thereof.

[0023] In some cases, a light source may be used to acquire and / or collect one or more molecular signatures from a biological sample. In some cases, the light source may include a laser, pulsed laser, continuous-wave laser, or any combination thereof. In some cases, one or more molecular signatures may be detected, measured, and / or acquired using matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MADLI ToF MS), laser ablation electrospray ionization (LAESI), trapped ion mobility analysis (TIMS), time-of-flight (TOF) mass spectrometry, protein fluorescence assay, or any combination thereof.

[0024] method In some cases, the disclosure provided herein describes a method (100) for classifying the phenotype of a subject, as shown in Figure 1. In some cases, the method may include obtaining, collecting, and / or sampling one or more organic molecule signatures from multiple locations along a biological sample of the subject (102) and determining the phenotype of the subject from one or more organic molecule signatures (104). In some cases, one or more organic molecule signatures may include molecular signatures of molecules having a mass-to-charge ratio of at least 50 daltons (Da). In some cases, determining the phenotype of a subject may include training a predictive model, as described elsewhere herein, using one or more organic molecule signatures and associated phenotype labels of a set of subjects different from the subject, and providing one or more organic molecule signatures of the subject to the trained predictive model to output the phenotype of the subject. In some cases, sampling may create a set of data points for one or more organic molecule signatures at one or more locations among multiple locations on the biological sample. In some cases, the set of data points may represent the dynamic biological response of the subject measured at multiple locations along the biological sample. The locations on the biological sample where one or more organic molecular signatures are acquired, collected, and / or sampled may correspond to specific growth times of the biological sample, e.g., earlier or later points in the biological sample's growth time. For example, in the case of a hair biological sample, one or more locations on the hair biological sample may correspond to a hair growth period of approximately 20 minutes for the subject, and a section of approximately 1 centimeter may correspond to a growth period of approximately 1 month for the subject.

[0025] In some cases, the first of multiple locations may be adjacent to the second of multiple locations. In some cases, the multiple locations may overlap. In some cases, the multiple locations may not overlap and may include separate regions on the biological sample. In some cases, the multiple locations may be separated by a predetermined distance. In some cases, the distance may vary across multiple locations along the biological sample. In some cases, acquisition, collection, and / or sampling may be performed along the axis of the biological sample, starting at the location closest to the root or hairline of the biological sample, e.g., the location of the biological sample closest to the hair follicle, the location on the nail closest to the cuticle, the location toward the central axis of the tooth cross-section, or the axis corresponding to any combination thereof. In some cases, one or more organic molecular signatures obtained at a location at the hairline of the biological sample may indicate and / or represent one or more organic molecular signatures at an earlier point in the development of the organism in question.

[0026] In some cases, multiple locations include at least about 100, at least about 200, at least about 300, at least about 500, at least about 700, at least about 800, at least about 1000, at least about 1500, at least about 2000, at least about 2500, at least about 3000, at least about 3500, at least about 4000, at least about 4500, at least about 5000, at least about 5500, at least about 6000, at least about 6500, at least about 7000, at least about 7500, at least about 8000, at least about 8500, at least about 9000, at least about 9500, at least about 10000, or at least about 10000 locations on the biological sample.

[0027] In some cases, one or more organic molecular signatures may include molecular signatures of molecules having a mass-to-charge ratio of approximately 50 Da to approximately 500,000 Da. In some cases, one or more organic molecule signatures are approximately 50Da to 100Da, approximately 50Da to 500Da, approximately 50Da to 1,000Da, approximately 50Da to 10,000Da, approximately 50Da to 20,000Da, approximately 50Da to 40,000Da, approximately 50Da to 50,000Da, approximately 50Da to 100,000Da, approximately 50Da to 250,000Da, approximately 50Da to 500,000Da, approximately 100Da to 500Da, approximately 100Da to 1,000Da, approximately 100Da to 10,000Da, and approximately 100Da. a~approx. 20,000Da, approx. 100Da~approx. 40,000Da, approx. 100Da~approx. 50,000Da, approx. 100Da~approx. 100,000Da, approx. 100Da~approx. 250,000Da, approx. 100Da~approx. 500,000Da, approx. 500Da~approx. 1,000Da, approx. 500Da~approx. 10,000Da, approx. 500Da~approx. 20,000Da, approx. 500Da~approx. 40,000Da, approx. 500Da~approx. 50,000Da, approx. 500Da~approx. 100,000Da, approx. 500Da~approx. 250,000Da, approx. 500Da~approx. 500,000Da 00Da, approx. 1,000Da~approx. 10,000Da, approx. 1,000Da~approx. 20,000Da, approx. 1,000Da~approx. 40,000Da, approx. 1,000Da~approx. 50,000Da, approx. 1,000Da~approx. 100,000Da, approx. 1,000Da~approx. 250,000Da, approx. 1,000Da~approx. 500,000Da, approx. 10,000Da~approx. 20,000Da, approx. 10,000Da~approx. 40,000Da, approx. 10,000Da~approx. 50,000Da, approx. 10,000Da~approx. 100,000Da, approx. 10,000Da~ Approximately 250,000 Da, approximately 10,000 Da to approximately 500,000 Da, approximately 20,000 Da to approximately 40,000 Da, approximately 20,000 Da to approximately 50,000 Da, approximately 20,000 Da to approximately 100,000 Da, approximately 20,000 Da to approximately 250,000 Da, approximately 20,000 Da to approximately 500,000 Da, approximately 40,000 Da to approximately 50,000 Da, approximately 40,000 Da to approximately 100,000 Da, approximately 40,000 Da to approximately 250,000 Da, approximately 40,000 Da to approximately 500,000 Da, approximately 50,000 Da to approximately 100,The molecular signatures may include those of molecules having mass-to-charge ratios of 000Da, approximately 50,000Da to approximately 250,000Da, approximately 50,000Da to approximately 500,000Da, approximately 100,000Da to approximately 250,000Da, approximately 100,000Da to approximately 500,000Da, or approximately 250,000Da to approximately 500,000Da. In some cases, one or more organic molecular signatures may include molecular signatures of molecules having mass-to-charge ratios of approximately 50 Da, 100 Da, 500 Da, 1,000 Da, 10,000 Da, 20,000 Da, 40,000 Da, 50,000 Da, 100,000 Da, 250,000 Da, or 500,000 Da. In some cases, one or more organic molecular signatures may include molecular signatures of molecules having a mass-to-charge ratio of at least about 50 Da, about 100 Da, about 500 Da, about 1,000 Da, about 10,000 Da, about 20,000 Da, about 40,000 Da, about 50,000 Da, about 100,000 Da, or about 250,000 Da. In some cases, one or more organic molecular signatures may include molecular signatures of molecules having a mass-to-charge ratio of up to about 100 Da, about 500 Da, about 1,000 Da, about 10,000 Da, about 20,000 Da, about 40,000 Da, about 50,000 Da, about 100,000 Da, about 250,000 Da, or about 500,000 Da. ,

[0028] In some cases, one or more organic molecule signatures may include one or more time-resolved organic molecule signatures, as shown in Figures 3A, 4A, 5A, 6A, 7A, and / or 8A. For example, one or more organic molecule signatures may be determined at each of a plurality of locations along a biological sample, as described elsewhere in this specification. In some cases, the plurality of locations along the biological sample may be locations along axes (e.g., linear and / or nonlinear axes) on the biological sample. In some cases, the linear and / or nonlinear axes may be on one or more surfaces of the biological sample. In some cases, the first and second locations of the plurality may be spatially overlapping, or they may be spatially distinct and not overlapping. In some cases, each of the locations along the biological sample may give a time dimension to one or more organic molecule signatures corresponding to the time period and / or growth period of interest. In some cases, the temporal variation in the concentration of one or more molecular signatures collected at multiple locations along a biological sample may provide characterization and / or determination of the target phenotype with an accuracy of at least approximately 90%, at least approximately 92%, at least approximately 94%, at least approximately 96%, at least approximately 98%, or at least approximately 98%. In some cases, the geometric mean or mean of the concentration of organic molecules over time may be calculated and used as a feature in the characterization and / or classification of the target phenotype.

[0029] In some cases, the disclosure provided herein describes a method for classifying the phenotype of a subject, as shown in Figure 2 (200). In some cases, the method may include, once one or more probes are placed on the biological sample of a subject, obtaining or collecting one or more molecular signatures from the biological sample of molecules having a mass-to-charge ratio of at least 50 Da (202), and determining the phenotype of the subject from the one or more molecular signatures. In some cases, the one or more molecular signatures may be determined simultaneously (204). In some cases, the one or more molecular signatures may include one or more organic molecular signatures. In some cases, a light source may be used to obtain or collect one or more molecular signatures from one or more probes placed on the biological sample. In some cases, the light source may include a laser, a pulsed laser, a continuous-wave laser, or any combination thereof. In some cases, one or more probes may include a binding site configured to bind to a protein. In some cases, a first probe among one or more probes may include a binding site targeted to bind to a first protein, and a second probe among one or more probes may include a binding site targeted to bind to a second protein. In some cases, the first and second proteins may be located at a distance such that the first and second probes can bind to each other to form a probe complex. In some cases, a signaling molecule, such as a fluorescent molecule, may be bound to the probe complex and detected by exciting the signaling molecule with a light source and detecting the signal therefrom. In some cases, detection of a fluorescent molecule and / or the associated intensity of a fluorescent molecule may result in the concentration and / or presence of a molecule of one or more molecular signatures in a biological sample. In some cases, the composite index may be calculated and / or determined from one or more molecular signatures of one or more subjects. In some cases, the composite index may be used to distinguish one or more groups or sets of subjects based on classified and / or characterized phenotypes. In some cases, the composite index may be determined by one or more calculation methods.In some cases, the calculation method may include supervised discriminant analysis, canonical correlation analysis, exploratory factor analysis, confirmatory factor analysis, partial least squares, partial least squares discriminant analysis, linear discriminant analysis, or any combination thereof. In some cases, determining the phenotype of a subject may include training a predictive model, as described elsewhere herein, with one or more molecular signatures and associated phenotypic labels of a set of subjects different from the subject, and providing one or more molecular signatures of the subject to the trained predictive model to output the phenotype of the subject.

[0030] In some cases, determining and / or classifying the phenotype of a subject may involve processing one or more molecular signatures acquired at one or more locations among a plurality of locations on the biological sample of the subject. In some cases, determining and / or classifying the phenotype of a subject from one or more molecular signatures, e.g., one or more molecular signatures acquired and / or obtained at one or more locations among a plurality of locations on the biological sample of the subject, may involve processing one or more molecular signatures acquired and / or obtained at one or more locations among a plurality of locations on the biological sample to generate one or more features of the one or more molecular signatures. In some cases, computational analysis and / or processing may involve determining differences between one or more molecular signatures across a biological sample, e.g., one or more molecular signatures acquired and / or obtained at one or more adjacent locations among a plurality of locations on the biological sample, e.g., one or more adjacent locations among a plurality of locations on the biological sample may include temporal relationships. For example, one or more molecular signatures acquired and / or collected at a first location on a biological sample may include and / or be associated with a value at a first time point, and one or more molecular signatures acquired and / or collected at a second location adjacent to the first location on the biological sample may include and / or be associated with a value at a second time point different from the first time point. In some cases, one or more molecular signatures between a first location, a second location, and / or another location among a plurality of locations may provide a time signature of one or more molecular signatures. In some cases, the time dynamics of one or more molecular time signatures may be processed and / or analyzed.In some cases, one or more molecular signatures may be processed and / or analyzed by dimensionality reduction techniques and / or methods as described elsewhere herein, for example, by independent component analysis (ICA) and / or principal component analysis (PCA), non-negative matrix factorization (NNMF), unsupervised dimensionality reduction, supervised dimensionality reduction, or any combination thereof of one or more molecular signatures and / or one or more features of one or more molecular signatures. In some cases, the temporal dynamics of one or more molecular signatures may be processed and / or analyzed by recurrent quantification analysis (RQA) to extract features describing the temporal dynamics of one or more molecular signatures and / or to extract features of the one or more molecular signatures after dimensionality reduction, as described elsewhere herein. In some cases, processing and / or analyzing the temporal dynamics of one or more molecular signatures may result in one or more features of the temporal dynamics of one or more molecular signatures. In some cases, one or more features may include relapse rate, relapse time (RT), determinism, Lmax, mean diagonal length (MDL), maximum diagonal length, divergence, Shannon entropy in diagonal length, relapse tendency, laminar flow, trapping time (TT), maximum vertical length, Shannon entropy in vertical length, mean relapse time, Shannon entropy in relapse time, most likely number of relapses, or any combination thereof.

[0031] RQA may measure the temporal and / or time-dependent variability of domains and / or properties of one or more molecular signatures acquired at one or more locations among a plurality of locations of a biological sample, as described elsewhere in this specification. RQA may include feature estimations, as described elsewhere in this specification, that describe the periodic properties of one or more temporal and / or time-dependent aspects of one or more molecular signatures.

[0032] The methods and characteristics of RQA are described, for example, by Webber et al., “Simpler Methods Do It Better: Success of Recurrence Quantification Analysis as a General Purpose Data Analysis Tool,” Physics Letters A 373, 3753-3756 (2009) and Marwan et al., “Recurrence Plots for the Analysis of Complex Systems,” Physics Reports 438, 237-239 (2007), the contents of which are incorporated herein by reference in whole. In some embodiments, one or more time-dependent molecular signatures may be analyzed by other analytical methods such as Fourier transform, wavelet analysis, cosiner analysis, or any combination thereof. Similar metrics may be derived by applying such techniques, including spectral analysis of the frequency components of one or more molecular signatures and the powers associated with them. These metrics and associated derived measures may be used in place of, and / or in addition to, features derived from RQA to analyze one or more time-dependent molecular signatures obtained from biological samples to provide, determine, classify, and / or characterize one or more phenotypes of one subject and / or multiple phenotypes of multiple subjects.

[0033] RQA may include determining, constructing, and / or displaying recursive plots that visualize and / or analyze the dynamic temporal structure of one or more molecular signatures. Such recursive plots can illustrate the phase process in continuous measurements by plotting a given sequence against the time-lag derivation of that sequence. From a one-dimensional molecular signature measured from a hair shaft, further dimensions may be computationally derived, and the molecular signature may be embedded in a higher-dimensional space called a phase diagram, where t refers to the value of the original molecular signature, and the dimensions (t+τ) and (t+2τ) may be derived by delaying the time series of the original molecular signature by an interval τ. Subsequently, the embedded phase diagram may be subjected to the following analysis, a recursive plot may be constructed, and a recursive quantification analysis may be performed. A recursive quantification plot can be derived from a phase diagram by applying a threshold function to each point in the phase diagram. On the corresponding recursive plot, which typically consists of a binary matrix of squares represented in white or black space, a given point is assigned a value of 1 for each time interval, and other points in the phase diagram share the spatial limit of the assigned threshold boundary. The RQA method is applied to a recursive plot to examine the interval of delay between states in a given system, where black points reflect the time interval when the system revisits the same state. A periodic process in which the system continuously repeats a given state pattern may be represented by black diagonals in the recursive plot, periods of stability are represented by a square structure, spurious repeats are represented by black points, and unique events are represented by white space.

[0034] In some embodiments, the recursive plot may be constructed for one or more molecular signatures (for example, to visualize an interactive periodic pattern of two or more molecular signatures, which may be referred to as cross-recursive quantification analysis or joint recursive quantification analysis). In some embodiments, the recursive plot may be constructed for a combination of three or more molecular signatures.

[0035] In some embodiments, data analysis may include analyzing recursive plots to obtain a set of features associated with the recursive plots. Features, which may be interchangeably referred to as “rhythmic features” or “dynamic features,” can provide quantitative measures that describe the periodicity, predictability, and transitivity present in one or more molecular signatures. Features may be selected from a set that includes recurrence rate, determinism, mean diagonal length, maximum diagonal length, divergence, Shannon entropy in diagonal length, recurrence tendency, laminar flow, trapping time, maximum vertical length, Shannon entropy in vertical length, mean recurrence time, Shannon entropy in recurrence time, number of most likely recurrences, or any combination thereof, as described elsewhere in this specification.

[0036] In some embodiments, the data analysis may further include providing the acquired set of features as input to one or more trained predictive models and / or one or more machine learning algorithms. In some embodiments, the one or more trained predictive models and / or one or more machine learning algorithms may include predictive computation algorithms to acquire the probability of one or more objects having a phenotype. In some embodiments, the predictive models and / or machine learning computation algorithms perform the following calculations:

[0037]

number

[0038] Weight parameters β1, ..., β k The probability p(target) may be defined based on the training of a predictive model and / or a machine learning algorithm. The probability p(target) may be given as a number in the range of 0 to 1, where 1 corresponds to a 100% probability that the target has the phenotype.

[0039] In some embodiments, data analysis may include applying a threshold to the acquired probability p(subject). If the acquired probability p(subject) is above a predetermined threshold, the subject may be evaluated as having a phenotype. If the acquired probability is below the threshold, the subject may be evaluated as not having a phenotype. In some embodiments, the threshold is about 0.3 to 0.6 (for example, a predetermined threshold may be about 0.3, about 0.35, about 0.4, about 0.45, about 0.5, about 0.55, or about 0.6). The value assigned to the stochastic threshold may be predetermined or estimated when training a predictive model and / or machine learning algorithm via the use of a receiver operating characteristic (ROC) chart, and the optimal threshold used corresponds to the value that yields the maximum area under the curve (AUROC). In some embodiments, the acquired probability may be expressed in terms of associated odds (e.g., odds ratios (OR) which can be derived from the probability, such as OR = p / (1-p)). For example, the evaluation may include evaluating the odds that the subject has a biological state.

[0040] The actions described above represent each of the methods or sets of actions according to the embodiments, but many variations are possible. These actions may be completed in different orders. Actions may be added or omitted. Some actions may include partial actions. Many actions may be repeated any number of times if beneficial.

[0041] One or more operations of each method or set of operations may be performed using one or more circuits, such as those described herein, logic circuits, such as a processor or programmable array logic for a field-programmable gate array. The circuits may be programmed to provide one or more operations or sets of operations of each method, and the program may include program instructions stored in computer-readable memory, or programmed operations of logic circuits, such as programmable array logic or a field-programmable gate array.

[0042] system The disclosure provided herein describes a system for performing and / or carrying out the methods of the disclosure, as described elsewhere herein. In some cases, the system may include a system for classifying the phenotype of a subject, comprising one or more processors and a memory storing one or more programs to be executed by the one or more processors, the one or more programs including instructions for (i) acquiring, collecting, and / or receiving one or more organic molecular signatures of a biological sample from a plurality of locations along the biological sample of a subject, and (ii) determining the phenotype of the subject from the one or more organic molecular signatures of the subject. In some cases, the phenotype of a subject may include a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof. In some cases, the disease phenotype may include autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis (ALS), cancer, or any combination thereof. In some cases, the exogenous compound may include nicotine, melamine, or any combination thereof. In some cases, the endogenous compound may include metabolites, signaling molecules, or any combination thereof. The signaling molecule may include hypotaurine. In some cases, the endogenous metabolite may include creatinine. In some cases, the dietary supplement may include agmatine. In some cases, the drug may include a drug for treating heartburn, acid reflux, peptic ulcers, or any combination thereof. In some cases, the drug may include betasol. In some cases, the exposure phenotype may include the subject's exposure to environmental chemicals. In some cases, the biological sample may include hair, teeth, fingernails, toenails, or any combination thereof.

[0043] In some cases, one or more organic molecular signatures may include molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da, or a mass-to-charge ratio as described elsewhere herein. In some cases, one or more organic molecular signatures may include one or more time-resolved organic molecular signatures.

[0044] In some cases, the system may include a light source configured to acquire or collect one or more organic molecular signatures from multiple locations along the biological sample. In some cases, the light source may include a laser, pulsed laser, continuous-wave laser, or any combination thereof. In some cases, one or more organic molecular signatures may be acquired or collected by performing MALDI-ToF MS, LAESI, TIMS, ToF mass spectrometry, protein fluorescence assay, or any combination thereof on the biological sample.

[0045] In some cases, the system may include instructions to determine changes in the subject's phenotype and / or response when the subject is administered a drug and / or dietary supplement. In some cases, the subject's phenotype may be used to indicate how to make adjustments, such as completely changing the drug and / or dietary supplement, adding the drug and / or dietary supplement, identifying a new drug and / or dietary supplement to administer to the subject, changing the drug and / or dietary supplement administration regimen, or any combination thereof. In some cases, the administered drug and / or dietary supplement may alleviate the disease of the subject, or one or more symptoms of the disease and / or illness.

[0046] In some cases, the instruction to determine the phenotype of a target may include training a predictive model, as described elsewhere herein, using one or more organic molecule signatures and associated phenotypic labels of a set of targets different from the target, and providing one or more organic molecule signatures of the target to the trained predictive model to output the phenotype of the target.

[0047] The disclosure provided herein describes a system for performing and / or carrying out the methods of the disclosure as described elsewhere herein. In some cases, the system is a system for classifying the phenotype of a subject, comprising one or more processors and a memory storing one or more programs to be executed by the one or more processors, the one or more programs including instructions for (i) obtaining or collecting one or more molecular signatures from a biological sample having a mass-to-charge ratio of at least 50 Da when one or more probes are placed on a biological sample of a subject, and (ii) determining the phenotype of the subject from the one or more molecular signatures of the subject. In some cases, the phenotype of a subject may include a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof. In some cases, the disease phenotype may include autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis (ALS), or any combination thereof. In some cases, the exogenous compound may include nicotine, melamine, or any combination thereof. In some cases, the endogenous compound may include metabolites, signaling molecules, or any combination thereof. The signaling molecule may include hypotaurine. In some cases, the endogenous metabolite may include creatinine. In some cases, the dietary supplement may include agmatine. In some cases, the drug may include medication for treating heartburn, acid reflux, peptic ulcers, or any combination thereof. In some cases, the drug may include betasol. In some cases, the exposure phenotype may include the subject's exposure to environmental chemicals. In some cases, the biological sample may include hair, teeth, fingernails, toenails, or any combination thereof.

[0048] In some cases, the system may include a light source that can be used to acquire or collect one or more molecular signatures from one or more probes placed on a biological sample. In some cases, the light source may include a laser, a pulsed laser, a continuous-wave laser, or any combination thereof. In some cases, one or more probes may include a binding site configured to bind to a protein. In some cases, a first probe of one or more probes may include a binding site targeted to bind to a first protein, and a second probe of one or more probes may include a binding site targeted to bind to a second protein. In some cases, the first and second proteins may be located at a distance such that the first and second probes can bind to each other to form a probe complex. In some cases, a signaling molecule, such as a fluorescent molecule, may be bound to the probe complex and detected by the light source. In some cases, detection of the fluorescent molecule and / or the associated intensity of the fluorescent molecule may result in a concentration of the molecule of one or more molecular signatures of the biological sample. In some cases, the instruction to determine the phenotype of a target may include training a predictive model, as described elsewhere herein, using one or more molecular signatures and associated phenotypic labels of a set of targets different from the target, and providing one or more organic molecular signatures of the target to the trained predictive model to output the phenotype of the target.

[0049] In some cases, the system may include instructions to determine changes in the subject's phenotype and / or response when the subject is administered a drug and / or dietary supplement. In some cases, the subject's phenotype may be used to indicate how to make adjustments, such as completely changing the drug and / or dietary supplement, adding the drug and / or dietary supplement, identifying a new drug and / or dietary supplement to administer to the subject, changing the drug and / or dietary supplement administration regimen, or any combination thereof. In some cases, the administered drug and / or dietary supplement may alleviate the disease of the subject, or one or more symptoms of the disease and / or illness.

[0050] Computer system Figure 12 shows a computer system 900 suitable for carrying out the methods of the Disclosure, as described elsewhere in this Spec. In some cases, the computer system may process one or more signals of one or more collected and / or acquired molecular signatures, as described elsewhere in this Spec, and may carry out and / or train one or more machine learning algorithms and / or one or more predictive models, as described elsewhere in this Spec. The computer system 900 may process various aspects of the data and / or information of the Disclosure, such as, for example, one or more molecular signatures of a biological sample of interest (e.g., one or more organic molecular signatures), features derived from one or more molecular signatures, features derived from the mean and / or geometric mean of signals (e.g., concentrations) of one or more organic molecular signatures collected and / or acquired across multiple locations on the biological sample, features derived from one or more molecular signatures acquired from one or more probes placed on the surface of the biological sample, feature determination of the phenotype of interest, or any combination thereof. The computer system 900 may be an electronic device. Electronic devices may include mobile electronic devices, desktop computer devices, laptop devices, servers, cloud computing platforms, or any combination thereof.

[0051] The computer system 900 may include a central processing unit (CPU, also referred to herein as "processor" and "computer processor") 902, which may be a single-core or multi-core processor, or multiple processors for parallel processing. The computer system 900 may further include memory or storage locations 904 (e.g., random-access memory, read-only memory, flash memory), electronic storage devices 906 (e.g., hard disks), a communication interface 908 for communicating with one or more other devices (e.g., a network adapter), and peripheral devices 910 such as caches, other memory, data storage, and / or electronic display adapters. The memory 904, storage devices 906, interface 908, and peripheral devices 910 may be in communication with the CPU 902 via a communication bus (solid line), such as a motherboard. The storage device 906 may be a data storage device for storing data (or a data repository, which is either a local and / or networked data repository). The computer system 900 may be operably coupled to a computer network ("network") 916 using the communication interface 908. Network 916 may be the Internet, the Internet and / or an extranet, or an intranet and / or extranet in communication with the Internet. Network 916 may optionally be a telecommunications and / or data network. Network 916 may include one or more computer servers that can enable distributed computing, such as cloud computing. Network 916 may optionally implement a peer-to-peer network with the help of computer system 900, which can enable devices coupled to computer system 900 to act as clients or servers.

[0052] The CPU 902 may execute a sequence of machine-readable instructions that can be embodied in a program or software. These instructions may be directed to the CPU 902, which may then be programmed or otherwise configured to perform the methods of this disclosure described elsewhere in this Spec. Examples of operations performed by the CPU 902 may include fetching, decoding, executing, and writing back.

[0053] The CPU 902 may be part of a circuit, such as an integrated circuit. One or more other components of the system 900 may be included in the circuit. In some cases, the circuit may be an application-specific integrated circuit (ASIC).

[0054] The storage device 906 may store files such as drivers, libraries, and / or saved programs. The storage device 906 may store one or more molecular signatures of the biological sample of interest (e.g., one or more organic molecular signatures), features derived from one or more molecular signatures, features derived from the mean and / or geometric mean of the concentrations of one or more organic molecular signatures collected and / or acquired across multiple locations on the biological sample, features derived from one or more molecular signatures acquired from one or more probes placed on the surface of the biological sample, feature determinations of the phenotype of interest, or any combination thereof. The computer system 900 may optionally include one or more additional data storage devices outside of the computer system 900, such as being located on a remote server that is in communication with the computer system 900 via an intranet or the internet.

[0055] The methods described herein may be implemented by machine-executable code (e.g., a computer processor) stored in an electronic storage location of the computer device 900, such as memory 904 and / or electronic storage device 906. The machine-executable and / or machine-readable code may be provided in software form. During use, the code may be executed by the processor 902. In some cases, for immediate access by the processor 902, the code may be retrieved from storage device 906 and stored in memory 904. In some cases, electronic storage device 906 may be omitted, and the machine-executable instructions may be stored on memory 904.

[0056] The code may be pre-compiled and configured for use in a machine equipped with a processor adapted to run the code, or it may be compiled at runtime. The code may be provided in a programming language that can be chosen to allow the code to be executed either pre-compiled or as-compiled.

[0057] Embodiments of the systems and methods provided herein, such as computer system 900, may be embodied in programming. Various embodiments of the technology can typically be considered “products” or “manufactured goods” in the form of machine (or processor) executable code and / or associated data, which are held or embedded in some kind of machine-readable medium. The machine-executable code may be stored on electronic storage devices, such as memory (e.g., read-only memory, random-access memory, flash memory), or hard disks. The “storage” type of medium may include any or all of tangible memory such as computers and processors, and / or modules associated therewith, such as various semiconductor memories, tape drives, disk drives, etc., which may at any time provide non-temporary storage for software programming. All or part of the software may sometimes be communicated over the Internet, an intranet, or a combination thereof, and / or various other telecommunications networks. Such communication may, for example, enable the loading of software from one computer or processor to another computer or processor, for example, from a management server or host computer to an application server computer platform. Therefore, other types of media that can hold software elements include optical waves, radio waves, and electromagnetic waves, such as wired and optical fixed telephone networks, as well as those used throughout the physical interfaces between local devices via various air links. Physical elements that carry such waves, such as wired or wireless links and optical links, may also be considered media that carry software. As used herein, unless limited to non-temporary and tangible “storage” media, terms such as computer or machine “readable media” refer to any medium involved in providing instructions to a processor for execution.

[0058] Therefore, machine-readable media such as computer executable code may take many forms, including but not limited to tangible storage media, carrier media, or physical transmission media. Non-volatile storage media may include optical disks or magnetic disks, such as any storage device, such as any computer(s), which may be used to implement databases, etc. Volatile storage media may include dynamic memory, such as the main memory of such a computer platform. Tangible transmission media may include coaxial cables, copper wires, optical fibers, or any combination thereof, such as wires that make up a bus in a computer device. Carrier media may take the form of electrical signals or electromagnetic signals, or acoustic waves or light waves, such as those generated during radio frequency (RF) and infrared (IR) data communications. Therefore, common forms of computer-readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tapes, and any other magnetic media; CD-ROMs, DVDs, or DVD-ROMs, and any other optical media; punched card paper tapes, and any other physical storage media with a pattern of holes; RAM, ROMs, PROMs, and EPROMs, FLASH-EPROMs, and any other memory chips or cartridges; carriers that carry data or instructions; cables or links that carry such carriers; any combination thereof; or any other media from which a computer can read programming code and / or data. Many of these forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.

[0059] The computer system may include, or be in communication with, an electronic display 912 that may have a user interface (UI) 914 for viewing feature determination predictions of one or more molecular signatures and / or phenotypes of a target biological sample based on one or more molecular signatures of the target biological sample (e.g., one or more organic molecular signatures). Examples of UIs include, but are not limited to, graphical user interfaces (GUIs) and web-based user interfaces.

[0060] Predictive models and machine learning algorithms The methods and / or systems of the present disclosure can process, analyze, and / or classify one or more molecular signatures and / or one or more features of the temporal dynamics of one or more molecular signatures of a biological sample, as described elsewhere in this specification, to determine a phenotype. In some cases, processing, analyzing, and / or classifying one or more molecular signatures and / or one or more features of one or more molecular signatures may be performed by one or more machine learning algorithms and / or one or more predictive models, provided instructions to one or more processors, as described elsewhere in this specification. For example, one or more machine learning algorithms and / or predictive models may process one or more, or two or more features (i.e., multiple features) of one or more molecular signatures, as described elsewhere in this specification.

[0061] In some cases, the phenotype of a target and / or the phenotypes of multiple targets may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with a sensitivity of at least about 70%, at least about 75%, at least about 80%, at least about 85%, or at least about 90%.

[0062] In some cases, the phenotype of a target and / or the phenotypes of multiple targets may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with a sensitivity of up to approximately 70%, up to approximately 75%, up to approximately 80%, up to approximately 85%, or up to approximately 90%.

[0063] In some cases, the phenotype of a target and / or the phenotypes of multiple targets may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with specificity of at least approximately 70%, at least approximately 75%, at least approximately 80%, at least approximately 85%, or at least approximately 90%.

[0064] In some cases, the target phenotype and / or the phenotypes of multiple targets may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with specificity up to approximately 70%, 75%, 80%, 85%, or 90%.

[0065] In some cases, the phenotype of a subject and / or the phenotype of multiple subjects may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with a positive predictive value of at least approximately 70%, at least approximately 75%, at least approximately 80%, at least approximately 85%, or at least approximately 90%.

[0066] In some cases, the phenotype of a subject and / or the phenotypes of multiple subjects may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with positive predictive values ​​of up to approximately 70%, 75%, 80%, 85%, or 90%.

[0067] In some cases, the phenotype of a subject and / or the phenotypes of multiple subjects may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with negative predictive values ​​of at least approximately 70%, at least approximately 75%, at least approximately 80%, at least approximately 85%, or at least approximately 90%.

[0068] In some cases, the phenotype of a target and / or the phenotypes of multiple targets may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with negative predictive values ​​of up to approximately 70%, 75%, 80%, 85%, or 90%.

[0069] In some cases, the phenotype of a target and / or the phenotypes of multiple targets may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with an area under the receiver operating characteristic curve (AUROC) of at least about 0.65, at least about 0.70, at least about 0.75, at least about 0.80, at least about 0.82, at least about 0.84, at least about 0.86, at least about 0.88, or at least about 0.90.

[0070] In some cases, the target phenotype and / or the phenotypes of multiple targets may be determined and / or predicted by one or more machine learning algorithms and / or one or more predictive models with a receiver operating characteristic area (AUROC) of up to approximately 0.65, up to approximately 0.70, up to approximately 0.75, up to approximately 0.80, up to approximately 0.82, up to approximately 0.84, up to approximately 0.86, up to approximately 0.88, or up to approximately 0.90.

[0071] The algorithms and / or predictive models can be implemented by software during execution by the central processing unit 902. In some cases, the predictive model may include a machine learning predictive model. In some cases, the machine learning predictive model may include one or more statistical algorithms, machine learning algorithms, or artificial intelligence algorithms. Examples of algorithms, machine learning algorithms, and / or predictive models used include support vector machines (SVMs), naive Bayes classification, random forests, neural networks (e.g., deep neural networks (DNNs), recurrent neural networks (RNNs), deep RNNs, long-shorter memory (LSTM) recurrent neural networks (RNNs), decision tree algorithms, unsupervised clustering algorithms, supervised clustering algorithms, regression algorithms, gradient boosting algorithms (e.g., gradient boosted decision trees, etc., gradient boosted implementations of machine learning algorithms and / or predictive models), gated recurrent units (GRUs), supervised learning algorithms, unsupervised learning algorithms, and statistical deep learning algorithms for classification and regression. , or any combination thereof may be mentioned. In some cases, the recurrent neural network may include units that may be LSTM units and / or GRUs. In some cases, the predictive model and / or machine learning algorithm may include an ensemble of one or more predictive models and / or machine learning algorithms. In some cases, one or more predictive models and / or one or more machine learning algorithms may be arranged in parallel, for example, a first one or more predictive models and / or one or more machine learning algorithms and a second one or more predictive models and / or one or more machine learning algorithms may provide outputs to a third one or more predictive models and / or one or more machine learning algorithms, which then render a determination of the phenotype of one or more targets.

[0072] Machine learning algorithms and / or predictive models may similarly include estimation of ensemble models composed of multiple predictive models, and may utilize techniques such as gradient boosting in the construction of gradient boosted decision trees, for example. Machine learning predictive models may be trained using one or more training datasets corresponding to data of one or more subjects. In some embodiments, one or more training datasets may include one or more molecular signatures, one or more features of one or more molecular signatures, and feature determinations of corresponding phenotypes of one or more molecular signatures of one or more subjects and / or one or more groups of one or more subjects, one or more features of one or more molecular signatures, or a combination thereof. In some cases, one or more machine learning algorithms and / or one or more predictive models may be trained using one or more molecular signatures of one or more subjects (e.g., one or more training subjects) and / or features of one or more molecular signatures acquired across multiple locations of one or more corresponding biological samples of one or more subjects, as described elsewhere in this specification.

[0073] In some cases, this disclosure describes a method for training an untrained or partially untrained machine learning algorithm or predictive model, comprising: collecting or acquiring one or more molecular signatures of a plurality of biological samples to be trained, in a computer system having one or more processors and memory for storing one or more programs to be executed by the one or more processors, wherein a first subset of the plurality of trained samples has a first phenotype associated with one or more molecular signatures, and a second subset of the plurality of trained samples has a second phenotype associated with one or more molecular signatures; and training an untrained or partially untrained machine learning algorithm or predictive model using one or more molecular signatures of the plurality of trained samples and the corresponding first and second phenotypes associated with one or more molecular signatures, thereby creating or generating a trained predictive model. In some cases, one or more molecular signatures of a sample, a plurality of trained samples, or a combination thereof may include one or more organic molecular signatures. In some cases, untrained or partially untrained machine learning algorithms and / or predictive models may be further trained with one or more signals and / or one or more images of fluorescent markers of one or more protein probes bound to a biological sample.

[0074] In some cases, the present disclosure relates to a method for training a machine learning model or predictive model in a computer system as described elsewhere herein, having one or more processors and memory for storing one or more programs to be executed by the one or more processors, (a) for each of the multiple training subjects, where a first subset of the multiple training subjects has a first phenotype as described elsewhere herein, associated with one or more first features of one or more first molecular signatures, and a second subset of the multiple training subjects has a second phenotype associated with one or more second features of one or more second molecular signatures, (i) sampling, acquiring, and / or obtaining each of the multiple locations on a biological sample of the training subject. The present invention describes a method comprising: (ii) obtaining a plurality of molecular signatures; (ii) analyzing and / or processing the sampled, obtained, and / or acquired molecular signatures at multiple locations in order to determine and / or derive one or more features of one or more molecular signatures at multiple locations on a biological sample; and (b) training an untrained or partially untrained machine learning algorithm and / or predictive model using (i) one or more corresponding features of each of the multiple training subjects, and (ii) the corresponding phenotype of each of the multiple training subjects, selected from a first phenotype and a second phenotype, thereby obtaining a trained model that provides an indicator of whether a test subject has a first phenotype associated with one or more features of one or more molecular signatures acquired at multiple locations on a biological sample of the test subject. In some cases, the machine learning model and / or predictive model may be trained on one or more organic molecular signatures as described elsewhere in this specification.In some cases, the values ​​of one or more features of the subject may be provided to a trained machine learning algorithm and / or predictive model as input that can provide the machine learning algorithm and / or predictive model with an output of the type of phenotype of the subject.

[0075] In some cases, one or more trained machine learning algorithms and / or one or more trained predictive models may be configured to process and / or analyze one or more and / or two or more features of one or more molecular signatures, as described elsewhere herein, for example, to determine and / or predict the phenotype of one and / or more subjects. In some cases, one or more trained machine learning algorithms and / or one or more trained predictive models may be configured to process and / or analyze one or more organic signatures, as described elsewhere herein.

[0076] In some cases, a trained predictive model and / or machine learning algorithm may include multiple parameters, where “parameter” means any coefficients and / or values ​​of internal or external elements (e.g., weights and / or hyperparameters) of a predictive model and / or machine learning algorithm that can influence (e.g., modify, fit, and / or adjust) one or more inputs, outputs, and / or features within the predictive model and / or machine learning algorithm (e.g., if the predictive model and / or machine learning algorithm is a regressor or classifier). For example, in some embodiments, parameters of a model and / or machine learning algorithm may refer to any coefficients, weights, and / or hyperparameters that can be used to control, modify, fit, and / or adjust the behavior, learning, and / or performance of the predictive model and / or machine learning algorithm. In some cases, parameters may be used to increase or decrease the influence of inputs (e.g., features) to the predictive model and / or machine learning algorithm. For example, parameters may be used to increase or decrease the influence of nodes (e.g., neural networks), where nodes include one or more activation functions. The assignment of parameters to specific inputs, outputs, and / or functions of a predictive model and / or machine learning algorithm does not have to be limited to any one paradigm of a given predictive model and / or machine learning algorithm, but can be used in any suitable predictive model and / or machine learning algorithm for the desired performance. In some cases, the parameters may include fixed values. In some cases, the parameter values ​​may be adjustable manually and / or automatically. In some cases, the parameter values ​​may be modified by the validation and / or training process of the predictive model and / or machine learning algorithm (e.g., by error minimization and / or backpropagation).In some embodiments, the predictive models and / or machine learning algorithms of the present disclosure may include a plurality of parameters. In some embodiments, the plurality of parameters associated with a predictive model and / or a machine learning algorithm (e.g., an untrained model, a partially trained model, and / or a fully trained model) may include n parameters, where n≥2, n≥5, n≥10, n≥25, n≥40, n≥50, n≥75, n≥100, n≥125, n≥150, n≥200, n≥225, n≥250, n≥350, n≥500, n≥600, n≥750, n≥1,000, n≥2,000, n≥4,000, n≥5,000, n≥7,500, n≥10,000, n≥20,000, n≥40,000, n≥75,000, n≥100,000, n≥200,000, n≥500,000, n≥1×10 6 , n≥5×10 6 , or n≥1×10 7 . In some cases, n is between 10,000 and 1×10 7 , between 100,000 and 5×10 6 , or between 500,000 and 1×10 6 .

[0077] The training dataset may be generated from one or more cohorts of subjects having, for example, one or more common features, such as a molecular signature, one or more features of one or more molecular signatures, or a combination thereof, and a phenotype (e.g., a label). The training dataset may include a set of features. The labels of the training data for one or more subjects (e.g., one or more molecular signatures and / or one or more features of one or more molecular signatures) may include the phenotype of the subject (e.g., a patient).

[0078] Features used to train one or more predictive models and / or one or more machine learning algorithms, and / or features provided as input to one or more trained predictive models and / or one or more trained machine learning algorithms, may include demographic information of the subject derived from electronic medical records (EMR), medical observations of the subject, or any combination thereof. Features may include clinical characteristics such as a specific range or classification of dynamic molecular signatures. Features used to train one or more predictive models and / or one or more machine learning algorithms, and / or features provided as input to one or more trained predictive models and / or one or more trained machine learning algorithms, may include information of the subject such as the subject's age, medical history of the subject, other medical conditions, current or past medications taken by the subject, time since the subject's last observation and / or assessment, or any combination thereof. In some cases, one or more predictive models and / or one or more machine learning algorithms may include an algorithmic architecture that includes a neural network with a set of input features, such as the subject's vital signs and other measures based on the subject's health, the subject's medical history, and / or the subject's demographics. For example, a set of features collected from a given object at a given point in time may collectively function as a signature that can represent the phenotype of the object at that point in time.

[0079] In some cases, the range of molecular signature data and / or other health measures for one or more subjects may be represented as multiple disparate continuous ranges of values ​​for continuous measures. In some cases, classifications of molecular signatures and other health measures may be represented as multiple disparate sets of values ​​for measures (e.g., {"High", "Low"}, {"High", "Normal"}, {"Low", "Normal"}, {"High", "Borderline High", "Normal", "Low"}, etc.). Clinical characteristics may also include clinical labels indicating the patient's health history, such as previously made phenotypic determinations, classifications, and / or diagnoses, previously administered clinical treatments (e.g., drugs, surgical treatments, chemotherapy, radiotherapy, immunotherapy, etc.), behavioral factors, other health conditions (e.g., history of hypertension or high blood pressure, hyperglycemia or high blood glucose, hypercholesterolemia or high blood cholesterol, allergic reactions or other side effects, etc.), or any combination thereof.

[0080] Clinical outcomes may include temporal characteristics associated with the presence or absence, diagnosis, determination, and / or prognosis of the subject's phenotype. For example, temporal characteristics may indicate that the subject's phenotype was classified, determined, and / or diagnosed within a specific period following a previous clinical outcome (e.g., discharge, administration of medication or other treatment, or administration of a clinical procedure such as surgery). Such periods may be, for example, about 1 hour, 2 hours, 3 hours, 4 hours, 6 hours, 8 hours, 10 hours, 12 hours, 14 hours, 16 hours, 18 hours, 20 hours, 22 hours, 24 hours, 2 days, 3 days, 4 days, 5 days, 6 days, 7 days, 10 days, 2 weeks, 3 weeks, 4 weeks, 1 month, 2 months, 3 months, 4 months, 6 months, 8 months, 10 months, 1 year, or more than 1 year.

[0081] The input data and / or features provided to one or more predictive models and / or one or more machine learning algorithms may be structured by aggregating the data into bins, or alternatively by using one-hot encoding. The input data and / or features may include feature values ​​or vectors derived from the aforementioned inputs, such as cross-correlations computed between separate molecular signatures and / or molecular signature features or other measurements over a fixed period, as well as finite differences between discrete derivatives or continuous measurements. Such periods may be, for example, about 1 hour, about 2 hours, about 3 hours, about 4 hours, about 6 hours, about 8 hours, about 10 hours, about 12 hours, about 14 hours, about 16 hours, about 18 hours, about 20 hours, about 22 hours, about 24 hours, about 2 days, about 3 days, about 4 days, about 5 days, about 6 days, about 7 days, about 10 days, about 2 weeks, about 3 weeks, about 4 weeks, about 1 month, about 2 months, about 3 months, about 4 months, about 6 months, about 8 months, about 10 months, about 1 year, or may exceed about 1 year.

[0082] Training records may be constructed from a sequence of observations. Such sequences may have a fixed length to facilitate data processing. For example, the sequence may be zero-padded or selected as an independent subset of records for a single subject.

[0083] One or more predictive models and / or one or more machine learning algorithms may process one or more input features to produce one or more output values ​​containing one or more phenotypes. For example, such phenotypes may include a binary classification of healthy / normal health status (e.g., absence of disease or disability) or adverse health status (e.g., presence of disease or disability), a group classification of classification labels (e.g., “no disease or disability”, “obvious disease or disability”, and “risk of disease or disability”), the likelihood of developing a particular disease or disability (e.g., relative likelihood or probability), a score indicating the presence of disease or disability, a score indicating the level of systemic inflammation experienced by the patient, a “risk factor” indicating the probability of death for the patient, a prediction of the time at which the patient is expected to develop disease or disability, a confidence interval for any numerical prediction, or any combination thereof. Various predictive models and / or machine learning algorithms may be cascaded such that the output of one or more predictive models and / or one or more machine learning algorithms can also be used as one or more input features to subsequent layers or subsections of one or more predictive models and / or one or more machine learning algorithms.

[0084] One or more predictive models and / or machine learning algorithms can be trained (for example, by determining the weights and correlations of the predictive models and / or machine learning algorithms) to generate real-time classifications or predictions, using datasets described elsewhere herein (e.g., training datasets). Such datasets may be large enough to generate statistically significant classifications or predictions. For example, a dataset may include a database of non-identifiable data, including one or more molecular signatures, other measurements from a hospital or other clinical setting, or any combination thereof.

[0085] Datasets as described elsewhere in this specification may be divided into subsets such as training datasets, expansion datasets, and test datasets (which may be discrete or overlapping). For example, a dataset may be divided into a training dataset containing 80% of the dataset, an expansion dataset containing 10% of the dataset, and a test dataset containing 10% of the dataset. The training dataset may contain about 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, or 90% of the dataset. The expansion dataset may contain about 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, or 90% of the dataset. The test dataset may contain about 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, or 90% of the dataset. The training set (e.g., the training dataset) may be selected by random sampling of the data sets corresponding to one or more target cohorts to ensure sampling independence. In some cases, the training set (e.g., the training dataset) may be selected by proportional sampling of the data sets corresponding to one or more target cohorts to ensure sampling independence.

[0086] To improve the accuracy of predictions by predictive models and / or machine learning algorithms and to reduce overfitting of predictive models and / or machine learning algorithms, datasets may be augmented to increase the number of samples in the training set. For example, data augmentation may include rearranging the order of observations in the training records. To address datasets with missing observations, methods for imputing the missing data, such as forward filling, back filling, linear interpolation, and multitask Gaussian processes, may be used. To remove confounding factors, datasets may be filtered. For example, a subset of the target dataset may be excluded from the database.

[0087] Neural network techniques, such as dropout or regularization, may be used while training one or more predictive models and / or one or more machine learning algorithms to prevent overfitting. The neural network may include multiple subnetworks, each configured to produce a classification or prediction of a different type of output information (for example, they may be combined to form the overall output of the neural network). The one or more predictive models and / or one or more machine learning algorithms may alternatively utilize statistical algorithms or related algorithms, including random forests, classification and regression trees, support vector machines, discriminant analysis, regression techniques, ensembles and gradient-boosted variations thereof, or any combination thereof.

[0088] When one or more predictive models and / or one or more machine learning algorithms generate a phenotypic classification or prediction, a notification (e.g., an alert or alarm) may be generated and sent to a healthcare provider, such as a physician, nurse, healthcare worker management, or any combination thereof, treating the subject within a hospital. The notification may be sent via automated phone, short message service (SMS), multimedia messaging service (MMS) message, email, alert in a dashboard, or any combination thereof. The notification may include output information such as a phenotypic prediction, the likelihood of the phenotypic, the expected time to onset of the phenotypic, a confidence interval for the likelihood or time, a recommended course of treatment for the phenotypic, or any combination thereof.

[0089] Different performance metrics may be generated to validate the performance of one or more predictive models and / or one or more machine learning algorithms. For example, the area under the receiver operating curve (AUROC) may be used to determine the diagnostic and / or classification capabilities of one or more predictive models and / or one or more machine learning algorithms. For example, one or more predictive models and / or one or more machine learning algorithms may use adjustable classification thresholds so that their specificity and sensitivity are adjustable, and a receiver operating characteristic curve (ROC) may be used to identify different operating points corresponding to different values ​​of specificity and sensitivity for one or more predictive models and / or one or more machine learning algorithms.

[0090] In some cases, such as when the dataset is not large enough, cross-validation may be performed to assess the robustness of one or more predictive models and / or one or more machine learning algorithms across different training and test datasets.

[0091] To calculate performance metrics such as sensitivity, specificity, precision, positive predictive value (PPV), negative predictive value (NPV), area under the precision-recall curve (AUPRC), area under the receiver operating characteristic curve (AUROC), any combination thereof, or similar, the following definitions may be used: “False positive” refers to an outcome where a positive outcome or result is incorrectly or prematurely produced (e.g., before or without the actual onset of the phenotype). “True positive” refers to an outcome where a positive outcome or result is correctly produced when the subject has the phenotype (e.g., the subject exhibits symptoms of the phenotype or the subject's records show the phenotype). “False negative” refers to an outcome where a negative outcome or result is produced but the subject has the phenotype (e.g., the subject exhibits symptoms of the phenotype or the subject's records show the phenotype). “True negative” refers to an outcome where a negative outcome or result is produced (e.g., before or without the actual onset of the phenotype).

[0092] One or more predictive models and / or one or more machine learning algorithms may be trained until certain predetermined conditions for accuracy or performance are met, such as having a minimum desired value corresponding to a classification and / or diagnostic accuracy measure. For example, the diagnostic accuracy measure may correspond to a prediction of the likelihood of the occurrence of a subject's phenotype. Another example is that the diagnostic accuracy measure may correspond to a prediction of the likelihood of exacerbation or recurrence of a previously treated phenotype in the subject. Examples of diagnostic accuracy measures may include sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), precision, area under the precision-recall curve (AUPRC), and area under the receiver operating characteristic (ROC) curve (AUROC), corresponding to the diagnostic accuracy of detecting or predicting a phenotype.

[0093] For example, such a predetermined condition may be that the sensitivity predicting the phenotype includes values ​​such as at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0094] As another example, such a given condition may be that the specificity predicting the phenotype is, for example, at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0095] As another example, such a given condition may be that the positive predictive value (PPV) predicting the phenotype includes values ​​such as at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0096] As another example, such a given condition may be that the negative predictive value (NPV) predicting the phenotype includes values ​​such as at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0097] As another example, such a given condition may be that the area under the curve (AUC) (AUROC) of the receiver operating characteristic (ROC) curve predicting the phenotype includes values ​​of at least about 0.50, at least about 0.55, at least about 0.60, at least about 0.65, at least about 0.70, at least about 0.75, at least about 0.80, at least about 0.85, at least about 0.90, at least about 0.95, at least about 0.96, at least about 0.97, at least about 0.98, or at least about 0.99.

[0098] As another example, such a given condition may be that the area under the precision-recall curve (AUPRC) predicting the phenotype includes values ​​of at least about 0.10, at least about 0.15, at least about 0.20, at least about 0.25, at least about 0.30, at least about 0.35, at least about 0.40, at least about 0.45, at least about 0.50, at least about 0.55, at least about 0.60, at least about 0.65, at least about 0.70, at least about 0.75, at least about 0.80, at least about 0.85, at least about 0.90, at least about 0.95, at least about 0.96, at least about 0.97, at least about 0.98, or at least about 0.99.

[0099] In some embodiments, the trained model may be trained or configured to predict phenotypes with a sensitivity of at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0100] In some embodiments, the trained model may be trained or configured to predict phenotypes with specificity of at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0101] In some embodiments, the trained model may be trained or configured to predict phenotypes with a positive predictive value (PPV) of at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0102] In some embodiments, the trained model may be trained or configured to predict phenotypes with a negative predictive value (NPV) of at least about 50%, at least about 55%, at least about 60%, at least about 65%, at least about 70%, at least about 75%, at least about 80%, at least about 85%, at least about 90%, at least about 95%, at least about 96%, at least about 97%, at least about 98%, or at least about 99%.

[0103] In some embodiments, the trained model may be trained or configured to predict the phenotype with an Area Under Curve (AUC) (AUROC) of at least about 0.50, at least about 0.55, at least about 0.60, at least about 0.65, at least about 0.70, at least about 0.75, at least about 0.80, at least about 0.85, at least about 0.90, at least about 0.95, at least about 0.96, at least about 0.97, at least about 0.98, or at least about 0.99 of the Area Under Curve (AUC) (AUROC) of the receiver operating characteristic (ROC) curve.

[0104] In some embodiments, the trained model may be trained or configured to predict phenotypes with an area under the precision-recall curve (AUPRC) of at least about 0.10, at least about 0.15, at least about 0.20, at least about 0.25, at least about 0.30, at least about 0.35, at least about 0.40, at least about 0.45, at least about 0.50, at least about 0.55, at least about 0.60, at least about 0.65, at least about 0.70, at least about 0.75, at least about 0.80, at least about 0.85, at least about 0.90, at least about 0.95, at least about 0.96, at least about 0.97, at least about 0.98, or at least about 0.99.

[0105] The training dataset may be collected from training subjects (e.g., humans). Each training subject has a diagnostic status indicating either that it is diagnosed and / or classified as having the phenotype, or that it is not diagnosed as having the phenotype. In some cases, the training subjects include one or more humans. In some embodiments, the training subjects may be children aged 12 years or younger (e.g., 5, 4, 3, 2, 1 year, 9 months, 6 months, 3 months, or 1 month or younger). In some embodiments, the children may be between approximately 12 years and approximately 5 years old. In some embodiments, the subjects may be under approximately 12, 11, 10, 9, 8, 7, 5, 4, 3, 2, or 1 year old. In some embodiments, the subjects may be at least approximately 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, or 12 years old. Training procedures as described elsewhere in this specification may be performed for each training subject of multiple training subjects.

[0106] In some embodiments, one or more predictive models and / or one or more machine learning algorithms may include a neural network or a convolutional neural network. See Vincent et al., 2010, “Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion,” J Mach Learn Res 11, pp. 3371-3408, Larochelle et al., 2009, “Exploring strategies for training deep neural networks,” J Mach Learn Res 10, pp. 1-40, and Hassoun, 1995, Fundamentals of Artificial Neural Networks, Massachusetts Institute of Technology, each of which is incorporated herein by reference.

[0107] Independent component analysis (ICA) in unsupervised dimensionality reduction of molecular signature data, as described elsewhere in this specification, is described in Lee, T.-W. (1998): Independent component analysis: Theory and applications, Boston, Mass: Kluwer Academic Publishers, ISBN 0-7923-8261-7, and Hyvarinen, A.; Karhunen, J.; Oja, E. (2001): Independent Component Analysis, New York: Wiley, ISBN 978-0-471-40540-5, which are incorporated herein by reference as a whole.

[0108] Principal component analysis (PCA) in unsupervised dimensionality reduction of molecular signature data, as described elsewhere in this specification, is described in Jolliffe, IT (2002). Principal Component Analysis. Springer Series in Statistics. New York: Springer-Verlag. doi:10.1007 / b98835. ISBN 978-0-387-95442-4, which is incorporated herein by reference in its entirety.

[0109] SVM is mentioned in Cristianini and Shawe-Taylor, 2000, “An Introduction to Support Vector Machines,” Cambridge University Press, Cambridge; the minutes of the 5th Annual ACM Workshop on Computational Learning Theory; Boser et al., 1992, “A training algorithm for optimal margin classifiers,” ACM Press, Pittsburgh, Pa., pp.142-152; Vapnik, 1998, Statistical Learning Theory, Wiley, New York; Mount, 2001, Bioinformatics: sequence and genome analysis, Cold Spring Harbor Laboratory Press, Cold Spring Harbor, NY; Duda, Pattern Classification, Second Edition, 2001, John Wiley & Sons, Inc., pp.259, 262-265; and Hastie, 2001, The Elements of Statistical Learning, Springer, New York; and Furey et al. This is described in al., 2000, Bioinformatics 16, 906-914, each of which is incorporated herein by reference. When used for classification, SVM may separate a given set of binary-labeled data by a hyperplane that is as far away from the labeled data as possible. If linear separation is not possible, SVM can work in combination with the technique of a “kernel” that can automatically achieve a nonlinear mapping to the feature space. The hyperplane found by the SVM in the feature space may correspond to a nonlinear decision boundary in the input space.

[0110] Decision trees are outlined in Duda, 2001, Pattern Classification, John Wiley & Sons, Inc., New York, pp. 395–396, which is incorporated herein by reference. Decision tree-based methods divide the feature space into sets of rectangles, each to which a model (such as a constant) can be fitted. In some embodiments, the decision tree may be a random forest regression. One particular algorithm that may be used is Classification and Regression Tree (CART). Other particular decision tree algorithms include, but are not limited to, ID3, C4.5, MART, and Random Forest. CART, ID3, and C4.5 are described in Duda, 2001, Pattern Classification, John Wiley & Sons, Inc., New York, pp. 396–408 and pp. 411–412, which is incorporated herein by reference. CART, MART, and C4.5 are described in Hastie et al., 2001, *The Elements of Statistical Learning*, Springer-Verlag, New York, Chapter 9, which is incorporated herein by reference in its entirety. Random forests are described in Breiman, 1999, “Random Forests—Random Features,” Technical Report 567, Statistics Department, UC Berkeley, September 1999, which is incorporated herein by reference in its entirety.

[0111] Clustering (e.g., unsupervised and supervised clustering model algorithms) is described, for example, on pages 211–256 of Duda and Hart, Pattern Classification and Scene Analysis, 1973, John Wiley & Sons, Inc., New York (hereinafter "Duda 1973"), which is incorporated herein by reference in its entirety. As described in Section 6.7 of Duda 1973, the clustering problem may be described as one of finding natural groups within a dataset. Two problems may be addressed in identifying natural groups. First, a method is determined for measuring the similarity (or dissimilarity) between two samples. This metric (similarity measure) may be used to ensure that samples in one cluster are more similar to each other than samples in other clusters. Second, a mechanism may be determined for dividing the data into clusters using the similarity measure. Similarity measures are discussed in Section 6.7 of Duda 1973, and one way to begin a clustering investigation may be to define a distance function and compute a distance matrix between all pairs of samples in the training set. Where distance is a good measure of similarity, the distance between reference substances in the same cluster may be significantly shorter than the distance between reference substances in different clusters. However, as stated on page 215 of Duda 1973, clustering does not necessarily require the use of a distance metric. For example, a nonmetric similarity function s(x,x') can be used to compare two vectors x and x'. Traditionally, s(x,x') may be a symmetric function whose value can be large when x and x' are "similar" in some way. An example of a nonmetric similarity function s(x,x') is provided, for example, on page 218 of Duda 1973. Once a method is chosen for measuring the "similarity" or "dissimilarity" between points in the dataset, clustering may require a criterion function to measure the clustering quality of any division of the data. Dataset splitting that extremizes the criterion function may be used to cluster the data.For example, see page 217 of Duda 1973. The reference function is discussed, for example, in section 6.8 of Duda 1973. More recently, see Duda et al., Pattern Classification, 2. nd The edition, published by John Wiley & Sons, Inc., New York, contains a detailed description of clustering on pages 537–563. Further details on clustering techniques can be found in Kaufman and Rousseeuw, 1990, Finding Groups in Data: An Introduction to Cluster Analysis, Wiley, New York, NY; Everitt, 1993, Cluster analysis (3rd ed.), Wiley, New York, NY; and Backer, 1995, Computer-Assisted Reasoning in Cluster Analysis, Prentice Hall, Upper Saddle River, New Jersey, each of which is incorporated herein by reference. Specific exemplary clustering techniques that may be used in this disclosure include, but are not limited to, hierarchical clustering (agglomerative clustering using nearest neighbor, farthest neighbor, mean linkage, centroid, or sum-of-squares algorithms), k-means clustering, fuzzy k-means clustering algorithms, Jarvis-Patrick clustering, or any combination thereof. In some embodiments, the clustering may include unsupervised clustering, in which case there is no preconceived notion about which clusters should be formed when the training set is clustered.

[0112] Regression models such as multi-category logit models are described, for example, in Agresti, An Introduction to Categorical Data Analysis, 1996, John Wiley & Sons, Inc., New York, Chapter 8, which is incorporated herein by reference in its entirety. In some embodiments, one or more predictive models and / or one or more machine learning algorithms may utilize the regression models disclosed in Hastie et al., 2001, The Elements of Statistical Learning, Springer-Verlag, New York, which is also incorporated herein by reference in its entirety. In some embodiments, gradient boosting models may be used, for example, for the classification algorithms described herein, and these gradient boosting models are described in Boehmke, Bradley; Greenwell, Brandon (2019). “Gradient Boosting”. Hands-On Machine Learning with R. Chapman & Hall. pp.221-245. ISBN 978-1-138-49568-5., which is incorporated herein by reference as a whole. In some embodiments, ensemble modeling techniques may be used, for example, for the classification algorithms described herein, and these ensemble modeling techniques are described in the implementation forms of the classification models herein, and are described in Zhou Zhihua (2012). Ensemble Methods: Foundations and Algorithms. Chapman and Hall / CRC. ISBN 978-1-439-83003-1, which is incorporated herein by reference as a whole.

[0113] In some embodiments, machine learning analysis may be performed by a device that runs one or more programs (e.g., one or more programs stored in non-persistent or persistent memory) that include instructions for performing data analysis. In some embodiments, data analysis may be performed by a system comprising at least one processor (e.g., a processing core) and memory (e.g., one or more programs stored in non-persistent or persistent memory) that includes instructions for performing data analysis. [Examples]

[0114] The following examples are included for illustrative purposes only and are not intended to limit the scope of the present invention.

[0115] Example 1: Association between the concentration of organic molecular signatures and autism spectrum disorder As described by the methods and / or systems provided herein, organic molecular signatures were obtained from a set of subject hair biosamples to determine whether the mean concentrations of the organic molecular signatures distinguished subjects belonging to the control group from those belonging to the autism spectrum disorder group. Specifically, the organic molecular signatures analyzed included hypotaurine (Figure 3A), melamine (Figure 4A), agmatine (Figure 5A), betasol (Figure 6A), and creatine (Figure 7A), as indicated by the concentration measurements of representative organic molecular signatures. The geometric mean of all concentration values ​​for each organic molecular signature was determined across all subjects in the two groups and plotted together with the standard error of the mean for each molecule (Figures 3B, 4B, 5B, 6B, and 7B). These results show that the geometric mean concentrations of each organic molecular signature provide a distinguishing feature between the two groups.

[0116] Predictive models were trained using concentration features of organic molecular signatures combined with labels specifying the target group (i.e., healthy subjects or subjects with autism spectrum disorder). The trained predictive models were then used on samples of subjects not included in the training data to determine the presence of autism spectrum disorder. The performance of the predictive models is shown in Figure 9, from the receiver operating characteristic (ROC) curve and area under the ROC curve. The predictive models classified subjects with autism spectrum disorder phenotypes with 80% sensitivity and 100% specificity. The area under the curve of the predictive models was 0.983.

[0117] Example 2: Organic Molecule Exposure Signature Using the methods and / or systems of this disclosure, as described elsewhere in this specification, the concentrations of nicotine organic molecular signatures in biomedical hair samples from smokers and non-smokers were measured to determine whether the nicotine organic molecular signatures classified and / or distinguished between smokers and non-smokers, as seen in Figures 8A–8B. From Figures 8A–8B, it can be seen that the average concentration of nicotine organic molecular signatures (Figure 8B) distinguished between smokers and non-smokers.

[0118] Example 3: Probe-based organic molecular signature Using the methods and / or systems of this disclosure, as described elsewhere in this specification, one or more organic molecular signatures of the control, disease autism spectrum disorder (Figures 10A–10B) phenotype, and disease amyotrophic lateral sclerosis (Figures 11A–11B) phenotype were determined by placing one or more probes, as described elsewhere in this specification, on the teeth of subjects in the associated test groups. As described elsewhere in this specification, one or more probes can target one or more proteins in the biological sample. One or more probes, as described elsewhere in this specification, may include a target binding moiety that targets one of several organic molecules. Organic molecular signatures obtained from 100 organic compounds and the significance of these associated features for autism spectrum disorder and amyotrophic lateral sclerosis are shown in Figures 10B and 11B, respectively. For each group of organic molecule signatures, a composite index determined by linear discriminant analysis was created and plotted against the control group and the disease groups, ASD (shown in Figure 10A) and ALS (shown in Figure 11A). The error bars represent the standard error of the mean of the composite index. Figures 10A and 11A show that the composite index scores of the identified organic molecules distinguish between the control group and the disease group.

[0119] Preferred embodiments of the present invention are shown and described herein, but it will be apparent to those skilled in the art that such embodiments are provided only as examples. Numerous variations, modifications, and substitutions will be conjured here upon those skilled in the art without departing from the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be used in the practice of the present invention. The following embodiments and claims define the scope of the present invention, and the methods and structures within these claims, as well as their equivalents, are intended to be encompassed thereby.

[0120] Embodiment Embodiment 1 is a method for classifying the phenotype of a subject, comprising obtaining or collecting one or more organic molecular signatures from multiple locations along a biological sample of the subject, and determining the phenotype of the subject from the one or more organic molecular signatures of the subject.

[0121] Embodiment 2 includes the method according to Embodiment 1, wherein one or more organic molecular signatures include the molecular signature of a molecule having a mass-to-charge ratio of at least 50 daltons (Da).

[0122] Embodiment 3 comprises the method of Embodiment 1 or 2, wherein one or more organic molecule signatures include one or more time-resolved organic molecule signatures.

[0123] Embodiment 4 includes the method according to any one of Embodiments 1 to 3, wherein a light source is used to acquire or collect one or more organic molecular signatures from multiple locations along a biological sample.

[0124] Embodiment 5 includes the method of Embodiment 4, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

[0125] Embodiment 6 includes the method according to any one of Embodiments 1 to 5, wherein the target phenotype includes a molecular phenotype, physiological phenotype, behavioral phenotype, disease phenotype, healthy phenotype, exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

[0126] Embodiment 7 includes the method of Embodiment 6, wherein the disease phenotype includes autism spectrum disorder (ASD), attention deficit hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

[0127] Embodiment 8 includes the method of Embodiment 6 or 7, wherein the exogenous compound comprises nicotine, melamine, or any combination thereof.

[0128] Embodiment 9 comprises the method of any one of Embodiments 6 to 8, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

[0129] Embodiment 10 includes the method according to Embodiment 9, wherein the signaling molecule comprises hypotaurine.

[0130] Embodiment 11 includes the method of Embodiment 9 or 10, wherein the endogenous metabolite includes creatinine.

[0131] Embodiment 12 includes a method according to any one of Embodiments 6 to 11, wherein the nutritional supplement contains agmatine.

[0132] Embodiment 13 includes the method according to any one of Embodiments 6 to 12, wherein the pharmaceutical product includes a pharmaceutical product for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

[0133] Embodiment 14 includes the method of Embodiment 13, wherein the pharmaceutical product comprises betasol.

[0134] Embodiment 15 includes a method according to any one of Embodiments 6 to 14, wherein the exposure phenotype includes exposure of the subject to environmental chemicals.

[0135] Embodiment 16 includes the method according to any one of Embodiments 1 to 15, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

[0136] Embodiment 17 includes a method according to any one of Embodiments 1 to 16, wherein acquiring or collecting a biological sample involves performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof.

[0137] Embodiment 18 includes a method according to any one of Embodiments 1 to 17, wherein the subject is administered or ingested a pharmaceutical, dietary supplement, or combination thereof for the treatment of a disease of the subject, and the subject's phenotype includes a response to the pharmaceutical, dietary supplement, or combination thereof.

[0138] Embodiment 19 includes the method of Embodiment 18, wherein the phenotype is used to determine the adjustment of pharmaceuticals, dietary supplements, or combinations thereof to alleviate the disease in question.

[0139] Embodiment 20 includes the method of Embodiment 19, wherein the adjustment of a pharmaceutical, dietary supplement, or combination thereof involves administering an improved or novel pharmaceutical, dietary supplement, or combination thereof.

[0140] Embodiment 21 includes the method according to any one of Embodiments 1 to 20, wherein one or more organic molecule signatures include the temporal concentration of one or more organic molecules obtained or collected from the biological sample of interest.

[0141] Embodiment 22 includes a method according to any one of Embodiments 1 to 21, wherein determining the phenotype of a target includes training a predictive model using one or more organic molecule signatures and associated phenotype labels of a set of targets different from the target, and providing one or more organic molecule signatures of the target to the trained predictive model to output the phenotype of the target.

[0142] Embodiment 23 is a method for classifying the phenotype of a target, comprising: when one or more probes are placed on the target biological sample, obtaining or collecting one or more molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da from the biological sample; and determining the phenotype of the target from the one or more molecular signatures of the target.

[0143] Embodiment 24 includes the method according to Embodiment 23, wherein one or more molecular signatures include one or more organic molecular signatures.

[0144] Embodiment 25 includes the method of Embodiment 23 or 24, wherein a light source is used to obtain or collect one or more molecular signatures from one or more probes placed on a biological sample.

[0145] Embodiment 26 includes the method of Embodiment 25, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

[0146] Embodiment 27 includes the method according to any one of Embodiments 23 to 26, wherein the phenotype in question includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

[0147] Embodiment 28 includes the method of Embodiment 27, wherein the disease phenotype includes autism spectrum disorder (ASD), attention deficit hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

[0148] Embodiment 29 includes the method of Embodiment 27 or 28, wherein the exogenous compound comprises nicotine, melamine, or any combination thereof.

[0149] Embodiment 30 includes the method according to any one of Embodiments 27 to 29, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

[0150] Embodiment 31 includes the method according to Embodiment 30, wherein the signaling molecule comprises hypotaurine.

[0151] Embodiment 32 includes the method according to Embodiment 30 or 31, wherein the endogenous metabolite includes creatinine.

[0152] Embodiment 33 includes a method according to any one of Embodiments 27 to 32, wherein the nutritional supplement contains agmatine.

[0153] Embodiment 34 includes the method according to any one of Embodiments 27 to 33, wherein the pharmaceutical product includes a pharmaceutical product for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

[0154] Embodiment 35 includes the method of Embodiment 34, wherein the pharmaceutical product comprises betasol.

[0155] Embodiment 36 includes the method according to any one of Embodiments 27 to 35, wherein the exposure phenotype includes exposure of the subject to environmental chemicals.

[0156] Embodiment 37 includes the method according to any one of Embodiments 23 to 36, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

[0157] Embodiment 38 includes a method according to any one of Embodiments 23 to 37, wherein obtaining or collecting involves performing a protein fluorescence assay using one or more probes.

[0158] Embodiment 39 includes a method according to any one of Embodiments 23 to 38, wherein the subject is administered or ingested a pharmaceutical, dietary supplement, or combination thereof for the treatment of the disease of the subject, and the subject's phenotype includes a response to the pharmaceutical, dietary supplement, or combination thereof.

[0159] Embodiment 40 includes the method of claim 39, wherein the phenotype is used to determine the adjustment of a drug, dietary supplement, or combination thereof to alleviate the disease in question.

[0160] Embodiment 41 includes the method of Embodiment 39 or 40, wherein the preparation of a pharmaceutical, dietary supplement, or combination thereof involves administering an improved or novel pharmaceutical, dietary supplement, or combination thereof.

[0161] Embodiment 42 includes a method according to any one of Embodiments 23 to 41, wherein determining the phenotype of a target includes training a predictive model using one or more molecular signatures and associated phenotype labels of a set of targets different from the target, and providing one or more molecular signatures of the target to the trained predictive model to output the phenotype of the target.

[0162] Embodiment 43 is a system for classifying the phenotype of a target, comprising one or more processors and a memory for storing one or more programs to be executed by the one or more processors, wherein the one or more programs include instructions for (i) acquiring or collecting one or more organic molecular signatures of a biological sample from a plurality of locations along the biological sample of a target, and (ii) determining the phenotype of a target from the one or more organic molecular signatures of the target.

[0163] Embodiment 44 includes the system described in Embodiment 43, wherein one or more organic molecular signatures include molecular signatures of molecules having a mass-to-charge ratio of at least 50 daltons (Da).

[0164] Embodiment 45 includes the system described in Embodiment 43 or 44, wherein one or more organic molecular signatures include one or more time-resolved organic molecular signatures.

[0165] Embodiment 46 includes the system described in any one of Embodiments 43 to 45, wherein a light source is used to acquire or collect one or more organic molecular signatures from multiple locations along a biological sample.

[0166] Embodiment 47 includes the system described in Embodiment 46, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

[0167] Embodiment 48 includes a system according to any one of Embodiments 43 to 47, wherein the target phenotype includes a molecular phenotype, physiological phenotype, behavioral phenotype, disease phenotype, healthy phenotype, exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

[0168] Embodiment 49 includes the system described in Embodiment 48, wherein the disease phenotype includes autism spectrum disorder (ASD), attention deficit hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

[0169] Embodiment 50 includes the system described in Embodiment 48 or 49, wherein the exogenous compound includes nicotine, melamine, or any combination thereof.

[0170] Embodiment 51 includes a system according to any one of Embodiments 48 to 50, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

[0171] Embodiment 52 includes the system described in Embodiment 51, wherein the signaling molecule comprises hypotaurine.

[0172] Embodiment 53 includes the system described in Embodiment 51 or 52, wherein the endogenous metabolite includes creatinine.

[0173] Embodiment 54 includes a system according to any one of Embodiments 48 to 53, wherein the nutritional supplement contains agmatine.

[0174] Embodiment 55 includes a system according to any one of Embodiments 48 to 54, wherein the pharmaceutical is a pharmaceutical for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

[0175] Embodiment 56 includes the system described in Embodiment 55, wherein the pharmaceutical product comprises betasol.

[0176] Embodiment 57 includes a system according to any one of Embodiments 48 to 56, wherein the exposure phenotype includes exposure of the subject to environmental chemicals.

[0177] Embodiment 58 includes the system described in any one of Embodiments 43 to 57, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

[0178] Embodiment 59 includes a system according to any one of Embodiments 43 to 58, wherein acquiring or collecting a biological sample involves performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof.

[0179] Embodiment 60 includes a system according to any one of Embodiments 43 to 59, wherein the subject is administered or ingested a pharmaceutical, dietary supplement, or combination thereof for the treatment of the disease of the subject, and the subject's phenotype includes a response to the pharmaceutical, dietary supplement, or combination thereof.

[0180] Embodiment 61 includes the system described in Embodiment 60, wherein the phenotype is used to determine the adjustment of pharmaceuticals, dietary supplements, or combinations thereof to alleviate the disease in question.

[0181] Embodiment 62 includes the system described in Embodiment 61, wherein the adjustment of a pharmaceutical, nutritional supplement, or combination thereof involves administering an improved or novel pharmaceutical, nutritional supplement, or combination thereof.

[0182] Embodiment 63 includes a system according to any one of Embodiments 43 to 62, wherein one or more organic molecule signatures include the temporal concentrations of one or more organic molecules obtained or collected from a biological sample of interest.

[0183] Embodiment 64 includes a system according to any one of Embodiments 43 to 63, wherein determining the phenotype of a target includes (i) training a predictive model using one or more organic molecule signatures and associated phenotype labels of a set of targets different from the target, and (ii) providing one or more organic molecule signatures of the target to the trained predictive model and outputting the phenotype of the target.

[0184] Embodiment 65 is a system for classifying the phenotype of a target, comprising one or more processors and a memory for storing one or more programs to be executed by the one or more processors, wherein the one or more programs include instructions for (i) obtaining or collecting one or more molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da from a biological sample when one or more probes are placed on the biological sample of a target, and (ii) determining the phenotype of a target from the one or more molecular signatures of the target.

[0185] Embodiment 66 includes the system described in Embodiment 65, wherein one or more molecular signatures include one or more organic molecular signatures.

[0186] Embodiment 67 includes the system described in Embodiment 65 or 66, wherein a light source is used to obtain or collect one or more molecular signatures from a biological sample.

[0187] Embodiment 68 includes the system described in Embodiment 67, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

[0188] Embodiment 69 includes a system according to any one of Embodiments 65 to 68, wherein the target phenotype includes a molecular phenotype, physiological phenotype, behavioral phenotype, disease phenotype, healthy phenotype, exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

[0189] Embodiment 70 includes the system described in Embodiment 69, wherein the disease phenotype includes autism spectrum disorder (ASD), attention deficit hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

[0190] Embodiment 71 includes the system described in Embodiment 69 or 70, wherein the exogenous compound includes nicotine, melamine, or any combination thereof.

[0191] Embodiment 72 includes the system described in any one of Embodiments 69 to 71, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

[0192] Embodiment 73 includes the system described in Embodiment 72, wherein the signaling molecule comprises hypotaurine.

[0193] Embodiment 74 includes the system described in Embodiment 72 or 73, wherein the endogenous metabolite includes creatinine.

[0194] Embodiment 75 includes a system according to any one of Embodiments 69 to 74, wherein the nutritional supplement contains agmatine.

[0195] Embodiment 76 includes a system according to any one of Embodiments 69 to 75, wherein the pharmaceutical is a pharmaceutical for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

[0196] Embodiment 77 comprises a system according to any one of Embodiments 69 to 76, wherein the pharmaceutical product comprises betasol.

[0197] Embodiment 78 includes a system according to any one of Embodiments 69 to 77, wherein the exposure phenotype includes exposure of the subject to environmental chemicals.

[0198] Embodiment 79 includes the system described in any one of Embodiments 65 to 78, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

[0199] Embodiment 80 includes the system described in any one of Embodiments 65 to 79, wherein the command to acquire or collect includes performing a protein fluorescence assay using one or more probes.

[0200] Embodiment 81 includes a system according to any one of Embodiments 65 to 80, wherein the subject is administered or ingested a pharmaceutical, dietary supplement, or combination thereof for the treatment of a disease of the subject, and the subject's phenotype includes a response to the pharmaceutical, dietary supplement, or combination thereof.

[0201] Embodiment 82 includes the system described in Embodiment 81, wherein the phenotype is used to determine the adjustment of pharmaceuticals, dietary supplements, or combinations thereof to alleviate the disease in question.

[0202] Embodiment 83 includes the system described in Embodiment 82, wherein the adjustment of a pharmaceutical, nutritional supplement, or combination thereof involves administering an improved or novel pharmaceutical, nutritional supplement, or combination thereof.

[0203] Embodiment 84 includes the system described in any one of Embodiments 65 to 83, wherein the instruction to determine the phenotype of a target includes training a predictive model using one or more molecular signatures and associated phenotype labels of a set of targets different from the target, and providing one or more molecular signatures of the target to the trained predictive model and outputting the phenotype of the target.

[0204] Embodiment 85 is a method for training an untrained or partially untrained machine learning algorithm or predictive model, comprising: collecting or acquiring one or more organic molecular signatures of a plurality of biological samples to be trained, in a computer system having one or more processors and memory for storing one or more programs to be executed by the one or more processors, wherein a first subset of the plurality of training samples has a first phenotype associated with one or more organic molecular signatures, and a second subset of the plurality of training samples has a second phenotype associated with one or more organic molecular signatures; and training an untrained or partially untrained machine learning algorithm or predictive model using one or more organic molecular signatures of the plurality of training samples and the corresponding first and second phenotypes associated with one or more organic molecular signatures, thereby creating or generating a trained predictive model.

[0205] Embodiment 86 includes the method of Embodiment 85, wherein one or more organic molecular signatures include one or more organic molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da.

[0206] Embodiment 87 includes the method of Embodiment 85 or 0, wherein one or more organic molecular signatures include one or more time-resolved organic molecular signatures.

[0207] Embodiment 88 includes the method according to any one of Embodiments 85 to 87, wherein a light source is used to obtain or collect one or more organic molecular signatures from multiple biological samples to be trained.

[0208] Embodiment 89 includes the method of Embodiment 88, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

[0209] Embodiment 90 includes the method according to any one of Embodiments 85 to 89, wherein the first or second phenotype includes a molecular phenotype, physiological phenotype, behavioral phenotype, disease phenotype, healthy phenotype, exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

[0210] Embodiment 91 includes the method of Embodiment 90, wherein the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

[0211] Embodiment 92 includes the method of Embodiment 90 or 91, wherein the exogenous compound includes nicotine, melamine, or any combination thereof.

[0212] Embodiment 93 comprises the method of any one of Embodiments 90 to 92, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

[0213] Embodiment 94 includes the method of Embodiment 93, wherein the signaling molecule comprises hypotaurine.

[0214] Embodiment 95 includes the method of Embodiment 93 or 94, wherein the endogenous metabolite includes creatinine.

[0215] Embodiment 96 comprises a method according to any one of Embodiments 90 to 95, wherein the nutritional supplement contains agmatine.

[0216] Embodiment 97 includes the method according to any one of Embodiments 90 to 96, wherein the pharmaceutical is a pharmaceutical for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

[0217] Embodiment 98 comprises a method according to any one of Embodiments 90 to 97, wherein the pharmaceutical product comprises betasol.

[0218] Embodiment 99 includes a method according to any one of Embodiments 90 to 98, wherein the exposure phenotype includes exposure of the subject to environmental chemicals.

[0219] Embodiment 100 includes the method according to any one of Embodiments 85 to 99, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

[0220] Embodiment 101 includes a method according to any one of Embodiments 85 to 100, wherein acquiring or collecting a biological sample involves performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof.

[0221] Embodiment 102 includes the method according to any one of Embodiments 85 to 101, wherein multiple training subjects are administered or ingested pharmaceuticals, nutritional supplements, or combinations thereof for treating diseases of the multiple training subjects, and the first or second phenotype of the multiple training subjects includes a response to the pharmaceuticals, nutritional supplements, or combinations thereof.

[0222] Embodiment 103 includes the method of Embodiment 102, wherein the first or second phenotype is used to determine the adjustment of a drug, dietary supplement, or combination thereof to alleviate the disease in question.

[0223] Embodiment 104 includes the method of Embodiment 103, wherein the adjustment of a pharmaceutical, dietary supplement, or combination thereof involves administering an improved or novel pharmaceutical, dietary supplement, or combination thereof.

[0224] Embodiment 105 includes the method according to any one of Embodiments 85 to 104, wherein one or more organic molecular signatures include the temporal concentrations of one or more organic molecular signatures obtained or collected from multiple biological samples under training.

Claims

1. A method for classifying the phenotype of an object, Obtaining or collecting one or more organic molecular signatures from multiple locations along the target biological sample, Determining the phenotype of the target from the signature of one or more organic molecules of the target. Methods that include...

2. The method according to claim 1, wherein the one or more organic molecular signatures include the molecular signature of a molecule having a mass-to-charge ratio of at least 50 Daltons (Da).

3. The method according to claim 1, wherein the one or more organic molecular signatures include one or more time-resolved organic molecular signatures.

4. The method according to claim 1, wherein a light source is used to obtain or collect one or more organic molecular signatures from the plurality of locations along the biological sample.

5. The method according to claim 4, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

6. The method according to claim 1, wherein the phenotype of the subject includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a nutritional supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

7. The method according to claim 6, wherein the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

8. The method according to claim 6, wherein the exogenous compound comprises nicotine, melamine, or any combination thereof.

9. The method according to claim 6, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

10. The method according to claim 9, wherein the signal transduction molecule comprises hypotaurine.

11. The method according to claim 9, wherein the endogenous metabolite includes creatinine.

12. The method according to claim 6, wherein the nutritional supplement contains agmatine.

13. The method according to claim 6, wherein the pharmaceutical product includes a pharmaceutical product for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

14. The method according to claim 13, wherein the pharmaceutical product comprises betasol.

15. The method according to claim 6, wherein the exposure phenotype includes exposure of the subject to an environmental chemical substance.

16. The method according to claim 1, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

17. The method according to claim 1, wherein obtaining or collecting the biological sample involves performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof.

18. The method according to claim 1, wherein the subject is administered or ingested a pharmaceutical, nutritional supplement, or combination thereof for the treatment of a disease of the subject, and the phenotype of the subject includes a response to the pharmaceutical, nutritional supplement, or combination thereof.

19. The method according to claim 18, wherein the phenotype is used to determine the adjustment of the pharmaceutical, dietary supplement, or combination thereof in order to alleviate the disease of the subject.

20. The method according to claim 19, wherein the adjustment of the pharmaceutical product, nutritional supplement, or combination thereof includes administering an improved or novel pharmaceutical product, nutritional supplement, or combination thereof.

21. The method according to claim 1, wherein the one or more organic molecule signatures include the temporal concentration of one or more organic molecules obtained or collected from the biological sample of the subject.

22. Determining the phenotype of the aforementioned target is Training a predictive model using one or more organic molecule signatures and associated phenotypic labels from a set of targets different from the aforementioned target, The signatures of one or more organic molecules of the target are provided to the trained predictive model, and the phenotype of the target is output. The method according to claim 1, including the method described in claim 1.

23. A method for classifying the phenotype of an object, When one or more probes are placed on the target biological sample, one or more molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da are obtained or collected from the biological sample. Determining the phenotype of the target from one or more molecular signatures of the target. Methods that include...

24. The method according to claim 23, wherein the one or more molecular signatures include one or more organic molecular signatures.

25. The method according to claim 23, wherein a light source is used to obtain or collect one or more molecular signatures from one or more probes placed on the biological sample.

26. The method according to claim 25, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

27. The method according to claim 23, wherein the phenotype of the subject includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a nutritional supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

28. The method according to claim 27, wherein the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

29. The method according to claim 27, wherein the exogenous compound comprises nicotine, melamine, or any combination thereof.

30. The method according to claim 27, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

31. The method according to claim 30, wherein the signal transduction molecule comprises hypotaurine.

32. The method according to claim 30, wherein the endogenous metabolite includes creatinine.

33. The method according to claim 27, wherein the nutritional supplement contains agmatine.

34. The method according to claim 27, wherein the pharmaceutical product comprises a pharmaceutical product for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

35. The method according to claim 34, wherein the pharmaceutical product comprises betasol.

36. The method according to claim 27, wherein the exposure phenotype includes exposure of the subject to an environmental chemical substance.

37. The method according to claim 23, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

38. The method according to claim 23, wherein obtaining or collecting includes performing a protein fluorescence assay using one or more probes.

39. The method according to claim 23, wherein the subject is administered or ingested a pharmaceutical, nutritional supplement, or combination thereof for the treatment of a disease of the subject, and the phenotype of the subject includes a response to the pharmaceutical, nutritional supplement, or combination thereof.

40. The method according to claim 39, wherein the phenotype is used to determine the adjustment of the pharmaceutical, dietary supplement, or combination thereof in order to alleviate the disease of the subject.

41. The method according to claim 40, wherein the adjustment of the pharmaceutical product, nutritional supplement, or combination thereof includes administering an improved or novel pharmaceutical product, nutritional supplement, or combination thereof.

42. Determining the phenotype of the aforementioned target is Training a predictive model using one or more molecular signatures and associated phenotypic labels of a set of targets different from the aforementioned target, Provide one or more molecular signatures of the target to the trained prediction model and output the phenotype of the target. The method according to claim 23, including the method described in claim 23.

43. A system for classifying the phenotype of an object, A memory that stores one or more processors and one or more programs to be executed by the one or more processors, wherein the one or more programs are (i) Obtain or collect one or more organic molecular signatures of the biological sample from multiple locations along the target biological sample, (ii) A memory and an instruction that determines the phenotype of the object from the one or more organic molecular signatures of the object. A system equipped with these features.

44. The system according to claim 43, wherein the one or more organic molecular signatures include molecular signatures of molecules having a mass-to-charge ratio of at least 50 Daltons (Da).

45. The system according to claim 43, wherein the one or more organic molecular signatures include one or more time-resolved organic molecular signatures.

46. The system according to claim 43, wherein a light source is used to acquire or collect one or more organic molecular signatures from the plurality of locations along the biological sample.

47. The system according to claim 46, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

48. The system according to claim 43, wherein the phenotype of the subject includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a nutritional supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

49. The system according to claim 48, wherein the disease phenotype includes autism spectrum disorder (ASD), attention deficit hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

50. The system according to claim 48, wherein the exogenous compound comprises nicotine, melamine, or any combination thereof.

51. The system according to claim 48, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

52. The system according to claim 51, wherein the signal transduction molecule comprises hypotaurine.

53. The system according to claim 51, wherein the endogenous metabolite includes creatinine.

54. The system according to claim 48, wherein the nutritional supplement contains agmatine.

55. The system according to claim 48, wherein the pharmaceuticals include pharmaceuticals for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

56. The system according to claim 55, wherein the pharmaceutical product comprises betasol.

57. The system according to claim 48, wherein the exposure phenotype includes exposure of the subject to environmental chemicals.

58. The system according to claim 43, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

59. The system according to claim 43, wherein acquiring or collecting the biological sample involves performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof.

60. The system according to claim 43, wherein the subject is administered or ingested a pharmaceutical, nutritional supplement, or combination thereof for the treatment of a disease of the subject, and the phenotype of the subject includes a response to the pharmaceutical, nutritional supplement, or combination thereof.

61. The system according to claim 60, wherein the phenotype is used to determine the adjustment of the pharmaceutical, nutritional supplement, or combination thereof in order to alleviate the disease of the subject.

62. The system according to claim 61, wherein the adjustment of the pharmaceutical product, nutritional supplement, or combination thereof includes administering an improved or novel pharmaceutical product, nutritional supplement, or combination thereof.

63. The system according to claim 43, wherein the one or more organic molecule signatures include the temporal concentration of one or more organic molecules obtained or collected from the biological sample of the subject.

64. Determining the phenotype of the aforementioned target is (i) Training a predictive model using one or more organic molecule signatures and associated phenotypic labels from a set of targets different from the aforementioned targets, (ii) Providing one or more organic molecule signatures of the target to the trained predictive model and outputting the phenotype of the target. The system according to claim 43, including the system described in claim 43.

65. A system for classifying the phenotype of an object, A memory that stores one or more processors and one or more programs to be executed by the one or more processors, wherein the one or more programs are (i) When one or more probes are placed on the target biological sample, one or more molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da are obtained or collected from the biological sample. (ii) A memory and an instruction that determines the phenotype of the object from the one or more molecular signatures of the object. A system equipped with these features.

66. The system according to claim 65, wherein the one or more molecular signatures include one or more organic molecular signatures.

67. The system according to claim 65, wherein a light source is used to obtain or collect the one or more molecular signatures from the biological sample.

68. The system according to claim 66, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

69. The system according to claim 65, wherein the phenotype of the subject includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a nutritional supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

70. The system according to claim 69, wherein the disease phenotype includes autism spectrum disorder (ASD), attention-deficit / hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

71. The system according to claim 69, wherein the exogenous compound comprises nicotine, melamine, or any combination thereof.

72. The system according to claim 69, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

73. The system according to claim 72, wherein the signal transduction molecule comprises hypotaurine.

74. The system according to claim 72, wherein the endogenous metabolite includes creatinine.

75. The system according to claim 69, wherein the nutritional supplement contains agmatine.

76. The system according to claim 69, wherein the pharmaceuticals include pharmaceuticals for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

77. The system according to claim 69, wherein the pharmaceutical product comprises betasol.

78. The system according to claim 69, wherein the exposure phenotype includes exposure of the subject to environmental chemicals.

79. The system according to claim 65, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

80. The system according to claim 65, wherein the command to be acquired or collected includes performing a protein fluorescence assay using the one or more probes.

81. The system according to claim 65, wherein the subject is administered or ingested a pharmaceutical, nutritional supplement, or combination thereof for the treatment of a disease of the subject, and the phenotype of the subject includes a response to the pharmaceutical, nutritional supplement, or combination thereof.

82. The system according to claim 81, wherein the phenotype is used to determine the adjustment of the pharmaceutical, nutritional supplement, or combination thereof in order to alleviate the disease of the subject.

83. The system according to claim 82, wherein the adjustment of the pharmaceutical product, nutritional supplement, or combination thereof includes administering an improved or novel pharmaceutical product, nutritional supplement, or combination thereof.

84. The instruction that determines the phenotype of the target, (iii) Training a predictive model using one or more molecular signatures and associated phenotypic labels of a set of targets different from the aforementioned target, (iv) Providing one or more molecular signatures of the subject to the trained predictive model and outputting the phenotype of the subject. The system according to claim 65, including the system described in claim 65.

85. A method for training an untrained or partially untrained machine learning algorithm or predictive model, In a computer system having one or more processors and memory for storing one or more programs to be executed by the one or more processors, The method of collecting or acquiring one or more organic molecular signatures from multiple biological samples of training subjects, wherein a first subset of the multiple training subjects has a first phenotype associated with the one or more organic molecular signatures, and a second subset of the multiple training subjects has a second phenotype associated with the one or more organic molecular signatures. Training an untrained or partially untrained machine learning algorithm or predictive model using the one or more organic molecule signatures of the plurality of training targets and the corresponding first and second phenotypes associated with the one or more organic molecule signatures, thereby creating or generating a trained predictive model. Methods that include...

86. The method according to claim 85, wherein the one or more organic molecular signatures include one or more organic molecular signatures of molecules having a mass-to-charge ratio of at least 50 Da.

87. The method according to claim 85, wherein the one or more organic molecular signatures include one or more time-resolved organic molecular signatures.

88. The method according to claim 85, wherein a light source is used to obtain or collect one or more organic molecular signatures from the plurality of biological samples to be trained.

89. The method according to claim 88, wherein the light source includes a laser, a pulsed laser, a continuous-wave laser, or any combination thereof.

90. The method according to claim 85, wherein the first phenotype or the second phenotype includes a molecular phenotype, a physiological phenotype, a behavioral phenotype, a disease phenotype, a healthy phenotype, an exposure phenotype, one or more upregulated or downregulated physiological pathways, a response to a drug, a response to a dietary supplement, the presence of an exogenous compound, the presence of an endogenous compound, the presence of inflammation, or any combination thereof.

91. The method according to claim 90, wherein the disease phenotype includes autism spectrum disorder (ASD), attention deficit hyperactivity disorder, amyotrophic lateral sclerosis, or any combination thereof.

92. The method according to claim 90, wherein the exogenous compound comprises nicotine, melamine, or any combination thereof.

93. The method according to claim 90, wherein the endogenous compound comprises an endogenous metabolite, a signaling molecule, or any combination thereof.

94. The method according to claim 93, wherein the signal transduction molecule comprises hypotaurine.

95. The method according to claim 93, wherein the endogenous metabolite includes creatinine.

96. The method according to claim 90, wherein the nutritional supplement contains agmatine.

97. The method according to claim 90, wherein the pharmaceutical product includes a pharmaceutical product for treating heartburn, acid reflux, peptic ulcers, or any combination thereof.

98. The method according to claim 90, wherein the pharmaceutical product comprises betasol.

99. The method according to claim 90, wherein the exposure phenotype includes exposure of the subject to an environmental chemical substance.

100. The method according to claim 85, wherein the biological sample includes a sample of hair, teeth, fingernails, toenails, or any combination thereof.

101. The method according to claim 85, wherein obtaining or collecting the biological sample involves performing matrix-assisted laser desorption / ionization time-of-flight mass spectrometry (MALDI-ToF MS), laser ablation electrospray ionization (LAESI), protein fluorescence assay, or any combination thereof.

102. The method according to claim 85, wherein the plurality of trainees are administered or ingested pharmaceuticals, nutritional supplements, or combinations thereof for treating diseases of the plurality of trainees, and the first phenotype or the second phenotype of the plurality of trainees includes a response to the pharmaceuticals, nutritional supplements, or combinations thereof.

103. The method according to claim 102, wherein the first phenotype or the second phenotype is used to determine the adjustment of the pharmaceutical, dietary supplement, or combination thereof in order to alleviate the disease of the subject.

104. The method according to claim 103, wherein the adjustment of the pharmaceutical product, nutritional supplement, or combination thereof includes administering an improved or novel pharmaceutical product, nutritional supplement, or combination thereof.

105. The method according to claim 85, wherein the one or more organic molecular signatures include the temporal concentrations of the one or more organic molecular signatures obtained or collected from the plurality of biological samples to be trained.

Images