A METHOD FOR OPTIMIZING FUTURE HEALTH OR FUTURE PERFORMANCE IN AN ANIMAL

Abstract

The present disclosure provides systems and methods for optimizing future health or future performance in an animal. The methods can include obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract, mammary gland, reproductive system, or respiratory system. The methods can include defining a query for future health or future performance of the animal. The methods can include selecting a model from a model repository based on the sample dataset and the query. The method can include executing the selected model using the sample dataset and the query to make predictions, generate recommendations, or generate interventions about future health or future performance of the animal. The methods can include reporting the predictions, recommendations, or interventions about future health or future performance, and implementing one or more interventions by based on the predictions, recommendations, or interventions. Other aspects are also provided herein.

Description

112 A METHOD FOR OPTIMIZING FUTURE HEALTH OR FUTURE PERFORMANCE IN AN ANIMAL CROSS-REFERENCE TO RELATED ORDERS

[001] This application claims the benefit of US Provisional Patent Application No. 63 / 490,920, filed March 17, 2023, which is incorporated herein by reference in its entirety. FIELD

[002] The present disclosure relates to systems and methods for optimizing the future health and performance of an animal. Specifically, the present disclosure relates to systems and methods for optimizing the future health and performance of an animal using metagenomic data and various metadata to make one or more predictions, recommendations, or interventions about future health measures or future performance measures of an animal or group of animals. BACKGROUND

[003] The swine microbiome undergoes longitudinal and dynamic changes throughout the pig's lifespan. In some cases, dynamic changes provide beneficial outcomes for pigs, while in other cases dynamic changes can lead to disease and poor performance measures. Beginning at birth and maturing through the sow's reproductive stage, the swine microbiome is continuously changing, as influenced by the transitions and exposures experienced by the pig throughout its life, including transitions from gilt to sow, during weaning, during farrowing, as impacted by environmental exposure or pathogens, a change in diet and nutritional management, use of antimicrobials, and so on. Large dynamic changes in the swine microbiome can have significant negative impacts on animal health and performance, and can adversely affect a range of health and performance measures. Such measures of Petition 870250080933, dated 09 / 09 / 2025, page 12 / 138 / 112 health and performance can include the animal's overall health, body weight, average daily weight gain, feed intake, feed conversion rate, and much more. Without insight into the composition of the pig's microbiome throughout its lifespan, it may be difficult or impossible to adapt various aspects of pig farming to address the effects of dynamic changes.

[004] Previous efforts to address the problem of dynamic microbiome changes include using a subset of biomarkers from retrospective metagenomic data obtained at the population level to achieve specific results. Such methods avoided using large microbiome datasets at the individual animal level and therefore did not use the entire microbiome to leverage the impact that dynamic changes within the entire microbiome had on the future health and performance of existing individual animals or a subset of a group of animals. Furthermore, such methods did not use multigenerational data to predict the future health and performance of an individual animal or a subset of a group of animals.Thus, there is a need to provide a system and methods for using large-scale metagenomic data for an existing animal to predict the future health and performance of that animal, and which can also be used for individual animal selection or group-level selection of a subset of animals to apply personalized interventions in order to optimize the future health and performance of the animal or a subset of animals. SUMMARY

[005] The present disclosure provides a method for optimizing the future health or future performance of an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract, mammary gland, Petition 870250080933, dated 09 / 09 / 2025, p. 13 / 138 / 112 reproductive system or respiratory system of the animal. The method may additionally include defining a query including one or more target queries for the animal's future health or future performance. The method may additionally include selecting a model from a model repository based on the sample dataset and the query including the one or more targets. The method may additionally include running the selected model using the sample dataset and the query including the one or more targets to make predictions, generate recommendations, or generate interventions about the animal's future health or future performance. The method may additionally include reporting the predictions, recommendations, or interventions about future health or future performance, or combinations thereof.The method may additionally include the implementation of one or more interventions such as one or more adjustments to nutrition, management systems, healthcare, or the animal's rearing environment, based on predictions, recommendations, or interventions.

[006] The present disclosure provides a multigenerational microbiome system for optimizing future health or future performance in one or more animals. The multigenerational microbiome system may include: a metagenomic component configured to receive metagenomic data obtained from a microbiome sample of one or more animals; a metadata acquisition component configured to receive metadata about one or more animals; a query acquisition component configured to receive one or more target queries for the future health or future performance of one or more animals; and a processing component. The processing component of the multigenerational microbiome system may include a model selection mechanism, wherein the model selection mechanism is configured to select a model or set of models from a model repository based on the metagenomic data, metadata, and target query; a mechanism toPetition 870250080933, dated 09 / 09 / 2025, page 14 / 138 / 112 prediction generation, wherein the prediction generation mechanism is configured to run the selected model or set of models to generate one or more predictions about the animal's future health or future performance; a recommendation prioritization mechanism, wherein the recommendation prioritization mechanism is configured to use the predictions to identify an animal or animals at risk of future adverse health or future adverse performance, and to generate one or more recommendations that are prioritized to address the identified risk; and an intervention prioritization mechanism, wherein the intervention prioritization mechanism is configured to use the one or more predictions or recommendations to generate one or more interventions that are prioritized to address the identified risk.The multigenerational microbiome mechanism may additionally include a reporting mechanism configured to receive predictions, recommendations, or interventions, and generate one or more reports that include the specific predictions, recommendations, or interventions, or a combination thereof, and a detailed rationale for appropriate adjustments to optimize future health or performance in an animal or group of animals; and an adjustment component configured to implement the one or more interventions as one or more adjustments to the animal or group of animals.

[007] The present disclosure may include a method for predicting future health or future performance in an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract, mammary gland, reproductive system, or respiratory system of the animal. The method may further include defining a query including one or more target queries for the animal's future health or future performance. The method may further include selecting a model from a model repository based on the sample dataset and the query including Petition 870250080933, dated 09 / 09 / 2025, page 15 / 138 / 112, one or more targets, wherein each model selected from the model repository is generated by a model building mechanism, and wherein the model building mechanism was trained using one or more metagenomic datasets or metadata obtained from one or more observational and interventional studies. The method may additionally include running the selected model using the sample dataset and querying including one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance. The method may additionally include reporting the predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof.The method may additionally include the implementation of one or more interventions such as one or more adjustments to nutrition, management systems, healthcare, or the animal's rearing environment, based on predictions, recommendations, or interventions.

[008] The present disclosure includes a method for optimizing the future health or future performance of an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within an animal's reproductive system. The method may further include defining a query including one or more target queries for the animal's future health or future performance. The method may further include selecting a model from a model repository based on the sample dataset and the query including the one or more targets. The method may further include running the selected model using the sample dataset and the query including the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance. The method may further include reporting the predictions, recommendations, or interventions regarding the animal's future health or future performance. Petition 870250080933, dated 09 / 09 / 2025, page 16 / 138 / 112 of future performance, or combinations thereof. The method may additionally include the implementation of one or more interventions such as one or more adjustments to nutrition, management system, health care or the animal's rearing environment, based on predictions, recommendations or interventions.

[009] The present disclosure includes a method for optimizing the future health or future performance of an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within an animal mammary gland. The method may further include defining a query including one or more target queries for the animal's future health or future performance. The method may further include selecting a model from a model repository based on the sample dataset and the query including the one or more targets. The method may further include running the selected model using the sample dataset and the query including the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance.The method may additionally include reporting predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof. The method may additionally include implementing one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment, based on the predictions, recommendations, or interventions.

[0010] The present disclosure provides a method for optimizing the future health or future performance of an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within an animal's respiratory system. The method may further include defining a query including one or Petition 870250080933, dated 09 / 09 / 2025, p. 17 / 138 / 112 more target queries for the animal's future health or future performance. The method may additionally include selecting a model from a model repository based on the sample dataset and the query including one or more targets. The method may additionally include running the selected model using the sample dataset and the query including one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance. The method may additionally include reporting the predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof. The method may additionally include implementing one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment, based on the predictions, recommendations, or interventions. BRIEF DESCRIPTION OF THE FIGURES

[0011] The drawings illustrate, in general and by way of example, but not by way of limitation, various aspects discussed here.

[0012] Figure 1 is a schematic representation of a multigenerational microbiome system according to various aspects of the present invention.

[0013] Figure 2 is a schematic representation of the components of a multigenerational microbiome system according to various aspects of the present invention.

[0014] Figure 3 is a schematic representation of a selection matrix according to various aspects of the present invention.

[0015] Figure 4 is a schematic representation of a model-making system according to various aspects of the present invention.

[0016] Figure 5 is a schematic representation of a process flow according to various aspects of the present invention. Petition 870250080933, dated 09 / 09 / 2025, p. 18 / 138 / 112

[0017] Figure 6 is a flow diagram of a method according to various aspects of the present invention.

[0018] Figure 7 is a schematic representation of a computing environment according to various aspects of the present invention. DETAILED DESCRIPTION

[0019] Detailed reference will now be made to certain aspects of the disclosed matter, examples of which are illustrated in part in the accompanying drawings. Although the disclosed matter is described in conjunction with the listed claims, it will be understood that the exemplified matter is not intended to limit the claims to that disclosed matter.

[0020] The pig microbiome has a strong correlation with an animal's future health and performance. The pig microbiome can be used to understand and predict future health and performance throughout any stage of the pig's life cycle. The pig microbiome can be sampled from any number of pig locations, including the gastrointestinal tract, reproductive system, mammary glands, and respiratory system, and can be used to extract metagenomic data useful in identifying relationships between the current state of the microbiome and future health and performance outcomes. The present disclosure provides the use of multigenerational microbiome data to predict measures of future health and future performance in animals.The microbiome of a given animal or group of animals can be repeatedly investigated throughout the animal's life cycle to provide personalized interventions to optimize future health and performance measures for that animal or group of animals. The systems and methods described herein use multiple predictive models to select high-performing animals and / or to identify areas where low-performing animals require personalized interventions to improve their performance. The systems and methods of the present invention also use multiple predictive models to select animals that... Petition 870250080933, dated 09 / 09 / 2025, page 19 / 138 / 112 exhibit a robust microbiome and / or to identify areas where animals with general health concerns are selected for personalized interventions to improve their health.

[0021] As used in this document, the term gastrointestinal tract may refer to the tract or passage that contains all the major organs of the digestive system (e.g., the mouth, esophagus, stomach, small intestine, and large intestine) and that leads from the mouth to the anus.

[0022] As used in this document, the term reproductive system may refer to the tissues, glands, and organs involved in the production of offspring. In particular, the reproductive system of the females described herein (e.g., sows) may include the ovaries, uterine horn, uterine body, cervix, vagina, vulva, mammary glands, and nipples.

[0023] As used in this document, the term respiratory system may refer to the organs and structures that enable breathing to facilitate gas exchange within an animal. The organs and structures of the respiratory system may include the nostrils, nasal passages, nasal septum, pharynx, larynx, trachea, bronchial tree, bronchi, alveoli, and lungs. Multigenerational microbiome systems

[0024] The multigenerational microbiome systems of the present invention may include a series of components configured to explore the relationship between metagenomic data, pig metadata, and one or more questions to be answered about the future health and performance of an animal or group of animals. With reference now to Figure 1, a schematic diagram illustrating a multigenerational microbiome system 100 for optimizing future health measures or future performance measures in an animal is shown according to the various aspects of Petition 870250080933, dated 09 / 09 / 2025, page 20 / 138 / 112 present invention. The multigenerational microbiome system 100 is configured to generate predictions, recommendations, or interventions regarding future health measures or future performance measures for an animal or group of animals using multigenerational microbiome data obtained from one or more past generations of the animals to predict future health and future performance at the individual animal level or at the group level. It will be recognized that multigenerational microbiome data may include microbiome data obtained from related past generations or unrelated past generations. The future health measures or future performance measures targeted by the systems and methods of the present invention will be described in more detail elsewhere in this document.Multigenerational microbiome data can include metagenomic data obtained from a microbiome sample from any current or past generation of animals or groups of animals.

[0025] The multigenerational microbiome system 100 can implement any of the many permutations of the methods and techniques described herein. The multigenerational microbiome system 100 can include an animal component 102, a sample acquisition component 104, a metadata acquisition component 106, a query acquisition component 108, a sample preparation component 110, a metagenomic component 112, a processing component 114, a reporting mechanism 128, and a tuning component 138.

[0026] As used in this document, the term metadata may refer to any characteristic about an animal or about how the animal is raised and about any microbiome sampling characteristics, including body weight, birth weight, animal breed, animal sex, body composition, growth rate, feed conversion rate, mortality, morbidity, habitability, disease history, health and performance measures, reproductive measures, pathological states Petition 870250080933, dated 09 / 09 / 2025, page 21 / 138 / 112 current or previous pathogenic risks (e.g., gastrointestinal pathogenic risks, respiratory pathogenic risks, reproductive system pathogenic risks, mammary gland pathogenic risks), type of feed, vaccines administered and date of vaccine administration, type of supplement, use of antimicrobial resistance promoters, management system (e.g., conventional farming or farmed animals raised with antibiotics), geographic location, farming conditions, animal life stage (e.g., gilt, sow, or piglet), type of microbiome sample (e.g., fecal, rectal, vaginal, mammary, nasal, oral, pulmonary, etc.), life stage of microbiome sampling (e.g., pre-weaning, weaning, post-weaning, finishing, gestation, pre-partum, parturition, post-partum, etc.).), age / time of microbiome sampling, metagenomic method used (e.g., DNA- or RNA-based shotgun sequencing, 16S ribosomal RNA gene sequencing, 18S ribosomal RNA gene sequencing, or internal transcribed spacer amplicon (ITS) sequencing), farm location, herd size, animal heart circumference measurement, nutrition, and any other data, such as demographic or biometric data relevant to an animal or group of animals.

[0027] It will be recognized that the microbiome sample isolated from an animal and used to generate metagenomic data may be isolated from the gastrointestinal tract, including a sample from within the gastrointestinal tract, including, but not limited to, oral, cecal, colon or rectal samples, or a fresh fecal sample; from the reproductive system (e.g., proximal or distal vaginal samples); from the mammary glands (e.g., milk or colostrum samples); or from the respiratory system (e.g., nasopharyngeal, bronchoalveolar lavage or pulmonary samples).

[0028] As used in this document, the term metagenomic data may refer to sequencing data obtained about Petition 870250080933, dated 09 / 09 / 2025, page 22 / 138 / 112 a microbiome sample, including any of the samples mentioned above, such as a fecal sample, a rectal sample, a vaginal sample, a breast sample, an oral sample, a nasal sample, or a lung sample using one or more sequencing technologies, including, but not limited to, whole genome sequencing techniques (e.g., DNA-based or RNA-based shotgun sequencing), 16S ribosomal RNA gene sequencing, 18S ribosomal RNA gene sequencing, or internal transcript spacer amplicon (ITS) sequencing.

[0029] The animal component 102 suitable for the systems and methods described herein may include one or more types of wild or domesticated swine at various life stages, including, but not limited to, piglets, gilts, sows, ham-producing pigs, castrated pigs, wild boars, pregnant females, fattening pigs, growing pigs, finished pigs, pigs, swine, small animals, breeding animals, castrated pigs, or sows. In many respects, the animal component 102 suitable for the systems and methods described herein may include piglets, gilts, or sows. The animal component 102 may also have associated with it any additional information about the physical attributes of the animals, including, but not limited to, breed, body weight, body composition, growth rate, feed conversion rate, mortality, morbidity, habitability, disease history, general health, and the like.The animal component 102 may additionally include techniques, methods and devices for acquiring any further information about animals.

[0030] Sample acquisition component 104 may include various systems or techniques for acquiring biological samples from animals. Sample acquisition component 104 may be configured to obtain biological samples from animals from one or more agricultural sites in one or more geographic regions. By way of example, biological samples are Petition 870250080933, dated 09 / 09 / 2025, page 23 / 138 / 112 obtained through the use of a permeable material or substrate, such as a cotton swab, sponge, or other material that is configured to collect and retain biological material (e.g., digestion-related elements such as chyme, or excretions such as animal feces) from a surface or orifice of the gastrointestinal tract of animals. In another example, biological samples may be obtained through the use of a non-permeable material, such as a tube, vial, or other glass or polymer container that is configured to receive biological samples directly from animals or indirectly from animals, such as a fecal sample obtained directly from feces or other excretions. The biological sample may include a sample of the microbial community obtained from within a gastrointestinal tract, reproductive system, mammary glands, or respiratory system of animals, as described elsewhere in this document.In one example, a biological sample may be obtained from a segment of the gastrointestinal tract of animals, such as from the stomach, duodenum, jejunum, ileum, cecum, or colon of processed animals. In another example, biological samples are obtained from exposed animal orifices or from animal excrement. In yet another example, biological samples may be obtained from the reproductive system, such as from the proximal or distal vagina. In some examples, a biological sample may be obtained from the mammary glands, including milk or colostrum samples. In other examples, a biological sample may be obtained from the respiratory system, including nasopharyngeal, bronchoalveolar lavage, or pulmonary samples.

[0031] Sample acquisition component 104 may include a standardized sample acquisition set (e.g., a sample kit) that includes a glass or polymer tube, a chemical solution or reagent, and one or more swabs or other substrates for extracting a biological sample. The tube may be pre-filled with a chemical solution. Petition 870250080933, dated 09 / 09 / 2025, page 24 / 138 / 112 For example, the chemical solution might include a solution that is configured to lyse microbiota cells and preserve DNA and / or RNA. In one example, the sample acquisition kit might include prescribed sample collection and handling protocols. Such protocols might include instructions regarding the number of samples and a schedule for sample collection per animal or group of animals, a process for collecting and storing each sample, and a process for sending the samples for analysis. The sample acquisition kit, including the protocols described here, can standardize the sample acquisition process and thus reduce variations in metagenomic data obtained from the samples.

[0032] Metadata acquisition component 106 may include various systems or methods for acquiring metadata about animals. Metadata acquisition component 106 may be configured to receive metadata from one or more animals from one or more agricultural sites in one or more geographic regions. Metadata may include, but should not be limited to, one or more of the following: body weight, breed, body composition, growth rate, feed conversion rate, mortality, morbidity, habitability, disease history, general health, reproductive measurements, pathological states, pathogenic risks (e.g., gastrointestinal pathogenic risks, future respiratory pathogenic risks, future reproductive system pathogenic risks, future mammary gland pathogenic risks), feeding data, supplementary data, or other data describing an animal characteristic as described elsewhere in this document.The metadata acquisition component 106 can be configured to receive indicative input of one or more metadata types.

[0033] The query acquisition component 108 can include various systems or methods for receiving a target query about animals. The query acquisition component 108 can be configured to receive Petition 870250080933, dated 09 / 09 / 2025, p. 25 / 138 / 112 one or more target queries for future health measures or future performance measures of one or more animals. The input received by query acquisition component 108 may be indicative of a target query selection, a specific type of sequencing data (described elsewhere in this document), and the like. Target queries may be generalized to all animal life stages, or they may be specific to one or more life stages, including piglet, sow, or gilt life stages.For example, it may be desirable to interrogate one or more target queries for piglets, wherein the one or more queries investigate any of the following: piglet growth rate, piglet average daily weight gain, piglet microbiome alpha diversity, piglet habitability, piglet mortality, piglet general health, piglet gastrointestinal pathologies risk, piglet respiratory pathologies risk, piglet antimicrobial growth promoter use, piglet microbiome composition, piglet microbiome function, piglet microbiome network interaction, piglet microbiome stability, piglet microbiome robustness, and / or piglet microbiome resilience.It will be recognized that target queries for future health measures or future performance measures of piglets may include one or more current or future life stages of the piglet, such as birth, a nursery stage, a pre-weaning stage, a weaning stage, a post-weaning stage, a finishing stage, or during any transition between any of the preceding stages from piglet to adult pig.

[0034] In addition, it may be desirable to interrogate one or more target queries for sows, wherein the one or more queries investigate any of the following: sow habitability, sow mortality, sow general health, risk of sow gastrointestinal pathologies, risk of sow respiratory pathologies, risk of sow reproductive system pathologies, risk of sow mammary gland pathologies. Petition 870250080933, dated 09 / 09 / 2025, page 26 / 138 / 112 sow, the use of an antimicrobial growth promoter in sows, the composition of the sow microbiome, the function of the sow microbiome, the interaction of the sow microbiome network, the stability of the sow microbiome, the robustness of the sow microbiome, the resilience of the sow microbiome, the reproductive performance of the sow and / or the ratio between sows and piglets.

[0035] In addition, it may be desirable to interrogate one or more target queries for gilts, wherein the one or more queries investigate any of the following: gilt habitability, gilt mortality, gilt general health, risk of gilt gastrointestinal pathologies, risk of gilt respiratory pathologies, risk of gilt reproductive system pathologies, use of an antimicrobial growth promoter in gilts, gilt microbiome composition, gilt microbiome function, gilt microbiome network interaction, gilt microbiome stability, gilt microbiome robustness, gilt microbiome resilience, and / or future gilt reproductive performance.

[0036] Sample preparation component 110 may include any system or technique suitable for preparing a biological sample obtained from animals for digitization, such as for generating metagenomic data in biological samples. Sample preparation component 110 may include the preparation of a sample from the gastrointestinal tract, reproductive system, mammary glands, or respiratory system of the animal, as described elsewhere in this document, in order to obtain metagenomic data about the animal's microbiome from such locations. In the case of microbiome data, the sample may be prepared to obtain metagenomic data using sequencing that provides sequences (e.g., deoxyribonucleic acid (DNA) sequences or ribonucleic acid (RNA) sequences), such as operational taxonomic unit (OTU) sequences. Petition 870250080933, dated 09 / 09 / 2025, page 27 / 138 / 112 amplicon sequence variants (ASVs), 16S ribosomal RNA gene sequences, 18S ribosomal RNA gene sequences, shotgun sequences, internal transcribed spacer (ITS) amplicon sequences, or any other suitable genetic marker sequences. Metagenomic data may include information indicative of the relative or absolute abundance, diversity, taxonomy, or distribution of microbiota of given taxonomic classifications in the microbiome of the animal from which the biological sample is obtained. In certain examples, metagenomic data may include data indicative of metabolites detected in the biological sample, in order to identify functional aspects of a microbiome, including selected metabolic pathways or catalytic activity.

[0037] Metagenomic component 112 may include any appropriate analytical techniques and tools to generate metagenomic data. Metagenomic component 112 may be configured to receive metagenomic data obtained from a microbiome sample from one or more animals. Metagenomic component 112 may apply any number of techniques and tools to directly or indirectly assess the genetic content of a microbial community sample obtained from within a gastrointestinal tract or reproductive system of animals. Metagenomic component 112 may generate information about the functional gene composition and / or nucleotide variations within the microbial community sample.Metagenomic component 112 may apply one or more sequencing technologies to a microbiome sample, including, but not limited to, whole genome sequencing techniques, including shotgun sequencing, 16S ribosomal RNA gene sequencing, 18S ribosomal RNA gene sequencing, or internal transcript spacer amplicon (ITS) sequencing, and the like. It will be recognized that, when analyzing community samples... Petition 870250080933, dated 09 / 09 / 2025, page 28 / 138 / 112. For microbial samples prepared from the gastrointestinal tract, reproductive system, mammary glands, or respiratory system, the entirety of the representative metagenomic data from these samples is analyzed without further analysis of the data into a predetermined subset of metagenomic data. By way of example, the metagenomic data generated by the systems and methods in this document include the entire 16S RNA gene sequence, the entire 18S RNA gene sequence, the entire shotgun metagenome, and the like. Such metagenomic data are not further reduced to a smaller subset of data. It will also be acknowledged that the metagenomic data generated by the systems and methods in this document are not pooled at any point during sample acquisition, preparation, or analysis. Furthermore, it will be understood that the microbial community samples analyzed in this document are unique to each individual animal being investigated.

[0038] Processing component 114 can be configured to receive metadata, target queries, and metagenomic data from metadata acquisition component 106, query acquisition component 108, and metagenomic component 112. Processing component 114 can include any number of computing resources including one or more of a computer, tablet, mobile phone, server, computing system, microprocessor, circuit, memory, computing environment, or a partition of a computing environment, all of which are allocated to a user of the computing resources and configured to process metagenomic data.The 114 processing component can be coupled to a communications network, such as the Internet, a wireless network, a local area network (LAN), a wide area network (WAN), and similar networks, and can be configured to communicate via wireless communications, including Wi-Fi, Bluetooth, satellite, and similar technologies. Petition 870250080933, dated 09 / 09 / 2025, page 29 / 138 / 112 through wired connections, including a telephone, a coaxial cable, an optical fiber, twisted pair cables and the like.

[0039] The processing component 114 may additionally include one or more machine learning components, including a model selection mechanism 116, a prediction generation mechanism 118, a recommendation prioritization mechanism 120, or an intervention prioritization mechanism 122. The processing component 114 may additionally include a model repository 124 and a data repository 126. It will be recognized that the processing component 114 may additionally include additional components not shown in Figure 1, including a model generation mechanism, a model update mechanism, and the like.

[0040] The model selection mechanism 116 can be configured to select one or more trained models from the model repository 124 based on a sample dataset and a target query. The sample dataset can include one or more data types, including metadata and / or metagenomic data, as defined in this document. The model selection mechanism 116 can be configured to select a model from the model repository 124 that best fits the received inputs. By way of example, for each combination of metadata, data and metagenomic types, and selected target query, the model selection mechanism 116 can be configured to select one or more trained and validated models from the model repository 124 that are configured to provide one or more predictions, recommendations, or interventions to answer the user-defined query.It will be recognized that the model selection mechanism 116 provides the model or set of models to the prediction generation mechanism 118 once a model or set of models is selected. Exemplary models are described in more detail elsewhere. Petition 870250080933, dated 09 / 09 / 2025, page 30 / 138 / 112 in this document.

[0041] The prediction generation mechanism 118 can be configured to run a model or set of models selected by the model selection mechanism 116. Model execution may include providing the model with all metagenomic data to generate one or more predictions, which may be qualitative or quantitative, and which pertain to the model's specific query and may correspond to future health measures or future performance measures of the animal. Each model run by the prediction generation mechanism 118 can generate a different set of predictions. The predictions generated by the prediction generation mechanism 118 can be provided to the recommendation prioritization mechanism 120 and the intervention prioritization mechanism 122, where they are used to identify risks and prioritize solutions.

[0042] The recommendation prioritization mechanism 120 can be configured to use the predictions generated by the prediction generation mechanism 118 to identify an animal or animals that are at risk of future adverse health or adverse future performance, and generate one or more recommendations that are prioritized to address the identified risk. By way of example, recommendations can be tailored to improve future health measures or future performance measures of an animal or group of animals in view of the original target query. Exemplary recommendations are described in more detail elsewhere in this document.

[0043] The intervention prioritization mechanism 122 can be configured to use one or more recommendations identified and prioritized by the recommendation prioritization mechanism 120 to identify an animal or animals that are at risk of future adverse health or adverse performance, and / or generate one or more interventions that are prioritized to address the identified risk. By way of example, the Petition 870250080933, dated 09 / 09 / 2025, page 31 / 138 / 112 interventions can be adapted to improve future health measures or future performance measures of an animal or group of animals in view of the original target consultation. Exemplary interventions are described in more detail elsewhere in this document.

[0044] The processing component 114 may additionally include a model repository 124 and a data repository 126. With reference now to Figure 2, the model repository 124 and the data repository 126 are shown in more detail according to various aspects of the present invention. The model repository 124 may be configured to store one or more trained and validated models. The models may include one or more models, including prediction models, recommendation models, or intervention models. The models stored in the model repository 124 include models that are identified by their associated parameter data. The model repository 124 may also be configured to store parameter data, wherein the parameter data may be specific to a given model to differentiate one model from another, wherein the parameter data correlate with the metadata as defined herein.Once a target query is defined, the model selection mechanism 116 can look at the parameters to select the appropriate model. The model repository 124 can also be configured to store profile data, which may include previously used profiles that are used to compare new predictions and to determine how to prioritize a given recommendation or intervention. Models can be stored in memory, such as in RAM, DRAM, SRAM, ROM, PROM, EPROM, EEPROM, etc., and as discussed in more detail with reference to Figure 7. Models can be stored locally or they can be stored on a network, such as within cloud computing resources or various servers or databases. Petition 870250080933, dated 09 / 09 / 2025, page 32 / 138 / 112 communicatively coupled to the processing component 114. In several respects, the model repository 124 is pre-established before obtaining predictions, recommendations, and interventions, as will be described in relation to model training elsewhere in this document. In several respects, the model repository 124 is a database.

[0045] Data repository 126 can be configured to store various types of data, including metagenomic data and metadata. Metagenomic data may include sequences obtained using whole genome sequencing, 16S ribosomal RNA gene sequences, 18S ribosomal RNA gene sequences, shotgun sequences, internal transcript spacer (ITS) amplicon sequences, or any other suitable genetic marker sequences. Metadata may include one or more of a number of models, the animal life stage (e.g., piglet, sow, or gilt), the sample type, the sampling time (e.g., pre-weaning, weaning, post-weaning, growing / finishing, gestation, pre-partum, parturition, post-partum, etc.).The metagenomic method used, the animal breed, the farm location, the herd size, the management system, the animal's weight, the animal's heart circumference measurement, feeding data, habitability, a pathogenic risk (e.g., a gastrointestinal pathogenic risk, a future respiratory pathogenic risk, a future reproductive system pathogenic risk, a future mammary gland pathogenic risk), pathological states, performance metrics, reproductive measurements, and any other data, such as demographic or biometric data relevant to an animal or group of animals. The 126 data repository may also include one or more model validations, wherein model validations include model validation data related to model performance, including, but not limited to, model accuracy, model sensitivity, etc. Model validation data may also be used. Petition 870250080933, dated 09 / 09 / 2025, page 33 / 138 / 112 by the model selection mechanism 116 when selecting the model (e.g., the prediction model, the recommendation model, or the intervention model) with the best compatibility. The data repository 126 can be communicatively coupled to the model repository 124. Metagenomic data and metadata can be stored in memory, such as in RAM, DRAM, SRAM, ROM, PROM, EPROM, EEPROM, etc., and as discussed in more detail with reference to Figure 7. Metagenomic data and metadata can be stored locally or can be stored on a network, such as within cloud computing resources or various servers or databases that are communicatively coupled to the processing component 114. In many respects, the data repository 126 can be a database.

[0046] The reporting mechanism 128 can be configured to receive the predictions, recommendations, and interventions from the processing component 114 to generate one or more reports that include the specific predictions, recommendations, or interventions, or a combination thereof, and a detailed rationale for the adjustments appropriate to optimize future health measures or future performance measures in an animal or group of animals. It will be recognized that the reporting mechanism 128 can be integral to the processing component 114 or can be a separate component. The reports generated by the reporting mechanism 128 can include one or more health status predictions 130, performance predictions 132, prioritized recommendations 134, and prioritized interventions 136.In one aspect, the 128 report creation mechanism can be configured to generate one or more reports in a machine-readable data structure for display in a graphical user interface that is configured to provide a user with the report, including the specific predictions, recommendations or interventions and the associated rationale. Petition 870250080933, dated 09 / 09 / 2025, page 34 / 138 / 112 as adapted to a specific animal. One or more reports may be communicated by the reporting mechanism 128 or by the processing component 114 to a user display, which may be static or interactive, and may also provide information about the purchase of customized feed or customized supplements to improve future health measures or future performance measures of an animal or group of animals. The reports generated by the reporting mechanism 128 may be used to guide the implementation of one or more predictions, recommendations or interventions in the field.It will be recognized that the predictions, recommendations, or interventions are designed to reduce the incidence or severity of a disease, improve health and performance measures in the animal, reduce the number of animals that need to be culled within a population, select individual animals, including an indication for future enhanced health measures or future performance measures, identify individual animals that require interventions, or reduce reliance on antimicrobial drugs.

[0047] The adjustments component 138 can be configured to implement one or more interventions that are generated and prioritized by the intervention prioritization mechanism 122 as one or more adjustments to the nutrition of an animal or group of animals, a management system, health care, or a rearing environment. The management system may include a conventional animal rearing system, such as with the use of antimicrobial compounds as prophylaxis (e.g., antibiotics, zinc oxide, etc.), or a rearing system where animals are reared using alternatives to antimicrobial compounds (e.g., prebiotics, probiotics, postbiotics, phytogenics, etc.). The rearing environment may include an agricultural site, a slaughterhouse, and the like. Adjustments may include one or more adjustments to management operations and / or sites 140 on the farm, including, but not limited to, a change from conventional rearing. Petition 870250080933, dated 09 / 09 / 2025, page 35 / 138 / 112 for an environment where animals are raised without antimicrobials, or vice versa, increasing or decreasing herd size, implementing one or more culling decisions, isolating one or more animals, and the like. Adjustments may include implementing one or more supplement incorporations or adjustments 142, including, but not limited to, adding or removing one or more supplement compositions to treat one or more nutritional deficiencies or to optimize gastrointestinal, reproductive, mammary, or respiratory measures, altering an existing supplement composition, adding or removing a supplement containing one or more antimicrobial growth promoters in the diet, and the like.Adjustments may include making one or more adjustments to the diet 144, including, but not limited to, adding or removing a diet composition or compositions to treat one or more nutritional deficiencies, altering a diet composition, such as changing from a nursery diet to an adult diet, adding one or more vitamins or minerals, adding or removing one or more antimicrobial growth promoters in a diet, adding or removing prebiotics, probiotics, postbiotics, phytogenics, and the like. Adjustments may include making one or more medication or vaccine adjustments 146, including, but not limited to, administering one or more vaccines to prevent or treat a disease, administering one or more medications to prevent or treat a disease, and the like. Target queries

[0048] The target queries in this document can define a question related to the future health or future performance of an animal or group of animals. Target queries can include any of a series of questions configured to predict a measure of future health or a measure of future performance in an animal. Target queries can include a query related to any of the following non-limiting examples for any of a piglet, a sow, or a gilt, or Petition 870250080933, dated 09 / 09 / 2025, page 36 / 138 / 112 groups thereof, when appropriate for development: future birth weight, future body weight, future feed conversion ratio, future feed intake, future body composition, future growth rate, future average daily weight gain, future heart circumference diameter, future habitability, future mortality, future morbidity, future risks of gastrointestinal pathologies, future risks of respiratory pathologies, future risks of reproductive system pathologies, future risks of mammary gland pathologies, future litter size, future number of piglets born alive, future number of stillborn piglets, future parity, future sow mortality, or future incidence of uterine prolapse, or any combination thereof. Models

[0049] The models in this document can be selected by the model selection mechanism 116 as described above. In one aspect, the selection of a model by the model selection mechanism 116 can occur according to one or more model selection matrices. With reference now to Figure 3, an exemplary model selection matrix 300 is shown according to various aspects of the present invention. The model selection matrix 300 can be configured to receive metagenomic data and metadata in 302. The model selection matrix 300 analyzes the metagenomic data and metadata, and determines from which life stage of the animal the microbiome sample data were obtained according to criterion 1 in 304, where this may further include the gilt stage (not shown).The 300 model selection matrix analyzes metagenomic data and metadata, and determines what type of sample the microbiome sample data represent according to criterion 2 in 306. It will be recognized that, although only fecal or vaginal samples are shown in 306, the other types of biological samples described here may also be considered at this stage. The selection matrix of... Petition 870250080933, dated 09 / 09 / 2025, page 37 / 138 / 112, model 300 analyzes metagenomic data and metadata and determines what type of metagenomic analysis was performed to obtain the metagenomic data according to criterion 3 in 308. Multiple types of metagenomic data are defined elsewhere in this document and are additionally considered in 308. The model selection matrix 300 analyzes the target query and then determines a suitable model or set of models to provide a prediction based on the inputs according to criterion 4 in 310. It will be acknowledged that not all target queries, as described herein, are listed in 310, but are within the scope of the model selection matrix 300 as described.

[0050] The models in this document may include models trained for predicting health and performance, predicting ideal recommendations for nutrition and health management, and predicting the most appropriate and effective interventions to implement with the animals. The models in this document may include trained models including prediction models, recommendation models, and intervention models. The models may be trained according to one or more supervised or unsupervised machine learning algorithms, microbial network modeling, and metagenomic data and metadata obtained from one or more observational studies of swine or interventional studies of swine and a given target query. Machine learning algorithms suitable for use in the present invention may include different machine learning / artificial intelligence algorithms, such as supervised or unsupervised machine learning algorithms.Examples of suitable supervised machine learning algorithms may include, but are not limited to, Bayesian networks, decision trees, k-nearest neighbors, linear classifiers, linear regression, logistic regression, Naive Bayes algorithms, neural networks, quadratic classifiers, random forests, support vector machines (SVMs). Petition 870250080933, dated 09 / 09 / 2025, page 38 / 138 / 112 XGBoost, and other suitable algorithms. Examples of suitable unsupervised machine learning algorithms include, but should not be limited to, expectation maximization algorithms, vector quantization, information obstruction methods, kmeans clustering, hierarchical clustering, and dimensionality reduction (e.g., principal component analysis).

[0051] With reference now to Figure 4, a schematic diagram illustrating a model-building system 400 for creating a model repository is shown according to the various aspects of the present invention. The model-building system 400 may include analogous components configured to operate as described in relation to the multigenerational microbiome system 100 in Figure 1, including an animal component 402, a sample acquisition component 404, a metadata acquisition component 406, a query acquisition component 408, a sample preparation component 410, and a metagenomic component 412. The model-building system 400 may further include one or more observational studies and interventional studies 401.The model-building system 400 can be communicatively coupled to the processing component 114 of the multigenerational microbiome system 100, so that the models generated by the model-building system 400 can be deposited and stored in the model repository 124. The processing component 114 may further include a model-building mechanism 414, wherein the model-building mechanism 414 is configured to receive metagenomic data, metadata, and a target query from one or more observational and interventional studies 401 to generate suitable models for use in the present invention. It will be recognized that the models in this document can be continuously improved and updated using data obtained from additional observational and interventional studies, as well as using data obtained from... Petition 870250080933, dated 09 / 09 / 2025, page 39 / 138 / 112, based on the application of the systems and methods in this document to one or more agricultural production sites where animals are being raised for the market.

[0052] Observational studies and interventional studies 401 can be used to provide multigenerational microbiome data obtained from one or more past generations to predict future health and performance at the individual animal or group level. Observational studies of swine may include studies conducted by observing piglets, sows, and gilts in their rearing environment and collecting data on various health and performance metrics across multiple generations of animals. Observational studies are conducted without interference, such as through control of the environment, feed rations, medication schedules, slaughter, vaccination schedules, and the like. Interventional studies may include studies conducted by controlling one or more variables and performing one or more interventions to obtain data on how animals respond at the individual or group level, as well as across generations.Data obtained from observational and interventional studies are used to train the models of the present invention, such as by identifying one or more health or performance risks that require intervention to optimize future health or performance measures of an animal or group of animals. The trained models are then incorporated into the 124 model repository for use in generating one or more predictions, recommendations, or interventions, based on the target input query, metadata, and metagenomic data.

[0053] Model validations may include information to validate any of the prediction models, recommendation models, or intervention models stored in the data repository 126. Model validations may include one or more executed processes. Petition 870250080933, dated 09 / 09 / 2025, page 40 / 138 / 112 after training a given model to confirm that the model achieves its intended purpose. In one aspect, model validations may include determining the predictive accuracy of a given model.

[0054] Predictive models may include those models that include one or more predictions about future health measures or future performance measures of an animal.Predictive models may include, but should not be limited to, one or more predictive models that: predict a future body weight, a future feed conversion ratio, a future feed intake, a future body composition, a future growth rate, a future average daily weight gain, a future heart circumference diameter, a future habitability, a future mortality, a future morbidity, a future risk of gastrointestinal pathologies, a future risk of respiratory pathologies, a future risk of reproductive system pathologies, a future risk of mammary gland pathologies, a future litter size, a future number of live-born piglets, a future number of stillborn piglets, a future parity, a future sow mortality, or a future incidence of uterine prolapse, or any combination thereof.It will be recognized that in some aspects of the methods of the present invention, predictions are provided to a user for forecasting purposes.

[0055] Recommendation models may include those models that include one or more recommendations related to future health measures or future performance measures of an animal. Recommendation models may include, but should not be limited to, one or more recommendation models that recommend: changing a feed or supplement composition, adding or removing a feed or supplement composition, administering one or more vaccines, administering one or more medications, making changes to a rearing environment or management system, selecting an animal including an indication for health measures. Petition 870250080933, dated 09 / 09 / 2025, page 41 / 138 / 112 future or improved future performance measures, slaughtering an animal including an indication for decreased future health measures or future performance measures, selecting a gilt including an indication for improved future health measures or future performance measures, or adding or removing antimicrobial growth promoters in an animal's diet, or any combination thereof. It will be recognized that in some aspects of the methods of the present invention, predictions and recommendations are provided to a user along with customized management recommendations.

[0056] Intervention models may include those models that include one or more interventions related to future health measures or future performance measures of an animal.Intervention models may include, but are not limited to, one or more intervention models that provide interventions including: altering a feed or supplement composition, providing a feed or supplement composition, adding or removing a feed or supplement composition, administering one or more vaccines, administering one or more medications, making changes to the rearing environment and management system, making changes to the management system, selecting an animal including an indication for future health measures or improved future performance measures, culling an animal including an indication for future health measures or decreased future performance measures, selecting a gilt including an indication for future health measures or improved future performance measures, or adding or removing one or more antimicrobial growth promoters in an animal's diet.It will be recognized that in some aspects of the methods of the present invention, interventions are provided to a user along with the provision of customized management interventions, including customized dietary or supplement interventions. Petition 870250080933, dated 09 / 09 / 2025, page 42 / 138 / 112

[0057] The models in this document may include one or more models to generate predictions, recommendations, or interventions to predict future health measures or future performance measures of an animal, wherein the animal is a swine animal and wherein the swine animal is a piglet, a sow, or a gilt. In one aspect, the models in this document may include one or more piglet models, one or more sow models, or one or more gilt models. In one aspect, the models include one or more piglet models. In one aspect, the models include one or more sow models. In one aspect, the models include one or more gilt models. Piglet models

[0058] Piglet models may include models for predicting future health measures or future performance measures in piglets through the use of metagenomic data obtained from a piglet microbiome sample, including one or more piglet fecal samples or piglet rectal samples, or any other piglet biological sample as described elsewhere in this document. Piglet models may be used to predict health measures or performance measures at a future point in time in the life of the piglet or in the lives of a group of piglets, including one or more life stages, such as birth, a nursery stage, a pre-weaning stage, a weaning stage, a post-weaning stage, a growing-finishing stage, or during any transition between any of the preceding piglet to adult pig.

[0059] By way of non-limiting example, the following piglet models are contemplated for use in the systems and methods described herein, for any of the piglet life stages (e.g., birth, pre-weaning, weaning, post-weaning, piglet-to-adult transition, or during any transition between any of the preceding stages):

[0060] Piglet growth rate model: This model was Petition 870250080933, dated 09 / 09 / 2025, p. 43 / 138 / 112 trained and validated for use in predicting the growth rate of one or more piglets, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively at a future time point in the piglet's productive life.

[0061] Average daily gain model for piglets: This model has been trained and validated for use in predicting the average daily body weight gain of one or more piglets, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively at a given time, within a given time interval, or during a future point in the piglet's life.

[0062] Piglet Alpha Diversity Model: This model has been trained and validated for use in predicting the alpha diversity of the gut microbiome of one or more piglets at specific piglet life stages, either qualitatively (e.g., high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0063] Piglet Mortality Model: This model has been trained and validated for use in predicting the mortality (e.g., probability of death) of one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0064] Piglet habitability model: This model has been trained and validated for use in predicting the habitability (e.g., probability of survival) of one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0065] General health model for piglets: This model has been trained and validated for use in predicting the general health status or health measures of one or more piglets at specific life stages, qualitatively (e.g., in good / bad compartments, high / low compartments, quartiles, etc.) or Petition 870250080933, dated 09 / 09 / 2025, p. 44 / 138 / 112 quantitatively.

[0066] Piglet Gastrointestinal Pathology Risk Model: This model has been trained and validated for use in predicting the probability of incidence and / or severity of infection by single and / or multiple gastrointestinal pathogens (e.g., including but not limited to infection due to Escherichia coli, Salmonella enterica, Streptococcus suis, Clostridium perfringens type A and C, Lawsonia intracellularis, Brachyspira hyodysenteriae, Eimeria sp., Isosporasuis and Campylobacter coli, porcine epidemic diarrhea virus, rotavirus) in one or more piglets at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0067] Piglet Respiratory Pathology Risk Model: This model has been trained and validated for use in predicting the probability of incidence and / or severity of infection by single and / or multiple respiratory pathogens (e.g., including but not limited to infection due to Streptococcus suis, Mycoplasma hyopneumoniae, Actinobacillus pleuropneumoniae, Glaesserella parasuis (formerly classified as Haemophilus parasuis), Pasteurella multocida, Bordetella bronchiseptica, Mycoplasma hyorhinis, porcine reproductive and respiratory syndrome virus (i.e., PRRS), swine influenza and circovirus type 2 / 3) in one or more piglets at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0068] Piglet Antimicrobial Growth Promoter Model: This model has been trained and validated for use in predicting the use and / or benefit of specific antimicrobial growth promoters for one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively. Petition 870250080933, dated 09 / 09 / 2025, page 45 / 138 / 112

[0069] Model of biotic health and growth promoter for piglets: This model has been trained and validated for use in predicting the use and / or benefit of biotic health and growth promoters (e.g., prebiotics, probiotics, postbiotics, antibiotics, phytogenics) for one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0070] Piglet Microbiome Composition Model: This model has been trained and validated for use in predicting the gut microbiome composition and associated metrics (such as richness, diversity, or relative or absolute abundances of taxa) of one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0071] Functional model of the piglet microbiome: This model has been trained and validated for use in predicting the functional potential and / or capacity of the gut microbiome (as measured through carbohydrate-active enzymatic activity and KEGG pathways, among others) of one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0072] Piglet Microbiome Network Interaction Model: This model has been trained and validated for use in predicting interactions among members of the microbial community, including but not limited to core species, and positive and negative interactions, in the gut of one or more piglets at specific life stages, either qualitatively (e.g., high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0073] Piglet microbiome stability model: This model Petition 870250080933, dated 09 / 09 / 2025, page 46 / 138 / 112 was trained and validated for use in predicting the stability (as defined by daily variation in the microbiome) of the microbiome of one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0074] Piglet Microbiome Robustness Model: This model has been trained and validated for use in predicting the robustness (defined by the microbiome's ability to withstand changes caused by stressors) of the microbiome of one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0075] Piglet Microbiome Resilience Model: This model has been trained and validated for use in predicting the resilience (as defined by the ability and time it takes for the microbiome to return to equilibrium after the action of stressors) of the microbiome of one or more piglets at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively. Nut models

[0076] Sow models may include models for predicting future health measures or future performance measures in sows using microbiome data obtained from a sow's microbiome sample, including one or more sow fecal samples, rectal samples, vaginal samples, mammary samples, or respiratory samples. Sow models may be used to predict health measures or performance measures at a future point in the sow's life or the life of a group of sows, including one or more life stages, such as during gestation of a litter, during lactation of a litter, or during a gestation period. Petition 870250080933, dated 09 / 09 / 2025, page 47 / 138 / 112 preparation period for the next litter, postpartum, or during any transition between any of the preceding ones.

[0077] By way of non-limiting example, the following sow models are contemplated for use in the systems and methods described herein for sows in any of the various life stages of a sow (e.g., pre-farrowing, farrowing, post-farrowing, gestation, lactation, postpartum, etc.):

[0078] Sow Mortality Model: This model has been trained and validated for use in predicting mortality (e.g., probability of death) of one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0079] Sow habitability model: This model has been trained and validated for use in predicting the habitability (e.g., probability of survival) of one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0080] General health model for sows: This model has been trained and validated for use in predicting the general health status of one or more sows at specific life stages, either qualitatively (e.g., in good / bad, high / low compartments, quartiles) or quantitatively.

[0081] Sow Gastrointestinal Pathology Risk Model: This model has been trained and validated for use in predicting the probability of incidence and / or severity and / or prospect of risk of hosting / exposure to infection by single and / or multiple gastrointestinal pathogens (e.g., including but not limited to, infection due to Escherichia coli, Salmonella enterica, Streptococcus suis, porcine epidemic diarrhea virus, Clostridium perfringens types A and C, Lawsonia intracellularis, Brachyspira hyodysenteriae, Eimeria sp., Isospora suis, Campylobacter coli) in one or more sows at specific life stages, whether Petition 870250080933, dated 09 / 09 / 2025, page 48 / 138 / 112 qualitatively (for example, in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0082] Risk model for respiratory pathologies in sows: This model has been trained and validated for use in predicting the probability of incidence and / or severity and / or prospect of hosting / exposure to infection by single and / or multiple respiratory pathogens (e.g., including but not limited to infection due to Streptococcus suis, Mycoplasma hyopneumoniae, Actinobacillus pleuropneumoniae, Glaesserella parasuis (formerly classified as Haemophilus parasuis), Pasteurella multocida, Bordetella bronchiseptica, Mycoplasma hyorhinis, porcine reproductive and respiratory syndrome virus (i.e., PRRS), influenza, porcine circovirus type 2 / 3) in one or more sows at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0083] Risk model for sow reproductive system pathologies: This model has been trained and validated for use in predicting the probability of incidence and / or severity and / or prospect of hosting / exposure to single and / or multiple respiratory pathogen infection (e.g., including but not limited to, infection due to porcine reproductive and respiratory syndrome virus (i.e., PRRS), porcine circovirus type 2 / 3) in one or more sows at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0084] Risk model for mammary gland pathologies in sows: This model is used to predict the probability of incidence and / or severity and / or prospect of risk of hosting / exposure to infection by single and / or multiple mammary pathogens (e.g., infection due to Escherichia coli, Staphylococcus aureus, Klebsiella spp., and Petition 870250080933, dated 09 / 09 / 2025, page 49 / 138 / 112 Streptococcus spp.) from one or more sows at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0085] Antimicrobial Growth Promoter Model for Sows: This model has been trained and validated for use in predicting the use and / or benefit of specific antimicrobial growth promoters for one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0086] Biotic health and growth promoter model for sows: This model has been trained and validated for use in predicting the use and / or benefit of biotic health and growth promoters (e.g., prebiotics, probiotics, postbiotics, antibiotics, phytogenics) for one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0087] Sow Microbiome Composition Model: This model has been trained and validated for use in predicting the gut microbiome composition and associated metrics (such as richness and diversity) of one or more sows at specific life stages, either qualitatively (e.g., high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0088] Functional model of the sow microbiome: This model has been trained and validated for use in predicting the functional potential and / or capacity of the gut microbiome (as measured through carbohydrate-active enzymatic activity, KEGG pathways, among others) of one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively. Petition 870250080933, dated 09 / 09 / 2025, page 50 / 138 / 112

[0089] Sow Microbiome Network Interaction Model: This model has been trained and validated for use in predicting interactions between microbial members, including but not limited to core species, and positive and negative interactions, in the gut of one or more sows at specific life stages, either qualitatively (e.g., high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0090] Sow Microbiome Stability Model: This model has been trained and validated for use in predicting the stability (as defined by daily variation in the microbiome) of the microbiome of one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0091] Sow Microbiome Robustness Model: This model has been trained and validated for use in predicting the robustness (as defined by the microbiome's ability to withstand changes caused by stressors) of the microbiome of one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0092] Sow Microbiome Resilience Model: This model has been trained and validated for use in predicting the resilience (as defined by the ability and time it takes for the microbiome to return to equilibrium after the action of stressors) of the microbiome of one or more sows at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0093] Sow Reproductive Performance Model: This model has been trained and validated for use in predicting reproductive health and performance (e.g., measures such as litter size, average weight). Petition 870250080933, dated 09 / 09 / 2025, p. 51 / 138 / 112 at birth of piglets, litter weight at birth, total number of live-born animals, number of weak animals, number of stillborn animals, mummy count, average live weight, number of weaned piglets, average weight at weaning, weaned litter weight, litter weight gain, average daily gain, piglet weight gain, farrowing rate, weaning-to-estrus interval, average feed intake during lactation, weaned pigs per sow per year, lifetime performance, habitability) of one or more sows, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0094] Sow-to-piglet model: This model has been trained and validated for use in predicting the health (e.g., diarrhea score, habitability), performance (body weight, average daily gain, average daily feed intake, feed-gain ratio), and gut microbiome characteristics of offspring (e.g., piglets) using sow metagenomic data (e.g., fecal, rectal, vaginal, milk), either qualitatively (e.g., high / low compartments, quartiles, above / below average, etc.) or quantitatively. Marra models

[0095] Gilt models may include models for predicting future health measures or future performance measures in gilts using microbiome data obtained from a microbiome sample including one or more gilt fecal samples, gilt rectal samples, or gilt vaginal samples.

[0096] By way of non-limiting example, the following gilt models are contemplated for use in the systems and methods described herein for gilts of any age at any stage of their life:

[0097] Gilt mortality model: This model has been trained and validated for use in predicting the mortality (e.g., probability of death) of one or more gilts at specific life stages. Petition 870250080933, dated 09 / 09 / 2025, page 52 / 138 / 112 qualitatively (for example, in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0098] Gilt habitability model: This model has been trained and validated for use in predicting the habitability (e.g., probability of survival) of one or more gilts at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[0099] General health model for gilts: This model has been trained and validated for use in predicting the general health status of one or more gilts at specific life stages, either qualitatively (e.g., in good / bad, high / low compartments, quartiles) or quantitatively.

[00100] Risk model for gilt gastrointestinal pathologies: This model has been trained and validated for use in predicting the probability of incidence and / or severity of infection by single and / or multiple gastrointestinal pathogens (e.g., including but not limited to infection due to Escherichia coli, Salmonella enterica, Streptococcus suis, Clostridium perfringens type A and C, Lawsonia intracellularis, Brachyspira hyodysenteriae, Eimeria sp., Isospora suis, Campylobacter coli) in one or more gilts at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00101] Risk model for respiratory pathologies in gilts: This model has been trained and validated for use in predicting the probability of incidence and / or severity of infection by single and / or multiple respiratory pathogens (e.g., including but not limited to infection due to Streptococcus suis, Mycoplasma hyopneumoniae, Actinobacillus pleuropneumoniae, Glaesserella parasuis (Haemophilus parasuis), Pasteurella multocida, Bordetella bronchiseptica, Mycoplasma hyorhinis, porcine reproductive and respiratory syndrome virus (i.e., PRRS)), Petition 870250080933, dated 09 / 09 / 2025, page 53 / 138 / 112 swine influenza and circovirus type 2 / 3) of one or more gilts at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00102] Risk model for reproductive system pathologies in gilts: This model has been trained and validated for use in predicting the probability of incidence and / or severity and / or prospect of hosting / exposure to infection by a single and / or multiple respiratory pathogen (e.g., including but not limited to infection due to porcine reproductive and respiratory syndrome virus (i.e., PRRS), porcine circovirus type 2 / 3) in one or more gilts at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00103] Antimicrobial growth promoter model for gilts: This model has been trained and validated for use in predicting the use and / or benefit of specific antimicrobial growth promoters for one or more gilts at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00104] Model for promoting biotic health and growth in gilts: This model has been trained and validated for use in predicting the use and / or benefit of biotic health and growth promoters (e.g., prebiotics, probiotics, postbiotics, antibiotics, phytogenics) for one or more gilts at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00105] Model of gilt microbiome composition: This model was trained and validated for use in predicting the composition of the gut microbiome and associated metrics (such as richness, diversity) of one or more gilts at specific life stages. Petition 870250080933, dated 09 / 09 / 2025, page 54 / 138 / 112 qualitatively (for example, in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00106] Functional model of the gilt microbiome: This model has been trained and validated for use in predicting the functional potential and / or capacity of the gut microbiome (as measured through carbohydrate-active enzymatic activity, KEGG pathways, among others) of one or more gilts at specific life stages, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00107] Gilt Microbiome Network Interaction Model: This model has been trained and validated for use in predicting interactions between microbial members, including but not limited to core species, and positive and negative interactions, in the gut of one or more gilts at specific life stages, either qualitatively (e.g., high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00108] Gilt Microbiome Stability Model: This model has been trained and validated for use in predicting the stability (as defined by daily variation in the microbiome) of the microbiome of one or more gilts at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00109] Gilt Microbiome Robustness Model: This model has been trained and validated for use in predicting the robustness (as defined by the microbiome's ability to withstand changes caused by stressors) of the microbiome of one or more gilts at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00110] Gilt microbiome resilience model: This model Petition 870250080933, dated 09 / 09 / 2025, page 55 / 138 / 112 was trained and validated for use in predicting the resilience (as defined by the capacity and time the microbiome takes to return to equilibrium after the action of stressors) of the microbiome of one or more gilts at specific life stages, either qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00111] Future reproductive performance model of gilts: This model has been trained and validated for use in predicting the reproductive health and performance (e.g., measures such as litter size, average piglet birth weight, litter weight at birth, total number of live-born animals, number of weak animals, number of stillborn animals, mummy count, average live weight, number of weaned piglets, average weaning weight, weaned litter weight, litter weight gain, average daily gain, piglet weight gain, farrowing rate, weaning-to-estrus interval, average feed intake during lactation, weaned piglets per sow per year, lifetime performance, habitability, or age at first mating) of one or more gilts, qualitatively (e.g., in high / low compartments, quartiles, above / below average, etc.) or quantitatively.

[00112] As used in this document, the term stability, as it relates to the microbiome, refers to day-to-day variation in the microbiome, such as variation before and after a meal, or variation due to the type or source of food.

[00113] As used in this document, the term robustness, as it relates to the microbiome, refers to the microbiome's ability to withstand changes imposed on it by various stressors, such as pathogenic stressors or metabolic changes in the animal.

[00114] As used in this document, the term resilience, as it relates to the microbiome, refers to the capacity and time that the Petition 870250080933, dated 09 / 09 / 2025, p. 56 / 138 / 112 microbiome takes time to return to balance or near balance after being forced out of balance by various stressors, such as recovery after a pathogenic stressor or metabolic changes in the animal.

[00115] As used in this document, the term richness, as it relates to the microbiome, refers to the number of taxa or functions in a given biological sample, such as a fecal sample, a rectal sample, a vaginal sample, and a mammary sample. Richness is a measure of the number of different types of taxa or functions within a given sample, and the types of taxa may be similar or different between samples.

[00116] As used in this document, the term diversity, as it relates to the microbiome, refers to the richness and uniformity of distribution of each taxon or function in a given sample. Predictions, recommendations, interventions

[00117] The systems and methods of the present invention can generate and report customized predictions, recommendations, and interventions based on metagenomic data, metadata, and target queries and model runs.

[00118] Predictions may include predictions about an animal's future health measures or future performance measures. Predictions may include any predictions about a future state of one or more future health measures or future performance measures, including, but not limited to, one or more of the following: future body weight, future feed conversion ratio, future feed intake, future body composition, future meat quality (e.g., marbling, color, water holding capacity, and pH), future carcass quality, future growth rate, future average daily weight gain, future heart circumference diameter, future habitability, future mortality, future morbidity, future risk of gastrointestinal disorders, future risk of pathologies Petition 870250080933, dated 09 / 09 / 2025, page 57 / 138 / 112 respiratory, future risk of reproductive system pathologies, future risk of mammary gland pathologies, future litter size, future number of piglets born alive, future number of stillborn piglets, future parity, future sow mortality, or future incidence of uterine prolapse, or any combination thereof, for any of a piglet, a sow or a gilt when appropriate for development.

[00119] Recommendations may include recommendations regarding future health measures or future performance measures of an animal. Recommendations may include, but should not be limited to, a recommendation to change a feed or supplement composition, add or remove a feed or supplement composition, administer one or more vaccines, administer one or more medications, make changes to a rearing environment or management system, select an animal including an indication for improved future health measures or future performance measures, slaughter an animal including an indication for decreased future health measures or future performance measures, select a gilt including an indication for improved future health measures or future performance measures, or add or remove antimicrobial growth promoters in an animal's diet, or any combination thereof.Recommendations may include dosage, duration, and timing recommendations for administering one or more postbiotics, prebiotics, phytogenics, essential oils, or other nutrients to an animal's feed or animal supplement. Recommendations may include adding one or more postbiotics, prebiotics, phytogenics, essential oils, or other nutrients to an animal's feed or animal supplement. Recommendations may include removing one or more postbiotics, prebiotics, phytogenics, essential oils, or other nutrients from an animal's feed or animal supplement. Recommendations may include selecting an animal as one of... Petition 870250080933, dated 09 / 09 / 2025, page 58 / 138 / 112 high performance, high level of health, low level of performance requiring intervention, low level of health requiring intervention, etc. It will be recognized that recommendations can be provided to a user as personalized management recommendations tailored to the needs of a specific user.

[00120] Interventions may include interventions relating to future health measures or future performance measures of an animal.Interventions may include, but should not be limited to, one or more interventions, including: altering a feed or supplement composition, providing a feed or supplement composition, adding or removing a feed or supplement composition, administering one or more vaccines, administering one or more medications, making changes to the rearing environment and management system, making changes to the management system, selecting an animal including an indication for future health measures or improved future performance measures, culling an animal including an indication for future health measures or decreased future performance measures, selecting a gilt including an indication for future health measures or improved future performance measures, or adding or removing one or more antimicrobial growth promoters in an animal's diet.It will be recognized that interventions can be provided to a user as personalized management interventions, including personalized dietary or supplemental interventions tailored to the needs of a specific user. In one aspect, interventions can be administered to an animal or animals to improve the animal's future health and performance. By way of non-limiting example, interventions may include the administration of one or more dietary compositions, supplemental compositions and the like, wherein dietary compositions and supplemental compositions may include one or more of a microbial fermented product, including a product. Petition 870250080933, dated 09 / 09 / 2025, page 59 / 138 / 112 of postbiotic fermented product isolated from one or more strains of bacteria or yeasts. Interventions may also include the addition of one or more phytogenics or essential oils. Interventions may include providing a customized dosage, duration, and timing of administration of one or more postbiotics, prebiotics, phytogenics, essential oils, or other nutrition to an animal's feed or animal supplement in order to optimize the animal's future health and performance. Process flow

[00121] The process flow implemented by the multigenerational microbiome systems and methods of the present invention may include a data input at a front end of the multigenerational microbiome system 100. With reference now to Figure 5, an exemplary process flow 500 is provided, wherein the data input received at a front end input 502 includes a metadata input, a microbiome data input, and / or an input of a defined target query. The front end of the multigenerational microbiome system may include a graphical user interface suitable for displaying one or more user interfaces in a computer-readable data structure provided via a website, via a mobile application, and the like.Data input at the front end of the multigenerational microbiome system can be analyzed by processing component 114 at a back end 504 of the multigenerational microbiome system, whereby the model selection mechanism 116 is configured to select one or more models, and the prediction generation mechanism 118 is configured to run the one or more models as described with reference to Figure 1. The multigenerational microbiome system can further generate one or more reports via the report generation mechanism 128 and provide the report to the front end outputs 506 in a computer-readable data structure. Petition 870250080933, dated 09 / 09 / 2025, page 60 / 138 / 112, such as a suitable graphical user interface for display provided through a website, through a mobile application and the like, to provide the user with one or more predictions, recommendations and interventions. Methods

[00122] Several methods are provided that are implemented by the multigenerational microbiome systems of the present invention. With reference now to Figure 6, an exemplary method 600 is provided according to aspects of the present invention. Method 600 may include a method for optimizing future health or future performance in an animal, including obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract, mammary glands, reproductive system, or respiratory system of the animal in 602. Method 600 may further include defining a query including one or more target queries for future health or future performance of the animal in 604. Method 600 may further include selecting a model from a model repository based on the sample dataset and the query including the one or more target queries in 606.Method 600 may also include running the selected model using the sample dataset and the query, including one or more target queries, to make predictions, generate recommendations, or generate interventions regarding the animal's future health or performance in 608. Method 600 may also include reporting the predictions, recommendations, or interventions regarding future health or performance, or combinations thereof, in 610. Method 600 may also include implementing one or more interventions, such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment, based on the predictions, recommendations, or interventions in 612. In one aspect, method 600 may include obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract of the animal. Petition 870250080933, dated 09 / 09 / 2025, page 61 / 138 / 112 animal. In one aspect, method 600 may include obtaining a sample dataset indicative of an entire microbial community within the animal's mammary glands. In one aspect, method 600 may include obtaining a sample dataset indicative of an entire microbial community within an animal's reproductive system. In one aspect, method 600 may include obtaining a sample dataset indicative of an entire microbial community within an animal's respiratory system.

[00123] In several aspects of the methods in this document, method 600 can be repeated as many times as desired or necessary during an animal's life cycle. For example, method 600 can be repeated to monitor the animal's progress through transitions between life stages, in response to an intervention, or in response to exposure to a pathogen. Method 600 can be repeated as many times as desired or necessary to update a diet or feed supplement, to administer a medication or vaccine, to make changes to the farm management system, or to change rearing conditions.

[00124] In several aspects of the methods in this document, each model selected from the model repository is generated by a model generation engine, which was trained using one or more metagenomic data sets or metadata obtained from one or more observational and interventional studies conducted on one or more past generations of animals. In one aspect, each model selected from the model repository can be periodically retrained using newly acquired data obtained from one or more metagenomic data sets or metadata obtained from one or more observational and interventional studies, or from one or more metagenomic data sets or metadata obtained from one or more agricultural production sites. Petition 870250080933, dated 09 / 09 / 2025, page 62 / 138 / 112

[00125] The sample dataset suitable for use in the methods of the present invention may include metagenomic data. In one aspect, the sample dataset suitable for use in the methods of the present invention may include metagenomic data and metadata, each of which is described elsewhere in this document.

[00126] The sample dataset suitable for use in the methods of this document may include metagenomic data from at least one microbiome sample, including a fecal sample, a rectal sample, a vaginal sample, a nasal sample, an oral sample, a lung sample, or a mammary gland sample.

[00127] Targets for future health or future performance include one or more of the following: body weight, feed conversion ratio, feed intake, growth rate, average daily weight gain, heart circumference diameter, mortality, morbidity, risk of gastrointestinal disorders, risk of respiratory disorders, risk of reproductive system disorders, risk of mammary gland disorders, litter size, number of piglets born alive, number of stillborn piglets, parity, sow mortality during farrowing, or incidence of uterine prolapse.

[00128] The methods described herein can identify a model from the model repository including one or more trained models, such as a prediction model, a recommendation model, or an intervention model. The methods of the present invention can identify a prediction model from the model repository, wherein the prediction model may include one or more predictions related to the animal's future performance or future health. The one or more predictions may include a prediction of: future body weight, future feed conversion ratio, future feed intake, future growth rate, future average daily weight gain, future heart circumference diameter, future habitability, Petition 870250080933, dated 09 / 09 / 2025, page 63 / 138 / 112 future mortality, future morbidity, future risk of gastrointestinal pathologies, future risk of respiratory pathologies, future risk of reproductive system pathologies, future risk of mammary gland pathologies, future litter size, future number of piglets born alive, future number of stillborn piglets, future parity, future sow mortality, or future incidence of uterine prolapse, or any combination thereof.

[00129] The methods of the present invention can identify a recommendation model from the model repository, wherein the recommendation model may include one or more recommendations related to the future performance or future health of the animal. The one or more recommendations may include a recommendation to: change a feed composition or supplement, add or remove a feed composition or supplement, administer one or more vaccines, administer one or more medications, make changes to a rearing environment or management system, select an animal including an indication for improved future performance or future health, select a gilt including an indication for improved future performance or future health, or add or remove antimicrobial growth promoters in an animal's diet, or any combination thereof.

[00130] The methods of the present invention can identify an intervention model from the model repository, and the intervention model may include one or more interventions related to the animal's future performance or future health. One or more interventions may include: altering a feed composition or supplement, providing a feed composition or supplement, adding or removing a feed composition or supplement, administering one or more vaccines, administering one or more medications, making changes to the rearing environment and management system, making changes to the management system, Petition 870250080933, dated 09 / 09 / 2025, page 64 / 138 / 112 select an animal including an indication for improved future performance or future health, select a gilt including an indication for improved future performance or future health, or add or remove one or more antimicrobial growth promoters in an animal's diet, or any combination thereof.

[00131] The predictions, recommendations, or interventions created by the methods of the present invention are configured to reduce the incidence or severity of diseases, improve the health and performance measures of an animal, reduce the number of animals that need to be culled within a population, select individual animals including an indication for improved future performance or health, identify individual animals that require interventions, or reduce reliance on antimicrobial drugs.

[00132] In one aspect, the methods of the present invention are configured to select a model that has been generated based on metagenomic data from one or more past generations of animals.

[00133] In one aspect, the methods of the present invention are configured to select a model that has been generated based on the type of metagenomic data and the body location where the sample data were obtained.

[00134] In one aspect, the methods of the present invention are configured to select one or more from a piglet model, a sow model or a gilt model.

[00135] In one aspect, the methods of the present invention are configured to select a piglet model that includes one or more of the following: a piglet growth rate model, a piglet average daily gain model, a piglet alpha diversity model, a piglet mortality model, a piglet habitability model, a piglet general health model, a gastrointestinal pathological risk model of Petition 870250080933, dated 09 / 09 / 2025, page 65 / 138 / 112 piglets, a model of respiratory pathological risk in piglets, a model of antimicrobial growth promoter in piglets, a model of health and biotic growth promoter in piglets, a model of piglet microbiome composition, a functional model of the piglet microbiome, a model of network interaction of the piglet microbiome, a model of piglet microbiome stability, a model of piglet microbiome robustness, and a model of piglet microbiome resilience.

[00136] In one aspect, the methods in this document are configured to select a sow model that includes one or more of the following: a sow mortality model, a sow habitability model, a sow general health model, a sow gastrointestinal pathological risk model, a sow respiratory pathological risk model, a sow mammary gland pathological risk model, a sow antimicrobial growth promoter risk model, a sow biotic health and growth promoter model, a sow microbiome composition model, a sow microbiome functional model, a sow microbiome network interaction model, a sow microbiome stability model, a sow microbiome robustness model, a sow microbiome resilience model, a sow reproductive performance model, and a sow-to-piglet performance model.

[00137] In one aspect, the methods of the present invention are configured to select a gilt model that includes one or more of the following: a gilt mortality model, a gilt habitability model, a gilt general health model, a gilt gastrointestinal pathological risk model, a gilt respiratory pathological risk model, a gilt reproductive system risk model, a gilt antimicrobial growth promoter risk model, a gilt biotic health and growth promoter model, a model of Petition 870250080933, dated 09 / 09 / 2025, page 66 / 138 / 112 composition of the gilt microbiome, a functional model of the gilt microbiome, a network interaction model of the gilt microbiome, a stability model of the gilt microbiome, a robustness model of the gilt microbiome, a resilience model of the gilt microbiome, and a model of future reproductive performance of gilts.

[00138] In one aspect, the methods of the present invention may include where the animal includes a swine animal, wherein the animal may include a swine animal such as a piglet, a gilt or a sow. In one aspect, the methods include obtaining a sample from only one animal. In another aspect, the methods include obtaining a sample from more than one animal.

[00139] In one aspect, the present disclosure provides a method for optimizing future health or future performance in an animal, wherein the method includes obtaining a sample dataset indicative of an entire microbial community within an animal's reproductive system. The method may further include defining a query comprising one or more target queries for the animal's future health or future performance. The method may further include selecting a model from a model repository based on the sample dataset and the query comprising the one or more targets. The method may further include running the selected model using the sample dataset and the query comprising the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance.The method may additionally include reporting predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof. The method may also include implementing one or more interventions, providing a dietary composition or supplement composition based on the predictions, recommendations, or interventions. Petition 870250080933, dated 09 / 09 / 2025, page 67 / 138 / 112

[00140] The methods in this document may include the implementation of one or more interventions such as one or more adjustments including: changing from conventional rearing to an environment where one or more animals are raised without antimicrobials; changing from an environment where one or more animals are raised without antimicrobials to conventional rearing with antimicrobials; changing to a rearing system where one or more animals are raised using alternatives to antimicrobial compounds comprising prebiotics, probiotics, postbiotics or phytogenics; increasing or decreasing herd size; implementing one or more culling decisions; isolating one or more animals; adding or removing one or more supplement compositions; altering an existing supplement composition; adding or removing a supplement containing one or more antimicrobial growth promoters; adding or removing a feed composition or compositions to treat one or more nutritional deficiencies;To alter a food composition; to add one or more vitamins or minerals; to add or remove one or more antimicrobial growth promoters from a food; to administer one or more vaccines to prevent or treat a disease; or to administer one or more medications to prevent or treat a disease.

[00141] The methods in this document may include a method for predicting future health or future performance in an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract, mammary gland, reproductive system, or respiratory system of the animal. The method may further include defining a query including one or more target queries for the animal's future health or future performance. The method may further include selecting a model from a model repository based on the sample dataset and the query including the one or more targets, with each selected model being... Petition 870250080933, dated 09 / 09 / 2025, page 68 / 138 / 112 from the model repository is generated by a model building mechanism, and the model building mechanism was trained using one or more metagenomic datasets or metadata obtained from one or more observational and interventional studies. The method may additionally include running the selected model using the sample dataset and querying one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance. The method may additionally include reporting the predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof.The method may additionally include the implementation of one or more interventions such as one or more adjustments to nutrition, management systems, healthcare, or the animal's rearing environment, based on predictions, recommendations, or interventions.

[00142] The methods in this document may include a method for optimizing future health or future performance in an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within an animal's reproductive system. The method may further include defining a query including one or more target queries for the animal's future health or future performance. The method may further include selecting a model from a model repository based on the sample dataset and the query including the one or more targets. The method may further include running the selected model using the sample dataset and the query including the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance.The method may additionally include reporting predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof. The method may include... Petition 870250080933, dated 09 / 09 / 2025, p. 69 / 138 / 112 additionally the implementation of one or more interventions such as one or more adjustments in nutrition, management system, health care or animal rearing environment, based on predictions, recommendations or interventions.

[00143] The methods in this document may include a method for optimizing future health or future performance in an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within an animal mammary gland. The method may further include defining a query including one or more target queries for the animal's future health or future performance. The method may further include selecting a model from a model repository based on the sample dataset and the query including the one or more targets. The method may further include running the selected model using the sample dataset and the query including the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance.The method may additionally include reporting predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof. The method may additionally include implementing one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment, based on the predictions, recommendations, or interventions.

[00144] The present disclosure provides a method for optimizing the future health or future performance of an animal. The method may include obtaining a sample dataset indicative of an entire microbial community within an animal's respiratory system. The method may further include defining a query including one or more target queries for the animal's future health or future performance. Petition 870250080933, dated 09 / 09 / 2025, p. 70 / 138 / 112 The method may additionally include selecting a model from a model repository based on the sample dataset and the query including one or more targets. The method may additionally include running the selected model using the sample dataset and the query including one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance. The method may additionally include reporting the predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof. The method may additionally include implementing one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment, based on the predictions, recommendations, or interventions. Health and performance measures

[00145] The methods and systems of the present invention can be used to make predictions, recommendations or interventions related to future health or future performance for any of a piglet, a sow or a gilt.Future health or future performance may include one or more future health measures and future performance measures, including body weight; birth weight; body composition; growth rate; average daily weight gain; feed conversion rate; feed intake; mortality; morbidity; habitability; heart circumference diameter, including a measurement of the animal's heart circumference; general health; disease susceptibility, including pathological risks (e.g., a gastrointestinal pathological risk, a respiratory pathological risk, a reproductive system pathological risk, or a mammary gland pathological risk); or reproductive system measures, including litter size, number of piglets born alive, number of stillborn piglets, parity, sow mortality during farrowing, and uterine prolapse. (Compliant.) Petition 870250080933, dated 09 / 09 / 2025, p. 71 / 138 / 112 used in this document, the term general health may refer to an animal's daily state of health, including the absence of disease and the likelihood of it developing or not developing a disease in the future.

[00146] In one respect, the overall health of an animal or group of animals can be impacted by the animal's gut health and immune health function. Thus, future health measures may additionally include future gut health or future immune health function.As used in this document, the term gut health may refer to the efficient and effective digestion of food by the digestive system (e.g., esophagus, stomach, gallbladder, liver, pancreas, spleen, small intestine (e.g., duodenum, jejunum, ileum), and large intestine (e.g., cecum, colon, rectum)); to the healthy balance of the physical environment of the digestive tract, such as pH, osmolality, absence of excess gas, and a deficiency or excess of volatile fatty acids; to the healthy characteristics of the epithelia, such as the absence of increased intestinal permeability, reduced epithelial integrity, and mucosal inflammation; to the absence of abdominal pain caused by one or more adverse health conditions; and to the healthy balance of microbiomes associated with the lumen or mucosa; or any combination thereof.As used in this document, the term immune health may refer to the standard functioning of the immune system as it is understood, the immune system including at least the mucous membranes of the nose, mouth, and throat; the tonsils; the lymph nodes; the thymus; the spleen; the large and small intestines; the bone marrow; the immune cells of the blood, including at least monocytes, lymphocytes, neutrophils, eosinophils, basophils, macrophages, erythrocytes, platelets, stem cells and the like; and the skin. Animals

[00147] The systems and methods of the present invention can be Petition 870250080933, dated 09 / 09 / 2025, page 72 / 138 / 112, applicable to any type of animal. In several aspects, the animal may include any type of swine.

[00148] Pigs (Sus domesticus) suitable for analysis using multigenerational microbiome systems and methods of the present invention may include, but are not limited to, breeds including American Landrace, American Yorkshire, Angeln Saddleback, Ba Xuyen, Berkshire, Bentheim Spotted Black Pig, Iberian Black Pig, British Pig, Landrace, British Saddleback Pig, Chester White Pig, Choctaw, Cinta Senese, Danish Landrace Pig, Danish Protest Pig, Duroc, Dutch Landrace Pig, Gascon, Gloucestershire Old Spotted Pig, Guinea Pig, Hampshire Pig, Hereford, Large Black Pig, Large White Pig, Limousin, Lincolnshire Sheep Pig, Jeju Black, Juliana, Kagoshima Berkshire, Kunekune, Mangalica, Meishan, Medium White Pig, Micro, Moura, Hoofed Pig, Nustrale, Piétrain, Pig Poland-China, Ossabaw Island pig, sandy brown pig and black spots from Oxford, Sardinia,Small white pig, Wattle red pig, Swabian-Hall, Tamworth, Thuoc Nhieu, Tokyo-X, Vietnamese pot-bellied pig.

[00149] Pigs may include, but are not limited to, piglets, gilts, sows, ham-producing pigs, castrated pigs, wild boars, pregnant females, fattening pigs, growing pigs, finishing pigs, pigs, swine, small animals, breeders, castrated pigs, or sows. The animals in this document may be analyzed at any number of developmental life stages. Life stages may include birth, pre-weaning, weaning, post-weaning, pre-farrowing, farrowing, post-farrowing, gestation, lactation, and post-farrowing. In various respects, the animals suitable for the systems and methods described herein may include piglets, gilts, or sows. In one respect, the animal is a piglet. In one respect, the animal is a gilt. In one respect, the animal is a sow. Petition 870250080933, dated 09 / 09 / 2025, page 73 / 138 / 112 Computing environment

[00150] The multigenerational microbiome system may include a computer system and associated components. With reference now to Figure 7, a schematic representation of a 700 computer system is provided according to the various aspects of the systems and methods described herein. The 700 computer system is an example of one or more of the computing resources discussed herein.

[00151] In many respects, the 700 computer system can operate as a standalone device or can be connected (e.g., via a network) to other computers or computing components. In a networked deployment, the 700 computer system can operate as a server or a client machine in server-client network environments, or it can act as a peer machine in point-to-point (or distributed) network environments. The 700 computer system can include a personal computer (PC), a PC-like tablet, a hybrid tablet, a personal digital assistant (PDA), a mobile phone, or any machine capable of executing instructions (sequential or otherwise) that specify actions to be taken by that machine.Additionally, although only a single 700 computer system is illustrated, the term computer will also be understood to include any collection of computers that, individually or in groups, execute a set (or multiple sets) of instructions to perform any one or more of the methods discussed herein. Similarly, the term processor-based system should include any set of one or more machines that are controlled or operated by a processor (e.g., a computer) to execute instructions individually or collectively in order to perform any one or more of the methodologies discussed herein.

[00152] The exemplary computer system 700 includes by Petition 870250080933, dated 09 / 09 / 2025, page 74 / 138 / 112 less a processor 702 (for example, a central processing unit (CPU), a graphics processing unit (GPU), or both, processor cores, compute nodes, etc.), a main memory 704 and a static memory 706, which communicate with each other through a link 708 (for example, a bus). The computer system 700 may additionally include a video display unit 710, an alphanumeric input device 712 (for example, a keyboard), and a user interface (UI) navigation device 714 (for example, a mouse or a trackpad). In one example, the video display unit 710, the input device 712, and the UI navigation device 714 are incorporated into a single touchscreen.The computer system 700 may additionally include a storage device 716 (for example, a disk drive), such as a global positioning system (GPS) sensor, a compass, an accelerometer, a gyroscope, a magnetometer, or other sensors.

[00153] Storage unit 716 includes a machine-readable medium 720 where one or more sets of data structures and instructions 722 (e.g., software) are stored, which are incorporated into or used by any one or more of the methodologies or functions described herein. The instructions 722 may also be located, wholly or at least partially, within main memory 704, static memory 706, and / or within the processor 702 during their execution by the computer system 700, with main memory 704, static memory 706, and the processor 702 also constituting the machine-readable medium.

[00154] Although machine-readable media 720 is illustrated in an example as being a single medium, the term machine-readable media can include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) that store one or more 722 instructions. The term machine-readable media Petition 870250080933, dated 09 / 09 / 2025, page 75 / 138 / 112. The term "machine-readable media" should be considered as including any tangible media that is capable of storing, encoding, or transporting instructions for execution by the machine and that causes the machine to execute any one or more of the methodologies of this disclosure, or that is capable of storing, encoding, or transporting data structures used by, or associated with, such instructions. The term "machine-readable media" should, consequently, include, but not be limited to, solid-state memories and optical and magnetic media.Specific examples of machine-readable media include non-volatile memory, including, but not limited to, semiconductor memory devices (e.g., electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM)) and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.

[00155] Instructions 722 may be additionally transmitted or received over a communication network 724 using a transmission medium through the network interface device 718 using any of several well-known transfer protocols (e.g., HTTP). Examples of communication networks include a local area network (LAN), a wide area network (WAN), the internet, mobile phone networks, plain telephone networks (POTS), and wireless data networks (e.g., Bluetooth, Wi-Fi, 3G and 4G LTE / LTE-A, 5G, DSRC, or WiMAX networks). The term transmission medium should be considered as including any intangible media that is capable of storing, encoding, or transporting instructions for execution by the machine, and includes digital or analog communication signals or other intangible media to facilitate the communication of such software.

[00156] Aspects of the present invention can be implemented in one or a combination of hardware, firmware, and software. Petition 870250080933, dated 09 / 09 / 2025, page 76 / 138 / 112. Aspects of the present invention may also be implemented in the form of instructions stored in a machine-readable storage device, which may be read and executed by at least one processor in order to perform the operations described herein. A machine-readable storage device may include any non-transient mechanism for storing information in a machine-readable form (e.g., a computer). For example, a machine-readable storage device may include read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, and other storage devices and media.

[00157] A processor subsystem can be used to execute instructions on machine-readable media. The processor subsystem may include one or more processors, each with one or more cores. Additionally, the processor subsystem may be arranged in one or more physical devices. The processor subsystem may include one or more specialized processors, such as a graphics processing unit (GPU), a digital signal processor (PSD), a field-programmable gate array (FPGA), or a fixed-function processor.

[00158] Examples, as described herein, may include, or may operate on, one or more logic components, modules, or mechanisms. Modules may be hardware, software, or firmware communicatively coupled to one or more processors to perform the operations described herein. Modules may be hardware modules, and thus these modules may be considered tangible entities capable of performing specified operations and may be configured or arranged in a certain manner. In one example, circuits may be arranged (e.g., Petition 870250080933, dated 09 / 09 / 2025, page 77 / 138 / 112 internally or in relation to external entities such as other circuits) in a manner specified as a module. In one example, all or more computer systems or parts thereof (e.g., a stand-alone computer system, client or server) or one or more hardware processors may be configured by firmware or software (e.g., instructions, an application portion, or an application) as a module that operates to perform specified operations. In one example, the software may be in a machine-readable medium. In one example, the software, when executed by the underlying hardware of the module, causes the hardware to perform the specified operations.Consequently, the term hardware module is understood to encompass a tangible entity, being that entity which is physically constructed, specifically configured (e.g., physically connected) or configured (e.g., programmed) temporarily (e.g., transient) to operate in a specified manner or to perform part or all of any operation described herein. Considering examples where modules are configured temporarily, each module does not need to be instantiated at any point in time. For example, where the modules comprise a general-purpose hardware processor configured using software; the general-purpose hardware processor can be configured as different respective modules at different times.The software can, therefore, configure a hardware processor, for example, to establish a specific module at a given time and to establish a different module at a different time. The modules can also be software or firmware modules, which operate to execute the methods described here.

[00159] Circuits, as used in this document, may include, for example, individually or in any combination, physically connected circuits, programmable circuits such as processors of Petition 870250080933, dated 09 / 09 / 2025, page 78 / 138 / 112 computer that includes one or more individual instruction processing cores, state machine circuits, and / or firmware that stores instructions executed by a programmable circuit. The circuits or modules may, collectively or individually, be incorporated as a circuit that is part of a larger system, for example, an integrated circuit (IC), a system on a chip (SoC), desktop computers, laptop computers, tablet computers, servers, smartphones, etc.

[00160] As used in any embodiment of the present invention, the term logic may refer to firmware and / or circuits configured to perform any of the aforementioned operations. The firmware may be incorporated as code, instructions or sets of instructions and / or data that are rigidly encoded (e.g., non-volatile) in memory devices and / or circuits. Examples

[00161] Several aspects of the present invention can be better understood by reference to the following examples which are offered by way of illustration. The present invention is not limited to the examples given herein. Example 1: Experimental study design

[00162] Examples 2 to 6 below are based on an investigation of the microbiome in future body weight measurements and future heart circumference measurements in piglets. The animals included a total of 90 sows and a total of 360 piglets distributed across nine different farms in two Canadian provinces. A total of seven visits to each farm were used to perform body weight measurements of all animals. Actual body weights were calculated for piglets from the first to the fourth visit, and additional body weights were calculated using the heart circumference method from the fifth to the seventh visit. Heart circumference measurements were obtained according to the methods of Groesbeck et al. Petition 870250080933, dated 09 / 09 / 2025, p. 79 / 138 / 112 (see: Groesbeck, et al., Using cardiac delivery to determine weight in finishing pigs, Kansas State University, Agricultural Experiment Station and Cooperative Extension Service, (2002), pages 166-168). Visits are referred to throughout the Examples as Visits 1-7. Visit 1 was conducted over an average of 4 days ± 1 day, Visit 2 was conducted over an average of 11 days ± 2 days, Visit 3 was conducted over an average of 18 days ± 2 days, Visit 4 was conducted over an average of 27 days ± 3 days, Visit 5 was conducted over an average of 60 days ± 7 days, Visit 6 was conducted over an average of 97 days ± 15 days, and Visit 7 was conducted over an average of 157 days ± 12 days. Microbiome data were collected from piglet fecal samples from the first to the fourth visits, and from sow vaginal samples or sow fecal samples, as indicated in the Examples.Fresh fecal samples for piglets or sows were obtained by inserting a cotton swab into fresh feces or by inserting a cotton swab into the rectum of an animal. Vaginal samples from sows were obtained by inserting a cotton swab into the sow's vagina. Example 2: Identifying piglet groups that lead to future low and high body weight or low and high heart circumference.

[00163] The analysis in this example investigated the differences in piglet performance at various times during the piglet's productive life (from birth to slaughter), investigating in particular the pre-weaning and post-weaning effects on future body weight measurements or future heart circumference measurements.

[00164] In summary, pre-weaning microbiome samples were obtained from piglet fecal samples and were separately grouped to generate pre-weaning clusters (PRWC). Similarly, post-weaning microbiome samples were obtained from piglet fecal samples and were separately grouped to generate post-weaning clusters (POWC). Petition 870250080933, dated 09 / 09 / 2025, page 80 / 138 / 112 clusters). In both cases, no pruning of the genus was performed. The ideal number of identification and grouping of clusters was performed using Gap Statistics in MATLAB, using Spearman's correlation for genus and Aitchison's distance for samples. The clusters are considered as subgroups of the samples based on the similarity between the microbial compositions.

[00165] Body weight or heart circumference measurements were classified at a given time point (at later ages between 66 and 130 days) based on the grouping to which the piglet belonged at the time point prior to grouping. Statistical analyses were performed to verify statistical differences between subgroups using the Wilcoxon Rank Sum Test and false discovery rate correction (using the BH or Benjamini-Hochberg procedure). The clusters are defined as summarized in Table 1. Table 1: Pre-weaning and post-weaning groups Piglet Age (average) Group(s) 1 week after birth (4 days ± 1 day) at Visit 1 PRWC 3; PRWC 4 2 weeks after birth (11 days ± 2 days) at Visit 2 PRWC 1; PRWC 2; PRWC 5; PRWC 6 3 weeks after birth (18 days ± 2 days) at Visit 3 PRWC 2; PRWC 5; PRWC 6 4 weeks after birth (27 days ± 3 days) at Visit 4 POWC 1; POWC 2; POWC 3; POWC 4; POWC 5; POWC 6

[00166] In the first week after birth (i.e., at Visit 1 with a mean age of 4 days ± 1 day), samples were mainly clustered in PRWC 3 and PRWC 4. As the piglets matured, in the second week of life (i.e., at Visit 2 with a mean age of 11 days ± 2 days), samples were observed to spread among PRWC 1, PRWC 2, PRWC 5, and PRWC 6. Three weeks after birth (i.e., at Visit 3 with a mean age of 18 days ± 2 days) and approaching weaning age, samples clustered in PRWC 2, PRWC 5, and PRWC 6. During the first week post-weaning at Petition 870250080933, dated 09 / 09 / 2025, page 81 / 138 / 112 four weeks of life (i.e., at Visit 4 with a mean age of 27 days ± 3 days), the groups were spread across six different POWCs, including POWC 1, POWC 2, POWC 3, POWC 4, POWC 5 and POWC 6.

[00167] Several predictions regarding future heart circumference and body weight measurements were made based on grouping patterns. It was found that assigning a group in the first week of life was not indicative of heart circumference measurements at later times in life. Piglets belonging to PRWC 2 in the second week of life eventually exhibited smaller heart circumference measurements, which became more evident as they approached 130 days of age. Piglets belonging to PRWC 6 in the third week of life eventually had higher heart circumference measurements, which became more evident with age. Piglets belonging to POWC 1, POWC 2, and POWC 6 in the fourth week of life eventually had higher heart circumference measurements, which became more evident with age.Piglets belonging to POWC 3 and POWC 4 in the fourth week of life eventually had lower heart circumference measurements, which became more evident with age.

[00168] It was found that grouping in the first week of life was not indicative of body weight measurements at later stages of the piglet's life. Piglets belonging to PRWC 2 in the second week of life eventually had lower body weight measurements, which became more evident with age. Piglets belonging to PRWC 6 in the third week of life eventually had higher body weight measurements, which became more evident with age. Piglets belonging to POWC 1, POWC 2, and POWC 6 in the fourth week of life eventually had higher body weight measurements, which became more evident with age. The Petition 870250080933, dated 09 / 09 / 2025, page 82 / 138 / 112 piglets belonging to POWC 3 and POWC 4 in the fourth week of life eventually had lower body weight measurements, which became more evident with age. Overall, there are specific PRWCs and POWCs that are more likely to have higher or lower heart circumference and body weight measurements at later ages.

[00169] The p-values ​​of the statistical comparisons of the subgroups for heart circumference measurements at 97 days ± 15 days of life based on PRWC groupings are reported in Table 2. Table 2: Statistical comparisons in PRWC subgroups for heart circumference measurements Comparisons Visit 1 (p-values) Visit 2 (p-values) Visit 3 (p-values) PRWC 1 versus PRWC 2 NA 0.0025 0.3964 PRWC 1 versus PRWC 3 NA 1.0000 0.6122 PRWC 1 versus PRWC 4 NA 1.0000 NA PRWC 1 versus PRWC 5 NA 1.0000 0.4580 PRWC 1 versus PRWC 6 NA 1.0000 0.0260 PRWC 2 versus PRWC 3 0.0656 0.2745 0.5232 PRWC 2 versus PRWC 4 0.1905 0.2230 NA PRWC 2 versus PRWC 5 0.1905 0.0000 0.5861 PRWC 2 versus PRWC 6 0.0816 0.0000 0.0000 PRWC 3 versus PRWC 4 0.2497 1.0000 NA PRWC 3 versus PRWC 5 0.6414 1.0000 0.7284 PRWC 3 versus PRWC 6 0.7399 1.0000 0.6006 PRWC 4 versus PRWC 5 0.9572 1.0000 NA PRWC 4 versus PRWC 6 0.4938 1.0000 NA PRWC 5 versus PRWC 6 0.5000 1.0000 0.0022

[00170] The p-values ​​of the statistical comparisons of the subgroups for heart circumference measurements at 97 days ± 15 days of life based on the POWC groupings are reported in Table 3. Petition 870250080933, dated 09 / 09 / 2025, page 83 / 138 / 112 Table 3: Statistical comparisons in POWC subgroups for heart circumference measurements Comparisons Visit 4 (p-values) POWC 1 versus POWC 2 0.3927 POWC 1 versus POWC 3 0.0012 POWC 1 versus POWC 4 0.0029 POWC 1 versus POWC 5 0.0215 POWC 1 versus POWC 6 0.1268 POWC 2 versus POWC 3 0.0080 POWC 2 versus POWC 4 0.0257 POWC 2 versus POWC 5 0.1097 POWC 2 versus POWC 6 0.6999 POWC 3 versus POWC 4 0.6306 POWC 3 versus POWC 5 0.5477 POWC 3 versus POWC 6 0.0033 POWC 4 versus POWC 5 0.6306 Cluster 4 versus Cluster 6 0.0090 Cluster 5 versus Cluster 6 0.1097 Example 3: Identifying groups of sows that lead to low and high body weight measurements or low and high heart circumference measurements in piglets.

[00171] The analysis in this example investigated differences in sow microbiome on future piglet performance, specifically investigating the microbiome of sow fecal samples and sow vaginal samples on body weight measurements or heart circumference measurements in future generations of piglets.

[00172] In summary, fecal microbiome samples from sows were separately grouped into sow fecal clusters (SFCs), and vaginal microbiome samples from sows were separately grouped into sow vaginal clusters (SVCs). In both cases, no pruning of gender was performed. The optimal number of identification and grouping of clusters was performed using Gap Statistics in MATLAB, using Spearman's correlation for gender and the Petition 870250080933, dated 09 / 09 / 2025, page 84 / 138 / 112 Aitchison distance for samples. The groups are considered as subgroups of the samples based on the similarity between the microbial compositions.

[00173] Body weight or heart circumference measurements were grouped at a given time point (at visits between 66 and 130 days of age) based on the grouping to which the piglet belonged at the sow level. Statistical analyses were performed to check for statistical differences between subgroups using one or more generalized linear mixed models to control for province, farm, and sow effects, and then fitting all p-values ​​together. Sow fecal samples were grouped into four ideal SFCs, including SFC 1, SFC 2, SFC 3, and SFC 4. Sow vaginal samples were grouped into five ideal SVCs, including SVC 1, SVC 2, SVC 3, SVC 4, and SVC 5.

[00174] The results indicate that an assignment to SFC 1 was indicative of lower heart circumference measurements in piglets at approximately 130 days of age. An assignment to SFC 2 was indicative of higher heart circumference measurements in piglets at approximately 130 days of age. An assignment to SVC 3 was indicative of lower heart circumference measurements in piglets at approximately 130 days of age. An assignment to any one of SVC 1, SVC 2, and SVC 5 was indicative of higher heart circumference measurements in piglets at approximately 130 days of age. Overall, the data suggest that there are specific SRCs and SVCs for sows that are prone to having higher or lower heart circumference and body weight measurements between 66 and 130 days of age. Example 4: Determining a correlation between microbe type and body weight measurements.

[00175] The analysis in this example investigated which types of microbes Petition 870250080933, dated 09 / 09 / 2025, page 85 / 138 / 112 in fecal samples from piglets are correlated with future body weight gain in piglets.

[00176] The methods used to identify which microbes are associated with body weight gain in piglets include a combination of techniques. These include analyses that use Pearson, Limma, and MaAsLin correlation techniques. Pearson correlation measures the statistical relationship, or association, between different microbes in the microbiome and body weight measurements based on covariance. The Limma technique operates using an empirical Bayes method that estimates the precedent from the set of all elements. It can moderate sample variances, which include squared mean deviations (e.g., a type of sample mean). MaAsLin analysis relies on general linear models to accommodate most modern epidemiological study designs, including cross-sectional and longitudinal designs, and offers a variety of data exploration, normalization, and transformation options.

[00177] Microbes highly positively correlated with body weight were evaluated using all three techniques, and the results indicate that among the top 50 microbes identified, there was an overlap of 42 microbes across all three techniques. In this example, 51 microbes were identified by MaAsLin as highly positively correlated with body weight gain, 51 microbes were identified by Limma as highly positively correlated with body weight gain, and 50 microbes were identified by Limma as highly positively correlated with body weight gain. The microbes identified by each technique are summarized in Table 4. Table 4: Microbes positively correlated with body weight Microbe Pearson Limma MaAsLin Prevotellaceae_NK3B31_group 0.34709672 1.33631E-35 4.955E-15 Treponema 0.41566571 9.07938E-52 3.3769E-11 Rikenellaceae_RC9_gut_group 0.43952461 2.40204E-58 3.9589E-15 Lachnospiraceae_ND3007_group 0.40738912 1.32743E-49 6.4899E-11 Petition 870250080933, dated 09 / 09 / 2025, p. 86 / 138 / 112 Prevotella_7 0,40755482 1,19745E-49 7,8236E-19 Phascolarctobacterium 0,44415004 1,1105E-59 8,3836E-26 Prevotellaceae_UCG_001 0,34455 4,52E-35 1,09E-06 Eubacterium_hallii_group 0,377439 2,82E-42 2,66E-15 Succinivibrio 0,265786 5,08E-21 6,51E-21 Alloprevotella 0,401618 3,90E-48 3,81E-20 Prevotellaceae_UCG_003 0,497992 7,26E-77 1,67E-24 Intestinibacter 0,401288 4,77E-48 8,94E-10 CandidatusSoleaferrea 0,359065 3,80E-38 2,17E-10 Faecalibacterium 0,520006 7,98E-85 2,56E-12 Oscillospira 0,466222 2,34E-66 2,66E-11 Clostridium_sensu_stricto_6 0,36524 1,68E-39 5,73E-07 Monoglobus 0,373516 2,25E-41 8,17E-10 Ruminococcus_gauvreauii_group 0,33903 6,08E-34 6,78E-16 UCG002 0,408092 8,68E-50 2,92E-10 UCG008 0,395608 1,25E-46 3,85E-10 Lachnospiraceae_XPB1014_group 0,262239 1,74E-20 8,38E-07 UCG005 0,511606 1,02E-81 2,33E-20 Eubacterium_ruminantium_group 0,309541 2,73E-28 9,66E-06 Lachnospira 0,317114 1,11E-29 2,27E-09 Prevotella_9 0,575261 1,3527E-107 2,16E-37 Coprococcus 0,530452 8,28E-89 5,63E-14 Anaerovibrio 0,489857 4,55E-74 1,69E-16 Lachnospiraceae_UCG_010 0,385589 3,38E-44 3,05E-12 Lachnospiraceae_NK4A 136_grou p 0,386775 1,75E-44 3,34E-17 Shuttleworthia 0,350375 2,77E-36 2,28E-22 Family XIII AD3011 group 0,471067 6,88E-68 2,04E-15 Oscillibacter 0,449208 3,62E-61 2,95E-06 Megasphaera 0,295977 6,68E-26 2,61E-11 UCG009 0,365836 1,23E-39 1,30E-07 Fusicatenibacter 0,382635 1,71E-43 1,09E-21 IncertaeJSedis 0,276186 1,24E-22 2,61E-11 Agathobacter 0,529617 1,74E-88 5,49E-33 Christensenellaceae_R_7_group 0,493267 3,12E-75 3,47E-12 Fibrobacter 0,283215 9,21E-24 3,42E-06 Blautia 0,387203 1,38E-44 3,11E-18 NK4A214_group 0,439146 3,08E-58 1,40E-09 Subdoligranulum 0,57083 1,32E-105 1,75E-14 Lachnospiraceae_UCG_010 0,385589 3,38E-44 3,05E-12, Petição 870250080933, de 09 / 09 / 2025, pág. 87 / 138 / 112

[00178] This example further investigated which types of microbes are associated with the body weight of piglets in groups identified as predicted to have a very high future body weight and groups identified as predicted to have a very low future body weight.

[00179] Piglet weight gain between visits 1 and 4 was calculated as follows: weight gain per day = (pig weight at a given visit - initial pig weight at visit 1) / duration. Piglets were grouped based on weight gain into five groups, including: VL (Very Low), L (Low), M (Medium), H (High), and VH (Very High), with each group including approximately 230 samples per group (e.g., n=230 or n=232). An identification of microbes whose abundances were significantly different between pigs in the VL and VH groups was conducted, and the q-value (i.e., p-value adjusted for the false discovery rate (FHR)) for each is summarized in Table 5 and Table 6. Table 5: Microbes that contribute positively to and are associated with BW in the VH Group_______________________________________________ Microbe q-value Intestinibacter 2.02E-08 Agathobacter 1.23E-06 Shuttleworthia 1.23E-06 Lachnospiraceae_UCG_003 1.70E-05 Succinivibrio 0.000367 Lachnospiraceae_ND3007_group 0.000558 Ruminococcus_gauvreauii_group 0.000677 Lachnospira 0.000981 Fusicatenibacter 0.001082 Prevotella_9 0.00185 Aliivibrio 0.005842 UCG003 0.028676 Prevotellaceae_NK3B31_group 0.030389 Amnipila 0.030969 Anaerovorax 0.030969 Monoglobus 0.034515 possible_genus_Sk018 0.041248 Petition 870250080933, dated 09 / 09 / 2025, p. 88 / 138 / 112 Family Group XIII AD3011 0.044514 Table 6: Microbes that contribute positively to and are associated with BW in the VL Group Microbio valor q Prevotellaceae_UCG_001 1,29E-08 Eubacterium_xylanophilum_group 1,29E-08 Prevotella_9 2,32E-08 Agathobacter 3,36E-08 Shuttleworthia 1,82E-06 Anaerovibrio 2,36E-06 Lachnospiraceae_UCG_003 5,75E-06 Succinivibrio 7,27E-06 UCG009 1,18E-05 Eubacterium_siraeum_group 1,76E-05 Ruminococcus_gauvreauii_group 6,58E-05 Family_XIII__AD3011__group 8,14E-05 Fusicatenibacter 0,000189 Lachnospiraceae_UCG_004 0.000453 Alloprevotella 0.000563 Prevotellaceae_NK3B31_group 0.000799 UCG005 0.000837 Lachnospiraceae_ND3007_group 0.001267 Prevotellaceae_UCG_003 0.003244 Amnipila 0.004823 Alistipes 0.006407 Prevotella_7 0.012315 Not identified 0.019377 Blautia 0.021143 Catenibacillus 0.029267 IncertaeJSedis 0.031655 Phascolarctobacterium 0.03357 Streptococcus 0.034308 Oscillibacter 0.036183 possible_genus_Sk018 0.037677

[00180] In the VH group, 18 microbes were found to contribute positively and are significantly associated with BW, as tabulated in Table 5. In the VL group, 30 microbes were found to contribute positively and are significantly associated with BW, Petition 870250080933, dated 09 / 09 / 2025, p. 89 / 138 / 112 as tabulated in Table 6. Of these, 3 microbes were associated exclusively with the VH group and not with the VL group, including Intestinibacter, Coprococcus and Lachnospiraceae_NK4A136_group. Example 5: Predicting body weight measurements in piglets using linear regression models.

[00181] The analysis in this example examined the predictability of body weight in piglets using microbiome data and metadata with linear regression models.

[00182] A multiple linear regression (MLR) model was used to predict piglet body weight at visits 5 to 7 based on metadata and metagenomic data obtained during visits 1 to 4. The following data combinations were used to create the models applied to predict future body weights: metadata only, metagenomic data only, and metadata combined with metagenomic data. Metagenomic data were obtained from fecal samples taken from piglets at approximately 3 days (Visit 1), 10 days (Visit 2), 18 days (Visit 3), and 27 days (Visit 4) of age. More than 30 models were generated using various combinations of metadata and microbiome data.The metadata included in the model development included one or more combinations of the following metadata types (with query parameters in parentheses): body weight in kilograms (e.g., BW_kg), farm location (e.g., farm), litter cohort (e.g., cohort), parity (e.g., parity), litter size (e.g., litter_size), live-born piglets (e.g., live_born), stillborn piglets (e.g., still_birth), sex (e.g., sex), visit number (e.g., visit), age (e.g., age), grouping including VL, L, M, H, and VH (e.g., grouping), selected model (e.g., all genders, gender 30P, gender 30N, etc.), and pig identification number (e.g., pig_id). The models that... Petition 870250080933, dated 09 / 09 / 2025, pp. 90 / 138 / 112, which included a combination of metadata and microbiome data, presented the highest R2 values ​​when compared to other models, as tabulated in Table 7. Table 7: MLR models with different attributes and their performance. Model with Multiple Metadata Parameters R2 Adjusted R2 Root Mean Square Error (RMSE) Mean Error Mean Absolute Percent Error BW_kg ~ farm + cohort + parity + litter_size + live_born + still_birth + sex + visit + age 0.8232 0.8204 1.096 -0.013 19.94 BW_kg ~ farm + parity + sex + age + grouping 0.8978 0.896 0.833 0.049 16.539 BW_kg ~ farm + parity + sex + visit + age + grouping 0.8987 0.8987 0.828 0.034 16.397 BW_kg ~ farm + parity + sex + visit + age + grouping + all genders 0.9532 0.9113 2.879 0.132 35,919 BW_kg ~ farm + parity + sex + age + grouping + gender 30P + gender 30N 0.9098 0.9029 0.867 0.02 17,818 BW_kg ~ farm + parity + litter_size + live_born + still_birth + age + grouping + gender 30P + gender V30N 0.9122 0.9053 0.854 0.033 17,804 Example 6: Predictive models for piglet body weight gain, piglet litter size, and live piglet ratio.

[00183] The analysis in this example examined various predictive models for determining the future body weight of piglets, the future litter size of piglets, and the future proportion of live piglet births.

[00184] A set of classification models was developed using piglet or sow microbiome data as inputs to predict future outcomes at the piglet and sow levels. The classification models were chosen as a starting point for evaluating performance metrics. Thus, the objective of model development was to use the microbiome of individual animals. Petition 870250080933, dated 09 / 09 / 2025, pp. 91 / 138 / 112, aims to predict future performance (e.g., health measures, growth measures, other performance measures, and reproductive measures) to establish predictions for targeted interventions using feed or feed supplements that can provide animals with an adapted nutritional regimen to match their high-performing counterparts and / or improve their disease resistance. Both piglet and sow models were developed.

[00185] Piglet Models: Leveraging piglet fecal microbiome data, the information was used to a.) determine an ideal sampling window (since the piglet microbiome was assessed at different points in time) to maximize the predictive power of piglet performance, which is like a substitute for average daily gain used for performance; and b.) identify the ideal period (since growth can be measured at different time periods) to achieve the prediction that maximizes performance and is also practical and feasible for sampling.

[00186] Performance was measured by calculating average daily weight gain (ADG) between different time points. From visits 5 to 7, body weight was not measured, but instead estimated based on heart circumference measurement at that time. Since classification models require a categorical target, the estimated ADGs between different periods were dichotomized into high and low ADGs close to the observed mean.

[00187] Several models were developed, including 1.) all pre-weaning piglet microbiome samples (i.e., visits 1, 2, and 3) used to predict ADG between visits 1 and 5 and between visits 1 and 7; and 2.) fecal microbiome samples collected from piglets at visits 1, 2, 3, or 4 were used to predict ADG between visits 1 and 5 and between visits 1 and 7. The accuracy results of the logistic regression-based model for average daily weight gain (ADG) of piglets using microbiome data were analyzed. Petition 870250080933, dated 09 / 09 / 2025, page 92 / 138 / 112 fecal samples from piglets on different visits (i.e., 1, 2, 3 or 4), individually or in combination, are summarized in Table 8. Table 8: Accuracy results of the logistic regression-based model For average daily weight gain (ADG) of piglets Model input Model output Test set precision (%) Piglet fecal microbiome on visits 1 to 3 ADG between visits 1 and 5 60 Piglet fecal microbiome on visits 1 to 3 ADG between visits 1 and 7 74 Piglet fecal microbiome on visit 1 ADG between visits 1 and 5 53 Piglet fecal microbiome on visit 1 ADG between visits 1 and 7 59 Piglet fecal microbiome on visit 2 ADG between visits 1 and 5 56 Piglet fecal microbiome on visit 2 ADG between visits 1 and 7 65 Piglet fecal microbiome on visit 3 ADG between visits 1 and 5 60 Piglet fecal microbiome on visit 3 ADG between visits 1 and 7 78 Piglet fecal microbiome on visit 4 ADG between visits 1 and 5: 64. Piglet fecal microbiome on visit 4 ADG between visits 1 and 7: 78.

[00188] The 25 main microbes most strongly associated with an increased or decreased probability of high ADG using the microbiome from visit 3 as input are summarized in Table 9. Table 9: The 25 main microbes of the microbiome from visit 3 associated with increased and decreased likelihood of high ADG_____________________ Classification Increases the probability of high ADG Decreases the probability of high ADG 1 SP3_e08 Peptococcus 2 Romboutsia [Eubacterium] ruminantium group 3 Asaccharospora Actinobacillus 4 Sanguibacteroides Hungatella 5 Oscillibacter Monoglobus 6 Coriobacteriaceae_UCG_003 [Clostridium]_innocuum_group 7 Coprococcus Arcanobacterium 8 Blautia Phascolarctobacterium 9 Subdoligranulum Oribacterium 10 Catabacter Parasutterella 11 Filfactor Pygmaiobacter 12 Butyricicoccus Turicibacter 13 Elusimicrobium Succinivibrio 14 Allisonella Holdemanella Petition 870250080933, dated 09 / 09 / 2025, p. 93 / 138 / 112 15 Cerasicoccus Quinella 16 Peptoniphilus Acinetobacter 17 Anaerofilum Akkermansia 18 Solobacterium Synergistes 19 Cutibacterium Lachnospiraceae_UCG_004 20 Lachnospira Sphaerochaeta 21 CAG_873 Lachnospiraceae_UCG_002 22 Eubacterium Propionispira 23 Telluria p_1088_a5_gut group 24 Lachnospiraceae_UCG_008 [Eubacterium]_nodatum_group 25 CandidatusSoleaferrea GCA_900066755

[00189] The 25 main microbes most strongly associated with an increased or decreased probability of high ADG using the microbiome from visit 4 as input are summarized in Table 10. Table 10: The 25 main microbes of the microbiome from visit 4 associated with increased and decreased likelihood of high ADG__________________ Classification Increases the likelihood of high ADG Decreases the likelihood of high ADG 1 [Eubacterium]_eligens_group Ruminococcus 2 Campylobacter Bacteroides 3 Prevotella Anaerosporobacter 4 [Eubacterium]_fissicatena_group Prevotellaceae_UCG_001 5 Anaeroplasma Bacillus 6 HT002 Caproiciproducens 7 Akkermansia Schwartzia 8 Ruminobacter Alloprevotella 9 Lachnospira V9D2013_group 10 Lachnospiraceae_NK4A 136_grou p Syntrophococcus 11 Parasutterella Fusobacterium 12 Tyzzerella Neisseria 13 Anaerobiospirillum Succinivibrionaceae_UCG_002 14 GCA_900066575 Moraxella 15 Lachnospiraceae_AC2044_group Prevotellaceae_UCG_004 16 Acetitomaculum Family_XllI_AD3011_group 17 CAG_56 Catenibacterium 18 Oscillospira Potphyromonas 19 Succiniclasticum Conservatibacter 20 Intestinibacter Lachnobacterium 21 Lachnospiraceae_UCG_007 Efysipelotrichaceae_UCG_006 Petition 870250080933, dated 09 / 09 / 2025, p. 94 / 138 / 112 22 Arcanobacterium Sutterella 23 Prevotella_9 [Eubacterium] ruminantium group 24 Oscillibacter Alistipes 25 Alysiella Lachnospiraceae_UCG_008

[00190] The results indicate that the highest test set accuracy was observed when predicting ADG from visits 1 to 7, regardless of which samples or sample sets were used as model inputs (as tabulated in Table 8). Within the ADG from visits 1 to 7, the best performance was observed when using visits 3 or 4 as inputs (accuracy = 78%), suggesting that the piglet microbiome near weaning can be used as a key indicator of future performance. Furthermore, the logistic regression model coefficients were used to identify microbes that were strongly associated with a high or low ADG, as tabulated in Table 9 and Table 10, respectively.

[00191] Sow models: leveraging vaginal microbiome samples and fecal microbiome samples, the information was used to a.) determine which type of sow sample (vaginal or fecal) would be best for predicting sow reproductive performance and piglet outcomes; and b.) assess whether the sow microbiome (vaginal and / or fecal) can be used to predict microbiome development in piglets.

[00192] The piglet microbiome was characterized using the Shannon diversity index at each sampling time point of each visit, observing that a more diverse microbial composition is generally associated with improved gut health. Since classification models require a categorical target, Shannon diversity index values ​​were dichotomized into high and low diversities close to the observed mean. As there were 3 to 4 piglets sampled per sow, there were multiple targets for each sow sample set.

[00193] In addition to the development of the gut microbiome in piglets, Petition 870250080933, dated 09 / 09 / 2025, pp. 95 / 138 / 112, we evaluated whether the sow microbiome could be used to predict reproductive performance during farrowing. Reproductive performance was measured using litter size and the ratio of live births (i.e., live births / total litter size). These results were also dichotomized into high and low categories close to the observed average.

[00194] Several models have been developed, including 1.) fecal and vaginal microbiome samples; or vaginal microbiome samples from the sow only to predict Shannon diversity in individual piglets from that sow; 2.) fecal and vaginal microbiome samples; or vaginal microbiome samples from the sow only to predict litter size; and 3.) fecal and vaginal microbiome samples; or vaginal microbiome samples from the sow only to predict the proportion of live-born animals.

[00195] The accuracy results of the logistic regression-based model for measures of Shannon alpha diversity of piglets using fecal and / or vaginal microbiome data from sows are summarized in Table 11. Table 11: Precision of the logistic regression-based model for Shannon alpha diversity of piglets_________________________________________ Model Input Model Output Test Set Precision (%) Sow Fecal + Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 1 51 Sow Fecal + Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 2 57 Sow Fecal + Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 3 53 Sow Fecal + Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 4 55 Sow Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 1 55 Sow Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 2 54 Sow Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 3 57 Sow Vaginal Microbiome Piglet Shannon Alpha Diversity at Visit 4 56

[00196] Prediction of the piglet microbiome in general revealed that the accuracy of the test suite was quite low for all models, Petition 870250080933, dated 09 / 09 / 2025, page 96 / 138 / 112, however, for the same result, the accuracy was very similar or superior when using only the sow's vaginal microbiome as input, as shown in Table 11. These results indicate that the sow's vaginal microbiome is probably the main indicator to be measured when predicting the piglet gut microbiome.

[00197] The accuracy results of the logistic regression-based model for litter size and proportion of live-born animals using sow fecal and / or vaginal microbiome data are summarized in Table 12. Table 12: Accuracy of the logistic regression-based model for piglet litter size and proportion of live-born animals________ Model Input Model Output Test Set Accuracy (%) Sow Fecal + Vaginal Microbiome Litter Size 61 Sow Fecal + Vaginal Microbiome Live Birth Rate 52 Sow Vaginal Microbiome Litter Size 61 Sow Vaginal Microbiome Live Birth Rate 61

[00198] Overall, the prediction of sow reproductive performance revealed that, although the accuracy of the test set was low for all models, the results are similar to the models for piglet microbiome diversity - the use of the sow vaginal microbiome results in similar or better results than the use of samples of the sow vaginal and fecal microbiome, as shown in Table 12.

[00199] The data show that there are metagenomic and performance metric differences between piglets in different regions, depending on the type of rearing (conventional versus antibiotic-free), before and after weaning, between different ages, among others. There were associations between the sow's vaginal and / or fecal microbiome and the piglet's fecal microbiome. Microbes associated with overall body weight gain were identified, and specific microbes associated with very high body weight gain, including Intestinibacter, Coprococcus, and Lachnospiraceae_NK4A136_group. Regression models were identified to predict body weight of Petition 870250080933, dated 09 / 09 / 2025, page 97 / 138 / 112 piglets (adjusted R2 ~0.91) using microbiome and / or metadata that use regression models (e.g., as a function of farm + parity + sex + visit + age + grouping + all genders).Predictive models for piglet performance (e.g., body weight) and sow reproductive health (e.g., litter size and live birth rate) were used to identify models: to predict piglet performance (using body weight as a surrogate), the best ADG predictions were found using microbiome data from visit 3 and / or visit 4 as inputs – the microbiome near weaning appears especially important for predicting growth rate; in the pre-weaning stage, microbiome data from piglets at visit 3 showed 78% accuracy (using logistic regression) in predicting ADG; and in the post-weaning stage, microbiome data from piglets at visit 4 showed 78% accuracy (using logistic regression) in predicting ADG.Regardless of which piglet time point (determined by visit number) was used as input, model performance was always better for ADG visits 1–7 than for ADG visits 1–5. Inclusion of sow fecal microbiome data does not improve model performance compared to sow vaginal microbiome data, either for predicting piglet alpha diversity or sow reproductive performance. Overall, these findings demonstrate the use of the microbiome (individually and / or in its entirety) of individual animals to predict future health measures or future animal performance measures. Example 7: Case study on solutions for poor reproductive performance in sows and poor piglet performance.

[00200] The following example investigates the application of the multigenerational microbiome systems and methods of the present invention applied to Petition 870250080933, dated 09 / 09 / 2025, page 98 / 138 / 112 multiple herds of sows exhibiting low reproductive performance and low piglet performance, including low piglet habitability. Microbiome samples are collected from sows using fecal, vaginal, and milk samples from a subset of sows (e.g., 7 days before farrowing for fecal and vaginal samples, and from day 0 to 3 for colostrum or milk samples, where n=20). Microbiome samples are collected from piglets using fecal samples from a subset of piglets collected pre-weaning (e.g., on day 14, n=20). Samples are subjected to metagenomic analysis using shotgun metagenomics on fecal samples and 16S rRNA gene sequencing on milk and vaginal samples.

[00201] Model selection and predictions: One or more of the following models from the repository are selected: a piglet growth rate model, a piglet average daily gain model, a piglet alpha diversity model, a piglet mortality model, a piglet general health model, a piglet gastrointestinal pathogen risk model, a piglet respiratory pathogen risk model, a piglet antimicrobial growth promoter model, a piglet microbiome composition model, a piglet microbiome functional model, a piglet microbiome network interaction model, a piglet microbiome stability model, a piglet microbiome robustness model, a piglet microbiome resilience model, a sow microbiome composition model, a sow microbiome functional model, a sow microbiome network interaction model, a sow microbiome stability model,A model of sow microbiome robustness, a model of sow microbiome resilience, a model of sow reproductive performance, and a model of sow-to-piglet performance.

[00202] Predictions obtained by applying the selected models Petition 870250080933, dated 09 / 09 / 2025, pp. 99 / 138 / 112, may provide prioritized recommendations and interventions for multiple herds, designated herein as Herds 1 to 5.

[00203] For Herd 1, multiple predictions are obtained, indicating intermediate performance of the intestinal, reproductive, and mammary microbiomes at the sow level, which translates into non-ideal colonization of the piglet intestine and, as such, may lead to intermediate piglet performance and / or habitability with low pathological risk. The prioritized recommendations include strategies to promote microbiome performance in different body locations, both at the sow and piglet levels, using one or more postbiotic interventions. For example, the one or more interventions recommended for Herd 1 may include any of the following interventions described in Table 13. Table 13: Recommended interventions for Herd 1 Recommended Interventions, Herd 1 1. Cargill standard gestation, lactation, and finishing diets and Cargill Nurture™, PLUS nursery diet 2. XPC™ postbiotic at 500 ppm during gestation (from day -110 to day -5 relative to farrowing date) 3. XPC™ postbiotic at 500 ppm during lactation (from day -5 to day 21 relative to farrowing date) 4. DIA-V SWLQ™ postbiotic at 15 mL / sow / day (from day -5 to day 3 relative to farrowing date) 5. DIA-V Nursery™ postbiotic at 1000 ppm during Phase 1 of the piglet nursery program (from day 0 to day 7 post-weaning) 6. Postbiotic DIA-V Nursery™ at 1000 ppm during Phase 2 of the piglet nursery program (from day 7 to day 21 after weaning) 7. Postbiotic XPC™ at 1000 ppm during Phase 3 of the piglet nursery program (from day 21 to day 42 after weaning) 8. Postbiotic XPC™ at 1000 ppm during the finishing program (from day 42 after weaning until the end of the production cycle; from day 115 to 120)

[00204] For Herd 2, multiple predictions are obtained, indicating poor performance of the intestinal, reproductive, and mammary microbiomes at the sow level, which translates into non-ideal colonization of the piglets' intestines and, as such, may lead to poor piglet performance and / or habitability, with a low to medium risk of pathologies. The prioritized recommendations include strategies to promote the performance of the microbiome of Petition 870250080933, dated 09 / 09 / 2025, p. 100 / 138 / 112 sows and piglets in different body locations, both using one or more postbiotic interventions. For example, the one or more interventions recommended for Herd 2 may include any of the following interventions described in Table 14. Table 14: Recommended interventions for Herd 2 Recommended Interventions, Herd 2 1. Cargill standard gestation, lactation and finishing diets and Cargill Nurture™, PLUS nursery diet 2. XPC™ postbiotic at 500 ppm during gestation (pregnancy) (from day -110 to day -5 relative to farrowing date) 3. XPC™ postbiotic at 1000 ppm during lactation (from day -5 to day 21 relative to farrowing date) 4. DIA-V SWLQ™ postbiotic at 15 mL / sow / day (from day -5 to day 7 relative to farrowing date) 5. DIA-V Nursery™ postbiotic at 1500 ppm during Phase 1 of the piglet nursery program (from day 0 to day 7 post-weaning) 6. 7. Postbiotic DIA-V Nursery™ at 1000 ppm during Phase 2 of the piglet nursery program (from day 7 to day 21 after weaning) 8. Postbiotic XPC™ at 1000 ppm during Phase 3 of the piglet nursery program (from day 21 to day 42 after weaning) 9. Postbiotic XPC™ at 1000 ppm during the finishing program (from day 42 after weaning until the end of the production cycle; from day 115 to 120)

[00205] For Herd 3, multiple predictions are obtained, indicating poor performance of the intestinal, reproductive, and mammary microbiomes at the sow level, which translates into non-ideal colonization of the piglets' intestines and, as such, may lead to poor piglet performance and / or habitability, with a medium to high risk of pathologies. The prioritized recommendations include strategies to promote the microbiome performance of sows and piglets in different body locations, both at the sow and piglet levels, using one or more postbiotic interventions, and to suppress potential gastrointestinal pathologies using one or more essential oils as interventions at the piglet level. For example, the one or more interventions recommended for Herd 3 may include any of the following interventions described in Table 15. Petition 870250080933, dated 09 / 09 / 2025, pp. 101 / 138 / 112 Table 15: Recommended interventions for Herd 3 Recommended Interventions, Herd 3 1. Cargill standard gestation, lactation and finishing diets and Cargill Nurture Boost™, PLUS nursery diet 2. XPC™ postbiotic at 500 ppm during gestation (pregnancy) (from day -110 to day -5 relative to farrowing date) 3. XPC™ postbiotic at 1500 ppm during lactation (day -5 to day 21 relative to farrowing date) 4. DIA-V SWLQ™ postbiotic at 15 mL / sow / day (from day -5 to day 7 relative to farrowing date) 5. DIA-V Nursery™ postbiotic at 1500 ppm during Phase 1 of the piglet nursery program (from day 0 to day 7 post-weaning) 6. Postbiotic DIA-V Nursery™ at 1500 ppm during Phase 2 of the piglet nursery program (from day 7 to day 21 after weaning) 7. PLUS 8. Cynergy™ essential oil at 400 ppm during Phases 1 and 2 of the nursery program (from day 0 to day 21 after weaning) 9. Postbiotic XPC™ at 1000 ppm during Phase 3 of the piglet nursery program (from day 21 to day 42 after weaning) 10.Postbiotic NaturSafe™ at 1000 ppm during the finishing program (from day 42 after weaning until the end of the production cycle; from 115 to 120 days).

[00206] For Herd 4, multiple predictions are obtained, indicating poor performance of the intestinal, reproductive, and mammary microbiomes at the sow level, which translates into non-ideal colonization of the piglets' intestines and, as such, may lead to poor performance and / or habitability of the piglets, where the risk of pathologies is identified as high and with greater susceptibility to invasion by Escherichia coli (risk group for gastrointestinal pathologies). The prioritized recommendations include strategies to promote microbiome performance in different body locations using one or more postbiotic interventions and suppression of Escherichia coli in the piglets' intestines using one or more phytogenics or essential oils as interventions. For example, the one or more interventions recommended for Herd 4 may include any of the following interventions described in Table 16. Petition 870250080933, dated 09 / 09 / 2025, pp. 102 / 138 / 112 Table 16: Recommended interventions for Herd 4 Recommended Interventions, Herd 4 1. Cargill standard gestation, lactation and finishing diets and Cargill Nurture Boost™, PLUS nursery diet 2. XPC™ postbiotic at 750 ppm during gestation (pregnancy) (from day -110 to day -5 relative to farrowing date) 3. XPC™ postbiotic at 2000 ppm during lactation (day -5 to day 21 relative to farrowing date) 4. DIA-V SWLQ™ postbiotic at 15 mL / sow / day (from day -5 to day 7 relative to farrowing date) 5. DIA-V Nursery™ postbiotic at 2000 ppm during Phase 1 of the piglet nursery program (from day 0 to day 7 post-weaning) 6. Postbiotic DIA-V Nursery™ at 1500 ppm during Phase 2 of the piglet nursery program (from day 7 to day 21 after weaning) 7. PLUS 8. Option 1: Cynergy™ essential oil at 400 ppm during Phases 1 and 2 of the nursery program (from day 0 to day 21 after weaning) 9.Option 2: Fresta Protect™ phytogenic at 1000 ppm during Phases 1 and 2 of the nursery program (from day 0 to day 21 after weaning) 10. NaturSafe™ postbiotic at 1000 ppm during Phase 3 of the piglet nursery program (from day 21 to day 42 after weaning) 11. NaturSafe™ postbiotic at 1000 ppm during the finishing program (from day 42 after weaning until the end of the production cycle; from 115 to 120 days).

[00207] For Herd 5, multiple predictions are obtained, indicating poor performance of the intestinal, reproductive, and mammary microbiomes at the sow level, which translates into non-ideal colonization of the piglets' intestines and, as such, may lead to poor performance and / or habitability of the piglets, where the risk of pathologies is indicated as high and with greater susceptibility to invasion by Streptococcus suis (risk group for gastrointestinal pathologies). The prioritized recommendations include strategies to promote microbiome performance in different body locations and suppression of Streptococcus suis in the piglets' intestines using one or more postbiotic interventions. For example, the one or more interventions recommended for Herd 5 may include any of the following interventions described in Table 17. Petition 870250080933, dated 09 / 09 / 2025, pp. 103 / 138 / 112 Table 17: Recommended interventions for Herd 5 Recommended Interventions, Herd 5 1. Cargill standard gestation, lactation, and finishing diets and Cargill Nurture Low Complexity™, PLUS nursery diet 2. XPC™ postbiotic at 750 ppm during gestation (from day -110 to day -5 relative to farrowing date) 3. XPC™ postbiotic at 2000 ppm during lactation (from day -5 to day 21 relative to farrowing date) 4. DIA-V SWLQ™ postbiotic at 15 mL / sow / day (from day -5 to day 7 relative to farrowing date) 5. DIA-V Nursery™ at 2000 ppm during Phase 1 of the piglet nursery program (from day 0 to day 7 post-weaning) 6. DIA-V Nursery™ at 1500 ppm during Phase 2 of the piglet nursery program (from day 7 to day 21 after weaning) 7. PLUS 8. Option 1: Cynergy™ essential oil at 400 ppm during Phases 1 and 2 of the nursery program (from day 0 to day 21 after weaning) 9. Option 2: Fresta Protect™ phytogenic at 1000 ppm during Phases 1 and 2 of the nursery program (from day 0 to day 21 after weaning) 10.Postbiotic NaturSafe™ at 1000 ppm during Phase 3 of the piglet nursery program (from day 21 to day 42 after weaning) 11. Postbiotic NaturSafe™ at 1000 ppm during the finishing program (from day 42 after weaning until the end of the production cycle; from 115 days to 120 days).

[00208] The definitions described here apply to all aspects described herein, unless otherwise indicated.

[00209] In this document, the terms a, an, the, or the are used to include one or more of, unless the context clearly indicates otherwise. The term or is used to refer to a non-exclusive or except where otherwise indicated. All publications, patents, and patent documents referenced in this document are incorporated herein by reference in their entirety, as if they were incorporated individually by reference. In the event of inconsistent usage between this document and the documents incorporated by reference, the usage in the incorporated reference shall be deemed supplementary to that in this document; for irreconcilable inconsistencies, the usage in this document controls.

[00210] Values ​​expressed in a range format should be interpreted flexibly to include not only numerical values. Petition 870250080933, dated 09 / 09 / 2025, p. 104 / 138 / 112 explicitly enumerated as range limits, but also including all individual numerical values ​​or subranges covered by that range as if each numerical value and subrange were explicitly enumerated. For example, a range of approximately 0.1% to approximately 5% or approximately 0.1% to 5% should be interpreted as including not only approximately 0.1% to approximately 5%, but also the individual values ​​(e.g., 1%, 2%, 3%, and 4%) and subranges (e.g., 0.1% to 0.5%, 1.1% to 2.2%, 3.3% to 4.4%) within the indicated range. The statement "from approximately X to Y" has the same meaning as "from approximately X to approximately Y," unless otherwise indicated. Similarly, the statement "from approximately X, Y, or approximately Z" has the same meaning as "from approximately X, approximately Y, or approximately Z," unless otherwise indicated.

[00211] Except where expressly stated, ppm (parts per million), percentage and ratios are based on weight. The percentage on a weight basis (% w / w or % w / w) is also referred to as percentage by weight (%, by weight) or percentage by weight (%, by weight) in the present invention. ADDITIONAL EXAMPLES

[00212] The following are non-limiting examples of the invention.

[00213] Example 1. A method for optimizing future health or future performance in an animal, comprising: obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract, mammary gland, reproductive system, or respiratory system of the animal; defining a query comprising one or more target queries for the animal's future health or future performance; selecting a model from a model repository based on the sample dataset and the query comprising the one or more targets; running the selected model using the sample dataset and the query comprising the one or more targets to make predictions, generate Petition 870250080933, dated 09 / 09 / 2025, page 105 / 138 / 112 recommendations or generate interventions regarding the future health or future performance of the animal; report predictions, recommendations or interventions regarding future health or future performance, or combinations thereof; and implement one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment based on the predictions, recommendations or interventions.

[00214] Example 2. The method of example 1, where the sample dataset comprises metagenomic data.

[00215] Example 3. The method of either example 1 or 2, wherein the sample dataset comprises metagenomic data and metadata.

[00216] Example 4. The method of any of Examples 1 to 3, wherein the sample dataset comprises metagenomic data obtained through the use of one or more sequencing techniques comprising DNA-based or RNA-based shotgun sequencing, 16S ribosomal RNA gene sequencing, 18S ribosomal RNA gene sequencing, or internal transcript spacer amplicon sequencing.

[00217] Example 5. The method of any of Examples 1 to 4, wherein the sample dataset comprises metagenomic data from at least one microbiome sample comprising a fecal sample, a rectal sample, a vaginal sample, a nasal sample, an oral sample, a lung sample, or a mammary gland sample.

[00218] Example 6. The method of any of examples 1 to 5, wherein the sample dataset comprises animal-related metadata comprising one or more of the following: body weight, birth weight, animal breed, animal sex, body composition, growth rate, rate of Petition 870250080933, dated 09 / 09 / 2025, pp. 106 / 138 / 112 feed conversion, mortality, morbidity, habitability, disease history, health and performance measures, reproductive measures, current or previous pathological states, gastrointestinal pathological risks, respiratory pathological risks, reproductive system pathological risks, mammary gland pathological risks, type of feed, vaccines administered and date of vaccination administration, type of supplement, use of antimicrobial resistance promoters, conventional rearing, rearing of animals with antimicrobials, geographic location, rearing conditions, animal life stage, type of microbiome sample, microbiome sampling life stage, age or time of microbiome sampling, metagenomic method used, farm location, herd size, animal heart circumference measurement, or type of nutrition.

[00219] Example 7. The method of any of Examples 1 to 6, wherein the target queries for future health or future performance comprise one or more of the following: piglet growth rate, piglet average daily weight gain, piglet microbiome alpha diversity, piglet habitability, piglet mortality, piglet general health, piglet gastrointestinal pathology risk, piglet respiratory pathology risk, piglet antimicrobial growth promoter use, piglet microbiome composition, piglet microbiome function, piglet microbiome network interaction, piglet microbiome stability, piglet microbiome robustness, and / or piglet microbiome resilience;or one or more of the following: sow habitability, sow mortality, sow general health, risk of sow gastrointestinal pathology, risk of sow respiratory pathology, risk of sow reproductive system pathology, risk of sow mammary gland pathology, use of antimicrobial growth promoter in sows, sow microbiome composition, sow microbiome function, sow microbiome network interaction, sow microbiome stability, sow microbiome robustness, sow microbiome resilience; Petition 870250080933, dated 09 / 09 / 2025, pp. 107 / 138 / 112 sow reproductive performance and / or sow-to-piglet ratio; or one or more of the following: gilt habitability, gilt mortality, gilt general health, gilt gastrointestinal disease risk, gilt respiratory disease risk, gilt reproductive system disease risk, gilt antimicrobial growth promoter use, gilt microbiome composition, gilt microbiome function, gilt microbiome network interaction, gilt microbiome stability, gilt microbiome robustness, gilt microbiome resilience and / or gilt future reproductive performance.

[00220] Example 8. The method of any of examples 1 to 7, wherein the model selected from the model repository comprises one or more trained models comprising a prediction model, a recommendation model, or an intervention model.

[00221] Example 9. The method of any of examples 1 to 8, where the model selected from the model repository comprises a prediction model.

[00222] Example 10. The method of example 9, wherein the prediction model comprises one or more predictions relating to the future performance or future health of the animal; and wherein the one or more predictions comprise a prediction of: future body weight, future feed conversion ratio, future feed intake, future growth rate, future average daily weight gain, future heart circumference diameter, future habitability, future mortality, future morbidity, future risk of gastrointestinal pathologies, future risk of respiratory pathologies, future risk of reproductive system pathologies, future risk of mammary gland pathologies, future litter size, future number of piglets born alive, future number of stillborn piglets, future parity, future sow mortality, or future incidence of uterine prolapse. Petition 870250080933, dated 09 / 09 / 2025, pages 108 / 138 / 112

[00223] Example 11. The method of any of examples 1 to 8, where the model selected from the model repository comprises a recommendation model.

[00224] Example 12. The method of example 11, wherein the recommendation model comprises one or more recommendations relating to the future performance or future health of the animal; and wherein the one or more recommendations comprise a recommendation to: change a feed composition or supplement, add or remove a feed composition or supplement, administer one or more vaccines, administer one or more medications, make changes to a rearing environment or management system, select an animal comprising an indication for improved future performance or future health, select a gilt comprising an indication for improved future performance or future health, or add or remove antimicrobial growth promoters in an animal's diet.

[00225] Example 13. The method of any of examples 1 to 8, where the model selected from the model repository comprises an intervention model.

[00226] Example 14. The method of example 13, wherein the intervention model comprises one or more interventions related to the animal's future performance or future health; and wherein the one or more interventions comprise: altering a feed composition or supplement, providing a feed composition or supplement, adding or removing a feed composition or supplement, administering one or more vaccines, administering one or more medications, making changes to the rearing environment and management system, making changes to the management system, selecting an animal comprising an indication for improved future performance or future health, selecting a gilt comprising an indication for improved future performance or future health, or adding Petition 870250080933, dated 09 / 09 / 2025, pp. 109 / 138 / 112 or remove one or more antimicrobial growth promoters from an animal's diet.

[00227] Example 15. The method of any of Examples 1 to 14, in which predictions, recommendations, or interventions are designed to reduce the incidence or severity of a disease, improve animal health and performance measures, reduce the number of animals that need to be culled within a population, select individual animals that comprise an indication for improved future performance or health, identify individual animals that require interventions, or reduce reliance on antimicrobial drugs.

[00228] Example 16. The method of any of examples 1 to 15, where the model was generated based on metagenomic data or metadata from one or more past generations of animals.

[00229] Example 17. The method of any of examples 1 to 16, in which the model was additionally generated based on the metagenomic data types and the body location from which the sample data were obtained.

[00230] Example 18. The method of any of examples 1 to 17, wherein the model comprises one or more of a piglet model, a sow model or a gilt model.

[00231] Example 19. The method of example 18, further comprising a piglet model, wherein the piglet model comprises one or more of: a piglet growth rate model, a piglet average daily gain model, a piglet alpha diversity model, a piglet mortality model, a piglet habitability model, a piglet general health model, a piglet gastrointestinal pathological risk model, a piglet respiratory pathological risk model, a piglet antimicrobial growth promoter model, a piglet biotic health and growth promoter model, a model of Petition 870250080933, dated 09 / 09 / 2025, pp. 110 / 138 100 / 112 Piglet microbiome composition, a functional model of the piglet microbiome, a network interaction model of the piglet microbiome, a piglet microbiome stability model, a piglet microbiome robustness model, and a piglet microbiome resilience model.

[00232] Example 20.The method of Example 18, additionally comprising a sow model, wherein the sow model comprises one or more of: a sow mortality model, a sow habitability model, a sow general health model, a sow gastrointestinal pathological risk model, a sow respiratory pathological risk model, a sow reproductive system risk model, a sow mammary gland pathological risk model, a sow antimicrobial growth promoter risk model, a sow biotic health and growth promoter model, a sow microbiome composition model, a sow microbiome functional model, a sow microbiome network interaction model, a sow microbiome stability model, a sow microbiome robustness model, a sow microbiome resilience model, a sow reproductive performance model, and a sow-to-piglet performance model.

[00233] Example 21. The method of example 18, further comprising a gilt model, wherein the gilt model comprises one or more of: a gilt mortality model, a gilt habitability model, a gilt general health model, a gilt gastrointestinal pathology risk model, a gilt respiratory pathology risk model, a gilt reproductive system risk model, a gilt antimicrobial growth promoter risk model, a gilt health and biotic growth promoter model, a gilt microbiome composition model, a gilt microbiome functional model, a gilt microbiome network interaction model Petition 870250080933, dated 09 / 09 / 2025, pp. 111 / 138 101 / 112 gilts, a model of gilt microbiome stability, a model of gilt microbiome robustness, a model of gilt microbiome resilience, and a model of future gilt reproductive performance.

[00234] Example 22. The method of any of examples 1 to 21, wherein the animal comprises a swine.

[00235] Example 23. The method of any of examples 1 to 22, wherein the animal comprises a piglet, a gilt or a sow.

[00236] Example 24. The method of any of examples 1 to 23, wherein obtaining a sample data set additionally comprises obtaining a sample data set from more than one animal.

[00237] Example 25. The method of any of Examples 1 to 24, wherein the implementation of one or more interventions as one or more adjustments comprises: changing from conventional rearing to an environment where one or more animals are reared without antimicrobials; changing from an environment where one or more animals are reared without antimicrobials to conventional rearing with antimicrobials; changing to a rearing system where one or more animals are reared using alternatives to antimicrobial compounds comprising prebiotics, probiotics, postbiotics or phytogenics; increasing or decreasing herd size; implementing one or more culling decisions; isolating one or more animals; adding or removing one or more supplement compositions; altering an existing supplement composition; adding or removing a supplement containing one or more antimicrobial growth promoters;to add or remove a food composition or compositions to treat one or more nutritional deficiencies; to alter a food composition; to add one or more vitamins or minerals; to add or remove one or more antimicrobial growth promoters in a food; to administer one or more vaccines to prevent or treat a disease; or to administer one or more; Petition 870250080933, dated 09 / 09 / 2025, pages 112 / 138 102 / 112 medications to prevent or treat a disease.

[00238] Example 26. A multigenerational microbiome system for optimizing future health or future performance in one or more animals, comprising: a metagenomic component configured to receive metagenomic data obtained from a microbiome sample of one or more animals; a metadata acquisition component configured to receive metadata about one or more animals; a query acquisition component configured to receive one or more target queries for the future health or future performance of one or more animals; a processing component comprising a model selection mechanism, the model selection mechanism configured to select a model or set of models from a model repository based on the metagenomic data, metadata, and target query;A prediction generation mechanism configured to run the selected model or set of models to generate one or more predictions about the animal's future health or future performance; a recommendation prioritization mechanism configured to use the predictions to identify an animal or animals at risk of future adverse health or future adverse performance, and to generate one or more recommendations that are prioritized to address the identified risk; and an intervention prioritization mechanism configured to use the one or more predictions or recommendations to generate one or more interventions that are prioritized to address the identified risk.A reporting mechanism configured to receive predictions, recommendations, or interventions and generate one or more reports that include the specific predictions, recommendations, or interventions, or a combination thereof, and a detailed rationale for the adjustments appropriate to optimize future health or performance in an animal or group of animals; and an adjustment component configured to implement one or more interventions as one or more adjustments to; Petition 870250080933, dated 09 / 09 / 2025, pages 113 / 138 103 / 112 animal or group of animals.

[00239] Example 27. The system of example 26, additionally comprising a model repository configured to store one or more trained models, target queries, profiles, model performance metrics, or parameters.

[00240] Example 28. The system of either of examples 26 or 27, additionally comprising a data repository configured to store the metagenomic data or metadata.

[00241] Example 29. The system of any of Examples 26 to 28, wherein the implementation of one or more interventions as one or more adjustments for the animal or group of animals comprises: changing from conventional rearing to an environment where one or more animals are reared without antimicrobials; changing from an environment where one or more animals are reared without antimicrobials to conventional rearing with antimicrobials; changing to a rearing system where one or more animals are reared using alternatives to antimicrobial compounds comprising prebiotics, probiotics, postbiotics or phytogenics; increasing or decreasing herd size; implementing one or more culling decisions; isolating one or more animals; adding or removing one or more supplement compositions; altering an existing supplement composition; adding or removing a supplement containing one or more antimicrobial growth promoters;Adding or removing a food composition or compositions to treat one or more nutritional deficiencies; altering a food composition; adding one or more vitamins or minerals; adding or removing one or more antimicrobial growth promoters in a food; administering one or more vaccines to prevent or treat a disease; or administering one or more medications to prevent or treat a disease.

[00242] Example 30. The system of any of examples 26 to 29, Petition 870250080933, dated 09 / 09 / 2025, pages 114 / 138 104 / 112 where the metagenomic data comprise one or more of the following: DNA-based or RNA-based shotgun sequencing data, 16S ribosomal RNA gene sequencing data, 18S ribosomal RNA gene sequencing data, or internal transcript spacer amplicon sequencing data.

[00243] Example 31. The system of any of Examples 26 to 30, wherein the metadata comprises one or more of the following: body weight, birth weight, animal breed, animal sex, body composition, growth rate, feed conversion rate, mortality, morbidity, habitability, disease history, health and performance measures, reproductive measures, current or past pathological states, gastrointestinal pathological risks, respiratory pathological risks, reproductive system pathological risks, mammary gland pathological risks, type of feed, vaccines administered and date of vaccination administration, type of supplement, use of antimicrobial resistance promoters, conventional rearing, rearing with antimicrobials, geographic location, rearing conditions, animal life stage, type of microbiome sample, microbiome sampling life stage, age or time of microbiome sampling, metagenomic method used,Farm location, herd size, animal heart circumference measurement, or type of nutrition.

[00244] Example 32. The system of any of Examples 26 to 31, wherein the target queries for future health or future performance comprise one or more of the following: piglet growth rate, piglet average daily weight gain, piglet microbiome alpha diversity, piglet habitability, piglet mortality, piglet general health, piglet gastrointestinal pathology risk, piglet respiratory pathology risk, piglet antimicrobial growth promoter use, piglet microbiome composition, piglet microbiome function, piglet microbiome network interaction, piglet microbiome stability, piglet robustness Petition 870250080933, dated 09 / 09 / 2025, pages 115 / 138 105 / 112 piglet microbiome and / or piglet microbiome resilience; or one or more of the following: sow habitability, sow mortality, sow general health, risk of sow gastrointestinal pathology, risk of sow respiratory pathology, risk of sow reproductive system pathology, risk of sow mammary gland pathology, use of antimicrobial growth promoter in sows, sow microbiome composition, sow microbiome function, sow microbiome network interaction, sow microbiome stability, sow microbiome robustness, sow microbiome resilience, sow reproductive performance and / or sow-to-piglet ratio;or one or more of the following: gilt habitability, gilt mortality, gilt general health, risk of gastrointestinal pathology in gilts, risk of respiratory pathology in gilts, risk of reproductive system pathology in gilts, use of antimicrobial growth promoters in gilts, composition of the gilt microbiome, function of the gilt microbiome, network interaction of the gilt microbiome, stability of the gilt microbiome, robustness of the gilt microbiome, resilience of the gilt microbiome, and / or future reproductive performance of the gilt.

[00245] Example 33. The system of any of examples 26 to 32, wherein the model selected from the model repository comprises one or more trained models comprising a prediction model, a recommendation model, or an intervention model.

[00246] Example 34. The system of any of examples 26 to 33, where the model selected from the model repository comprises a prediction model.

[00247] Example 35. The system of example 34, wherein the prediction model comprises one or more predictions relating to the future performance or future health of the animal; and wherein the one or more predictions comprise a prediction of: future body weight, future feed conversion ratio, future feed intake, future growth rate, Petition 870250080933, dated 09 / 09 / 2025, pages 116 / 138 106 / 112 of future average daily weight gain, future heart circumference diameter, future habitability, future mortality, future morbidity, future risk of gastrointestinal pathologies, future risk of respiratory pathologies, future risk of reproductive system pathologies, future risk of mammary gland pathologies, future litter size, future number of piglets born alive, future number of stillborn piglets, future parity, future sow mortality, or future incidence of uterine prolapse.

[00248] Example 36. The system of any of examples 26 to 33, where the model identified from the model repository comprises a recommendation model.

[00249] Example 37. The system of example 36, wherein the recommendation model comprises one or more recommendations relating to the future performance or future health of the animal; and wherein the one or more recommendations comprise a recommendation to: change a feed composition or supplement, add or remove a feed composition or supplement, administer one or more vaccines, administer one or more medications, make changes to a rearing environment or management system, select an animal comprising an indication for improved future performance or future health, select a gilt comprising an indication for improved future performance or future health, or add or remove antimicrobial growth promoters in an animal's diet.

[00250] Example 38. The system of any of examples 26 to 33, where the model identified from the model repository comprises an intervention model.

[00251] Example 39. The method of example 38, wherein the intervention model comprises one or more interventions related to the animal's future performance or future health; and wherein one or more Petition 870250080933, dated 09 / 09 / 2025, pp. 117 / 138 107 / 112 interventions include: altering a feed composition or supplement, providing a feed composition or supplement, adding or removing a feed composition or supplement, administering one or more vaccines, administering one or more medications, making changes to the rearing environment and management system, making changes to the management system, selecting an animal comprising an indication for improved future performance or future health, selecting a gilt comprising an indication for improved future performance or future health, or adding or removing one or more antimicrobial growth promoters in an animal's diet.

[00252] Example 40. The system of any of Examples 26 to 39, in which predictions, recommendations, or interventions are configured to reduce the incidence or severity of a disease, improve animal health and performance measures, reduce the number of animals that need to be culled within a population, select individual animals that comprise an indication for improved future performance or health, identify individual animals that require interventions, or reduce reliance on antimicrobial drugs.

[00253] Example 41. The system of any of examples 26 to 40, where the model was generated based on metagenomic data or metadata from one or more past generations of animals.

[00254] Example 42. The system of any of examples 26 to 41, in which the model was additionally generated based on the metagenomic data types and the body location from which the sample data were obtained.

[00255] Example 43. The system of any of examples 26 to 42, wherein the model comprises one or more of a piglet model, a sow model or a gilt model.

[00256] Example 44. The system of example 43, comprising Petition 870250080933, dated 09 / 09 / 2025, pages 118 / 138 108 / 112 additionally a piglet model, wherein the piglet model comprises one or more of: a piglet growth rate model, a piglet average daily gain model, a piglet alpha diversity model, a piglet mortality model, a piglet habitability model, a piglet general health model, a piglet gastrointestinal pathological risk model, a piglet respiratory pathological risk model, a piglet antimicrobial growth promoter model, a piglet biotic health and growth promoter model, a piglet microbiome composition model, a piglet microbiome functional model, a piglet microbiome network interaction model, a piglet microbiome stability model, a piglet microbiome robustness model, and a piglet microbiome resilience model.

[00257] Example 45.The system of Example 43, further comprising a sow model, wherein the sow model comprises one or more of: a sow mortality model, a sow habitability model, a sow general health model, a sow gastrointestinal pathological risk model, a sow respiratory pathological risk model, a sow reproductive system risk model, a sow mammary gland pathological risk model, a sow antimicrobial growth promoter risk model, a sow biotic health and growth promoter model, a sow microbiome composition model, a sow microbiome functional model, a sow microbiome network interaction model, a sow microbiome stability model, a sow microbiome robustness model, a sow microbiome resilience model, a sow reproductive performance model, and a sow-to-piglet performance model.

[00258] Example 46. The system of example 43, additionally comprising a moose model, wherein the moose model comprises Petition 870250080933, dated 09 / 09 / 2025, pages 119 / 138 109 / 112 one or more of the following: a gilt mortality model, a gilt habitability model, a gilt general health model, a gilt gastrointestinal pathology risk model, a gilt respiratory pathology risk model, a gilt reproductive system risk model, a gilt antimicrobial growth promoter risk model, a gilt health and biotic growth promoter model, a gilt microbiome composition model, a gilt microbiome functional model, a gilt microbiome network interaction model, a gilt microbiome stability model, a gilt microbiome robustness model, a gilt microbiome resilience model, and a gilt future reproductive performance model.

[00259] Example 47. The system of any of examples 26 to 46, wherein the animal comprises a swine.

[00260] Example 48. The system of any of examples 26 to 47, wherein the animal comprises a piglet, a sow or a hog.

[00261] Example 49. The system of any of examples 26 to 48, where obtaining a sample data set additionally comprises obtaining a sample data set from more than one animal.

[00262] Example 50. A method for predicting future health or future performance in an animal, comprising: obtaining a sample dataset indicative of an entire microbial community within a gastrointestinal tract, mammary gland, reproductive system, or respiratory system of the animal; defining a query comprising one or more target queries for the animal's future health or future performance; selecting a model from a model repository based on the sample dataset and the query comprising the one or more targets; running the selected model using the sample dataset and the query comprising the one or more targets to make predictions, generate Petition 870250080933, dated 09 / 09 / 2025, pages 120 / 138 110 / 112 recommendations or generate interventions regarding the future health or future performance of the animal; report predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof; and implement one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment based on the predictions, recommendations, or interventions; wherein each model selected from the model repository is generated by a model generation engine, and wherein the model generation engine was trained using one or more metagenomic data or metadata obtained from one or more observational and interventional studies.

[00263] Example 51. The method of example 50, in which each model selected from the model repository is periodically retrained using newly acquired data obtained from one or more metagenomic data sets or metadata obtained from one or more observational and interventional studies, or from one or more metagenomic data sets or metadata obtained from one or more agricultural sites.

[00264] Example 52.The method of either of Examples 50 or 51, wherein the implementation of one or more interventions as one or more adjustments comprises: changing from conventional rearing to an environment where one or more animals are reared without antimicrobials; changing from an environment where one or more animals are reared without antimicrobials to conventional rearing with antimicrobials; changing to a rearing system where one or more animals are reared using alternatives to antimicrobial compounds comprising prebiotics, probiotics, postbiotics or phytogenics; increasing or decreasing herd size; implementing one or more culling decisions; isolating one or more animals; adding or removing one or more supplement compositions; altering an existing supplement composition; adding or removing a supplement containing one or more. Petition 870250080933, dated 09 / 09 / 2025, pages 121 / 138 111 / 112 more antimicrobial growth promoters; adding or removing a food composition or compositions to treat one or more nutritional deficiencies; altering a food composition; adding one or more vitamins or minerals; adding or removing one or more antimicrobial growth promoters in a food; administering one or more vaccines to prevent or treat a disease; or administering one or more medications to prevent or treat a disease.

[00265] Example 53. A method for optimizing future health or future performance in an animal, comprising: obtaining a sample dataset indicative of an entire microbial community within an animal's reproductive system; defining a query comprising one or more target queries for the animal's future health or future performance; selecting a model from a model repository based on the sample dataset and the query comprising the one or more targets; running the selected model using the sample dataset and the query comprising the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance; reporting the predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof;and implement one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment based on the predictions, recommendations, or interventions.

[00266] Example 54. A method for optimizing future health or future performance in an animal, comprising: obtaining a sample dataset indicative of an entire microbial community within an animal mammary gland; defining a query comprising one or more target queries for the animal's future health or future performance; selecting a model from a model repository based on Petition 870250080933, dated 09 / 09 / 2025, pages 122 / 138 112 / 112 sample dataset and query comprising one or more targets; run the selected model using the sample dataset and the query comprising one or more targets to make predictions, generate recommendations, or generate interventions about the animal's future health or future performance; report the predictions, recommendations, or interventions about future health or future performance, or combinations thereof; and implement one or more interventions as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment based on the predictions, recommendations, or interventions.

[00267] Example 55. A method for optimizing future health or future performance in an animal, comprising: obtaining a sample dataset indicative of an entire microbial community within an animal's respiratory system; defining a query comprising one or more target queries for the animal's future health or future performance; selecting a model from a model repository based on the sample dataset and the query comprising the one or more targets; running the selected model using the sample dataset and the query comprising the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance; reporting the predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof;and implement one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment based on the predictions, recommendations, or interventions. Petition 870250080933, dated 09 / 09 / 2025, pages 123 / 138

Claims

1 / 7 CLAIMS 1. A method for optimizing future health or future performance in an animal, characterized in that it comprises: obtaining a sample dataset indicative of an entire microbial community within the gastrointestinal tract, mammary gland, reproductive system, or respiratory system of an animal; defining a query comprising one or more target queries for the animal's future health or future performance; selecting a model from a model repository based on the sample dataset and the query comprising the one or more targets; executing the selected model using the sample dataset and the query comprising the one or more targets to make predictions, generate recommendations, or generate interventions regarding the animal's future health or future performance; reporting the predictions, recommendations, or interventions regarding future health or future performance, or combinations thereof;and implement one or more interventions such as one or more adjustments to the animal's nutrition, management system, health care, or rearing environment based on the predictions, recommendations, or interventions.

2. Method according to claim 1, characterized in that the sample dataset comprises metagenomic data.

3. A method according to either of claims 1 or 2, characterized in that the sample dataset comprises metagenomic data and metadata.

4. Method according to any of claims 1 to Petition 870250080933, dated 09 / 09 / 2025, p. 124 / 138 2 / 7 3, characterized in that the sample dataset comprises metagenomic data obtained through the use of one or more sequencing techniques comprising DNA-based or RNA-based shotgun sequencing, 16S ribosomal RNA gene sequencing, 18S ribosomal RNA gene sequencing, or internal transcript spacer amplicon sequencing.

5. A method according to any one of claims 1 to 4, characterized in that the sample dataset comprises metagenomic data from at least one microbiome sample comprising a fecal sample, a rectal sample, a vaginal sample, a nasal sample, an oral sample, a lung sample, or a mammary gland sample.

6. A method according to any one of claims 1 to 5, characterized in that the sample dataset comprises animal-related metadata including one or more of the following: body weight, birth weight, animal breed, animal sex, body composition, growth rate, feed conversion rate, mortality, morbidity, habitability, disease history, health and performance measures, reproductive measures, current or previous pathological states, gastrointestinal pathological risks, respiratory pathological risks, reproductive system pathological risks, mammary gland pathological risks, type of feed, vaccines administered and date of vaccination administration, type of supplement, use of antimicrobial resistance promoters, conventional rearing, rearing with antimicrobials, geographic location, rearing conditions, animal life stage, type of microbiome sample, life stage of microbiome sampling,Age or time of microbiome sampling, metagenomic method used, farm location, herd size, animal heart circumference measurement, or type of nutrition. Petition 870250080933, dated 09 / 09 / 2025, pp. 125 / 138 3 / 7, 7. A method according to any one of claims 1 to 6, characterized in that the target queries for future health or future performance comprise one or more of the following: piglet growth rate, piglet average daily weight gain, piglet microbiome alpha diversity, piglet habitability, piglet mortality, piglet general health, piglet gastrointestinal pathology risk, piglet respiratory pathology risk, piglet antimicrobial growth promoter use, piglet microbiome composition, piglet microbiome function, piglet microbiome network interaction, piglet microbiome stability, piglet microbiome robustness and / or piglet microbiome resilience;or one or more of the following: sow habitability, sow mortality, sow general health, risk of sow gastrointestinal pathology, risk of sow respiratory pathology, risk of sow reproductive system pathology, risk of sow mammary gland pathology, use of antimicrobial growth promoter in sows, sow microbiome composition, sow microbiome function, sow microbiome network interaction, sow microbiome stability, sow microbiome robustness, sow microbiome resilience, sow reproductive performance and / or sow-to-piglet ratio;or one or more of the following: gilt habitability, gilt mortality, gilt general health, risk of gastrointestinal pathology in gilts, risk of respiratory pathology in gilts, risk of reproductive system pathology in gilts, use of antimicrobial growth promoters in gilts, composition of the gilt microbiome, function of the gilt microbiome, network interaction of the gilt microbiome, stability of the gilt microbiome, robustness of the gilt microbiome, resilience of the gilt microbiome, and / or future reproductive performance of the gilt.

8. Method according to any one of claims 1 to 7, characterized in that the model selected from the repository of models comprises one or more trained models comprising a prediction model, a recommendation model or an intervention model.

9. A method according to any one of claims 1 to 8, characterized in that the model selected from the model repository comprises a prediction model.

10. A method according to claim 9, characterized in that the prediction model comprises one or more predictions related to the future performance or future health of the animal; and wherein the one or more predictions comprise a prediction of: future body weight, future feed conversion ratio, future feed intake, future growth rate, future average daily weight gain, future heart circumference diameter, future habitability, future mortality, future morbidity, future risk of gastrointestinal pathologies, future risk of respiratory pathologies, future risk of reproductive system pathologies, future risk of mammary gland pathologies, future litter size, future number of live-born piglets, future number of stillborn piglets, future parity, future sow mortality, or future incidence of uterine prolapse.

11. A method according to any one of claims 1 to 8, characterized in that the model selected from the model repository comprises a recommendation model.

12. Method according to claim 11, characterized in that the recommendation model comprises one or more recommendations relating to the future performance or future health of the animal; and wherein the one or more recommendations comprise a recommendation to: alter a feed composition or supplement, add or remove a feed composition or supplement, administer one or more vaccines, administer one or more medications, make changes to a rearing environment or management system, select an animal comprising an indication for improved future performance or future health, select a gilt comprising an indication for improved future performance or future health, or add or remove antimicrobial growth promoters in an animal's diet.

13. A method according to any one of claims 1 to 8, characterized in that the model selected from the model repository comprises an intervention model.

14. A method according to claim 13, characterized in that the intervention model comprises one or more interventions related to the animal's future performance or future health; and wherein the one or more interventions comprise: altering a feed composition or supplement, providing a feed composition or supplement, adding or removing a feed composition or supplement, administering one or more vaccines, administering one or more medications, making changes to the rearing environment and management system, making changes to the management system, selecting an animal comprising an indication for improved future performance or future health, selecting a gilt comprising an indication for improved future performance or future health, or adding or removing one or more antimicrobial growth promoters in an animal's diet.

15. A method according to any one of claims 1 to 14, characterized in that the predictions, recommendations, or interventions are designed to reduce the incidence or severity of a disease, improve animal health and performance measures, reduce the number of animals that need to be culled within a population, Petition 870250080933, dated 09 / 09 / 2025, pp. 128 / 138 6 / 7 select individual animals that comprise an indication for improved future performance or health, identify individual animals that require interventions, or reduce reliance on antimicrobial drugs.

16. A method according to any one of claims 1 to 16, characterized in that the model is additionally generated based on the types of metagenomic data and the body location from which the sample data were obtained.

17. A method according to any one of claims 1 to 17, characterized in that the model comprises one or more of a piglet model, a sow model, or a gilt model.

18. Method according to claim 18, characterized in that it further comprises a piglet model, wherein the piglet model comprises one or more of: a piglet growth rate model, a piglet average daily gain model, a piglet alpha diversity model, a piglet mortality model, a piglet habitability model, a piglet general health model, a piglet gastrointestinal pathological risk model, a piglet respiratory pathological risk model, a piglet antimicrobial growth promoter model, a piglet biotic health and growth promoter model, a piglet microbiome composition model, a piglet microbiome functional model, a piglet microbiome network interaction model, a piglet microbiome stability model, a piglet microbiome robustness model, and a piglet microbiome resilience model.

19. Method according to claim 18, characterized in that it further comprises a sow model, wherein the sow model comprises one or more of: a sow mortality model, a sow habitability model, a Petition 870250080933, dated 09 / 09 / 2025, page.129 / 138 7 / 7 general health of sows, a gastrointestinal pathological risk model of sows, a respiratory pathological risk model of sows, a reproductive system risk model of sows, a mammary gland pathological risk model of sows, an antimicrobial growth promoter risk model of sows, a biotic health and growth promoter model of sows, a microbiome composition model of sows, a functional model of the sow microbiome, a network interaction model of the sow microbiome, a microbiome stability model of sows, a microbiome robustness model of sows, a microbiome resilience model of sows, a reproductive performance model of sows, and a sow-to-piglet performance model.

20. Method according to claim 18, characterized in that it further comprises a gilt model, wherein the gilt model comprises one or more of: a gilt mortality model, a gilt habitability model, a gilt general health model, a gilt gastrointestinal pathology risk model, a gilt respiratory pathology risk model, a gilt reproductive system risk model, a gilt antimicrobial growth promoter risk model, a gilt health and biotic growth promoter model, a gilt microbiome composition model, a gilt microbiome functional model, a gilt microbiome network interaction model, a gilt microbiome stability model, a gilt microbiome robustness model, a gilt microbiome resilience model, and a future reproductive performance model. of piglets. Petition 870250080933, dated 09 / 09 / 2025, pp. 130 / 138

Images