Abstract: The disclosed systems and methods provide a systematic approach to analyzing an individual's lifestyle factors (e.g., foods consumed by the individual) that contribute to the individual's current or potential for disease, and taking further action based on that analysis. One example embodiment is a machine learning system that includes a food composition layer, chemical compounds layer, and disease layer. The food composition layer provides representations of chemical compounds of foods consumed or to be consumed by the individual. The chemical compounds layer is coupled to the food composition layer by links and filters the representations of the chemical compounds based on genetic or metabolic information of the individual, resulting in representations of personalized filtered chemical compounds.

Abstract: The disclosed systems and methods provide a systematic approach to analyzing an individual's lifestyle factors (e.g., foods consumed by the individual) that contribute to the individual's current or potential for disease, and taking further action based on that analysis. One example embodiment is a machine learning system that includes a food composition layer, chemical compounds layer, and disease layer. The food composition layer provides representations of chemical compounds of foods consumed or to be consumed by the individual. The chemical compounds layer is coupled to the food composition layer by links and filters the representations of the chemical compounds based on genetic or metabolic information of the individual, resulting in representations of personalized filtered chemical compounds.

Abstract: Systems and methods for identifying a degree of food processing based on food nutrient content are provided. Given in a nutrient profile for a food that includes nutrient content data for the food, a vector of probabilities is generated in which each probability of the vector represents a probability associated with a processing category for the food. A food processing score is determined based on the vector of probabilities and displayed. An individual food score can also be determined based on a plurality of food processing scores. The individual food processing score can be weight-based or calorie-based.

Abstract: The present disclosure discusses a system and method for disease module detection. More particularly, a protein network and list of seed proteins are provided to the system. The system iteratively selects one or more candidate proteins for inclusion in the list of seed proteins. The system calculates a connectivity factor for each of the connections of the candidate proteins to proteins listed as seed proteins. Responsive to the calculated connectivity factors the system adds one or more of the candidate proteins to list of seed proteins. At the end of the iterative process the list of seed proteins can be indicative of the disease module.

Abstract: The disclosed systems and methods provide a systematic approach to analyzing an individual's lifestyle factors (e.g., foods consumed by the individual) that contribute to the individual's current or potential for disease, and taking further action based on that analysis. One example embodiment is a machine learning system that includes a food composition layer, chemical compounds layer, and disease layer. The food composition layer provides representations of chemical compounds of foods consumed or to be consumed by the individual. The chemical compounds layer is coupled to the food composition layer by links and filters the representations of the chemical compounds based on genetic or metabolic information of the individual, resulting in representations of personalized filtered chemical compounds.

Abstract: Methods and systems for filtering data in a protein-protein interaction network are provided, which can be used to identify potential food-drug interactions. A method of filtering data in protein-protein interaction network includes mapping proteins associated with a plurality of chemicals of a first type (e.g drugs) and proteins associated with one or more chemicals of a second type (e.g., foods). The method further includes determining proximities of proteins associated with the plurality of chemicals of the first type and proteins associated with the one or more chemicals of the second type and generating a reduced dataset of proteins within the protein-protein interaction network. The reduced dataset includes proteins associated with a subset of the plurality of chemicals of the first type based on the determined proximities.

Abstract: The disclosed systems and methods provide a systematic approach to analyzing an individual's lifestyle factors (e.g., foods consumed by the individual) that contribute to the individual's current or potential for disease, and taking further action based on that analysis. One example embodiment is a machine learning system that includes a food composition layer, chemical compounds layer, and disease layer. The food composition layer provides representations of chemical compounds of foods consumed or to be consumed by the individual. The chemical compounds layer is coupled to the food composition layer by links and filters the representations of the chemical compounds based on genetic or metabolic information of the individual, resulting in representations of personalized filtered chemical compounds.

Abstract: Systems and methods of identifying a disease associated with a therapeutic chemical are presented. A method includes generating a candidate disease list based on proximities of proteins associated with a plurality of diseases and proteins associated with a therapeutic chemical in a protein-protein interaction network. The method further includes applying gene expression information associated with the therapeutic chemical to generate enrichment scores for diseases of the candidate disease list and identifying at least one disease associated with the therapeutic chemical based on the determined enrichment scores.

Abstract: Provided herein are methods of treating a vascular disease or condition in a subject in need thereof, comprising administering to the subject an effective amount of a vascular disease associated polyphenol (e.g., rosmarinic acid), or a pharmaceutically acceptable salt thereof. Also provided herein are methods of promoting or supporting vascular health in a subject, and methods of inhibiting platelet function (e.g., platelet aggregation) in a subject.

Abstract: Methods and systems for generating drug repurposing predictions for a disease caused by a pathogen, such as a novel pathogen, are provided. A multi-modal system includes a protein-protein interaction network (PPI), a graph neural network (GNN), a diffusion module, a proximity module, and an aggregation module. The GNN is configured to predict new edges between candidate drug nodes and disease nodes in an embedded representation of the PPI to produce a decoded embedding space. The diffusion module is configured to determine a proximity distance for pairs of nodes in the PPI, and the proximity module is configured to determine a proximity distance for pairs of nodes in the PPI, each pair comprising a pathogen-protein node and a drug-protein node. A ranked list of candidate drugs predicted to be effective in treatment of the disease based on candidate drug lists generated by the other modules is generated by the aggregation module.

Abstract: The present technology relates to methods that determine one or more subgroups of subjects within a population of subjects diagnosed with the same disease. In some embodiments, the methods include determining differential gene expression of at least one subgroup in the population using divisive Shuffling Approach (VIStA). In some embodiments, the method includes determining at least one clinical characteristic of each subgroup and/or determining a significant set of clinical characteristics of the disease order.

Abstract: The disclosed methods and systems allow for a systematic quantification of the heterogeneity of disease states between different subjects on a molecular (e.g., gene or protein expression) level. One example embodiment of the invention is a method for determining a disease state of a patient. The method includes generating personalized biomarker expression perturbation profiles for a plurality of individual subjects with a disease. The profiles include representations of biomarker expressions that are perturbed beyond a threshold amount. The method also includes creating a disease module by combining representations of biomarkers from the personalized profiles. The disease module includes a network of representations of biomarkers having perturbations associated with the disease. The method also includes accessing biomarker data for the patient from a sample obtained from the patient and determining the disease state of the patient based on a comparison of the biomarker data and the disease module.

Abstract: The present disclosure discusses a system and method for disease module detection. More particularly, a protein network and list of seed proteins are provided to the system. The system iteratively selects one or more candidate proteins for inclusion in the list of seed proteins. The system calculates a connectivity factor for each of the connections of the candidate proteins to proteins listed as seed proteins. Responsive to the calculated connectivity factors the system adds one or more of the candidate proteins to list of seed proteins. At the end of the iterative process the list of seed proteins can be indicative of the disease module.

Abstract: Systems and methods are disclosed for predicting a product's (e.g., a book's) performance prior to its availability. An example embodiment is a system for machine learning classification that includes representations of characteristics of products, a pre-processor, and a machine learning classifier. The pre-processor can determine (i) representations of comparative intrinsic characteristics of the products based on the representations of characteristics of products and (ii) representations of corresponding comparative extrinsic characteristics of the products. The pre-processor can generate a data structure representing relationships between the comparative intrinsic characteristics and the comparative extrinsic characteristics. The machine learning classifier is trained with the data structure. The classifier can return representations of comparative extrinsic characteristics in response to given comparative intrinsic characteristics.

Abstract: The disclosed systems and methods provide a systematic approach to analyzing an individual's lifestyle factors (e.g., foods consumed by the individual) that contribute to the individual's current or potential for disease, and taking further action based on that analysis. One example embodiment is a machine learning system that includes a food composition layer, chemical compounds layer, and disease layer. The food composition layer provides representations of chemical compounds of foods consumed or to be consumed by the individual. The chemical compounds layer is coupled to the food composition layer by links and filters the representations of the chemical compounds based on genetic or metabolic information of the individual, resulting in representations of personalized filtered chemical compounds.

Abstract: Network-based relative proximity measures according to the present invention quantify the closeness between any two sets of nodes (e.g., drug targets and disease genes in a biological network, or groups of people in a social network). The proximity takes into account the scale-free nature of real-world networks and corrects for degree-bias (i.e., due to incompleteness or study biases) by incorporating various distance definitions between the two sets of nodes and comparison of these distances to those of randomly selected nodes in the network (i.e., the distance relative to random expectation), therefore improving processing of the network data. In brief, the proximity offers a formal framework to characterize the distance between two sets of nodes in the network with key applications in various domains from network pharmacology (e.g., discovering novel uses for existing drugs) to social sciences (e.g., defining similarity between groups of individuals).

Abstract: The present disclosure discusses a system and method for disease module detection. More particularly, a protein network and list of seed proteins are provided to the system. The system iteratively selects one or more candidate proteins for inclusion in the list of seed proteins. The system calculates a connectivity factor for each of the connections of the candidate proteins to proteins listed as seed proteins. Responsive to the calculated connectivity factors the system adds one or more of the candidate proteins to list of seed proteins. At the end of the iterative process the list of seed proteins can be indicative of the disease module.

Abstract: The present technology relates to methods that determine one or more subgroups of subjects within a population of subjects diagnosed with the same disease. In some embodiments, the methods include determining differential gene expression of at least one subgroup in the population using divisive Shuffling Approach (VIStA). In some embodiments, the method includes determining at least one clinical characteristic of each subgroup and/or determining a significant set of clinical characteristics of the disease order.

Abstract: A system for predicting future disease for a subject comprising: a population information set comprising population disease diagnoses for members of a population; a subject-specific information set comprising at least one subject-specific disease diagnosis; and a diagnoses-based prediction module configured to predict one or more future diseases for the subject based on said subject-specific disease diagnosis and said population disease diagnoses for population members having at least one disease in common with the subject.

Abstract: A system for predicting future disease for a subject comprising: a population information set comprising population disease diagnoses for members of a population; a subject-specific information set comprising at least one subject-specific disease diagnosis; and a diagnoses-based prediction module configured to predict one or more future diseases for the subject based on said subject-specific disease diagnosis and said population disease diagnoses for population members having at least one disease in common with the subject.