The present invention relates to a method for predicting a drug-drug interaction and a drug-food interaction by using structural information of a drug and, more particularly, to a method for predicting the mechanism of action and activity of a drug interaction through interaction prediction results expressed by a standardized sentence. When using a method for predicting a drug interaction according to the present invention, a drug interaction can be predicted quickly and accurately, and in particular, activity information of an unknown compound can also be predicted by expressing a prediction result by means of a sentence, and thus the method is very useful for developing a drug exhibiting desired activity without causing adverse effects.

The present invention provides compositions and methods that can be used to identify an antigen or epitope region of an antigen specific for a disease or other condition. Such methods incorporate k-mer binding statistics to serum antibody from condition and control cohort samples to predict the suitability of antigen sequences identified as relevant to the disease or condition as antigen markers. Also disclosed herein are systems for performing the same.

The present invention provides compositions and methods that can be used to identify an antigen or epitope region of an antigen specific for a disease or other condition. Such methods incorporate k-mer binding statistics to serum antibody from condition and control cohort samples to predict the suitability of antigen sequences identified as relevant to the disease or condition as antigen markers. Also disclosed herein are systems for performing the same.

Devices, systems, and techniques for controlling delivery of therapy for diabetes are described. In one example, a system includes a wearable device configured to generate user activity data associated with an arm of a user; and one or more processors configured to: identify at least one gesture indicative of utilization of an injection device for preparation of an insulin injection based on the user activity data; based on the at least one identified gesture, generate information indicative of at least one of an amount or type of insulin dosage in the insulin injection by the injection device; compare the generated information to a criteria of a proper insulin injection; and output information indicative of whether the criteria is satisfied based on the comparison.

Devices, systems, and techniques for controlling delivery of therapy for diabetes are described. In one example, a system includes a wearable device configured to generate user activity data associated with an arm of a user; and one or more processors configured to: identify at least one gesture indicative of utilization of an injection device for preparation of an insulin injection based on the user activity data; based on the at least one identified gesture, generate information indicative of at least one of an amount or type of insulin dosage in the insulin injection by the injection device; compare the generated information to a criteria of a proper insulin injection; and output information indicative of whether the criteria is satisfied based on the comparison.

Disclosed herein are systems and methods for significantly improving the accuracy of drug selection for patients diagnosed with, or symptomatic for, urinary tract infections (UTIs). In some embodiments, the systems and methods utilize real-time patient data linked to geographic distribution maps of resistance to different antimicrobial treatments for UTIs. The combination of real-time date and resistance maps allow for more accurate selection of appropriate UTI therapy for the patient.

Disclosed herein are systems and methods for significantly improving the accuracy of drug selection for patients diagnosed with, or symptomatic for, urinary tract infections (UTIs). In some embodiments, the systems and methods utilize real-time patient data linked to geographic distribution maps of resistance to different antimicrobial treatments for UTIs. The combination of real-time date and resistance maps allow for more accurate selection of appropriate UTI therapy for the patient.

Embodiments of the invention relate to a system and method for population-based medication risk stratification and for generating a personalized medication risk score. The system and method may pertain to a software that relates pharmacological characteristics of medications and patient's drug regimen data into algorithms that (1) enable identification and/or prognosis of high-risk patients for adverse drug events within a population distribution, and (2) allow computation of a personalized medication risk score which provides personalized, evidence-based information for safer drug use to mitigate medication risks.

Embodiments of the invention relate to a system and method for population-based medication risk stratification and for generating a personalized medication risk score. The system and method may pertain to a software that relates pharmacological characteristics of medications and patient's drug regimen data into algorithms that (1) enable identification and/or prognosis of high-risk patients for adverse drug events within a population distribution, and (2) allow computation of a personalized medication risk score which provides personalized, evidence-based information for safer drug use to mitigate medication risks.

Systems and methods are provided for generating and training a relation extraction model configured to extract document-level relations. Systems obtain a knowledge database that comprises a plurality of entity tuples and a plurality of relation types, use the knowledge database to generate annotated relation instances based on relation instances that are identified in a set of unlabeled text, generate a training dataset comprising the annotated relation instances and the set of unlabeled text, and generate the machine learning model via modular self-supervision. Systems and methods are also provided for using a relation extraction model to extract document-level relations in specific use scenarios, such as for extracting drug response relations from full-text medical research articles.