International Business Machines Corporation

Katherine Shen

Achille Belly Fokoue-Nkoutche

Ping Zhang

Sanjoy Dey

William Scott Spangler

Jacques Labrie

Richard L Martin

Alix M Lacoste

Hrishikesh Sathe

A method, computer system, and a computer program product for generating a candidate set of entities from a training set of entities is provided. The present invention may include determining an ontology class for an input entity in the training set of entities. The present invention may include adding the input entity to an ontology list. The present invention may then include assigning an entity score to the input entity. The present invention may also include normalizing the ontology list of entity scores. The present invention may lastly include selecting the candidate set of entities with the highest entity score.

Generating a candidate set of entities from a training set

Embodiments of the present invention disclose a method, a computer program product, and a computer system for predicting drug and disease interactions. A computer identifies one or more drug similarity measures between one or more drugs and one or more disease similarity measures between one or more diseases. In addition, the computer identifies one or more interactions between the one or more drugs and the one or more diseases, then calculates one or more drug-disease feature vectors based on the one or more interactions, the one or more drug similarity measures, and the one or more disease similarity measures. Furthermore, the computer calculates a first probability indicating whether a first drug of the one or more drugs will interact with a first disease of the one or more diseases based on a model, wherein the model is trained based on the one or more drug-disease feature vectors.

Predicting interactions between drugs and diseases

Mechanisms are provided that implement a plurality of heterogeneous causality models and a metaclassifier for predicting a likelihood of causality between a drug and an adverse event (AE). The plurality of heterogenous causality models process drug information to generate a plurality of risk predictions for a drug and AE pair. The risk predictions include a risk score or a risk label indicating a probability of the AE occurring with use of the drug. The plurality of heterogenous causality models provide risk predictions, associated with the drug and AE pair, to a metaclassifier which generates a single causality score value indicative of a probability of causality between the drug and the AE, of the drug and AE pair, based on an aggregation of the risk predictions from the plurality of heterogenous causality models. The metaclassifier outputs the single causality score value in association with information identifying the drug and AE pair.

Evaluating drug-adverse event causality based on an integration of heterogeneous drug safety causality models

Mechanisms are provided that implement a plurality of heterogeneous causality models and a metaclassifier for predicting a likelihood of causality between a drug and an adverse event (AE). The plurality of heterogenous causality models process drug information for the drug to generate a plurality of risk predictions for a drug and AE pair. The risk predictions include at least one of a risk score or a risk label indicating a probability of the AE occurring with use of the drug. The plurality of heterogenous causality models provide the risk predictions, associated with the drug and AE pair, to a metaclassifier which generates a single causality score value indicative of a probability of causality between the drug and the AE, of the drug and AE pair, based on an aggregation of the risk predictions from the plurality of heterogenous causality models. The metaclassifier outputs the single causality score value in association with information identifying the drug and AE pair.

A method for ranking a relationship between drugs and adverse events includes creating a matrix of associations between a plurality of drugs and a plurality of adverse events and factoring the matrix of associates into a pair of matrix factors. The matrix factors, when multiplied, approximate the matrix of associations, and a product of the matrix factors is a matrix of observed scores. The method further includes determining, for each drug and adverse event pair in the matrix of observed scores, a z-score, an expected score for each drug and adverse event pair, and a standard deviation for each drug and adverse event pair, calculating a probability of a relationship between a drug and adverse event using the z-score for the drug and adverse event pair, and determining that the drug and adverse event are related, when the probability of a relationship is greater than a predetermined magnitude.

Estimating the probability of matrix factorization results

A method, computer system, and a computer program product for identifying and storing at least one representation to at least one chemical compound is provided. The present invention may include identifying a chemical compound associated with a source data. The present invention may also include assigning a structure representation to the identified chemical compound associated with the source data. The present invention may further include computing an unformulated representation based on the assigned structure representation. The present invention may then include indexing the computed unformulated representation and the assigned structure representation. The present invention may further include storing the indexed unformulated representation and the indexed structure representation separately as single records in a database.

Chemical formulation-aware cognitive search and analytics

Embodiments of the present invention disclose a method, a computer program product, and a computer system for predicting drug and food interactions. A computer identifies one or more drug similarity measures between one or more drugs and one or more food similarity measures between one or more foods. In addition, the computer identifies one or more interactions between the one or more drugs and the one or more foods, then calculates one or more drug-food feature vectors based on the one or more interactions, the one or more drug similarity measures, and the one or more food similarity measures. Furthermore, the computer calculates a first probability indicating whether a first drug of the one or more drugs will interact with a first food of the one or more foods based on a model, wherein the model is trained based on the one or more drug-food feature vectors.

Growing community of inventors

New York, NY, United States of America

Katherine Shen