UTILIZING A COMPOUND-PERTURBATION ANOMALY DETECTION MODEL TO IDENTIFY OUTLIER COMPOUND-PERTURBATION RELATIONSHIPS

Abstract

The present disclosure relates to systems, non-transitory computer-readable media, and methods that identifies outlier gene-compound relationships by leveraging a trained machine learning classification model and a compound-perturbation anomaly detection model. Indeed, in one or more implementations, the disclosed systems generate a plurality of compound-perturbation interaction predictions by using a machine learning classification model trained using a plurality of compound-perturbation features. For instance, the disclosed systems select a set of target features from the plurality of compound-perturbation features based on contribution values of the compound-perturbation features in generating the compound-perturbation interaction predictions. In some instances, the disclosed systems train a compound-perturbation anomaly detection model to identify outlier compound-perturbation relationships from the set of target features.

CPC Classifications