Method and System for Predicting Adverse Drug Reactions Using BioAssay Data

摘要

An embodiment of the present invention uses logistic regression models that correlate post-marketing ADRs with screening data from the PubChem BioAssay database. These models of the present invention analyze ADRs at the level of organ systems, the System Organ Classes (SOCs). In testing to evaluate an embodiment of the present invention, nine of 19 SOCs under consideration were found to be significantly correlated with pre-clinical screening data. For six of eight established drugs for which SOC-specific adversities could be retropredicted, prior knowledge was found that support these predictions. SOC-specific adversities were then predicted for three unapproved or recently introduced drugs.