Deep Learning Prediction of Adverse Drug Reactions in Drug Discovery Using Open TG–GATEs and FAERS Databases

With the advancements in Artificial intelligence (AI) and accumulation of healthrelated big data, it has become increasingly feasible commonplace to leverage machine learning technologies analyze clinical omics metadata assess possibility adverse drug reactions or events (ADRs) course discovery. Here, we have described a novel approach that combined drug-induced gene expression profile from Open TG-GATEs (Toxicogenomics Project-Genomics Assisted Toxicity Evaluation Systems) ADR occurrence information FAERS (FDA [Food Drug Administration] Adverse Events Reporting System) database predict likelihood ADRs. We generated total 14 models using Deep Neural Networks (DNN) different ADRs; validation tests, our achieved mean accuracy 85.71%, indicating successfully consistently predicted ADRs for wide range drugs. As an example, model context Duodenal ulcer. believe will help while testing pharmaceutical compounds, be useful researchers