Predicting neurological Adverse Drug Reactions based on biological, chemical and phenotypic properties of drugs using machine learning models.

ABSTRACT: Adverse drug reactions (ADRs) have become one of the primary reasons for the failure of drugs and a leading cause of deaths. Owing to the severe effects of ADRs, there is an urgent need for the generation of effective models which can accurately predict ADRs during early stages of drug development based on integration of various features of drugs. In the current study, we have focused on neurological ADRs and have used various properties of drugs that include biological properties (targets, transporters and enzymes), chemical properties (substructure fingerprints), phenotypic properties (side effects (SE) and therapeutic indications) and a combinations of the two and three levels of features. We employed relief-based feature selection technique to identify relevant properties and used mach

SUBMITTER: Jamal S 

PROVIDER: S-EPMC5429831 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature