Drug Side Effect Profiles as Molecular Descriptors for Predictive Modeling of Target Bioactivity

Abstract

We have explored the potential of using side effect profiles of drugs to predict their bioactivities at the receptor level. Serotonin 5-HT6 binding and dopamine antagonism were investigated in separate studies. A set of 5-HT6 binders and non-binders was retrieved from the PDSP Ki database, whereas dopamine antagonists were retrieved from the MeSH Pharmaceutical Action file. The side effect data was extracted from ChemoText, a data repository containing MeSH annotations pulled from MEDLINE records. These side effects profiles were treated as molecular descriptors enabling a QSAR-like approach to build models that could reliably discriminate different classes of molecules, e.g., binders versus non-binders, and dopamine antagonists versus non-antagonists. Selected models with the best external prediction performances were applied to a library of ca. 1000 chemicals with known side effects profiles in order to predict their potential 5-HT6 binding and/or dopamine antagonism. In each case the virtual screening process was able to identify putatively active compounds that through subsequent literature-based validation were found to be likely or known 5-HT6 binders or dopamine antagonists. These results demonstrate that side effect profiles can be utilized to predict a drug's unknown molecular activity, thus representing a valuable opportunity in repositioning the drug for a new indications.

Keywords: Drug repurposing; Machine learning; QSAR; Side effects.