Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases

RİFAİOĞLU A. S. , Atas H., Martin M. J. , Cetin-Atalay R., Atalay V., Dogan T.

BRIEFINGS IN BIOINFORMATICS, vol.20, no.5, pp.1878-1912, 2019 (Journal Indexed in SCI) identifier identifier identifier

  • Publication Type: Article / Review
  • Volume: 20 Issue: 5
  • Publication Date: 2019
  • Doi Number: 10.1093/bib/bby061
  • Page Numbers: pp.1878-1912
  • Keywords: virtual screening, drug-target interactions, ligand-based VS and proteochemometric modelling, machine learning, deep learning, compound and bioactivity databases, gold-standard data sets, LARGE-SCALE PREDICTION, MEASURING SEMANTIC SIMILARITY, TARGET INTERACTIONS, PROTEIN-STRUCTURE, WEB SERVER, NEURAL-NETWORKS, PHYSICOCHEMICAL FEATURES, TOPOLOGICAL DESCRIPTORS, MOLECULAR DOCKING, SCORING FUNCTIONS


The identification of interactions between drugs/compounds and their targets is crucial for the development of new drugs. In vitro screening experiments (i.e. bioassays) are frequently used for this purpose; however, experimental approaches are insufficient to explore novel drug-target interactions, mainly because of feasibility problems, as they are labour intensive, costly and time consuming. A computational field known as 'virtual screening' (VS) has emerged in the past decades to aid experimental drug discovery studies by statistically estimating unknown bio-interactions between compounds and biological targets. These methods use the physico-chemical and structural properties of compounds and/or target proteins along with the experimentally verified bio-interaction information to generate predictive models. Lately, sophisticated machine learning techniques are applied in VS to elevate the predictive performance.