ADMET modeling approaches in drug discovery

Leonardo L G Ferreira; Adriano D Andricopulo

doi:10.1016/j.drudis.2019.03.015

ADMET modeling approaches in drug discovery

Drug Discov Today. 2019 May;24(5):1157-1165. doi: 10.1016/j.drudis.2019.03.015. Epub 2019 Mar 16.

Authors

Leonardo L G Ferreira¹, Adriano D Andricopulo²

Affiliations

¹ Laboratory of Medicinal and Computational Chemistry, Center for Research and Innovation in Biodiversity and Drug Discovery, Physics Institute of Sao Carlos, University of Sao Paulo, Av. Joao Dagnone 1100, 13563-120, Sao Carlos, SP, Brazil.
² Laboratory of Medicinal and Computational Chemistry, Center for Research and Innovation in Biodiversity and Drug Discovery, Physics Institute of Sao Carlos, University of Sao Paulo, Av. Joao Dagnone 1100, 13563-120, Sao Carlos, SP, Brazil. Electronic address: aandrico@ifsc.usp.br.

PMID: 30890362
DOI: 10.1016/j.drudis.2019.03.015

Abstract

In silico prediction of ADMET is an important component of pharmaceutical R&D. Last year, the FDA approved 59 new molecular entities, with small molecules comprising 64% of the therapies approved in 2018. Estimation of pharmacokinetic properties in the early phases of drug discovery has been central to guiding hit-to-lead and lead-optimization efforts. Given the outstanding complexity of the current R&D model, drug discovery players have intensely pursued molecular modeling strategies to identify patterns in ADMET data and convert them into knowledge. The field has advanced alongside the progress of chemoinformatics, which has evolved from traditional chemometrics to advanced machine learning methods.

Publication types

Research Support, Non-U.S. Gov't
Review

MeSH terms

Animals
Drug Discovery*
Drug-Related Side Effects and Adverse Reactions*
Humans
Machine Learning
Models, Biological*
Pharmaceutical Preparations / metabolism
Pharmacokinetics*

Substances

Pharmaceutical Preparations