ADMET modeling approaches in drug discovery

被引：489

作者：

Ferreira, Leonardo L. G. ^{[1
]}

Andricopulo, Adriano D. ^{[1
]}

机构：

[1] Univ Sao Paulo, Phys Inst Sao Carlos, Ctr Res & Innovat Biodivers & Drug Discovery, Lab Med & Computat Chem, Av Joao Dagnone 1100, BR-13563120 Sao Carlos, SP, Brazil

来源：

DRUG DISCOVERY TODAY | 2019年 / 24卷 / 05期

基金：

巴西圣保罗研究基金会;

关键词：

ORAL BIOAVAILABILITY; METABOLIC STABILITY; LEARNING-METHODS; RANDOM FOREST; PREDICTION; ABSORPTION; CLASSIFICATION; COMBINATORIAL; OPTIMIZATION; INTELLIGENCE;

D O I：

10.1016/j.drudis.2019.03.015

中图分类号：

R9 [药学];

学科分类号：

1007 ;

摘要：

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.

引用

页码：1157 / 1165

页数：9

共 71 条

[41] Property distribution of drug-related chemical databases [J].