6 Deep Learning in Drug Discovery

被引：451

作者：

Gawehn, Erik ^{[1
]}

Hiss, Jan A. ^{[1
]}

Schneider, Gisbert ^{[1
]}

机构：

[1] ETH, Swiss Fed Inst Technol, Dept Chem & Appl Biosci, Vladimir Prelog Weg 4, CH-8093 Zurich, Switzerland

来源：

MOLECULAR INFORMATICS | 2016年 / 35卷 / 01期

基金：

瑞士国家科学基金会;

关键词：

bioinformatics; cheminformatics; drug design; machine-learning; neural network; virtual screening; ARTIFICIAL NEURAL-NETWORKS; SUPPORT VECTOR MACHINE; APPLICABILITY DOMAIN; SECONDARY STRUCTURE; PROTEIN-STRUCTURE; BIG DATA; DESIGN; TOOLS; REPRESENTATION; ARCHITECTURES;

D O I：

10.1002/minf.201501008

中图分类号：

R914 [药物化学];

学科分类号：

100701 ;

摘要：

Artificial neural networks had their first heyday in molecular informatics and drug discovery approximately two decades ago. Currently, we are witnessing renewed interest in adapting advanced neural network architectures for pharmaceutical research by borrowing from the field of deep learning. Compared with some of the other life sciences, their application in drug discovery is still limited. Here, we provide an overview of this emerging field of molecular informatics, present the basic concepts of prominent deep learning methods and offer motivation to explore these techniques for their usefulness in computer-assisted drug discovery and design. We specifically emphasize deep neural networks, restricted Boltzmann machine networks and convolutional networks.

引用

页码：3 / 14

页数：12

共 166 条

[1]

ACKLEY DH, 1985, COGNITIVE SCI, V9, P147

[2] Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research [J].