Deep Learning in Drug Discovery

• Published in: Molecular informatics Vol. 35; no. 1; pp. 3 - 14
• Main Authors: Gawehn, Erik, Hiss, Jan A., Schneider, Gisbert
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY-VCH Verlag 01.01.2016; WILEY‐VCH Verlag; Wiley Subscription Services, Inc
• Subjects: Artificial Intelligence; bioinformatics; cheminformatics; Computational Biology - methods; drug design; Drug Discovery - methods; Humans; Informatics; Machine Learning; neural network; Neural networks; Neural Networks (Computer); Pharmaceutical industry; Proteomics - methods; virtual screening; machine-learning; virtual screening; drug design; neural network; bioinformatics; cheminformatics
• ISSN: 1868-1743; 1868-1751; 1868-1751
• DOI: 10.1002/minf.201501008

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.