Journal of Computer-Aided Molecular Design

, Volume 30, Issue 8, pp 595–608

Molecular graph convolutions: moving beyond fingerprints

  • Steven Kearnes
  • Kevin McCloskey
  • Marc Berndl
  • Vijay Pande
  • Patrick Riley
Article

DOI: 10.1007/s10822-016-9938-8

Cite this article as:
Kearnes, S., McCloskey, K., Berndl, M. et al. J Comput Aided Mol Des (2016) 30: 595. doi:10.1007/s10822-016-9938-8

Abstract

Molecular “fingerprints” encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular graph convolutions, a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph—atoms, bonds, distances, etc.—which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

Keywords

Machine learning Virtual screening Deep learning Artificial neural networks Molecular descriptors 

Supplementary material

10822_2016_9938_MOESM1_ESM.pdf (1.2 mb)
Supplementary material 1 (pdf 1207 KB)

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Stanford UniversityStanfordUSA
  2. 2.Google Inc.Mountain ViewUSA