Exploring Chemical Space with Machine Learning

Authors

  • Josep Arús-Pous Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Bern, Freiestrasse 3, CH-3012 Bern
  • Mahendra Awale Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Bern, Freiestrasse 3, CH-3012 Bern
  • Daniel Probst Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Bern, Freiestrasse 3, CH-3012 Bern
  • Jean-Louis Reymond Department of Chemistry and Biochemistry, National Center for Competence in Research NCCR TransCure, University of Bern, Freiestrasse 3, CH-3012 Bern;, Email: jean-louis.reymond@dcb.unibe.ch

DOI:

https://doi.org/10.2533/chimia.2019.1018

PMID:

31883554

Keywords:

Chemical space, Data visualization, Deep learning, Molecular databases, Polypharmacology

Abstract

Chemical space is a concept to organize molecular diversity by postulating that different molecules occupy different regions of a mathematical space where the position of each molecule is defined by its properties. Our aim is to develop methods to explicitly explore chemical space in the area of drug discovery. Here we review our implementations of machine learning in this project, including our use of deep neural networks to enumerate the GDB13 database from a small sample set, to generate analogs of drugs and natural products after training with fragment-size molecules, and to predict the polypharmacology of molecules after training with known bioactive compounds from ChEMBL. We also discuss visualization methods for big data as means to keep track and learn from machine learning results. Computational tools discussed in this review are freely available at http://gdb.unibe.ch and https://github.com/reymond-group.

Downloads

Published

2019-12-18

How to Cite

[1]
J. Arús-Pous, M. Awale, D. Probst, J.-L. Reymond, Chimia 2019, 73, 1018, DOI: 10.2533/chimia.2019.1018.