Format

Send to

Choose Destination
J Comput Aided Mol Des. 2017 Apr;31(4):379-391. doi: 10.1007/s10822-016-0008-z. Epub 2017 Mar 9.

Bayesian molecular design with a chemical language model.

Author information

1
The Graduate University for Advanced Studies (SOKENDAI), Tachikawa, Japan.
2
Japan Advanced Institute of Science and Technology (JAIST), Nomi, Japan.
3
National Institute for Materials Science (NIMS), Tsukuba, Japan.
4
PRESTO, Japan Science and Technology Agency (JST), Kawaguchi, Japan.
5
The KAITEKI Institute, Inc., Tokyo, Japan.
6
The Graduate University for Advanced Studies (SOKENDAI), Tachikawa, Japan. yoshidar@ism.ac.jp.
7
National Institute for Materials Science (NIMS), Tsukuba, Japan. yoshidar@ism.ac.jp.
8
The Institute of Statistical Mathematics (ISM), Research Organization of Information and Systems, Tachikawa, Japan. yoshidar@ism.ac.jp.

Abstract

The aim of computational molecular design is the identification of promising hypothetical molecules with a predefined set of desired properties. We address the issue of accelerating the material discovery with state-of-the-art machine learning techniques. The method involves two different types of prediction; the forward and backward predictions. The objective of the forward prediction is to create a set of machine learning models on various properties of a given molecule. Inverting the trained forward models through Bayes' law, we derive a posterior distribution for the backward prediction, which is conditioned by a desired property requirement. Exploring high-probability regions of the posterior with a sequential Monte Carlo technique, molecules that exhibit the desired properties can computationally be created. One major difficulty in the computational creation of molecules is the exclusion of the occurrence of chemically unfavorable structures. To circumvent this issue, we derive a chemical language model that acquires commonly occurring patterns of chemical fragments through natural language processing of ASCII strings of existing compounds, which follow the SMILES chemical language notation. In the backward prediction, the trained language model is used to refine chemical strings such that the properties of the resulting structures fall within the desired property region while chemically unfavorable structures are successfully removed. The present method is demonstrated through the design of small organic molecules with the property requirements on HOMO-LUMO gap and internal energy. The R package iqspr is available at the CRAN repository.

KEYWORDS:

Bayesian analysis; Inverse-QSPR; Molecular design; Natural language processing; SMILES; Small organic molecules

PMID:
28281211
PMCID:
PMC5393296
DOI:
10.1007/s10822-016-0008-z
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Springer Icon for PubMed Central
Loading ...
Support Center