BERT Learns (and Teaches) Chemistry

Modern computational organic chemistry is becoming increasingly data-driven. There remain a large number of important unsolved problems in this area such as product prediction given reactants, drug discovery, and metric-optimized molecule synthesis, but efforts to solve these problems using machine...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Payne, Josh, Srouji, Mario, Dian Ang Yap, Kosaraju, Vineet
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.07.2020
Subjects
Chemical properties
Chemical synthesis
Chemistry
Convolution
Datasets
Functional groups
Graphical representations
Machine learning
Molecular structure
Organic chemistry
Substructures
Toxicity
Online AccessGet full text

Cover

More Information
Summary:Modern computational organic chemistry is becoming increasingly data-driven. There remain a large number of important unsolved problems in this area such as product prediction given reactants, drug discovery, and metric-optimized molecule synthesis, but efforts to solve these problems using machine learning have also increased in recent years. In this work, we propose the use of attention to study functional groups and other property-impacting molecular substructures from a data-driven perspective, using a transformer-based model (BERT) on datasets of string representations of molecules and analyzing the behavior of its attention heads. We then apply the representations of functional groups and atoms learned by the model to tackle problems of toxicity, solubility, drug-likeness, and synthesis accessibility on smaller datasets using the learned representations as features for graph convolution and attention models on the graph structure of molecules, as well as fine-tuning of BERT. Finally, we propose the use of attention visualization as a helpful tool for chemistry practitioners and students to quickly identify important substructures in various chemical properties.
ISSN:2331-8422