Saved in:
Bibliographic Details
Main Authors: Payne, Josh, Srouji, Mario, Yap, Dian Ang, Kosaraju, Vineet
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2007.16012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915780611801088
author Payne, Josh
Srouji, Mario
Yap, Dian Ang
Kosaraju, Vineet
author_facet Payne, Josh
Srouji, Mario
Yap, Dian Ang
Kosaraju, Vineet
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2007_16012
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle BERT Learns (and Teaches) Chemistry
Payne, Josh
Srouji, Mario
Yap, Dian Ang
Kosaraju, Vineet
Biomolecules
Artificial Intelligence
Computation and Language
Machine Learning
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.
title BERT Learns (and Teaches) Chemistry
topic Biomolecules
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2007.16012