BERT Learns (and Teaches) Chemistry
arXiv:2007.16012
Abstract
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.
arXiv comment10 pages, 5 figures
References in corpus (10)
- Semi-Supervised Classification with Graph Convolutional Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Inductive Representation Learning on Large Graphs
- Reasoning about Entailment with Neural Attention
- Few-Shot Learning with Graph Neural Networks
- Massively Multitask Networks for Drug Discovery
- Multi-Task Deep Neural Networks for Natural Language Understanding
- exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models
- Identifying and Controlling Important Neurons in Neural Machine Translation
- Discovering Molecular Functional Groups Using Graph Convolutional Neural Networks