Predicting Chemical Properties using Self-Attention Multi-task Learning based on SMILES Representation

TL;DR

This paper introduces a novel self-attention based multi-task learning model for predicting chemical properties from SMILES representations, demonstrating competitive performance on benchmark datasets.

Contribution

The study proposes a new self-attention model tailored for chemical property prediction, improving upon existing transformer-based approaches in a multi-task learning setting.

Findings

Achieved competitive results on benchmark datasets

Demonstrated effectiveness of self-attention in multi-task learning for chemistry

Provided open-source code and datasets for reproducibility

Abstract

In the computational prediction of chemical compound properties, molecular descriptors and fingerprints encoded to low dimensional vectors are used. The selection of proper molecular descriptors and fingerprints is both important and challenging as the performance of such models is highly dependent on descriptors. To overcome this challenge, natural language processing models that utilize simplified molecular input line-entry system as input were studied, and several transformer-variant models achieved superior results when compared with conventional methods. In this study, we explored the structural differences of the transformer-variant model and proposed a new self-attention based model. The representation learning performance of the self-attention module was evaluated in a multi-task learning environment using imbalanced chemical datasets. The experiment results showed that our model achieved competitive outcomes on several benchmark datasets. The source code of our experiment is available at https://github.com/arwhirang/sa-mtl and the dataset is available from the same URL.