Translation between Molecules and Natural Language

TL;DR

MolT5 is a self-supervised framework that enables translation between molecules and natural language, facilitating tasks like molecule captioning and de novo molecule generation, addressing data scarcity in chemistry.

Contribution

Introduces MolT5, a novel self-supervised model for molecule-language translation, pioneering new cross-modal tasks in chemistry and improving generation quality.

Findings

Models produce high-quality molecule and caption outputs

Effective in molecule captioning and generation tasks

Addresses data scarcity in chemical domain

Abstract

We present $\textbf{MolT5}$ $-$ a self-supervised learning framework for pretraining models on a vast amount of unlabeled natural language text and molecule strings. $\textbf{MolT5}$ allows for new, useful, and challenging analogs of traditional vision-language tasks, such as molecule captioning and text-based de novo molecule generation (altogether: translation between molecules and language), which we explore for the first time. Since $\textbf{MolT5}$ pretrains models on single-modal data, it helps overcome the chemistry domain shortcoming of data scarcity. Furthermore, we consider several metrics, including a new cross-modal embedding-based metric, to evaluate the tasks of molecule captioning and text-based molecule generation. Our results show that $\textbf{MolT5}$-based models are able to generate outputs, both molecules and captions, which in many cases are high quality.