Language models in molecular discovery

TL;DR

This paper reviews how language models, especially transformer-based ones, are transforming molecular discovery by aiding drug design, property prediction, and reaction chemistry, and discusses future integration with computational tools.

Contribution

It provides a comprehensive overview of the current role of language models in molecular discovery and introduces a vision for future AI-augmented chemical research.

Findings

Language models accelerate early-stage drug discovery.

Open-source tools lower barriers to scientific language modeling.

Future integration of chatbots with chemistry tools is envisioned.

Abstract

The success of language models, especially transformer-based architectures, has trickled into other domains giving rise to "scientific language models" that operate on small molecules, proteins or polymers. In chemistry, language models contribute to accelerating the molecule discovery cycle as evidenced by promising recent findings in early-stage drug discovery. Here, we review the role of language models in molecular discovery, underlining their strength in de novo drug design, property prediction and reaction chemistry. We highlight valuable open-source software assets thus lowering the entry barrier to the field of scientific language modeling. Last, we sketch a vision for future molecular design that combines a chatbot interface with access to computational chemistry tools. Our contribution serves as a valuable resource for researchers, chemists, and AI enthusiasts interested in understanding how language models can and will be used to accelerate chemical discovery.