EXCERPT

This article will provide an overview of some recent breakthroughs of deep learning-based language models in molecular biology. We will discuss how these advances will converge with the direct training of LLMs on large-scale biomolecular and population health data in the coming years and propel the field forward. Given that LLMs and deep learning are familiar to a broader audience than is molecular biology, we begin with a brief overview of LLMs, continue with a more detailed introduction to molecular biology, then proceed to describe a few recent LLM advances in molecular biology, and finally glance at the future.