Evolutionary-scale prediction of atomic-level protein structure with a language model

It is shown that direct inference of structure from primary sequence using a large language model enables an order of magnitude speed-up in high resolution structure prediction, which results in prediction that is up to 60x faster than state-of-the-art while maintaining resolution and accuracy.

Abstract

Recent advances in machine learning have leveraged evolutionary information in multiple sequence alignments to predict protein structure. We demonstrate direct inference of full atomic-level protein structure from primary sequence using a large language model. As language models of protein sequences are scaled up to 15 billion parameters, an atomic-resolution picture of protein structure emerges in the learned representations. This results in an order-of-magnitude acceleration of high-resolution structure prediction, which enables large-scale structural characterization of metagenomic proteins. We apply this capability to construct the ESM Metagenomic Atlas by predicting structures for >617 million metagenomic protein sequences, including >225 million that are predicted with high confidence, which gives a view into the vast breadth and diversity of natural proteins.