ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing

TL;DR

This paper demonstrates that large-scale self-supervised language models trained on protein sequences can effectively capture biophysical features and outperform traditional methods in predicting protein structure and localization, without relying on evolutionary data.

Contribution

The study introduces a suite of protein language models trained on massive datasets using high-performance computing, achieving state-of-the-art results in structural and localization predictions without evolutionary information.

Findings

Protein embeddings capture biophysical features.

Models outperform state-of-the-art in secondary structure prediction.

Embeddings enable accurate localization and membrane classification.

Abstract

Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models taken from NLP. These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The LMs were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw protein LM-embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks. The first was a per-residue prediction of protein secondary structure (3-state accuracy Q3=81%-87%); the second were per-protein predictions of protein sub-cellular localization (ten-state accuracy: Q10=81%) and membrane vs. water-soluble (2-state accuracy Q2=91%). For the per-residue predictions the transfer of the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without using evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that protein LMs learned some of the grammar of the language of life. To facilitate future work, we released our models at https://github.com/agemagician/ProtTrans.