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

by   Ahmed Elnaggar, et al.

Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive language models (Transformer-XL, XLNet) and two auto-encoder models (Bert, Albert) on data from UniRef and BFD containing up to 393 billion amino acids (words) from 2.1 billion protein sequences (22- and 112-times the entire English Wikipedia). The LMs were trained on the Summit supercomputer at Oak Ridge National Laboratory (ORNL), using 936 nodes (total 5616 GPUs) and one TPU Pod (V3-512 or V3-1024). We validated the advantage of up-scaling LMs to larger models supported by bigger data by predicting secondary structure (3-states: Q3=76-84, 8-states: Q8=65-73), sub-cellular localization for 10 cellular compartments (Q10=74) and whether a protein is membrane-bound or water-soluble (Q2=89). Dimensionality reduction revealed that the LM-embeddings from unlabeled data (only protein sequences) captured important biophysical properties governing protein shape. This implied learning some of the grammar of the language of life realized in protein sequences. The successful up-scaling of protein LMs through HPC to larger data sets slightly reduced the gap between models trained on evolutionary information and LMs. The official GitHub repository:


page 6

page 9

page 10

page 16

page 25

page 27


Pre-training Protein Language Models with Label-Agnostic Binding Pairs Enhances Performance in Downstream Tasks

Less than 1 annotated. Natural Language Processing (NLP) community has r...

Modeling Protein Using Large-scale Pretrain Language Model

Protein is linked to almost every life process. Therefore, analyzing the...

ProGen2: Exploring the Boundaries of Protein Language Models

Attention-based models trained on protein sequences have demonstrated in...

OntoProtein: Protein Pretraining With Gene Ontology Embedding

Self-supervised protein language models have proved their effectiveness ...

Protein language models trained on multiple sequence alignments learn phylogenetic relationships

Self-supervised neural language models with attention have recently been...

BERTology Meets Biology: Interpreting Attention in Protein Language Models

Transformer architectures have proven to learn useful representations fo...

FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours

Protein structure prediction is an important method for understanding ge...

Code Repositories


Review of dataset and papers about protein structure design and prediction with deep learning.

view repo