Protein language model embedded geometric graphs power inter-protein contact prediction

Si, Yunda; Yan, Chengfei

doi:10.1101/2023.01.07.523121

Cited by 4 publications

(2 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the transformative progress brought by deep learning to protein structure prediction [2][3][4][5], predicting protein complex structure and ligand binding sites is fast advancing with AFM and related methods, but also with other deep learning models based on structural representations [73][74][75][76]. Combining the latter [77,78] and, more generally, structural information [79] with the power of sequence-based language models is starting to bring even further progress.…”

Section: Discussionmentioning

confidence: 99%

Pairing interacting protein sequences using masked language modeling

Lupo

Sgarbossa

Bitbol

2023

Preprint

View full text Add to dashboard Cite

Predicting which proteins interact together from amino-acid sequences is an important task. We develop a method to pair interacting protein sequences which leverages the power of protein language models trained on multiple sequence alignments, such as MSA Transformer and the EvoFormer module of AlphaFold. We formulate the problem of pairing interacting partners among the paralogs of two protein families in a differentiable way. We introduce a method called DiffPALM that solves it by exploiting the ability of MSA Transformer to fill in masked amino acids in multiple sequence alignments using the surrounding context. MSA Transformer encodes coevolution between functionally or structurally coupled amino acids. We show that it captures inter-chain coevolution, while it was trained on single-chain data, which means that it can be used out-of-distribution. Relying on MSA Transformer without fine-tuning, DiffPALM outperforms existing coevolution-based pairing methods on difficult benchmarks of shallow multiple sequence alignments extracted from ubiquitous prokaryotic protein datasets. It also outperforms an alternative method based on a state-of-the-art protein language model trained on single sequences. Paired alignments of interacting protein sequences are a crucial ingredient of supervised deep learning methods to predict the three-dimensional structure of protein complexes. DiffPALM substantially improves the structure prediction of some eukaryotic protein complexes by AlphaFold-Multimer, without significantly deteriorating any of those we tested. It also achieves competitive performance with using orthology-based pairing.

show abstract

Section: Discussionmentioning

confidence: 99%

Pairing interacting protein sequences using masked language modeling

Lupo

Sgarbossa

Bitbol

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This particular architecture was later combined with a generic transformer to create ESM-IF1 [33] which produces embeddings that consist of 512-dimensional vectors for each residue of a protein structure. The ESM-IF1 embeddings have been used for epitope prediction [34] and protein-protein interaction (PPI) prediction [35]. Successes such as these suggest that the embeddings contain task-relevant information relating to the protein function and biochemical activity.…”

Section: Introductionmentioning

confidence: 99%

Learnt representations of proteins can be used for accurate prediction of small molecule binding sites on experimentally determined and predicted protein structures

Carbery,

Buttenschoen,

Skyner

et al. 2023

Preprint

View full text Add to dashboard Cite

Protein-ligand binding site prediction is a useful tool for understanding the functional behaviour and potential drug-target interactions of a novel protein of interest. However, most binding site prediction methods are tested by providing crystallised ligand-bound (holo) structures as input. This testing regime is insufficient to understand the performance on novel protein targets where experimental structures are not available. An alternative option is to provide computationally predicted protein structures, but this is not commonly tested. However, due to the training data used, computationally-predicted protein structures tend to be extremely accurate, and are often biased toward a holo conformation. In this study we describe and benchmark IF-SitePred, a protein-ligand binding site prediction method which is based on the labelling of ESM-IF1 protein language model embeddings combined with point cloud annotation and clustering. We show that not only is IF-SitePred competitive with state-of-the-art methods when predicting binding sites on experimental structures, but it performs better on proxies for novel proteins where low accuracy has been simulated by molecular dynamics. Finally, IF-SitePred outperforms other methods if ensembles of predicted protein structures are generated.

show abstract