Skip to content
Log in
Open access

Expanding the scope of protein language modeling to protein-protein interactions with MSA Pairformer.

Yo Akiyama Zhidian Zhang Olivia Tang R. Kim M. Mirdita Martin Steinegger Sergey Ovchinnikov
Jul 2026 · Cell · 2 citations · 100 references
Medicine

TL;DR

Multiple sequence alignment (MSA) Pairformer is presented, a protein language model that builds on AlphaFold2/3's bidirectional refinement between sequence and pairwise residue representations to accurately model the evolution of protein-protein interactions, despite training exclusively on individual chains.

Abstract

Protein-protein interactions underlie biological complexity, and modeling their coevolution is essential for characterizing and engineering molecular assemblies. While protein and genomic language models have excelled at modeling individual proteins, extending these capabilities to protein complexes remains challenging. We present multiple sequence alignment (MSA) Pairformer, a protein language model that builds on AlphaFold2/3's bidirectional refinement between sequence and pairwise residue representations to accurately model the evolution of protein-protein interactions, despite training exclusively on individual chains. MSA Pairformer achieves nearly 3-fold improvement over existing methods in predicting protein-protein interface contacts and better distinguishes binding from non-binding sequences. A learned attention mechanism selectively weights sequences by their inferred evolutionary relevance, enabling discovery of subfamily-specific contacts. On single-protein benchmarks, it achieves state-of-the-art contact prediction and strong variant effect prediction using only 111 million parameters, over two orders of magnitude smaller than frontier models. These results offer an evolutionarily grounded, computationally efficient alternative to the scaling paradigm.

DOI PubMed Semantic Scholar
Read PDF

Similar papers

Open access Jun 2026

Hybrid Approach to Protein–Protein Complex Affinity Prediction Based on Language Models and Molecular Dynamics

HyBind-NN is developed, a multimodal graph neural network that integrates protein language models (PLMs) with 3D structural and dynamic datasets to predict protein–protein and protein–peptide affinity, and it is demonstrated that combining ESM-2 sequence embeddings with precise 3D Voronoi spatial geometry enables accurate affinity predictions across diverse structural datasets.

E. A. Bogdanova, A. Chernukhin, Alexey K. Shaytan · 0 citations
Review Open access Jul 2026

Decoding viral protein sequences by large language models

This mini-review summarizes recent developments in devising and applying protein language models for biological sequences, emphasizing viral protein analysis, and outlines a road map for the potential application of LLMs in empowering virology research and pathogen surveillance.

Tianyi Fei, Siqi Li, Ziyue Yang et al. · 0 citations
Book Aug 2026

The Words of Proteins: Motif-Level Language Modeling for Interpretable Protein Generation

This work argues that explicitly modeling at the functional motif level provides both mechanistic insight into sequence-function relationships and interpretable control over protein generation, an important step toward compositional design of novel protein functions.

Boon How Low, W. Goh, Boyang Li et al. · 0 citations
Open access Aug 2026

PLMView: collaborative protein language model representations for fast and scalable specialized protein function inference

Applications to thioredoxins, visual opsins, and Tara Oceans environmental diatom cold-shock proteins show that PLMView can move from interpretable residue-level determinants in well-studied protein families to large-scale environmental functional discovery, linking molecular specialization to ecological distribution and transcriptional deployment across the global ocean.

Vinh-Son Pho, Alessandro Natale Bianchi, Mattéo Scarsini et al. · 0 citations
Jun 2026

Prot-ΔΔG: Prediction of protein–protein binding affinity changes upon mutations with pre-training strategies

Prot-ΔΔG is introduced, a purely sequence-based deep learning framework that integrates large-scale pre-trained protein language models with a BiGRU-DBRNN encoder that effectively captures evolutionary and context-dependent patterns without relying on structural inputs.

Han Zhou, Yuxiang Wang, Xiumin Shi et al. · 0 citations