ProteomeLM: A Proteome-Scale Language Model Enables Accurate and Rapid Prediction of Protein-Protein Interactions and Gene Essentiality Across Taxa

Cyril Malbranke, Gionata Paolo Zalaffi, Anne-Florence Bitbol

Keywords: protein language models, protein-protein interactions, gene essentiality, coevolution, proteomics

TL;DR: ProteomeLM is a transformer trained on entire proteomes across the tree of life that learns protein-protein interactions without supervision and enables interactome-wide screening six orders of magnitude faster than existing methods.

Abstract: Language models trained on biological sequences are advancing inference tasks from the scale of single proteins to that of genomic neighborhoods. Here, we introduce ProteomeLM, a transformer-based language model that uniquely operates on entire proteomes from species spanning the tree of life. ProteomeLM is trained to reconstruct masked protein embeddings using the whole proteomic context, yielding contextualized protein representations that reflect proteome-scale functional constraints. Notably, ProteomeLM's attention coefficients encode protein-protein interactions~(PPI), despite being trained without interaction labels. Furthermore, it enables interactome-wide PPI screening that is substantially more accurate, and orders of magnitude faster, than amino-acid coevolution-based methods. We further develop ProteomeLM-PPI, a supervised model that combines ProteomeLM embeddings and attention coefficients to achieve state-of-the-art PPI prediction across benchmarks and species. Finally, we introduce ProteomeLM-Ess, a supervised gene essentiality predictor that generalizes across diverse taxa. Our results demonstrate the potential of proteome-scale language models for addressing function and interactions at the organism level.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 101