{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/janusddg-a-thermodynamics-compliant-model-for","title":"JanusDDG: A Thermodynamics-Compliant Model for Sequence-Based Protein Stability via Two-Fronts Multi-Head Attention","arxiv_id":"2504.03278","date":"2025-04-04","proceeding":null,"authors":["Guido Barducci","Ivan Rossi","Francesco Codicè","Cesare Rollo","Valeria Repetto","Corrado Pancotti","Virginia Iannibelli","Tiziana Sanavia","Piero Fariselli"],"abstract":"Understanding how residue variations affect protein stability is crucial for designing functional proteins and deciphering the molecular mechanisms underlying disease-related mutations. Recent advances in protein language models (PLMs) have revolutionized computational protein analysis, enabling, among other things, more accurate predictions of mutational effects. In this work, we introduce JanusDDG, a deep learning framework that leverages PLM-derived embeddings and a bidirectional cross-attention transformer architecture to predict $\\Delta \\Delta G$ of single and multiple-residue mutations while simultaneously being constrained to respect fundamental thermodynamic properties, such as antisymmetry and transitivity. Unlike conventional self-attention, JanusDDG computes queries (Q) and values (V) as the difference between wild-type and mutant embeddings, while keys (K) alternate between the two. This cross-interleaved attention mechanism enables the model to capture mutation-induced perturbations while preserving essential contextual information. Experimental results show that JanusDDG achieves state-of-the-art performance in predicting $\\Delta \\Delta G$ from sequence alone, matching or exceeding the accuracy of structure-based methods for both single and multiple mutations. Code Availability:https://github.com/compbiomed-unito/JanusDDG","url_abs":"https://arxiv.org/abs/2504.03278v2","url_pdf":"https://arxiv.org/pdf/2504.03278v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"janusddg-a-thermodynamics-compliant-model-for","repo_url":"https://github.com/compbiomed-unito/JanusDDG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}