PuSH - Publication Server of Helmholtz Zentrum München

Barducci, G.* ; Rossi, I.* ; Codice, F.* ; Rollo, C.* ; Repetto, V.* ; Pancotti, C. ; Iannibelli, V.* ; Sanavia, T.* ; Fariselli, P.*

JanusDDG: A physics-informed neural network for sequence-based protein stability via two-fronts attention.

Comm. Biol. 9:494 (2026)
Publ. Version/Full Text Research data DOI
Open Access Gold
Creative Commons Lizenzvertrag
Predicting how residue variations affect protein stability is crucial for rational protein design and for assessing the impact of disease-related mutations. Recent advances in protein language models have revolutionized computational protein analysis, enabling more accurate predictions of mutational effects. However, balancing predictive accuracy with the fundamental laws of thermodynamics remains a challenge for sequence-based models. Here we show JanusDDG, a physics-informed neural network that leverages embeddings from protein language models and a bidirectional cross-attention transformer architecture to predict stability changes for both single and multiple residue mutations. By adopting a physics-informed paradigm, the model is explicitly constrained to satisfy fundamental thermodynamic principles, such as antisymmetry and transitivity, while maintaining high predictive performance. Instead of conventional self-attention, JanusDDG employs a cross-interleaved attention mechanism that computes the relationship between wild-type and mutant embeddings to capture mutation-induced perturbations while preserving essential contextual information. Our results demonstrate that JanusDDG achieves state-of-the-art performance in predicting stability changes from sequence alone, matching or exceeding the accuracy of structure-based methods for both single and multiple mutations.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords Prediction; Database
ISSN (print) / ISBN 2399-3642
e-ISSN 2399-3642
Journal Communications Biology
Quellenangaben Volume: 9, Issue: 1, Pages: , Article Number: 494 Supplement: ,
Publisher Springer
Publishing Place London
Reviewing status Peer reviewed
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Grants Italian Ministry of University and Research through the "Grant for Internationalization" program
Fondazione Compagnia di San Paolo