Saturday, May 9, 2026

MuFaDDG: A Sequence-Based Multiscale Feature Fusion Framework for Protein Stability Changes Prediction

Gong J, Ma P, Ren Z, Li S, Fu Z, Sun P, Ni M, Bo X. MuFaDDG: A Sequence-Based Multiscale Feature Fusion Framework for Protein Stability Changes Prediction. Bioinformatics. 2026 Apr 29:btag196. doi: 10.1093/bioinformatics/btag196. Epub ahead of print. PMID: 42057285.  

The study introduces MuFaDDG, a sequence-based tool for predicting protein stability changes. Frataxin was used as the primary case study (via the CAGI5 challenge) to validate the model's performance. MuFaDDG achieved high accuracy (ACC: 0.81) in predicting how mutations affect frataxin's stability, outperforming existing state-of-the-art methods.Conclusion: The model proves highly effective at identifying destabilizing mutations in frataxin, which is critical for understanding diseases like Friedreich's Ataxia.