2025/04/05 by Md Toki Tahmid, A.K.M. Mehedi Hasan, Md. Shamsuzzoha Bayzid · 1 voice
Biochemistry, Genetics and Molecular Biology · #Machine Learning in Bioinformatics #RNA and protein synthesis mechanisms #Protein Structure and Dynamics
paper · pdf · doi:10.1038/s42003-025-07534-w
openalex publication_date 2025/04/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/23
Identifying DNA-binding proteins and their binding residues is critical for understanding diverse biological processes, but conventional experimental approaches are slow and costly. Existing machine learning methods, while faster, often lack accuracy and struggle with data imbalance, relying heavily on evolutionary profiles like PSSMs and HMMs derived from multiple sequence alignments (MSAs). These dependencies make them unsuitable for orphan proteins or those that evolve rapidly. To address these challenges, we introduce TransBind, an alignment-free deep learning framework that predicts DNA-binding proteins and residues directly from a single primary sequence, eliminating the need for MSAs. By leveraging features from pre-trained protein language models, TransBind effectively handles the issue of data imbalance and achieves superior performance. Extensive evaluations using diverse experimental datasets and case studies demonstrate that TransBind significantly outperforms state-of-the-art methods in terms of both accuracy and computational efficiency. TransBind is available as a web server at https://trans-bind-web-server-frontend.vercel.app/ . An alignment-free deep learning framework predicts DNA-binding proteins and residues from primary sequences, eliminating multiple sequence alignments (MSAs). It uses protein language models and class-weighted training to address data imbalance and improve accuracy.