Prediction of Residue-Level Base Preference for DNA-Binding Proteins Using a Multimodal Learning Framework
JACS Au · 26.10.2026 · 6 (10) · 5663-5678
DOI: 10.1021/jacsau.6c00925 ↗Kurz gefasst
Fachartikel in der Zeitschrift JACS Au, online erschienen am 01.10.2026. Verfasst von Siyuan Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Systems Biomedicine (Ministry of Education), Shanghai Center for Systems Biomedicine, Shanghai Jiao Tong University, Shanghai 20024…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Key Research and Development Program of China, Natural Science Foundation of Shanghai, National Natural Science Foundation of China (NSFC).
Abstract (Originalsprache)
Specific recognition between proteins and DNA governs essential cellular functions, yet the binding specificity of most DNA-binding proteins (DBPs) remains experimentally uncharacterized and high-throughput experimental methods still lag far behind the ever-growing protein data set. Here, we present 3M-BSIP (3-modal base-specific interaction predictor), a multimodal deep learning framework capable of predicting the DNA-binding interface and residue-level base preference for DBPs. 3M-BSIP constructs a holistic protein representation by integrating three distinct modalities: a protein language model capturing evolutionary conservation; a graph neural network encoding 3D structural features; and a hierarchical encoder characterizing physicochemical properties of protein surface pointclouds. Comprehensive benchmarking demonstrates that 3M-BSIP achieves SOTA performance on both interface-residue identification and base-preference predictions. Crucially, the model maintains robust performance on computationally constructed protein structures and is also tolerant toward those undergoing profound structural rearrangements upon DNA binding. Two real-world applications of 3M-BSIP demonstrate that our model not only can accurately predict the specific binding motif of structurally unknown transcription factors but also, more importantly, can guide rapid reprogramming of the base preference of DBPs based on a purely computational pipeline. Therefore, 3M-BSIP holds great potential in annotating the binding motifs of all DBPs in a high-throughput manner and designing new DBPs with desired base specificities.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Systems Biomedicine (Ministry of Education), Shanghai Center for Systems Biomedicine, Shanghai Jiao Tong University, Shanghai 200240, China.
- State Key Laboratory of Microbial Metabolism, School of Life Sciences and Biotechnology, and Joint International Research Laboratory of Metabolic & Developmental Sciences, Shanghai Jiao Tong University, Shanghai 200240,…
- Department of Pediatric Hematology/Oncology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai 200240, China.
- Department of Anesthesiology, Songjiang Research Institute, Shanghai Key Laboratory of Emotions and Affective Disorders, Songjiang Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai 200240…
- Bio-X Institutes, Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders, the Collaborative Innovation Center for Brain Science, and Brain Science and Technology Research Center, Shanghai Jiao T…
- Key Laboratory of Gene Editing and Cell-Based Immunotherapy for Hematological Diseases, Shanghai 200240, China.
ORCID-Profile: Siyuan Li, Min-Juan Xu, Yong Zhang, Lin-Tai Da
Förderung
- National Key Research and Development Program of China
- Natural Science Foundation of Shanghai
- National Natural Science Foundation of China (NSFC)
Zitieren
APA
Li, S., He, W., Zhang, M., Zhang, X., Fang, W. Q., Xu, M. J., Shi, Y., Cai, Y., Zhang, Y., & Da, L. T. (2026). Prediction of Residue-Level Base Preference for DNA-Binding Proteins Using a Multimodal Learning Framework. JACS Au, 6(10), 5663-5678. https://doi.org/10.1021/jacsau.6c00925
Vancouver
Li S, He W, Zhang M, Zhang X, Fang WQ, Xu MJ, et al. Prediction of Residue-Level Base Preference for DNA-Binding Proteins Using a Multimodal Learning Framework. JACS Au. 2026;6(10):5663-5678. doi:10.1021/jacsau.6c00925
BibTeX
@article{Li2026,
author = {Li, Siyuan and He, Wenyan and Zhang, Mengru and Zhang, Xin and Fang, Wei-Qun and Xu, Min-Juan and Shi, Yi and Cai, Yujia and Zhang, Yong and Da, Lin-Tai},
title = {Prediction of Residue-Level Base Preference for DNA-Binding Proteins Using a Multimodal Learning Framework},
journal = {JACS Au},
year = {2026},
volume = {6},
number = {10},
pages = {5663--5678},
doi = {10.1021/jacsau.6c00925}
}
EUVIMED