2026-10-13T03:22:42Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34040247 2026-10-01T06:04:10Z category_1 category_4 category_7 category_13 category_14 category_734 category_931 category_132 category_133 category_135 portal_63 item_type_6 month_year_10_2026

Prediction of Residue-Level Base Preference for DNA-Binding Proteins Using a Multimodal Learning Framework Siyuan Li (178640) Wenyan He (10221187) Mengru Zhang (650401) Xin Zhang (35492) Wei-Qun Fang (25153221) Min-Juan Xu (5701733) Yi Shi (169113) Yujia Cai (8377134) Yong Zhang (5893) Lin-Tai Da (399373) Biophysics Biochemistry Medicine Genetics Molecular Biology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Infectious Diseases Plant Biology Computational Biology remains experimentally uncharacterized purely computational pipeline protein surface pointclouds holistic protein representation guide rapid reprogramming comprehensive benchmarking demonstrates specific binding motif desired base specificities also tolerant toward level base preference designing new dbps binding proteins using base preference preference predictions modal base binding specificity binding proteins binding motifs world applications two real throughput manner accurately predict 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. 2026-10-01T00:00:00Z Text Journal contribution 10.1021/jacsau.6c00925.s001 https://figshare.com/articles/journal_contribution/Prediction_of_Residue-Level_Base_Preference_for_DNA-Binding_Proteins_Using_a_Multimodal_Learning_Framework/34040247 CC BY-NC 4.0