CHAMS-DTA: cross hybrid attention with multi-stage sampling for drug-target binding affinity prediction
- 1Software and Big Data Technology Department, Dalian Neusoft University of Information, Dalian, 116023 Liaoning China
- 2Neusoft Research Institute, Dalian Neusoft University of Information, 8 Software Park Road, Ganjingzi District, Dalian City, 116023 Liaoning Province China
Abstract
Accurate prediction of drug-target binding affinity is crucial for computational drug discovery. In this work, we evaluate CHAMS-DTA on the standard kinase-centric benchmarks Davis and KIBA. We propose CHAMS-DTA, a three-stage coarse-to-fine framework that integrates cross-hybrid attention and adaptive gated fusion to progressively refine feature selection. At each stage, a cross-hybrid attention is used to capture both global interactions between the protein and drug molecules and local contextual information within the input sequences. This enables more accurate identification of key functional sites in both the protein and drug. Furthermore, an adaptive gated fusion mechanism is designed to selectively integrate cross-stage representations using learnable gates. This allows the model to dynamically determine the relative contribution of features from each stage. The proposed framework achieves not only high predictive accuracy but also provides initial insights into the model’s attention patterns, offering a degree of interpretability. Experimental results demonstrate that CHAMS-DTA achieves improved performance on specific evaluation metrics: the Concordance Index (CI) on the Davis dataset and the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}rm2\end{document} metric on the KIBA dataset.
Related
- EVALUATING MOLECULAR DYNAMICS FRAMES FOR BINDING AFFINITY PREDICTION AND VIRTUAL SCREENING
- Quantitative Protein–Ligand Binding Affinity Prediction from Quantum-Mechanical Scoring
- Reliability of AI Methods in Drug Discovery: Evaluation of Boltz-2 for Structure and Binding Affinity Prediction
- AlphaDTA: integrating AlphaFold3 embeddings and 3D complex structures for drug–target binding affinity prediction
- StructRSMA: A Proof-of-Concept Framework for PDB-Derived Contact-Supervised Transfer in RNA-Small Molecule Binding Affinity Prediction
BibTeX
@article{han2026chamsdta,
title = {{CHAMS-DTA: cross hybrid attention with multi-stage sampling for drug-target binding affinity prediction}},
author = {Li Han and Xinning Liu and Hui Zhou and Lei Zhao and Ling Kang and Quan Guo},
journal = {BMC Bioinformatics},
year = {2026},
month = aug,
doi = {10.1186/s12859-026-06608-8},
url = {https://doi.org/10.1186/s12859-026-06608-8},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - CHAMS-DTA: cross hybrid attention with multi-stage sampling for drug-target binding affinity prediction
AU - Li Han
AU - Xinning Liu
AU - Hui Zhou
AU - Lei Zhao
AU - Ling Kang
AU - Quan Guo
PY - 2026
DA - 2026/08/27
JO - BMC Bioinformatics
DO - 10.1186/s12859-026-06608-8
UR - https://doi.org/10.1186/s12859-026-06608-8
AB - Accurate prediction of drug-target binding affinity is crucial for computational drug discovery. In this work, we evaluate CHAMS-DTA on the standard kinase-centric benchmarks Davis and KIBA. We propose CHAMS-DTA, a three-stage coarse-to-fine framework that integrates cross-hybrid attention and adaptive gated fusion to progressively refine feature selection. At each stage, a cross-hybrid attention is used to capture both global interactions between the protein and drug molecules and local contextual information within the input sequences. This enables more accurate identification of key functional sites in both the protein and drug. Furthermore, an adaptive gated fusion mechanism is designed to selectively integrate cross-stage representations using learnable gates. This allows the model to dynamically determine the relative contribution of features from each stage. The proposed framework achieves not only high predictive accuracy but also provides initial insights into the model’s attention patterns, offering a degree of interpretability. Experimental results demonstrate that CHAMS-DTA achieves improved performance on specific evaluation metrics: the Concordance Index (CI) on the Davis dataset and the \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}r_m^2\end{document} metric on the KIBA dataset.
SN - 1471-2105
ER -