Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 43 min ago
Peer-reviewedCC BY-NC-ND 4.0BMC Bioinformatics

CHAMS-DTA: cross hybrid attention with multi-stage sampling for drug-target binding affinity prediction

  1. 1Software and Big Data Technology Department, Dalian Neusoft University of Information, Dalian, 116023 Liaoning China
  2. 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

  1. EVALUATING MOLECULAR DYNAMICS FRAMES FOR BINDING AFFINITY PREDICTION AND VIRTUAL SCREENING
    Jakub Poziemski, Pawel Siedlecki
    ChemRxivPreprintCC BYFull textGeneral chemistryChemRxiv
  2. Quantitative Protein–Ligand Binding Affinity Prediction from Quantum-Mechanical Scoring
    Jindřich Fanfrlík, Adam Pecina, Martin Lepšík +1
    ChemRxivPreprintCC BY-NC-NDFull textGeneral chemistryChemRxiv
  3. Reliability of AI Methods in Drug Discovery: Evaluation of Boltz-2 for Structure and Binding Affinity Prediction
    Shunzhou Wan, Xibei Zhang, Xue Xiao +1
    Journal of Chemical Theory and ComputationPeer-reviewedCC BYFull text23 citedMedicinal chemistry & drug discoveryOpenAlex
  4. AlphaDTA: integrating AlphaFold3 embeddings and 3D complex structures for drug–target binding affinity prediction
    Minjae Chung, Sejin Park, Hyunju Lee
    Journal of CheminformaticsPeer-reviewedCC BYFull textTheoretical & computational chemistryDOAJ
  5. StructRSMA: A Proof-of-Concept Framework for PDB-Derived Contact-Supervised Transfer in RNA-Small Molecule Binding Affinity Prediction
    Yuxin Wen, Yi Tian, Nguyen Quoc Khanh Le +1
    ACS OmegaPeer-reviewedCC BY 4.0Full textGeneral chemistryCrossref
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  -