Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated 5 min ago
Peer-reviewedCC BYBioinformatics

PCIM-DTA: pairwise conditional interaction modeling for drug–target affinity prediction under cold-start scenarios

  • Ziyou Zhou1,2
  • Min Chen2
  • 周文剑2
  • Qiong Xiao2
  1. 1Hunan Chuanshan Electronic Technology Co., Ltd , Hengyang, Hunan 421002,
  2. 2School of Computer Science and Engineering, Hunan Institute of Technology , Hengyang, Hunan 421002,
Open at sourcePDFDOICite

Abstract

MOTIVATION: Cold-start drug-target affinity prediction remains challenging because static interaction mechanisms cannot adapt to individual drug-target pairs. RESULTS: We propose PCIM-DTA, which constructs pair-level interaction representations and derives a pair-specific condition vector from global drug and target features. The condition vector modulates attention, pair-token features, distribution-aware recalibration, and regression parameters, while graph message passing captures higher-order dependencies. Experiments on Davis and BindingDB-Kd show that PCIM-DTA achieves competitive or superior performance under Warm, Cold-drug, Cold-target, Cold-both, and Scaffold-drug settings. Ablation studies support the contribution of each component. AVAILABILITY AND IMPLEMENTATION: The datasets used in this study are publicly available, including the Davis and BindingDB-Kd datasets. The implementation code of PCIM-DTA is publicly available at https://github.com/1322469934/PCIM-DTA.

Related

  1. HierL2GDTA: Hierarchical Interaction Modeling with Local and Global Features for Drug–Target Affinity Prediction
    Kaili Wang, Yaoxiang Yin, Yanglan Gan +2
    MoleculesPeer-reviewedCC BY 4.0General chemistryCrossref
  2. Microsolvation of Charged PAH Clusters: Modeling Interaction of Water Aggregates with Cationic Pyrene Dimer
    Héloïse Leboucher, Mathias Rapacioli, Aude Simon
    ACS Earth and Space ChemistryPeer-reviewedCC BY-NC-ND 4.0Full text1 citedTheoretical & computational chemistryHAL
  3. A historical journey of metabolite–protein interaction discovery: from data harmonization to AI-driven prediction
    Toby Lawrence, Ema Mocsonokyova, Adwait Mahesh Barde +4
    Briefings in BioinformaticsPeer-reviewedCC BY1 citedBioinformatics & computational biologyGeneral chemistryHAL
  4. From Reinforcement to Prediction: Mechanical Behavior and Modeling of CNT-Reinforced Cementitious Composites
    Nicolò Rimondotto, Alice Rossi, Matteo Pavese +1
    NanomaterialsPeer-reviewedCC BY 4.0Materials & polymersCrossref
  5. PolyGLOT: Graph-Token Language Modeling for Unified Polymer Property Prediction and Programmable Generation
    Tianle Yue, Ying Li
    ChemRxivPreprintCC BY-NC-NDFull textMaterials & polymersChemRxiv

Cite

BibTeXRIS
BibTeX
@article{zhou2026pcimdta,
  title = {{PCIM-DTA: pairwise conditional interaction modeling for drug–target affinity prediction under cold-start scenarios}},
  author = {Ziyou Zhou and Min Chen and 周文剑 and Qiong Xiao},
  journal = {Bioinformatics},
  year = {2026},
  month = aug,
  doi = {10.1093/bioinformatics/btag646},
  url = {https://doi.org/10.1093/bioinformatics/btag646},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - PCIM-DTA: pairwise conditional interaction modeling for drug–target affinity prediction under cold-start scenarios
AU  - Ziyou Zhou
AU  - Min Chen
AU  - 周文剑
AU  - Qiong Xiao
PY  - 2026
DA  - 2026/08/31
JO  - Bioinformatics
DO  - 10.1093/bioinformatics/btag646
UR  - https://doi.org/10.1093/bioinformatics/btag646
AB  - MOTIVATION: Cold-start drug-target affinity prediction remains challenging because static interaction mechanisms cannot adapt to individual drug-target pairs. RESULTS: We propose PCIM-DTA, which constructs pair-level interaction representations and derives a pair-specific condition vector from global drug and target features. The condition vector modulates attention, pair-token features, distribution-aware recalibration, and regression parameters, while graph message passing captures higher-order dependencies. Experiments on Davis and BindingDB-Kd show that PCIM-DTA achieves competitive or superior performance under Warm, Cold-drug, Cold-target, Cold-both, and Scaffold-drug settings. Ablation studies support the contribution of each component. AVAILABILITY AND IMPLEMENTATION: The datasets used in this study are publicly available, including the Davis and BindingDB-Kd datasets. The implementation code of PCIM-DTA is publicly available at https://github.com/1322469934/PCIM-DTA.
SN  - 1367-4803
SN  - 1367-4811
ER  -