Skip to content
DraconiticResearch
Search Sources API
223,421 studies31 sourcesUpdated 34 min ago
Peer-reviewedCC BYPLOS Computational Biology

Beyond unseen entities: Auditable cold-start evaluation for drug interaction prediction

  • Xiaoqing Ru1,2,3
  • Yansu Wang2
  • Quan Zou2
  • Mengting Niu2,4
4 affiliations
  1. 1The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou, China.
  2. 2Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, China.
  3. 3Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, Republic of Korea.
  4. 4School of Electronic and Communication Engineering, Shenzhen Polytechnic University, Shenzhen, China.
Read full textPDFDOICite

Abstract

Reliable generalization is essential for deploying drug–drug interaction (DDI) and drug–target interaction (DTI) models in drug discovery, pharmacovigilance, and clinical decision support. However, strong performance on random splits or weakly constrained evaluations may not reflect how well a model generalizes to new drugs, targets, or deployment conditions. In pairwise prediction, test instances may still resemble training examples in molecular structure, sequence, or network context. Such overlap can inflate performance estimates and make interpolation appear to be extrapolation. In this Perspective, we argue that cold-start evaluation should be treated as an auditable deployment claim. We organize common evaluation settings by their source and scope of novelty, ranging from random splits and entity-disjoint protocols to structure-level, temporal, domain-disjoint, and many-domain evaluations. The L0–L5 framework clarifies which deployment claim each setting is designed to test. Coverage, overlap, and distance quantify the resulting train–test discrepancy. We further provide a practical checklist for leakage control, validation alignment, candidate-pair construction, and domain-level risk reporting. This Perspective clarifies the boundaries and evidential scope of cold-start evaluation, providing a common basis for interpreting and comparing results across DDI and DTI studies.

Related

  1. Establishing standardized evaluation protocols for peptide-target interaction prediction: the PTI-TAPE consensus framework eDelphi
    William J. Waldock, Guangshun Wang, Ara Darzi +2
    Frontiers in bioinformaticsPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  2. BRIDGE-KO: auditable transfer learning with bridged knockoffs improves cross-cohort microbiome prediction of immunotherapy response
    Briefings in bioinformaticsPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  3. DeepEnzyKat: Turnover number prediction through enzyme-substrate interaction modeling and adaptive expert ensembles
    Guangran Zhang, Yujing Zhao, Yongwen Zhang +6
    ChemRxivPreprintCC BYMolecular biology & gene regulationChemRxiv
  4. A novel matrix multiplication framework for modeling genotype-by-environment interaction in genomic prediction
    Osval A. Montesinos-López, Abelardo Montesinos-López, Cricelio Montesinos-Lopez +5
    Frontiers in geneticsPeer-reviewedCC BYFull textGeneral biochemistryEurope PMC
  5. BioGraphBench-PPI enables audit-first evaluation of negative-sampling contracts and structural baselines in protein interaction networks
    Alejandro Cabrera-Andrade, Jorge Robalino-Díaz, Iván Dueñas-Espín +2
    Frontiers in bioinformaticsPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC

Cite

BibTeXRIS
BibTeX
@article{ru2026beyond,
  title = {{Beyond unseen entities: Auditable cold-start evaluation for drug interaction prediction}},
  author = {Xiaoqing Ru and Yansu Wang and Quan Zou and Mengting Niu},
  journal = {PLOS Computational Biology},
  year = {2026},
  month = nov,
  doi = {10.1371/journal.pcbi.1014927},
  url = {https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014927},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Beyond unseen entities: Auditable cold-start evaluation for drug interaction prediction
AU  - Xiaoqing Ru
AU  - Yansu Wang
AU  - Quan Zou
AU  - Mengting Niu
PY  - 2026
DA  - 2026/11/10
JO  - PLOS Computational Biology
DO  - 10.1371/journal.pcbi.1014927
UR  - https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014927
AB  - Reliable generalization is essential for deploying drug–drug interaction (DDI) and drug–target interaction (DTI) models in drug discovery, pharmacovigilance, and clinical decision support. However, strong performance on random splits or weakly constrained evaluations may not reflect how well a model generalizes to new drugs, targets, or deployment conditions. In pairwise prediction, test instances may still resemble training examples in molecular structure, sequence, or network context. Such overlap can inflate performance estimates and make interpolation appear to be extrapolation. In this Perspective, we argue that cold-start evaluation should be treated as an auditable deployment claim. We organize common evaluation settings by their source and scope of novelty, ranging from random splits and entity-disjoint protocols to structure-level, temporal, domain-disjoint, and many-domain evaluations. The L0–L5 framework clarifies which deployment claim each setting is designed to test. Coverage, overlap, and distance quantify the resulting train–test discrepancy. We further provide a practical checklist for leakage control, validation alignment, candidate-pair construction, and domain-level risk reporting. This Perspective clarifies the boundaries and evidential scope of cold-start evaluation, providing a common basis for interpreting and comparing results across DDI and DTI studies.
SN  - 1553-7358
SN  - 1553-734X
ER  -