CAFNet-DG: Task-Specific Modeling and Prevalence-Aware Evaluation for Adverse Drug Reaction Prioritization with Ordinal-Frequency Estimation.
- 1College of Electronic Information, Hunan First Normal University, Changsha 410205, China.
- 2School of Computer Science and Technology, Changsha University of Science and Technology, Changsha 410114, China.
Abstract
Adverse drug reaction (ADR) prioritization and ordinal-frequency estimation are related but distinct prediction objectives, while aggregate ranking performance in sparse annotation matrices can be strongly influenced by frequently annotated side effects. Within CAFNet-DG, CAFNet-D uses task-specific association and ordinal-frequency functions built on shared molecular-relational representations, while annotation prevalence is evaluated explicitly within each training fold. On a SIDER-derived dataset comprising 750 drugs and 994 side effects, replacing a shared output with task-specific functions produced the largest joint change in staged drug-disjoint ablation, increasing mAP from 0.340 to 0.382 and reducing RMSE from 1.754 to 1.142. A prevalence-only ranking achieved an mAP of 0.410, close to the CAFNet-DG value of 0.413, indicating that aggregate ADR ranking is strongly associated with the benchmark annotation distribution. Prevalence-matched, prevalence-stratified, frequently annotated side-effect removal, and per-drug analyses were therefore used to distinguish drug-conditioned ranking variation from global annotation-prevalence effects. An equal-weight same-architecture ensemble control yielded no significant differences from CAFNet-DG across seven ranking metrics after Holm correction; generic variance reduction therefore could not be excluded as an explanation for the modest score-integration gain. Scaffold-disjoint and independent-data evaluations showed modest transfer, while ordinal-frequency agreement on CT-ADE remained limited. The results support the CAFNet-D task-specific formulation and prevalence-aware evaluation, while CAFNet-DG provides the score-integration setting examined under matched ensemble controls.
Related
- Evaluation of Computational Neoantigen Prioritization Strategies for Personalized Cancer Vaccines.
- Accurate calling of low-frequency somatic mutations by sample-specific modeling of error rates
- Molecular Approach to Bovine Mastitis Control: In Vitro Evaluation of Pathogen-Specific IgY Antibodies in a Host–Pathogen Epithelial Challenge Model of Bovine Mammary Epithelium
- Integrative Transcriptomics and Machine Learning Nominate IL15- and PPP2R1A-Centered Programs in PTSD Using Pathway-Informed Autonomic–Cardiac Gene Prioritization
- MCOF: A Multi-Channel Attention-Based Omics Fusion Framework for Cancer Subtyping and Candidate Biomarker Prioritization
BibTeX
@article{li2026cafnetdg,
title = {{CAFNet-DG: Task-Specific Modeling and Prevalence-Aware Evaluation for Adverse Drug Reaction Prioritization with Ordinal-Frequency Estimation.}},
author = {Wen Li and Zhiyu Xu and Xiangqiong Wu and Ju Xiang and Xiaojie Zhang},
journal = {International journal of molecular sciences},
year = {2026},
month = sep,
doi = {10.3390/ijms27198685},
url = {https://europepmc.org/article/MED/42883930},
note = {CC BY},
}
RIS
TY - JOUR
TI - CAFNet-DG: Task-Specific Modeling and Prevalence-Aware Evaluation for Adverse Drug Reaction Prioritization with Ordinal-Frequency Estimation.
AU - Wen Li
AU - Zhiyu Xu
AU - Xiangqiong Wu
AU - Ju Xiang
AU - Xiaojie Zhang
PY - 2026
DA - 2026/09/28
JO - International journal of molecular sciences
DO - 10.3390/ijms27198685
UR - https://europepmc.org/article/MED/42883930
AB - Adverse drug reaction (ADR) prioritization and ordinal-frequency estimation are related but distinct prediction objectives, while aggregate ranking performance in sparse annotation matrices can be strongly influenced by frequently annotated side effects. Within CAFNet-DG, CAFNet-D uses task-specific association and ordinal-frequency functions built on shared molecular-relational representations, while annotation prevalence is evaluated explicitly within each training fold. On a SIDER-derived dataset comprising 750 drugs and 994 side effects, replacing a shared output with task-specific functions produced the largest joint change in staged drug-disjoint ablation, increasing mAP from 0.340 to 0.382 and reducing RMSE from 1.754 to 1.142. A prevalence-only ranking achieved an mAP of 0.410, close to the CAFNet-DG value of 0.413, indicating that aggregate ADR ranking is strongly associated with the benchmark annotation distribution. Prevalence-matched, prevalence-stratified, frequently annotated side-effect removal, and per-drug analyses were therefore used to distinguish drug-conditioned ranking variation from global annotation-prevalence effects. An equal-weight same-architecture ensemble control yielded no significant differences from CAFNet-DG across seven ranking metrics after Holm correction; generic variance reduction therefore could not be excluded as an explanation for the modest score-integration gain. Scaffold-disjoint and independent-data evaluations showed modest transfer, while ordinal-frequency agreement on CT-ADE remained limited. The results support the CAFNet-D task-specific formulation and prevalence-aware evaluation, while CAFNet-DG provides the score-integration setting examined under matched ensemble controls.
SN - 1422-0067
ER -