Daoyun Ding

Daoyun Ding

Auto-generated profile, based on publicly available information

Daoyun Ding

Department of Computer Sciences, University of Wisconsin–Madison, Madison, Wisconsin, USA

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
YYYifan Yang
Yifan Yang
DLDehan Li
Dehan Li
DDDaoyun Ding
Daoyun Ding
LSLingfeng Shi
Lingfeng Shi
HZHan Zhou
Han Zhou
YLYang Young Lu
Yang Young Lu
Protein language models (PLMs) are powerful predictors of protein interactions, but strong benchmark performance does not ensure reliable discoveries. We introduce PPI-Caliper, a model-agnostic framework that adapts conformal calibration to select interactions at user-specified false discovery rate (FDR) levels using held-out labels without retraining the predictor. Across five species, two PLM-based predictors, and two human training-data versions for each predictor, PPI-Caliper keeps empirical FDR at or below the target level under in-distribution calibration. Under distribution shift, transferred thresholds tend to become conservative when predictive performance improves, but can fail to control FDR when performance deteriorates. PPI-Caliper connects pre-trained interaction scores to explicit error targets and demonstrates why reliable biological discovery requires evaluating calibration alongside predictive accuracy.