PPI Candidate Ranking: Large-Scale Evaluation of a Domain Knowledge–Guided Pipeline

Maria Emilia Russo, Federico Di Valerio, Alessia Borghini, Alessio Ragno, Roberto Capobianco
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:106387-106401, 2026.

Abstract

Computational approaches have become central to Protein–Protein Interaction (PPI) research, complementing experimental techniques that remain costly and incomplete. While modern deep learning methods capture diverse biological signals and hold promise in expanding the known interactome, empirical validation remains a critical bottleneck due to its long and expensive procedures. To address this challenge, we introduce the problem of PPI candidate ranking, aiming to prioritize interactions for experimental testing. We propose a novel framework that leverages domain knowledge through interpretability-guided ranking and further refines prioritization by integrating complementary sources of evidence, including interaction scores, structural plausibility, and biomedical language features. Evaluations on a large-scale dataset constructed from successive STRING releases demonstrate that our approach yields significant improvements over two state-of-the-art PPI prediction models, providing more accurate and biologically coherent rankings.

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-russo26b, title = {{PPI} Candidate Ranking: Large-Scale Evaluation of a Domain Knowledge–Guided Pipeline}, author = {Russo, Maria Emilia and Valerio, Federico Di and Borghini, Alessia and Ragno, Alessio and Capobianco, Roberto}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {106387--106401}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/russo26b/russo26b.pdf}, url = {https://proceedings.mlr.press/v306/russo26b.html}, abstract = {Computational approaches have become central to Protein–Protein Interaction (PPI) research, complementing experimental techniques that remain costly and incomplete. While modern deep learning methods capture diverse biological signals and hold promise in expanding the known interactome, empirical validation remains a critical bottleneck due to its long and expensive procedures. To address this challenge, we introduce the problem of PPI candidate ranking, aiming to prioritize interactions for experimental testing. We propose a novel framework that leverages domain knowledge through interpretability-guided ranking and further refines prioritization by integrating complementary sources of evidence, including interaction scores, structural plausibility, and biomedical language features. Evaluations on a large-scale dataset constructed from successive STRING releases demonstrate that our approach yields significant improvements over two state-of-the-art PPI prediction models, providing more accurate and biologically coherent rankings.} }
Endnote
%0 Conference Paper %T PPI Candidate Ranking: Large-Scale Evaluation of a Domain Knowledge–Guided Pipeline %A Maria Emilia Russo %A Federico Di Valerio %A Alessia Borghini %A Alessio Ragno %A Roberto Capobianco %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-russo26b %I PMLR %P 106387--106401 %U https://proceedings.mlr.press/v306/russo26b.html %V 306 %X Computational approaches have become central to Protein–Protein Interaction (PPI) research, complementing experimental techniques that remain costly and incomplete. While modern deep learning methods capture diverse biological signals and hold promise in expanding the known interactome, empirical validation remains a critical bottleneck due to its long and expensive procedures. To address this challenge, we introduce the problem of PPI candidate ranking, aiming to prioritize interactions for experimental testing. We propose a novel framework that leverages domain knowledge through interpretability-guided ranking and further refines prioritization by integrating complementary sources of evidence, including interaction scores, structural plausibility, and biomedical language features. Evaluations on a large-scale dataset constructed from successive STRING releases demonstrate that our approach yields significant improvements over two state-of-the-art PPI prediction models, providing more accurate and biologically coherent rankings.
APA
Russo, M.E., Valerio, F.D., Borghini, A., Ragno, A. & Capobianco, R.. (2026). PPI Candidate Ranking: Large-Scale Evaluation of a Domain Knowledge–Guided Pipeline. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:106387-106401 Available from https://proceedings.mlr.press/v306/russo26b.html.

Related Material