Towards a Unified Framework for Protein Interaction Site Prediction Using Hierarchical Protein Representations
- 1University of Alabama at Birmingham, United States
Abstract
Proteins interact with a wide range of biomolecular partners, yet identifying the interaction sites that mediate these events remains a major challenge for understanding cellular function and guiding drug discovery. Existing computational methods are typically designed for specific interaction classes and often rely on task-specific features. Here, we introduce PRIME-ISP, a structure-based framework for predicting interaction sites across diverse biomolecular interaction types using a unified architecture. PRIME-ISP represents proteins at five organizational levels, including solvent-excluded surfaces, atoms, residues, secondary-structure elements, and whole proteins, and integrates information across these scales through coupled bottom-up and top-down propagation. This hierarchical representation jointly captures local geometry and global structural context, enabling a single architecture to address chemically and geometrically distinct binding problems without task-specific modifications. We evaluate PRIME-ISP on protein, peptide, DNA, RNA, small-molecule, metal, and carbohydrate interaction-site prediction benchmarks. Across these tasks, PRIME-ISP consistently outperforms a recent unified sequence-based predictor and achieves performance comparable to specialized methods while requiring no interaction-specific features. These results demonstrate that hierarchical structural representations provide a flexible foundation for interaction-site prediction across diverse biomolecular interactions. Source code and data are publicly available at https://github.com/HySonLab/PRIME-ISP
Related
- An extensible deep learning framework for multi-type chromatin interaction prediction through hierarchical adaptation strategies
- HMVA-DDI: A Hierarchical Multi-View Attention Network for Drug-Drug Interaction and Severity Prediction
- Alcohol and tobacco in cancer: A unified framework of interaction across carcinogenic pathways and cancer types
- A unified framework for quantitative splicing and transcript prediction
- PeTMiner: Mining plant endogenous target mimics via ternary interaction modeling with hierarchical attention and adaptive weighted loss
BibTeX
@misc{nguyen2026towards,
title = {{Towards a Unified Framework for Protein Interaction Site Prediction Using Hierarchical Protein Representations}},
author = {V. T. D. Nguyen and J. K. Johnstone and T.-S. Hy},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.18.759950},
url = {https://www.biorxiv.org/content/10.64898/2026.10.18.759950v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Towards a Unified Framework for Protein Interaction Site Prediction Using Hierarchical Protein Representations
AU - V. T. D. Nguyen
AU - J. K. Johnstone
AU - T.-S. Hy
PY - 2026
DA - 2026/10/18
PB - bioRxiv
DO - 10.64898/2026.10.18.759950
UR - https://www.biorxiv.org/content/10.64898/2026.10.18.759950v1
AB - Proteins interact with a wide range of biomolecular partners, yet identifying the interaction sites that mediate these events remains a major challenge for understanding cellular function and guiding drug discovery. Existing computational methods are typically designed for specific interaction classes and often rely on task-specific features. Here, we introduce PRIME-ISP, a structure-based framework for predicting interaction sites across diverse biomolecular interaction types using a unified architecture. PRIME-ISP represents proteins at five organizational levels, including solvent-excluded surfaces, atoms, residues, secondary-structure elements, and whole proteins, and integrates information across these scales through coupled bottom-up and top-down propagation. This hierarchical representation jointly captures local geometry and global structural context, enabling a single architecture to address chemically and geometrically distinct binding problems without task-specific modifications. We evaluate PRIME-ISP on protein, peptide, DNA, RNA, small-molecule, metal, and carbohydrate interaction-site prediction benchmarks. Across these tasks, PRIME-ISP consistently outperforms a recent unified sequence-based predictor and achieves performance comparable to specialized methods while requiring no interaction-specific features. These results demonstrate that hierarchical structural representations provide a flexible foundation for interaction-site prediction across diverse biomolecular interactions. Source code and data are publicly available at https://github.com/HySonLab/PRIME-ISP
ER -