GenSPARC: Generalized Structure- and Property-Aware Representations of Language Models for Compound-Protein Interaction Prediction
Authors:
Preprint
- 8 May 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Compound-protein interaction (CPI) prediction plays a crucial role in drug discovery by aiding the identification of binding and affinities between small molecules and proteins. Current deep learning models rely heavily on sequence-based representations and suffer from a lack of labeled data, which restricts their accuracy and generalizability. To overcome these challenges, we propose GenSPARC ( Gen eralized S tructure and P roperty A ware R epresentation for C PI prediction), a deep learning model that leverages structure-aware protein representations derived from AlphaFold2 predictions and Foldseek’s 3D interaction alphabet. Compound features were extracted using graph convolutional networks and a pretrained chemical language model, thereby ensuring comprehensive multimodal representation. A novel attention mechanism further enhanced interaction modeling by capturing intricate binding patterns. GenSPARC was validated successfully with multiple CPI benchmark datasets, demonstrating strong generalizability across challenging data splits and competitive results in virtual screening tasks. Therefore, GenSPARC will substantially advance artificial intelligence-driven drug discovery.Keywords
All Related Versions
- Version 1, 2025-05-08, Research Square
- Published version: Communications Chemistry, 9 (1).
This publication has 50 references indexed in Scilit:
- Evaluation of AlphaFold2 structures as docking targetsProtein Science, 2022
- Evaluating GPCR modeling and docking strategies in the era of deep learning-based protein structure predictionComputational and Structural Biotechnology Journal, 2022
- Explainable Deep Relational Networks for Predicting Compound–Protein Affinities and ContactsJournal of Chemical Information and Modeling, 2020
- Group sparse regularization for deep neural networksNeurocomputing, 2017
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009
- Recommendations for evaluation of computational methodsJournal of Computer-Aided Molecular Design, 2008
- What do we know and when do we know it?Journal of Computer-Aided Molecular Design, 2008
- Improved protein–ligand docking using GOLDProteins: Structure, Function, and Bioinformatics, 2003
- The role of protein 3D-structures in the drug discovery process2003
- The art and practice of structure-based drug design: A molecular modeling perspectiveMedicinal Research Reviews, 1996