PPIM-Struct: Leveraging Structural Embeddings for Predicting Protein-Protein Interaction Modulator Interactions
Issued Date
2025-06-04
Resource Type
Scopus ID
2-s2.0-105016332454
Journal Title
Iccbb 2024 Proceedings of the 2024 8th International Conference on Computational Biology and Bioinformatics
Start Page
20
End Page
24
Rights Holder(s)
SCOPUS
Bibliographic Citation
Iccbb 2024 Proceedings of the 2024 8th International Conference on Computational Biology and Bioinformatics (2025) , 20-24
Suggested Citation
Chiaranaipanich J., Achakulvisut T. PPIM-Struct: Leveraging Structural Embeddings for Predicting Protein-Protein Interaction Modulator Interactions. Iccbb 2024 Proceedings of the 2024 8th International Conference on Computational Biology and Bioinformatics (2025) , 20-24. 24. doi:10.1145/3715020.3715041 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/112270
Title
PPIM-Struct: Leveraging Structural Embeddings for Predicting Protein-Protein Interaction Modulator Interactions
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Protein-protein interactions (PPIs) are the basis of many important biological functions. However, previous studies mainly use chemical information such as charge and hydrophobicity to predict PPI modulators, which ignores 2D and 3D structural information that contributes to protein-protein modulator interactions. We develop PPIM-Struct, a structure-based method to predict the interaction between modulators and protein-protein interactions, using GCN-based protein embeddings and comparing different pre-trained modulator embeddings. We found that applying Morgan fingerprints with PPIM-Struct achieves the best F1-score of 82.2% on PPI-modulator interaction prediction, 9.6% and 8.6% higher than using GCN and Transformer embeddings, respectively. The high performance of Morgan fingerprint embeddings highlights the usefulness of a subgraph-level tokenizer for efficient molecular representations. We think this work can be extended to structural representations of similar chemicals, such as peptides, prodrugs, and lipids.