DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction
Abstract Predicting protein-ligand binding affinity is essential for understanding protein-ligand interactions and advancing drug discovery. Recent research has demonstrated the advantages of sequence-based models and graph-based models. In this study, we present a novel hybrid multimodal approach,...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-12-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-024-00938-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559184604135424 |
|---|---|
| author | Guishen Wang Hangchen Zhang Mengting Shao Yuncong Feng Chen Cao Xiaowen Hu |
| author_facet | Guishen Wang Hangchen Zhang Mengting Shao Yuncong Feng Chen Cao Xiaowen Hu |
| author_sort | Guishen Wang |
| collection | DOAJ |
| description | Abstract Predicting protein-ligand binding affinity is essential for understanding protein-ligand interactions and advancing drug discovery. Recent research has demonstrated the advantages of sequence-based models and graph-based models. In this study, we present a novel hybrid multimodal approach, DeepTGIN, which integrates transformers and graph isomorphism networks to predict protein-ligand binding affinity. DeepTGIN is designed to learn sequence and graph features efficiently. The DeepTGIN model comprises three modules: the data representation module, the encoder module, and the prediction module. The transformer encoder learns sequential features from proteins and protein pockets separately, while the graph isomorphism network extracts graph features from the ligands. To evaluate the performance of DeepTGIN, we compared it with state-of-the-art models using the PDBbind 2016 core set and PDBbind 2013 core set. DeepTGIN outperforms these models in terms of R, RMSE, MAE, SD, and CI metrics. Ablation studies further demonstrate the effectiveness of the ligand features and the encoder module. The code is available at: https://github.com/zhc-moushang/DeepTGIN . Scientific contribution DeepTGIN is a novel hybrid multimodal deep learning model for predict protein-ligand binding affinity. The model combines the Transformer encoder to extract sequence features from protein and protein pocket, while integrating graph isomorphism networks to capture features from the ligand. This model addresses the limitations of existing methods in exploring protein pocket and ligand features. |
| format | Article |
| id | doaj-art-fb9d3db7f0aa4d759133daa9c520f6f0 |
| institution | Kabale University |
| issn | 1758-2946 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj-art-fb9d3db7f0aa4d759133daa9c520f6f02025-01-05T12:44:16ZengBMCJournal of Cheminformatics1758-29462024-12-0116111210.1186/s13321-024-00938-6DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity predictionGuishen Wang0Hangchen Zhang1Mengting Shao2Yuncong Feng3Chen Cao4Xiaowen Hu5College of Computer Science and Engineering, Changchun University of TechnologyCollege of Computer Science and Engineering, Changchun University of TechnologyKey Laboratory for Bio-Electromagnetic Environment and Advanced Medical Theranostics, School of Biomedical Engineering and Informatics, Nanjing Medical UniversityCollege of Computer Science and Engineering, Changchun University of TechnologyKey Laboratory for Bio-Electromagnetic Environment and Advanced Medical Theranostics, School of Biomedical Engineering and Informatics, Nanjing Medical UniversitySchool of Biomedical Engineering and Informatics, Nanjing Medical UniversityAbstract Predicting protein-ligand binding affinity is essential for understanding protein-ligand interactions and advancing drug discovery. Recent research has demonstrated the advantages of sequence-based models and graph-based models. In this study, we present a novel hybrid multimodal approach, DeepTGIN, which integrates transformers and graph isomorphism networks to predict protein-ligand binding affinity. DeepTGIN is designed to learn sequence and graph features efficiently. The DeepTGIN model comprises three modules: the data representation module, the encoder module, and the prediction module. The transformer encoder learns sequential features from proteins and protein pockets separately, while the graph isomorphism network extracts graph features from the ligands. To evaluate the performance of DeepTGIN, we compared it with state-of-the-art models using the PDBbind 2016 core set and PDBbind 2013 core set. DeepTGIN outperforms these models in terms of R, RMSE, MAE, SD, and CI metrics. Ablation studies further demonstrate the effectiveness of the ligand features and the encoder module. The code is available at: https://github.com/zhc-moushang/DeepTGIN . Scientific contribution DeepTGIN is a novel hybrid multimodal deep learning model for predict protein-ligand binding affinity. The model combines the Transformer encoder to extract sequence features from protein and protein pocket, while integrating graph isomorphism networks to capture features from the ligand. This model addresses the limitations of existing methods in exploring protein pocket and ligand features.https://doi.org/10.1186/s13321-024-00938-6Protein-ligand binding affinity predictionTransformerGraph isomorphism networkMultimodal |
| spellingShingle | Guishen Wang Hangchen Zhang Mengting Shao Yuncong Feng Chen Cao Xiaowen Hu DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction Journal of Cheminformatics Protein-ligand binding affinity prediction Transformer Graph isomorphism network Multimodal |
| title | DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction |
| title_full | DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction |
| title_fullStr | DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction |
| title_full_unstemmed | DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction |
| title_short | DeepTGIN: a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein-ligand binding affinity prediction |
| title_sort | deeptgin a novel hybrid multimodal approach using transformers and graph isomorphism networks for protein ligand binding affinity prediction |
| topic | Protein-ligand binding affinity prediction Transformer Graph isomorphism network Multimodal |
| url | https://doi.org/10.1186/s13321-024-00938-6 |
| work_keys_str_mv | AT guishenwang deeptginanovelhybridmultimodalapproachusingtransformersandgraphisomorphismnetworksforproteinligandbindingaffinityprediction AT hangchenzhang deeptginanovelhybridmultimodalapproachusingtransformersandgraphisomorphismnetworksforproteinligandbindingaffinityprediction AT mengtingshao deeptginanovelhybridmultimodalapproachusingtransformersandgraphisomorphismnetworksforproteinligandbindingaffinityprediction AT yuncongfeng deeptginanovelhybridmultimodalapproachusingtransformersandgraphisomorphismnetworksforproteinligandbindingaffinityprediction AT chencao deeptginanovelhybridmultimodalapproachusingtransformersandgraphisomorphismnetworksforproteinligandbindingaffinityprediction AT xiaowenhu deeptginanovelhybridmultimodalapproachusingtransformersandgraphisomorphismnetworksforproteinligandbindingaffinityprediction |