ParaAntiProt provides paratope prediction using antibody and protein language models
Abstract Efficiently predicting the paratope holds immense potential for enhancing antibody design, treating cancers and other serious diseases, and advancing personalized medicine. Although traditional methods are highly accurate, they are often time-consuming, labor-intensive, and reliant on 3D st...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-80940-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846147906394914816 |
|---|---|
| author | Mahmood Kalemati Alireza Noroozi Aref Shahbakhsh Somayyeh Koohi |
| author_facet | Mahmood Kalemati Alireza Noroozi Aref Shahbakhsh Somayyeh Koohi |
| author_sort | Mahmood Kalemati |
| collection | DOAJ |
| description | Abstract Efficiently predicting the paratope holds immense potential for enhancing antibody design, treating cancers and other serious diseases, and advancing personalized medicine. Although traditional methods are highly accurate, they are often time-consuming, labor-intensive, and reliant on 3D structures, restricting their broader use. On the other hand, machine learning-based methods, besides relying on structural data, entail descriptor computation, consideration of diverse physicochemical properties, and feature engineering. Here, we develop a deep learning-assisted prediction method for paratope identification, relying solely on amino acid sequences and being antigen-agnostic. Built on the ProtTrans architecture, and utilizing pre-trained protein and antibody language models, we extract efficient embeddings for predicting paratope. By incorporating positional encoding for Complementarity Determining Regions, our model gains a deeper structural understanding, achieving remarkable performance with a 0.904 ROC AUC, 0.701 F1-score, and 0.585 MCC on benchmark datasets. In addition to yielding accurate antibody paratope predictions, our method exhibits strong performance in predicting nanobody paratope, achieving a ROC AUC of 0.912 and a PR AUC of 0.665 on the nanobody dataset. Notably, our approach outperforms structure-based prediction methods, boasting a PR AUC of 0.731. Various conducted ablation studies, which elaborate on the impact of each part of the model on the prediction task, show that the improvement in prediction performance by applying CDR positional encoding together with CNNs depends on the specific protein and antibody language models used. These results highlight the potential of our method to advance disease understanding and aid in the discovery of new diagnostics and antibody therapies. |
| format | Article |
| id | doaj-art-a65f9b14e0204a7d81b44e5c17d22e4d |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-a65f9b14e0204a7d81b44e5c17d22e4d2024-12-01T12:18:20ZengNature PortfolioScientific Reports2045-23222024-11-0114111510.1038/s41598-024-80940-yParaAntiProt provides paratope prediction using antibody and protein language modelsMahmood Kalemati0Alireza Noroozi1Aref Shahbakhsh2Somayyeh Koohi3Department of Computer Engineering, Sharif University of TechnologyDepartment of Computer Engineering, Sharif University of TechnologyDepartment of Computer Engineering, Sharif University of TechnologyDepartment of Computer Engineering, Sharif University of TechnologyAbstract Efficiently predicting the paratope holds immense potential for enhancing antibody design, treating cancers and other serious diseases, and advancing personalized medicine. Although traditional methods are highly accurate, they are often time-consuming, labor-intensive, and reliant on 3D structures, restricting their broader use. On the other hand, machine learning-based methods, besides relying on structural data, entail descriptor computation, consideration of diverse physicochemical properties, and feature engineering. Here, we develop a deep learning-assisted prediction method for paratope identification, relying solely on amino acid sequences and being antigen-agnostic. Built on the ProtTrans architecture, and utilizing pre-trained protein and antibody language models, we extract efficient embeddings for predicting paratope. By incorporating positional encoding for Complementarity Determining Regions, our model gains a deeper structural understanding, achieving remarkable performance with a 0.904 ROC AUC, 0.701 F1-score, and 0.585 MCC on benchmark datasets. In addition to yielding accurate antibody paratope predictions, our method exhibits strong performance in predicting nanobody paratope, achieving a ROC AUC of 0.912 and a PR AUC of 0.665 on the nanobody dataset. Notably, our approach outperforms structure-based prediction methods, boasting a PR AUC of 0.731. Various conducted ablation studies, which elaborate on the impact of each part of the model on the prediction task, show that the improvement in prediction performance by applying CDR positional encoding together with CNNs depends on the specific protein and antibody language models used. These results highlight the potential of our method to advance disease understanding and aid in the discovery of new diagnostics and antibody therapies.https://doi.org/10.1038/s41598-024-80940-yParatope predictionAntibody Language modelsProtein Language modelsComplementarity determining regionsDeep learning |
| spellingShingle | Mahmood Kalemati Alireza Noroozi Aref Shahbakhsh Somayyeh Koohi ParaAntiProt provides paratope prediction using antibody and protein language models Scientific Reports Paratope prediction Antibody Language models Protein Language models Complementarity determining regions Deep learning |
| title | ParaAntiProt provides paratope prediction using antibody and protein language models |
| title_full | ParaAntiProt provides paratope prediction using antibody and protein language models |
| title_fullStr | ParaAntiProt provides paratope prediction using antibody and protein language models |
| title_full_unstemmed | ParaAntiProt provides paratope prediction using antibody and protein language models |
| title_short | ParaAntiProt provides paratope prediction using antibody and protein language models |
| title_sort | paraantiprot provides paratope prediction using antibody and protein language models |
| topic | Paratope prediction Antibody Language models Protein Language models Complementarity determining regions Deep learning |
| url | https://doi.org/10.1038/s41598-024-80940-y |
| work_keys_str_mv | AT mahmoodkalemati paraantiprotprovidesparatopepredictionusingantibodyandproteinlanguagemodels AT alirezanoroozi paraantiprotprovidesparatopepredictionusingantibodyandproteinlanguagemodels AT arefshahbakhsh paraantiprotprovidesparatopepredictionusingantibodyandproteinlanguagemodels AT somayyehkoohi paraantiprotprovidesparatopepredictionusingantibodyandproteinlanguagemodels |