A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction Sites
The identification of protein–protein interaction (PPI) sites is essential in the research of protein function and the discovery of new drugs. So far, a variety of computational tools based on machine learning have been developed to accelerate the identification of PPI sites. However, existing metho...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Association for the Advancement of Science (AAAS)
2023-01-01
|
| Series: | Research |
| Online Access: | https://spj.science.org/doi/10.34133/research.0240 |
| _version_ | 1797280260942725120 |
|---|---|
| author | Minjie Mou Ziqi Pan Zhimeng Zhou Lingyan Zheng Hanyu Zhang Shuiyang Shi Fengcheng Li Xiuna Sun Feng Zhu |
| author_facet | Minjie Mou Ziqi Pan Zhimeng Zhou Lingyan Zheng Hanyu Zhang Shuiyang Shi Fengcheng Li Xiuna Sun Feng Zhu |
| author_sort | Minjie Mou |
| collection | DOAJ |
| description | The identification of protein–protein interaction (PPI) sites is essential in the research of protein function and the discovery of new drugs. So far, a variety of computational tools based on machine learning have been developed to accelerate the identification of PPI sites. However, existing methods suffer from the low predictive accuracy or the limited scope of application. Specifically, some methods learned only global or local sequential features, leading to low predictive accuracy, while others achieved improved performance by extracting residue interactions from structures but were limited in their application scope for the serious dependence on precise structure information. There is an urgent need to develop a method that integrates comprehensive information to realize proteome-wide accurate profiling of PPI sites. Herein, a novel ensemble framework for PPI sites prediction, EnsemPPIS, was therefore proposed based on transformer and gated convolutional networks. EnsemPPIS can effectively capture not only global and local patterns but also residue interactions. Specifically, EnsemPPIS was unique in (a) extracting residue interactions from protein sequences with transformer and (b) further integrating global and local sequential features with the ensemble learning strategy. Compared with various existing methods, EnsemPPIS exhibited either superior performance or broader applicability on multiple PPI sites prediction tasks. Moreover, pattern analysis based on the interpretability of EnsemPPIS demonstrated that EnsemPPIS was fully capable of learning residue interactions within the local structure of PPI sites using only sequence information. The web server of EnsemPPIS is freely available at http://idrblab.org/ensemppis. |
| first_indexed | 2024-03-07T16:37:38Z |
| format | Article |
| id | doaj.art-98873a96735c461d9ad43996250920c2 |
| institution | Directory Open Access Journal |
| issn | 2639-5274 |
| language | English |
| last_indexed | 2024-03-07T16:37:38Z |
| publishDate | 2023-01-01 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | Article |
| series | Research |
| spelling | doaj.art-98873a96735c461d9ad43996250920c22024-03-03T09:40:35ZengAmerican Association for the Advancement of Science (AAAS)Research2639-52742023-01-01610.34133/research.0240A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction SitesMinjie Mou0Ziqi Pan1Zhimeng Zhou2Lingyan Zheng3Hanyu Zhang4Shuiyang Shi5Fengcheng Li6Xiuna Sun7Feng Zhu8College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang UniversitySchool of Medicine, National Key Laboratory of Advanced Drug Delivery and Release Systems, Zhejiang University, Hangzhou 310058, China.The identification of protein–protein interaction (PPI) sites is essential in the research of protein function and the discovery of new drugs. So far, a variety of computational tools based on machine learning have been developed to accelerate the identification of PPI sites. However, existing methods suffer from the low predictive accuracy or the limited scope of application. Specifically, some methods learned only global or local sequential features, leading to low predictive accuracy, while others achieved improved performance by extracting residue interactions from structures but were limited in their application scope for the serious dependence on precise structure information. There is an urgent need to develop a method that integrates comprehensive information to realize proteome-wide accurate profiling of PPI sites. Herein, a novel ensemble framework for PPI sites prediction, EnsemPPIS, was therefore proposed based on transformer and gated convolutional networks. EnsemPPIS can effectively capture not only global and local patterns but also residue interactions. Specifically, EnsemPPIS was unique in (a) extracting residue interactions from protein sequences with transformer and (b) further integrating global and local sequential features with the ensemble learning strategy. Compared with various existing methods, EnsemPPIS exhibited either superior performance or broader applicability on multiple PPI sites prediction tasks. Moreover, pattern analysis based on the interpretability of EnsemPPIS demonstrated that EnsemPPIS was fully capable of learning residue interactions within the local structure of PPI sites using only sequence information. The web server of EnsemPPIS is freely available at http://idrblab.org/ensemppis.https://spj.science.org/doi/10.34133/research.0240 |
| spellingShingle | Minjie Mou Ziqi Pan Zhimeng Zhou Lingyan Zheng Hanyu Zhang Shuiyang Shi Fengcheng Li Xiuna Sun Feng Zhu A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction Sites Research |
| title | A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction Sites |
| title_full | A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction Sites |
| title_fullStr | A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction Sites |
| title_full_unstemmed | A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction Sites |
| title_short | A Transformer-Based Ensemble Framework for the Prediction of Protein–Protein Interaction Sites |
| title_sort | transformer based ensemble framework for the prediction of protein protein interaction sites |
| url | https://spj.science.org/doi/10.34133/research.0240 |
| work_keys_str_mv | AT minjiemou atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT ziqipan atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT zhimengzhou atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT lingyanzheng atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT hanyuzhang atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT shuiyangshi atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT fengchengli atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT xiunasun atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT fengzhu atransformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT minjiemou transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT ziqipan transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT zhimengzhou transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT lingyanzheng transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT hanyuzhang transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT shuiyangshi transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT fengchengli transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT xiunasun transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites AT fengzhu transformerbasedensembleframeworkforthepredictionofproteinproteininteractionsites |