Cargando…

A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites

Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-pr...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Pan, Zhang, Guiyang, Yu, Zu-Guo, Huang, Guohua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8576272/
https://www.ncbi.nlm.nih.gov/pubmed/34764983
http://dx.doi.org/10.3389/fgene.2021.752732
_version_ 1784595840228130816
author Wang, Pan
Zhang, Guiyang
Yu, Zu-Guo
Huang, Guohua
author_facet Wang, Pan
Zhang, Guiyang
Yu, Zu-Guo
Huang, Guohua
author_sort Wang, Pan
collection PubMed
description Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-protein interaction sites. In this article, we presented a method based on deep learning and XGBoost (called DeepPPISP-XGB) for predicting protein-protein interaction sites. The deep learning model served as a feature extractor to remove redundant information from protein sequences. The Extreme Gradient Boosting algorithm was used to construct a classifier for predicting protein-protein interaction sites. The DeepPPISP-XGB achieved the following results: area under the receiver operating characteristic curve of 0.681, a recall of 0.624, and area under the precision-recall curve of 0.339, being competitive with the state-of-the-art methods. We also validated the positive role of global features in predicting protein-protein interaction sites.
format Online
Article
Text
id pubmed-8576272
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85762722021-11-10 A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites Wang, Pan Zhang, Guiyang Yu, Zu-Guo Huang, Guohua Front Genet Genetics Knowledge about protein-protein interactions is beneficial in understanding cellular mechanisms. Protein-protein interactions are usually determined according to their protein-protein interaction sites. Due to the limitations of current techniques, it is still a challenging task to detect protein-protein interaction sites. In this article, we presented a method based on deep learning and XGBoost (called DeepPPISP-XGB) for predicting protein-protein interaction sites. The deep learning model served as a feature extractor to remove redundant information from protein sequences. The Extreme Gradient Boosting algorithm was used to construct a classifier for predicting protein-protein interaction sites. The DeepPPISP-XGB achieved the following results: area under the receiver operating characteristic curve of 0.681, a recall of 0.624, and area under the precision-recall curve of 0.339, being competitive with the state-of-the-art methods. We also validated the positive role of global features in predicting protein-protein interaction sites. Frontiers Media S.A. 2021-10-26 /pmc/articles/PMC8576272/ /pubmed/34764983 http://dx.doi.org/10.3389/fgene.2021.752732 Text en Copyright © 2021 Wang, Zhang, Yu and Huang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Genetics
Wang, Pan
Zhang, Guiyang
Yu, Zu-Guo
Huang, Guohua
A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites
title A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites
title_full A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites
title_fullStr A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites
title_full_unstemmed A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites
title_short A Deep Learning and XGBoost-Based Method for Predicting Protein-Protein Interaction Sites
title_sort deep learning and xgboost-based method for predicting protein-protein interaction sites
topic Genetics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8576272/
https://www.ncbi.nlm.nih.gov/pubmed/34764983
http://dx.doi.org/10.3389/fgene.2021.752732
work_keys_str_mv AT wangpan adeeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites
AT zhangguiyang adeeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites
AT yuzuguo adeeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites
AT huangguohua adeeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites
AT wangpan deeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites
AT zhangguiyang deeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites
AT yuzuguo deeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites
AT huangguohua deeplearningandxgboostbasedmethodforpredictingproteinproteininteractionsites