Cargando…

De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning

Moonlighting proteins (MPs) are a special type of protein with multiple independent functions. MPs play vital roles in cellular regulation, diseases, and biological pathways. At present, very few MPs have been discovered by biological experiments. Due to the lack of data sample, computation-based me...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Ying, Zhao, Jianing, Liu, Zhaoqian, Wang, Cankun, Wei, Lizheng, Han, Siyu, Du, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8019903/
https://www.ncbi.nlm.nih.gov/pubmed/33828582
http://dx.doi.org/10.3389/fgene.2021.630379
_version_ 1783674473495396352
author Li, Ying
Zhao, Jianing
Liu, Zhaoqian
Wang, Cankun
Wei, Lizheng
Han, Siyu
Du, Wei
author_facet Li, Ying
Zhao, Jianing
Liu, Zhaoqian
Wang, Cankun
Wei, Lizheng
Han, Siyu
Du, Wei
author_sort Li, Ying
collection PubMed
description Moonlighting proteins (MPs) are a special type of protein with multiple independent functions. MPs play vital roles in cellular regulation, diseases, and biological pathways. At present, very few MPs have been discovered by biological experiments. Due to the lack of data sample, computation-based methods to identify MPs are limited. Currently, there is no de-novo prediction method for MPs. Therefore, systematic research and identification of MPs are urgently required. In this paper, we propose a multimodal deep ensemble learning architecture, named MEL-MP, which is the first de novo computation model for predicting MPs. First, we extract four sequence-based features: primary protein sequence information, evolutionary information, physical and chemical properties, and secondary protein structure information. Second, we select specific classifiers for each kind of feature. Finally, we apply the stacked ensemble to integrate the output of each classifier. Through comprehensive model selection and cross-validation experiments, it is shown that specific classifiers for specific feature types can achieve superior performance. For validating the effectiveness of the fusion-based stacked ensemble, different feature fusion strategies including direct combination and a multimodal deep auto-encoder are used for comparative purposes. MEL-MP is shown to exhibit superior prediction performance (F-score = 0.891), surpassing the existing machine learning model, MPFit (F-score = 0.784). In addition, MEL-MP is leveraged to predict the potential MPs among all human proteins. Furthermore, the distribution of predicted MPs on different chromosomes, the evolution of MPs, the association of MPs with diseases, and the functional enrichment of MPs are also explored. Finally, for maximum convenience, a user-friendly web server is available at: http://ml.csbg-jlu.site/mel-mp/.
format Online
Article
Text
id pubmed-8019903
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-80199032021-04-06 De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning Li, Ying Zhao, Jianing Liu, Zhaoqian Wang, Cankun Wei, Lizheng Han, Siyu Du, Wei Front Genet Genetics Moonlighting proteins (MPs) are a special type of protein with multiple independent functions. MPs play vital roles in cellular regulation, diseases, and biological pathways. At present, very few MPs have been discovered by biological experiments. Due to the lack of data sample, computation-based methods to identify MPs are limited. Currently, there is no de-novo prediction method for MPs. Therefore, systematic research and identification of MPs are urgently required. In this paper, we propose a multimodal deep ensemble learning architecture, named MEL-MP, which is the first de novo computation model for predicting MPs. First, we extract four sequence-based features: primary protein sequence information, evolutionary information, physical and chemical properties, and secondary protein structure information. Second, we select specific classifiers for each kind of feature. Finally, we apply the stacked ensemble to integrate the output of each classifier. Through comprehensive model selection and cross-validation experiments, it is shown that specific classifiers for specific feature types can achieve superior performance. For validating the effectiveness of the fusion-based stacked ensemble, different feature fusion strategies including direct combination and a multimodal deep auto-encoder are used for comparative purposes. MEL-MP is shown to exhibit superior prediction performance (F-score = 0.891), surpassing the existing machine learning model, MPFit (F-score = 0.784). In addition, MEL-MP is leveraged to predict the potential MPs among all human proteins. Furthermore, the distribution of predicted MPs on different chromosomes, the evolution of MPs, the association of MPs with diseases, and the functional enrichment of MPs are also explored. Finally, for maximum convenience, a user-friendly web server is available at: http://ml.csbg-jlu.site/mel-mp/. Frontiers Media S.A. 2021-03-22 /pmc/articles/PMC8019903/ /pubmed/33828582 http://dx.doi.org/10.3389/fgene.2021.630379 Text en Copyright © 2021 Li, Zhao, Liu, Wang, Wei, Han and Du. http://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
Li, Ying
Zhao, Jianing
Liu, Zhaoqian
Wang, Cankun
Wei, Lizheng
Han, Siyu
Du, Wei
De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning
title De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning
title_full De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning
title_fullStr De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning
title_full_unstemmed De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning
title_short De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning
title_sort de novo prediction of moonlighting proteins using multimodal deep ensemble learning
topic Genetics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8019903/
https://www.ncbi.nlm.nih.gov/pubmed/33828582
http://dx.doi.org/10.3389/fgene.2021.630379
work_keys_str_mv AT liying denovopredictionofmoonlightingproteinsusingmultimodaldeepensemblelearning
AT zhaojianing denovopredictionofmoonlightingproteinsusingmultimodaldeepensemblelearning
AT liuzhaoqian denovopredictionofmoonlightingproteinsusingmultimodaldeepensemblelearning
AT wangcankun denovopredictionofmoonlightingproteinsusingmultimodaldeepensemblelearning
AT weilizheng denovopredictionofmoonlightingproteinsusingmultimodaldeepensemblelearning
AT hansiyu denovopredictionofmoonlightingproteinsusingmultimodaldeepensemblelearning
AT duwei denovopredictionofmoonlightingproteinsusingmultimodaldeepensemblelearning