Cargando…

A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers

Nowadays, various machine learning-based approaches using sequence information alone have been proposed for identifying DNA-binding proteins, which are crucial to many cellular processes, such as DNA replication, DNA repair and DNA modification. Among these methods, building a meaningful feature rep...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Xiu-Juan, Gong, Xiu-Jun, Yu, Hua, Xu, Jia-Hui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6116045/
https://www.ncbi.nlm.nih.gov/pubmed/30071697
http://dx.doi.org/10.3390/genes9080394
_version_ 1783351521435451392
author Liu, Xiu-Juan
Gong, Xiu-Jun
Yu, Hua
Xu, Jia-Hui
author_facet Liu, Xiu-Juan
Gong, Xiu-Jun
Yu, Hua
Xu, Jia-Hui
author_sort Liu, Xiu-Juan
collection PubMed
description Nowadays, various machine learning-based approaches using sequence information alone have been proposed for identifying DNA-binding proteins, which are crucial to many cellular processes, such as DNA replication, DNA repair and DNA modification. Among these methods, building a meaningful feature representation of the sequences and choosing an appropriate classifier are the most trivial tasks. Disclosing the significances and contributions of different feature spaces and classifiers to the final prediction is of the utmost importance, not only for the prediction performances, but also the practical clues of biological experiment designs. In this study, we propose a model stacking framework by orchestrating multi-view features and classifiers (MSFBinder) to investigate how to integrate and evaluate loosely-coupled models for predicting DNA-binding proteins. The framework integrates multi-view features including Local_DPP, 188D, Position-Specific Scoring Matrix (PSSM)_DWT and autocross-covariance of secondary structures(AC_Struc), which were extracted based on evolutionary information, sequence composition, physiochemical properties and predicted structural information, respectively. These features are fed into various loosely-coupled classifiers such as SVM and random forest. Then, a logistic regression model was applied to evaluate the contributions of these individual classifiers and to make the final prediction. When performing on the training dataset PDB1075, the proposed method achieves an accuracy of 83.53%. On the independent dataset PDB186, the method achieves an accuracy of 81.72%, which outperforms many existing methods. These results suggest that the framework is able to orchestrate various predicted models flexibly with good performances.
format Online
Article
Text
id pubmed-6116045
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-61160452018-08-31 A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers Liu, Xiu-Juan Gong, Xiu-Jun Yu, Hua Xu, Jia-Hui Genes (Basel) Article Nowadays, various machine learning-based approaches using sequence information alone have been proposed for identifying DNA-binding proteins, which are crucial to many cellular processes, such as DNA replication, DNA repair and DNA modification. Among these methods, building a meaningful feature representation of the sequences and choosing an appropriate classifier are the most trivial tasks. Disclosing the significances and contributions of different feature spaces and classifiers to the final prediction is of the utmost importance, not only for the prediction performances, but also the practical clues of biological experiment designs. In this study, we propose a model stacking framework by orchestrating multi-view features and classifiers (MSFBinder) to investigate how to integrate and evaluate loosely-coupled models for predicting DNA-binding proteins. The framework integrates multi-view features including Local_DPP, 188D, Position-Specific Scoring Matrix (PSSM)_DWT and autocross-covariance of secondary structures(AC_Struc), which were extracted based on evolutionary information, sequence composition, physiochemical properties and predicted structural information, respectively. These features are fed into various loosely-coupled classifiers such as SVM and random forest. Then, a logistic regression model was applied to evaluate the contributions of these individual classifiers and to make the final prediction. When performing on the training dataset PDB1075, the proposed method achieves an accuracy of 83.53%. On the independent dataset PDB186, the method achieves an accuracy of 81.72%, which outperforms many existing methods. These results suggest that the framework is able to orchestrate various predicted models flexibly with good performances. MDPI 2018-08-01 /pmc/articles/PMC6116045/ /pubmed/30071697 http://dx.doi.org/10.3390/genes9080394 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Liu, Xiu-Juan
Gong, Xiu-Jun
Yu, Hua
Xu, Jia-Hui
A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers
title A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers
title_full A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers
title_fullStr A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers
title_full_unstemmed A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers
title_short A Model Stacking Framework for Identifying DNA Binding Proteins by Orchestrating Multi-View Features and Classifiers
title_sort model stacking framework for identifying dna binding proteins by orchestrating multi-view features and classifiers
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6116045/
https://www.ncbi.nlm.nih.gov/pubmed/30071697
http://dx.doi.org/10.3390/genes9080394
work_keys_str_mv AT liuxiujuan amodelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers
AT gongxiujun amodelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers
AT yuhua amodelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers
AT xujiahui amodelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers
AT liuxiujuan modelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers
AT gongxiujun modelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers
AT yuhua modelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers
AT xujiahui modelstackingframeworkforidentifyingdnabindingproteinsbyorchestratingmultiviewfeaturesandclassifiers