A random forest learning assisted “divide and conquer” approach for peptide conformation search

Abstract Computational determination of peptide conformations is challenging as it is a problem of finding minima in a high-dimensional space. The “divide and conquer” approach is promising for reliably reducing the search space size. A random forest learning model is proposed here to expand the sco...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xin Chen, Bing Yang, Zijing Lin
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/11c873980d164176bff36fa4a2e6c005
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:11c873980d164176bff36fa4a2e6c005
record_format	dspace
spelling	oai:doaj.org-article:11c873980d164176bff36fa4a2e6c0052021-12-02T11:40:15ZA random forest learning assisted “divide and conquer” approach for peptide conformation search10.1038/s41598-018-27167-w2045-2322https://doaj.org/article/11c873980d164176bff36fa4a2e6c0052018-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-27167-whttps://doaj.org/toc/2045-2322Abstract Computational determination of peptide conformations is challenging as it is a problem of finding minima in a high-dimensional space. The “divide and conquer” approach is promising for reliably reducing the search space size. A random forest learning model is proposed here to expand the scope of applicability of the “divide and conquer” approach. A random forest classification algorithm is used to characterize the distributions of the backbone φ-ψ units (“words”). A random forest supervised learning model is developed to analyze the combinations of the φ-ψ units (“grammar”). It is found that amino acid residues may be grouped as equivalent “words”, while the φ-ψ combinations in low-energy peptide conformations follow a distinct “grammar”. The finding of equivalent words empowers the “divide and conquer” method with the flexibility of fragment substitution. The learnt grammar is used to improve the efficiency of the “divide and conquer” method by removing unfavorable φ-ψ combinations without the need of dedicated human effort. The machine learning assisted search method is illustrated by efficiently searching the conformations of GGG/AAA/GGGG/AAAA/GGGGG through assembling the structures of GFG/GFGG. Moreover, the computational cost of the new method is shown to increase rather slowly with the peptide length.Xin ChenBing YangZijing LinNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-8 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Xin Chen Bing Yang Zijing Lin A random forest learning assisted “divide and conquer” approach for peptide conformation search
description	Abstract Computational determination of peptide conformations is challenging as it is a problem of finding minima in a high-dimensional space. The “divide and conquer” approach is promising for reliably reducing the search space size. A random forest learning model is proposed here to expand the scope of applicability of the “divide and conquer” approach. A random forest classification algorithm is used to characterize the distributions of the backbone φ-ψ units (“words”). A random forest supervised learning model is developed to analyze the combinations of the φ-ψ units (“grammar”). It is found that amino acid residues may be grouped as equivalent “words”, while the φ-ψ combinations in low-energy peptide conformations follow a distinct “grammar”. The finding of equivalent words empowers the “divide and conquer” method with the flexibility of fragment substitution. The learnt grammar is used to improve the efficiency of the “divide and conquer” method by removing unfavorable φ-ψ combinations without the need of dedicated human effort. The machine learning assisted search method is illustrated by efficiently searching the conformations of GGG/AAA/GGGG/AAAA/GGGGG through assembling the structures of GFG/GFGG. Moreover, the computational cost of the new method is shown to increase rather slowly with the peptide length.
format	article
author	Xin Chen Bing Yang Zijing Lin
author_facet	Xin Chen Bing Yang Zijing Lin
author_sort	Xin Chen
title	A random forest learning assisted “divide and conquer” approach for peptide conformation search
title_short	A random forest learning assisted “divide and conquer” approach for peptide conformation search
title_full	A random forest learning assisted “divide and conquer” approach for peptide conformation search
title_fullStr	A random forest learning assisted “divide and conquer” approach for peptide conformation search
title_full_unstemmed	A random forest learning assisted “divide and conquer” approach for peptide conformation search
title_sort	random forest learning assisted “divide and conquer” approach for peptide conformation search
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/11c873980d164176bff36fa4a2e6c005
work_keys_str_mv	AT xinchen arandomforestlearningassisteddivideandconquerapproachforpeptideconformationsearch AT bingyang arandomforestlearningassisteddivideandconquerapproachforpeptideconformationsearch AT zijinglin arandomforestlearningassisteddivideandconquerapproachforpeptideconformationsearch AT xinchen randomforestlearningassisteddivideandconquerapproachforpeptideconformationsearch AT bingyang randomforestlearningassisteddivideandconquerapproachforpeptideconformationsearch AT zijinglin randomforestlearningassisteddivideandconquerapproachforpeptideconformationsearch
_version_	1718395624359985152

A random forest learning assisted “divide and conquer” approach for peptide conformation search

Ejemplares similares