The whole is greater than its parts: ensembling improves protein contact prediction

Abstract The prediction of amino acid contacts from protein sequence is an important problem, as protein contacts are a vital step towards the prediction of folded protein structures. We propose that a powerful concept from deep learning, called ensembling, can increase the accuracy of protein conta...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wendy M. Billings, Connor J. Morris, Dennis Della Corte
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d52d01b461ea4fc19ffcfa13bd818ae8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d52d01b461ea4fc19ffcfa13bd818ae8
record_format	dspace
spelling	oai:doaj.org-article:d52d01b461ea4fc19ffcfa13bd818ae82021-12-02T15:51:13ZThe whole is greater than its parts: ensembling improves protein contact prediction10.1038/s41598-021-87524-02045-2322https://doaj.org/article/d52d01b461ea4fc19ffcfa13bd818ae82021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87524-0https://doaj.org/toc/2045-2322Abstract The prediction of amino acid contacts from protein sequence is an important problem, as protein contacts are a vital step towards the prediction of folded protein structures. We propose that a powerful concept from deep learning, called ensembling, can increase the accuracy of protein contact predictions by combining the outputs of different neural network models. We show that ensembling the predictions made by different groups at the recent Critical Assessment of Protein Structure Prediction (CASP13) outperforms all individual groups. Further, we show that contacts derived from the distance predictions of three additional deep neural networks—AlphaFold, trRosetta, and ProSPr—can be substantially improved by ensembling all three networks. We also show that ensembling these recent deep neural networks with the best CASP13 group creates a superior contact prediction tool. Finally, we demonstrate that two ensembled networks can successfully differentiate between the folds of two highly homologous sequences. In order to build further on these findings, we propose the creation of a better protein contact benchmark set and additional open-source contact prediction methods.Wendy M. BillingsConnor J. MorrisDennis Della CorteNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-7 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Wendy M. Billings Connor J. Morris Dennis Della Corte The whole is greater than its parts: ensembling improves protein contact prediction
description	Abstract The prediction of amino acid contacts from protein sequence is an important problem, as protein contacts are a vital step towards the prediction of folded protein structures. We propose that a powerful concept from deep learning, called ensembling, can increase the accuracy of protein contact predictions by combining the outputs of different neural network models. We show that ensembling the predictions made by different groups at the recent Critical Assessment of Protein Structure Prediction (CASP13) outperforms all individual groups. Further, we show that contacts derived from the distance predictions of three additional deep neural networks—AlphaFold, trRosetta, and ProSPr—can be substantially improved by ensembling all three networks. We also show that ensembling these recent deep neural networks with the best CASP13 group creates a superior contact prediction tool. Finally, we demonstrate that two ensembled networks can successfully differentiate between the folds of two highly homologous sequences. In order to build further on these findings, we propose the creation of a better protein contact benchmark set and additional open-source contact prediction methods.
format	article
author	Wendy M. Billings Connor J. Morris Dennis Della Corte
author_facet	Wendy M. Billings Connor J. Morris Dennis Della Corte
author_sort	Wendy M. Billings
title	The whole is greater than its parts: ensembling improves protein contact prediction
title_short	The whole is greater than its parts: ensembling improves protein contact prediction
title_full	The whole is greater than its parts: ensembling improves protein contact prediction
title_fullStr	The whole is greater than its parts: ensembling improves protein contact prediction
title_full_unstemmed	The whole is greater than its parts: ensembling improves protein contact prediction
title_sort	whole is greater than its parts: ensembling improves protein contact prediction
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/d52d01b461ea4fc19ffcfa13bd818ae8
work_keys_str_mv	AT wendymbillings thewholeisgreaterthanitspartsensemblingimprovesproteincontactprediction AT connorjmorris thewholeisgreaterthanitspartsensemblingimprovesproteincontactprediction AT dennisdellacorte thewholeisgreaterthanitspartsensemblingimprovesproteincontactprediction AT wendymbillings wholeisgreaterthanitspartsensemblingimprovesproteincontactprediction AT connorjmorris wholeisgreaterthanitspartsensemblingimprovesproteincontactprediction AT dennisdellacorte wholeisgreaterthanitspartsensemblingimprovesproteincontactprediction
_version_	1718385660884156416

The whole is greater than its parts: ensembling improves protein contact prediction

Ejemplares similares