PANDA: Protein function prediction using domain architecture and affinity propagation

Abstract We developed PANDA (Propagation of Affinity and Domain Architecture) to predict protein functions in the format of Gene Ontology (GO) terms. PANDA at first executes profile-profile alignment algorithm to search against PfamA, KOG, COG, and SwissProt databases, and then launches PSI-BLAST ag...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zheng Wang, Chenguang Zhao, Yiheng Wang, Zheng Sun, Nan Wang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b61f5509c5fb4459a2857b45843d1ba2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b61f5509c5fb4459a2857b45843d1ba2
record_format	dspace
spelling	oai:doaj.org-article:b61f5509c5fb4459a2857b45843d1ba22021-12-02T15:08:53ZPANDA: Protein function prediction using domain architecture and affinity propagation10.1038/s41598-018-21849-12045-2322https://doaj.org/article/b61f5509c5fb4459a2857b45843d1ba22018-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-21849-1https://doaj.org/toc/2045-2322Abstract We developed PANDA (Propagation of Affinity and Domain Architecture) to predict protein functions in the format of Gene Ontology (GO) terms. PANDA at first executes profile-profile alignment algorithm to search against PfamA, KOG, COG, and SwissProt databases, and then launches PSI-BLAST against UniProt for homologue search. PANDA integrates a domain architecture inference algorithm based on the Bayesian statistics that calculates the probability of having a GO term. All the candidate GO terms are pooled and filtered based on Z-score. After that, the remaining GO terms are clustered using an affinity propagation algorithm based on the GO directed acyclic graph, followed by a second round of filtering on the clusters of GO terms. We benchmarked the performance of all the baseline predictors PANDA integrates and also for every pooling and filtering step of PANDA. It can be found that PANDA achieves better performances in terms of area under the curve for precision and recall compared to the baseline predictors. PANDA can be accessed from http://dna.cs.miami.edu/PANDA/.Zheng WangChenguang ZhaoYiheng WangZheng SunNan WangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-10 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Zheng Wang Chenguang Zhao Yiheng Wang Zheng Sun Nan Wang PANDA: Protein function prediction using domain architecture and affinity propagation
description	Abstract We developed PANDA (Propagation of Affinity and Domain Architecture) to predict protein functions in the format of Gene Ontology (GO) terms. PANDA at first executes profile-profile alignment algorithm to search against PfamA, KOG, COG, and SwissProt databases, and then launches PSI-BLAST against UniProt for homologue search. PANDA integrates a domain architecture inference algorithm based on the Bayesian statistics that calculates the probability of having a GO term. All the candidate GO terms are pooled and filtered based on Z-score. After that, the remaining GO terms are clustered using an affinity propagation algorithm based on the GO directed acyclic graph, followed by a second round of filtering on the clusters of GO terms. We benchmarked the performance of all the baseline predictors PANDA integrates and also for every pooling and filtering step of PANDA. It can be found that PANDA achieves better performances in terms of area under the curve for precision and recall compared to the baseline predictors. PANDA can be accessed from http://dna.cs.miami.edu/PANDA/.
format	article
author	Zheng Wang Chenguang Zhao Yiheng Wang Zheng Sun Nan Wang
author_facet	Zheng Wang Chenguang Zhao Yiheng Wang Zheng Sun Nan Wang
author_sort	Zheng Wang
title	PANDA: Protein function prediction using domain architecture and affinity propagation
title_short	PANDA: Protein function prediction using domain architecture and affinity propagation
title_full	PANDA: Protein function prediction using domain architecture and affinity propagation
title_fullStr	PANDA: Protein function prediction using domain architecture and affinity propagation
title_full_unstemmed	PANDA: Protein function prediction using domain architecture and affinity propagation
title_sort	panda: protein function prediction using domain architecture and affinity propagation
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/b61f5509c5fb4459a2857b45843d1ba2
work_keys_str_mv	AT zhengwang pandaproteinfunctionpredictionusingdomainarchitectureandaffinitypropagation AT chenguangzhao pandaproteinfunctionpredictionusingdomainarchitectureandaffinitypropagation AT yihengwang pandaproteinfunctionpredictionusingdomainarchitectureandaffinitypropagation AT zhengsun pandaproteinfunctionpredictionusingdomainarchitectureandaffinitypropagation AT nanwang pandaproteinfunctionpredictionusingdomainarchitectureandaffinitypropagation
_version_	1718388021742534656

PANDA: Protein function prediction using domain architecture and affinity propagation

Ejemplares similares