Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.

Predicting ligand binding sites (LBSs) on protein structures, which are obtained either from experimental or computational methods, is a useful first step in functional annotation or structure-based drug design for the protein structures. In this work, the structure-based machine learning algorithm...

Full description

Bibliographic Details
Main Authors: Jhih-Wei Jian, Pavadai Elumalai, Thejkiran Pitti, Chih Yuan Wu, Keng-Chang Tsai, Jeng-Yih Chang, Hung-Pin Peng, An-Suei Yang
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2016-01-01
Series:PLoS ONE
Online Access:http://europepmc.org/articles/PMC4981321?pdf=render
id doaj-9a41de82ba2b442896be0ec0b9d0b821
record_format Article
spelling doaj-9a41de82ba2b442896be0ec0b9d0b8212020-11-25T00:07:59ZengPublic Library of Science (PLoS)PLoS ONE1932-62032016-01-01118e016031510.1371/journal.pone.0160315Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.Jhih-Wei JianPavadai ElumalaiThejkiran PittiChih Yuan WuKeng-Chang TsaiJeng-Yih ChangHung-Pin PengAn-Suei YangPredicting ligand binding sites (LBSs) on protein structures, which are obtained either from experimental or computational methods, is a useful first step in functional annotation or structure-based drug design for the protein structures. In this work, the structure-based machine learning algorithm ISMBLab-LIG was developed to predict LBSs on protein surfaces with input attributes derived from the three-dimensional probability density maps of interacting atoms, which were reconstructed on the query protein surfaces and were relatively insensitive to local conformational variations of the tentative ligand binding sites. The prediction accuracy of the ISMBLab-LIG predictors is comparable to that of the best LBS predictors benchmarked on several well-established testing datasets. More importantly, the ISMBLab-LIG algorithm has substantial tolerance to the prediction uncertainties of computationally derived protein structure models. As such, the method is particularly useful for predicting LBSs not only on experimental protein structures without known LBS templates in the database but also on computationally predicted model protein structures with structural uncertainties in the tentative ligand binding sites.http://europepmc.org/articles/PMC4981321?pdf=render
collection DOAJ
language English
format Article
sources DOAJ
author Jhih-Wei Jian
Pavadai Elumalai
Thejkiran Pitti
Chih Yuan Wu
Keng-Chang Tsai
Jeng-Yih Chang
Hung-Pin Peng
An-Suei Yang
spellingShingle Jhih-Wei Jian
Pavadai Elumalai
Thejkiran Pitti
Chih Yuan Wu
Keng-Chang Tsai
Jeng-Yih Chang
Hung-Pin Peng
An-Suei Yang
Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.
PLoS ONE
author_facet Jhih-Wei Jian
Pavadai Elumalai
Thejkiran Pitti
Chih Yuan Wu
Keng-Chang Tsai
Jeng-Yih Chang
Hung-Pin Peng
An-Suei Yang
author_sort Jhih-Wei Jian
title Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.
title_short Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.
title_full Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.
title_fullStr Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.
title_full_unstemmed Predicting Ligand Binding Sites on Protein Surfaces by 3-Dimensional Probability Density Distributions of Interacting Atoms.
title_sort predicting ligand binding sites on protein surfaces by 3-dimensional probability density distributions of interacting atoms.
publisher Public Library of Science (PLoS)
series PLoS ONE
issn 1932-6203
publishDate 2016-01-01
description Predicting ligand binding sites (LBSs) on protein structures, which are obtained either from experimental or computational methods, is a useful first step in functional annotation or structure-based drug design for the protein structures. In this work, the structure-based machine learning algorithm ISMBLab-LIG was developed to predict LBSs on protein surfaces with input attributes derived from the three-dimensional probability density maps of interacting atoms, which were reconstructed on the query protein surfaces and were relatively insensitive to local conformational variations of the tentative ligand binding sites. The prediction accuracy of the ISMBLab-LIG predictors is comparable to that of the best LBS predictors benchmarked on several well-established testing datasets. More importantly, the ISMBLab-LIG algorithm has substantial tolerance to the prediction uncertainties of computationally derived protein structure models. As such, the method is particularly useful for predicting LBSs not only on experimental protein structures without known LBS templates in the database but also on computationally predicted model protein structures with structural uncertainties in the tentative ligand binding sites.
url http://europepmc.org/articles/PMC4981321?pdf=render
work_keys_str_mv AT jhihweijian predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
AT pavadaielumalai predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
AT thejkiranpitti predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
AT chihyuanwu predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
AT kengchangtsai predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
AT jengyihchang predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
AT hungpinpeng predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
AT ansueiyang predictingligandbindingsitesonproteinsurfacesby3dimensionalprobabilitydensitydistributionsofinteractingatoms
_version_ 1725417219384410112