APOLLO

A quality assessment service for single and multiple protein models

Zheng Wang, Jesse Eickholt, Jianlin Cheng

Research output: Contribution to journalArticle

55 Citations (Scopus)

Abstract

We built a web server named APOLLO, which can evaluate the absolute global and local qualities of a single protein model using machine learning methods or the global and local qualities of a pool of models using a pair-wise comparison approach. Based on our evaluations on 107 CASP9 (Critical Assessment of Techniques for Protein Structure Prediction) targets, the predicted quality scores generated from our machine learning and pair-wise methods have an average per-target correlation of 0.671 and 0.917, respectively, with the true model quality scores. Based on our test on 92 CASP9 targets, our predicted absolute local qualities have an average difference of 2.60 Å with the actual distances to native structure.

Original languageEnglish (US)
Article numberbtr268
Pages (from-to)1715-1716
Number of pages2
JournalBioinformatics
Volume27
Issue number12
DOIs
StatePublished - Jun 1 2011
Externally publishedYes

Fingerprint

Quality Assessment
Proteins
Protein
Learning systems
Target
Machine Learning
Servers
Protein Structure Prediction
Model
Pairwise Comparisons
Web Server
Evaluate
Evaluation

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

APOLLO : A quality assessment service for single and multiple protein models. / Wang, Zheng; Eickholt, Jesse; Cheng, Jianlin.

In: Bioinformatics, Vol. 27, No. 12, btr268, 01.06.2011, p. 1715-1716.

Research output: Contribution to journalArticle

Wang, Zheng ; Eickholt, Jesse ; Cheng, Jianlin. / APOLLO : A quality assessment service for single and multiple protein models. In: Bioinformatics. 2011 ; Vol. 27, No. 12. pp. 1715-1716.
@article{d9595f06fe0747d0b39fe9edf01d31c7,
title = "APOLLO: A quality assessment service for single and multiple protein models",
abstract = "We built a web server named APOLLO, which can evaluate the absolute global and local qualities of a single protein model using machine learning methods or the global and local qualities of a pool of models using a pair-wise comparison approach. Based on our evaluations on 107 CASP9 (Critical Assessment of Techniques for Protein Structure Prediction) targets, the predicted quality scores generated from our machine learning and pair-wise methods have an average per-target correlation of 0.671 and 0.917, respectively, with the true model quality scores. Based on our test on 92 CASP9 targets, our predicted absolute local qualities have an average difference of 2.60 {\AA} with the actual distances to native structure.",
author = "Zheng Wang and Jesse Eickholt and Jianlin Cheng",
year = "2011",
month = "6",
day = "1",
doi = "10.1093/bioinformatics/btr268",
language = "English (US)",
volume = "27",
pages = "1715--1716",
journal = "Bioinformatics (Oxford, England)",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "12",

}

TY - JOUR

T1 - APOLLO

T2 - A quality assessment service for single and multiple protein models

AU - Wang, Zheng

AU - Eickholt, Jesse

AU - Cheng, Jianlin

PY - 2011/6/1

Y1 - 2011/6/1

N2 - We built a web server named APOLLO, which can evaluate the absolute global and local qualities of a single protein model using machine learning methods or the global and local qualities of a pool of models using a pair-wise comparison approach. Based on our evaluations on 107 CASP9 (Critical Assessment of Techniques for Protein Structure Prediction) targets, the predicted quality scores generated from our machine learning and pair-wise methods have an average per-target correlation of 0.671 and 0.917, respectively, with the true model quality scores. Based on our test on 92 CASP9 targets, our predicted absolute local qualities have an average difference of 2.60 Å with the actual distances to native structure.

AB - We built a web server named APOLLO, which can evaluate the absolute global and local qualities of a single protein model using machine learning methods or the global and local qualities of a pool of models using a pair-wise comparison approach. Based on our evaluations on 107 CASP9 (Critical Assessment of Techniques for Protein Structure Prediction) targets, the predicted quality scores generated from our machine learning and pair-wise methods have an average per-target correlation of 0.671 and 0.917, respectively, with the true model quality scores. Based on our test on 92 CASP9 targets, our predicted absolute local qualities have an average difference of 2.60 Å with the actual distances to native structure.

UR - http://www.scopus.com/inward/record.url?scp=79958078892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958078892&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/btr268

DO - 10.1093/bioinformatics/btr268

M3 - Article

VL - 27

SP - 1715

EP - 1716

JO - Bioinformatics (Oxford, England)

JF - Bioinformatics (Oxford, England)

SN - 1367-4803

IS - 12

M1 - btr268

ER -