Literature DB >> 19786483

LIBRUS: combined machine learning and homology information for sequence-based ligand-binding residue prediction.

Chris Kauffman1, George Karypis.   

Abstract

MOTIVATION: Identifying residues that interact with ligands is useful as a first step to understanding protein function and as an aid to designing small molecules that target the protein for interaction. Several studies have shown that sequence features are very informative for this type of prediction, while structure features have also been useful when structure is available. We develop a sequence-based method, called LIBRUS, that combines homology-based transfer and direct prediction using machine learning and compare it to previous sequence-based work and current structure-based methods.
RESULTS: Our analysis shows that homology-based transfer is slightly more discriminating than a support vector machine learner using profiles and predicted secondary structure. We combine these two approaches in a method called LIBRUS. On a benchmark of 885 sequence-independent proteins, it achieves an area under the ROC curve (ROC) of 0.83 with 45% precision at 50% recall, a significant improvement over previous sequence-based efforts. On an independent benchmark set, a current method, FINDSITE, based on structure features achieves an ROC of 0.81 with 54% precision at 50% recall, while LIBRUS achieves an ROC of 0.82 with 39% precision at 50% recall at a smaller computational cost. When LIBRUS and FINDSITE predictions are combined, performance is increased beyond either reaching an ROC of 0.86 and 59% precision at 50% recall. AVAILABILITY: Software developed for this study is available at http://bioinfo.cs.umn.edu/supplements/binf2009 along with Supplementary data on the study.

Mesh:

Substances:

Year:  2009        PMID: 19786483      PMCID: PMC3167698          DOI: 10.1093/bioinformatics/btp561

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.937


  20 in total

1.  The Protein Data Bank.

Authors:  H M Berman; J Westbrook; Z Feng; G Gilliland; T N Bhat; H Weissig; I N Shindyalov; P E Bourne
Journal:  Nucleic Acids Res       Date:  2000-01-01       Impact factor: 16.971

2.  ASTRAL compendium enhancements.

Authors:  John-Marc Chandonia; Nigel S Walker; Loredana Lo Conte; Patrice Koehl; Michael Levitt; Steven E Brenner
Journal:  Nucleic Acids Res       Date:  2002-01-01       Impact factor: 16.971

3.  Automated analysis of interatomic contacts in proteins.

Authors:  V Sobolev; A Sorokine; J Prilusky; E E Abola; M Edelman
Journal:  Bioinformatics       Date:  1999-04       Impact factor: 6.937

Review 4.  Hit and lead generation: beyond high-throughput screening.

Authors:  Konrad H Bleicher; Hans-Joachim Böhm; Klaus Müller; Alexander I Alanine
Journal:  Nat Rev Drug Discov       Date:  2003-05       Impact factor: 84.694

5.  ORFeus: Detection of distant homology using sequence profiles and predicted secondary structure.

Authors:  Krzysztof Ginalski; Jakub Pas; Lucjan S Wyrwicz; Marcin von Grotthuss; Janusz M Bujnicki; Leszek Rychlewski
Journal:  Nucleic Acids Res       Date:  2003-07-01       Impact factor: 16.971

6.  Probabilistic scoring measures for profile-profile comparison yield more accurate short seed alignments.

Authors:  David Mittelman; Ruslan Sadreyev; Nick Grishin
Journal:  Bioinformatics       Date:  2003-08-12       Impact factor: 6.937

7.  Virtual screen for ligands of orphan G protein-coupled receptors.

Authors:  Joel R Bock; David A Gough
Journal:  J Chem Inf Model       Date:  2005 Sep-Oct       Impact factor: 4.956

8.  Improving homology models for protein-ligand binding sites.

Authors:  Chris Kauffman; Huzefa Rangwala; George Karypis
Journal:  Comput Syst Bioinformatics Conf       Date:  2008

Review 9.  Gapped BLAST and PSI-BLAST: a new generation of protein database search programs.

Authors:  S F Altschul; T L Madden; A A Schäffer; J Zhang; Z Zhang; W Miller; D J Lipman
Journal:  Nucleic Acids Res       Date:  1997-09-01       Impact factor: 16.971

10.  Systematic optimization of a lead-structure identities for a selective short peptide agonist for the human orphan receptor BRS-3.

Authors:  Dirk Weber; Claudia Berger; Timo Heinrich; Peter Eickelmann; Jochen Antel; Horst Kessler
Journal:  J Pept Sci       Date:  2002-08       Impact factor: 1.905

View more
  6 in total

1.  RNABindRPlus: a predictor that combines machine learning and sequence homology-based methods to improve the reliability of predicted RNA-binding residues in proteins.

Authors:  Rasna R Walia; Li C Xue; Katherine Wilkins; Yasser El-Manzalawy; Drena Dobbs; Vasant Honavar
Journal:  PLoS One       Date:  2014-05-20       Impact factor: 3.240

2.  LigandRFs: random forest ensemble to identify ligand-binding residues from sequence information alone.

Authors:  Peng Chen; Jianhua Z Huang; Xin Gao
Journal:  BMC Bioinformatics       Date:  2014-12-03       Impact factor: 3.169

3.  SmoPSI: Analysis and Prediction of Small Molecule Binding Sites Based on Protein Sequence Information.

Authors:  Wei Wang; Keliang Li; Hehe Lv; Hongjun Zhang; Shixun Wang; Junwei Huang
Journal:  Comput Math Methods Med       Date:  2019-11-13       Impact factor: 2.238

4.  Automatic generation of bioinformatics tools for predicting protein-ligand binding sites.

Authors:  Yusuke Komiyama; Masaki Banno; Kokoro Ueki; Gul Saad; Kentaro Shimizu
Journal:  Bioinformatics       Date:  2015-11-05       Impact factor: 6.937

5.  P2Rank: machine learning based tool for rapid and accurate prediction of ligand binding sites from protein structure.

Authors:  Radoslav Krivák; David Hoksza
Journal:  J Cheminform       Date:  2018-08-14       Impact factor: 5.514

6.  Predicting binding sites from unbound versus bound protein structures.

Authors:  Jordan J Clark; Zachary J Orban; Heather A Carlson
Journal:  Sci Rep       Date:  2020-09-28       Impact factor: 4.379

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.