Predicting protein-protein binding sites in membrane proteins

Andrew J. Bordner

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Background: Many integral membrane proteins, like their non-membrane counterparts, form either transient or permanent multi-subunit complexes in order to carry out their biochemical function. Computational methods that provide structural details of these interactions are needed since, despite their importance, relatively few structures of membrane protein complexes are available. Results: We present a method for predicting which residues are in protein-protein binding sites within the transmembrane regions of membrane proteins. The method uses a Random Forest classifier trained on residue type distributions and evolutionary conservation for individual surface residues, followed by spatial averaging of the residue scores. The prediction accuracy achieved for membrane proteins is comparable to that for non-membrane proteins. Also, like previous results for non-membrane proteins, the accuracy is significantly higher for residues distant from the binding site boundary. Furthermore, a predictor trained on non-membrane proteins was found to yield poor accuracy on membrane proteins, as expected from the different distribution of surface residue types between the two classes of proteins. Thus, although the same procedure can be used to predict binding sites in membrane and non-membrane proteins, separate predictors trained on each class of proteins are required. Finally, the contribution of each residue property to the overall prediction accuracy is analyzed and prediction examples are discussed. Conclusion: Given a membrane protein structure and a multiple alignment of related sequences, the presented method gives a prioritized list of which surface residues participate in intramembrane protein-protein interactions. The method has potential applications in guiding the experimental verification of membrane protein interactions, structure-based drug discovery, and also in constraining the search space for computational methods, such as protein docking or threading, that predict membrane protein complex structures.

Original languageEnglish (US)
Article number1471
Pages (from-to)312
Number of pages1
JournalBMC Bioinformatics
Volume10
DOIs
StatePublished - Sep 24 2009

Fingerprint

Membrane Protein
Binding sites
Protein Binding
Membrane Proteins
Binding Sites
Proteins
Membranes
Protein
Protein Structure
Computational Methods
Computational methods
Prediction
Predictors
Predict
Drug Discovery
Random Forest
Docking
Protein-protein Interaction
Sequence Alignment
Complex Structure

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Structural Biology
  • Applied Mathematics

Cite this

Predicting protein-protein binding sites in membrane proteins. / Bordner, Andrew J.

In: BMC Bioinformatics, Vol. 10, 1471, 24.09.2009, p. 312.

Research output: Contribution to journalArticle

Bordner, Andrew J. / Predicting protein-protein binding sites in membrane proteins. In: BMC Bioinformatics. 2009 ; Vol. 10. pp. 312.
@article{1b93988a152c492d8eb39404b6e3ea33,
title = "Predicting protein-protein binding sites in membrane proteins",
abstract = "Background: Many integral membrane proteins, like their non-membrane counterparts, form either transient or permanent multi-subunit complexes in order to carry out their biochemical function. Computational methods that provide structural details of these interactions are needed since, despite their importance, relatively few structures of membrane protein complexes are available. Results: We present a method for predicting which residues are in protein-protein binding sites within the transmembrane regions of membrane proteins. The method uses a Random Forest classifier trained on residue type distributions and evolutionary conservation for individual surface residues, followed by spatial averaging of the residue scores. The prediction accuracy achieved for membrane proteins is comparable to that for non-membrane proteins. Also, like previous results for non-membrane proteins, the accuracy is significantly higher for residues distant from the binding site boundary. Furthermore, a predictor trained on non-membrane proteins was found to yield poor accuracy on membrane proteins, as expected from the different distribution of surface residue types between the two classes of proteins. Thus, although the same procedure can be used to predict binding sites in membrane and non-membrane proteins, separate predictors trained on each class of proteins are required. Finally, the contribution of each residue property to the overall prediction accuracy is analyzed and prediction examples are discussed. Conclusion: Given a membrane protein structure and a multiple alignment of related sequences, the presented method gives a prioritized list of which surface residues participate in intramembrane protein-protein interactions. The method has potential applications in guiding the experimental verification of membrane protein interactions, structure-based drug discovery, and also in constraining the search space for computational methods, such as protein docking or threading, that predict membrane protein complex structures.",
author = "Bordner, {Andrew J.}",
year = "2009",
month = "9",
day = "24",
doi = "10.1186/1471-2105-10-312",
language = "English (US)",
volume = "10",
pages = "312",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Predicting protein-protein binding sites in membrane proteins

AU - Bordner, Andrew J.

PY - 2009/9/24

Y1 - 2009/9/24

N2 - Background: Many integral membrane proteins, like their non-membrane counterparts, form either transient or permanent multi-subunit complexes in order to carry out their biochemical function. Computational methods that provide structural details of these interactions are needed since, despite their importance, relatively few structures of membrane protein complexes are available. Results: We present a method for predicting which residues are in protein-protein binding sites within the transmembrane regions of membrane proteins. The method uses a Random Forest classifier trained on residue type distributions and evolutionary conservation for individual surface residues, followed by spatial averaging of the residue scores. The prediction accuracy achieved for membrane proteins is comparable to that for non-membrane proteins. Also, like previous results for non-membrane proteins, the accuracy is significantly higher for residues distant from the binding site boundary. Furthermore, a predictor trained on non-membrane proteins was found to yield poor accuracy on membrane proteins, as expected from the different distribution of surface residue types between the two classes of proteins. Thus, although the same procedure can be used to predict binding sites in membrane and non-membrane proteins, separate predictors trained on each class of proteins are required. Finally, the contribution of each residue property to the overall prediction accuracy is analyzed and prediction examples are discussed. Conclusion: Given a membrane protein structure and a multiple alignment of related sequences, the presented method gives a prioritized list of which surface residues participate in intramembrane protein-protein interactions. The method has potential applications in guiding the experimental verification of membrane protein interactions, structure-based drug discovery, and also in constraining the search space for computational methods, such as protein docking or threading, that predict membrane protein complex structures.

AB - Background: Many integral membrane proteins, like their non-membrane counterparts, form either transient or permanent multi-subunit complexes in order to carry out their biochemical function. Computational methods that provide structural details of these interactions are needed since, despite their importance, relatively few structures of membrane protein complexes are available. Results: We present a method for predicting which residues are in protein-protein binding sites within the transmembrane regions of membrane proteins. The method uses a Random Forest classifier trained on residue type distributions and evolutionary conservation for individual surface residues, followed by spatial averaging of the residue scores. The prediction accuracy achieved for membrane proteins is comparable to that for non-membrane proteins. Also, like previous results for non-membrane proteins, the accuracy is significantly higher for residues distant from the binding site boundary. Furthermore, a predictor trained on non-membrane proteins was found to yield poor accuracy on membrane proteins, as expected from the different distribution of surface residue types between the two classes of proteins. Thus, although the same procedure can be used to predict binding sites in membrane and non-membrane proteins, separate predictors trained on each class of proteins are required. Finally, the contribution of each residue property to the overall prediction accuracy is analyzed and prediction examples are discussed. Conclusion: Given a membrane protein structure and a multiple alignment of related sequences, the presented method gives a prioritized list of which surface residues participate in intramembrane protein-protein interactions. The method has potential applications in guiding the experimental verification of membrane protein interactions, structure-based drug discovery, and also in constraining the search space for computational methods, such as protein docking or threading, that predict membrane protein complex structures.

UR - http://www.scopus.com/inward/record.url?scp=70449408309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449408309&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-10-312

DO - 10.1186/1471-2105-10-312

M3 - Article

VL - 10

SP - 312

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 1471

ER -