Research Article

An automated decision-tree approach to predicting protein interaction hot spots

  1. Steven J. Darnell1,
  2. David Page2,
  3. Julie C. Mitchell1,3,*

Article first published online: 6 JUN 2007

DOI: 10.1002/prot.21474

Issue

Proteins: Structure, Function, and Bioinformatics

Proteins: Structure, Function, and Bioinformatics

Volume 68, Issue 4, pages 813–823, September 2007

Additional Information

How to Cite

Darnell, S. J., Page, D. and Mitchell, J. C. (2007), An automated decision-tree approach to predicting protein interaction hot spots. Proteins: Structure, Function, and Bioinformatics, 68: 813–823. doi: 10.1002/prot.21474

Author Information

  1. 1

    Department of Biochemistry, University of Wisconsin-Madison, Madison, Wisconsin 53706

  2. 2

    Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, Wisconsin 53706

  3. 3

    Department of Mathematics, University of Wisconsin-Madison, Madison, Wisconsin 53706

*433 Babcock Drive, Madison, Wisconsin 53706

Publication History

  1. Issue published online: 27 JUL 2007
  2. Article first published online: 6 JUN 2007
  3. Manuscript Accepted: 12 FEB 2007
  4. Manuscript Revised: 2 DEC 2006
  5. Manuscript Received: 10 AUG 2006

Funded by

  • National Library of Medicine Training Grant to the Computation and Informatics in Biology and Medicine Training Program. Grant Number: 5T15LM007359

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

View Full Article with Supporting Information (HTML) Get PDF (266K)

Keywords:

  • atomic density;
  • complemented pocket;
  • computational alanine scanning;
  • decision tree;
  • FADE;
  • protein–protein interface;
  • shape complementarity;
  • shape specificity;
  • site-directed mutagenesis

Abstract

Protein–protein interactions can be altered by mutating one or more “hot spots,” the subset of residues that account for most of the interface's binding free energy. The identification of hot spots requires a significant experimental effort, highlighting the practical value of hot spot predictions. We present two knowledge-based models that improve the ability to predict hot spots: K-FADE uses shape specificity features calculated by the Fast Atomic Density Evaluation (FADE) program, and K-CON uses biochemical contact features. The combined K-FADE/CON (KFC) model displays better overall predictive accuracy than computational alanine scanning (Robetta–Ala). In addition, because these methods predict different subsets of known hot spots, a large and significant increase in accuracy is achieved by combining KFC and Robetta–Ala. The KFC analysis is applied to the calmodulin (CaM)/smooth muscle myosin light chain kinase (smMLCK) interface, and to the bone morphogenetic protein-2 (BMP-2)/BMP receptor-type I (BMPR-IA) interface. The results indicate a strong correlation between KFC hot spot predictions and mutations that significantly reduce the binding affinity of the interface. Proteins 2007. © 2007 Wiley-Liss, Inc.

View Full Article with Supporting Information (HTML) Get PDF (266K)