Mining of protein contact maps for protein fold prediction

Abstract

The three‐dimensional structure of proteins is useful to carry out the biophysical and biochemical functions in a cell. Approaches to protein structure/fold prediction typically extract amino acid sequence features, and machine learning approaches are then applied to classification problem. Protein contact maps are two‐dimensional representations of the contacts among the amino acid residues in the folded protein structure. This paper highlights the need for a systematic study of these contact networks. Mining of contact maps to derive features pertaining to fold information offers a new mechanism for fold discovery from the protein sequence via the contact maps. These ideas are explored in the structural class of all‐alpha proteins to identify structural elements. A simple and computationally inexpensive algorithm based on triangle subdivision method is proposed to extract additional features from the contact map. The method successfully characterizes the off‐diagonal interactions in the contact map for predicting specific ‘folds’. The decision tree classification results show great promise in developing a new and simple tool for the challenging problem of fold prediction. © 2011 John Wiley & Sons, Inc. WIREs Data Mining Knowl Discov 2011 1 362–368 DOI: 10.1002/widm.35This article is categorized under: Algorithmic Development > Biological Data Mining Technologies > Classification Technologies > Machine Learning

Understanding contact patterns of protein structures from protein contact map and investigation of unique patterns in the globin‐like folded domains

“…The Unfolded region /Loops/turns are visualized as breaks in the diagonal for α helix and β sheet motifs. 11,31 Tiny clusters or isolated points in the PCM were found to characterize structurally relevant contacts between amino acids, along with the linear sequence of amino acids. The clusters of contacts represent the α helices that appear as bands along the main diagonal in the contact map since these contacts were involved between the first amino acid and every fourth successor residues.…”

“…The analysis of secondary structures using dynamics contact maps suggests that the helix bundle produced substantial diagonal contacts, while the β sheet produced much thinner diagonal contacts. [31][32][33] 3.4 | Parallel and anti-parallel strands in β protein structures An all-β protein is a class of structural domains in which the secondary structure is composed entirely of β-sheets, with a few isolated α-helices on the periphery. By analyzing the β proteins, the contacts present in the parallel strands were observed to be in the upper right region toward all the proteins.…”

Structural Protein Function Prediction - A Comprehensive Review

“…The matrix values are determined according to a threshold distance. Bhavani et al [58] used contact maps to predict protein folds. Based on triangle subdivision method and using decision tree for binary classification, they correctly predicted EFhand-like and cytochrome fold with accuracy of 96% and 79%, respectively.…”

Frequent substructures and fold classification from protein contact maps

“…Shi and Zhang [3] extracted secondary structure features from the distance maps of Protein Contact Network (PCN) to carry out structural class prediction. Recently, SuvarnaVani [5] extracted rules based on the diagonal information and the off -diagonal interactions in the contact map for EF-Handlike and Cytochrome-C folds. The objective of this paper is to demonstrate that analyzing patterns in contact maps will contribute to insight positioning of proteins within a specific structural class/fold and folding information.…”