CASP9 target classification

Abstract

The Critical Assessment of Protein Structure Prediction round 9 (CASP9) aimed to evaluate predictions for 129 experimentally determined protein structures. To assess tertiary structure predictions, these target structures were divided into domain-based evaluation units that were then classified into two assessment categories: template based modeling (TBM) and template free modeling (FM). CASP9 targets were split into domains of structurally compact evolutionary modules. For the targets with more than one defined domain, the decision to split structures into domains for evaluation was based on server performance. Target domains were categorized based on their evolutionary relatedness to existing templates as well as their difficulty levels indicated by server performance. Those target domains with sequence-related templates and high server prediction performance were classified as TMB, while those targets without identifiable templates and low server performance were classified as FM. However, using these generalizations for classification resulted in a blurred boundary between CASP9 assessment categories. Thus, the FM category included those domains without sequence detectable templates (25 target domains) as well as some domains with difficult to detect templates whose predictions were as poor as those without templates (5 target domains). Several interesting examples are discussed, including targets with sequence related templates that exhibit unusual structural differences, targets with homologous or analogous structure templates that are not detectable by sequence, and targets with new folds.

Template-based prediction of protein 8-state secondary structures

“…Cull5547 contains 5547 protein chains with at most 25% sequence identity and 2.0A resolution cutoff. Public benchmarks, including CB513 [12], Manesh215 [13], Carugo338 [14], and CASP9 targets [15] are used to benchmark our method.…”

Protein Tertiary Structures: Prediction from Amino Acid Sequences

“…Theoretical methods for protein structure prediction have been traditionally divided into three major categories: comparative modelling, fold recognition and ab-initio prediction (Morea and Tramontano, 2003;Tress et al, 2005a), although the distinctions between the three categories has become increasingly blurred in recent years (Kinch et al, 2011).…”

A NSGA-II Algorithm for the Residue-Residue Contact Prediction

“…Different approaches were developed as protein contact map predictors: artificial neural networks (ANNs) [3,4], support vector machines [5], evolutionary algorithms (EAs) [6] and template-based modeling [7]. Every two years, Critical Assessment of Protein Structure Prediction (CASP) competition [8] evaluates the most accurate computational methods for the PSP problem. One of the categories of this competition is called "Detecting residueresidue contacts in proteins (RR)".…”

“…A MOEA should be designed to achieve two purposes simultaneously: to achieve good approximations to the Pareto front and maintain the diversity of solutions, in order to adequately search the solution space and do not converge to a unique solution [12]. Some of the best known MOEAs are NSGA, SPEA, NSGA-II, SPEA-II and PAES-II [8].…”