Prediction of Protein Structural Classes

Abstract

A protein is usually classified into one of the following five structural classes: alpha, beta, alpha + beta, alpha/beta, and zeta (irregular). The structural class of a protein is correlated with its amino acid composition. However, given the amino acid composition of a protein, how may one predict its structural class? Various efforts have been made in addressing this problem. This review addresses the progress in this field, with the focus on the state of the art, which is featured by a novel prediction algorithm and a recently developed database. The novel algorithm is characterized by a covariance matrix that takes into account the coupling effect among different amino acid components of a protein. The new database was established based on the requirement that the classes should have (1) as many nonhomologous structures as possible, (2) good quality structure, and (3) typical or distinguishable features for each of the structural classes concerned. The very high success rate for both the training-set proteins and the testing-set proteins, which has been further validated by a simulated analysis and a jackknife analysis, indicates that it is possible to predict the structural class of a protein according to its amino acid composition if an ideal and complete database can be established. It also suggests that the overall fold of a protein is basically determined by its amino acid composition.

Adaptation of model proteins from cold to hot environments involves continuous and small adjustments of average parameters related to amino acid composition

“…In particular, the similarity of the protein structure and the occurrence of a common catalytic 6 mechanism in proteins isolated from sources adapted from cold to hot environments indicate that the challenge to the extreme environments has been likely accomplished by a fine modulation of the amino acid composition of proteins aimed at optimizing the number of specific weak interactions inside the protein core. Indeed, the amino acid composition has been found to play an important role in determining the protein structural class (Chou and Zhang, 1994;Chou and Zhang, 1995;Chou, 1995;Chou and Maggiora, 1998), in identifying protein subcellular localization, and many other attributes (Chou and Elrod, 1999;Chou, 2002). Evidence has been presented that the amino acid composition in the proteomes of Escherichia coli and Bacillus subtilis reflects a natural selection to enhance metabolic efficiency in these microorganisms (Akashi and Gojobori, 2002).…”

A network-QSAR model for prediction of genetic-component biomarkers in human colorectal cancer

“…The obtained results are similar to those of the previously described model from the quality of the statistical parameters point of view as in the percentage of good classification (see Table 3). In statistical prediction, three cross-validation methods are often used: subsampling test, independent dataset test, and jackknife test (Chou and Zhang, 1995). However, as demonstrated in (Chou and Shen, 2007), the jackknife test has the least arbitrariness and therefore has been increasingly and widely used to test various prediction methods (see, e.g., (Chen et al, 2008;Chen and Han, 2009;Chou and Shen, 2008a;Chou and Shen, 2008b;Chou and Shen, 2009;Ding et al, 2009a;Ding et al, 2009b;Du and Li, 2008;Georgiou et al, 2009;2008;Nanni and Lumini, 2009;Rezaei et al, 2008;Shi et al, 2008;Tian et al, 2008;Wang et al, 2008;Xiao et al, 2009b;Zeng et al, 2009;).…”

Evolution of multicellularity in Metazoa: comparative analysis of the subcellular localization of proteins in Saccharomyces, Drosophila and Caenorhabditis

“…Single-compartment prediction accuracy ranged from 44% (jackknifing) or 56% (training-testing) for the peroxisome proteins to 84% (jackknifing) or 83% (training-testing) for the cell membrane proteins. As described by Chou and Zhang (1995), when the number of proteins in a given set is not large enough (e.g. peroxisome and Golgi apparatus), the leave-one-out test may result in a severe loss of information.…”