Prediction of Cell Wall Lytic Enzymes Using Chous Amphiphilic Pseudo Amino Acid Composition

Abstract

Discriminating cell wall lytic enzymes from non lytic enzymes is a very important task for curing bacterial infections. In this paper, based on Chou's amphiphilic pseudo amino acid composition, we develop fisher-discriminant based classifier to predict cell wall lytic enzymes. Experiments show that 66.7% sensitivity with 88.6% specificity is obtained. The method is further able to predict endolysin and autolysin with an overall accuracy of 92.9%. Results demonstrated that our method can provide highly useful information for further bacterial control research.

Predicting protein folding rates using the concept of Chou's pseudo amino acid composition

“…69, among the three cross-validation methods, the jackknife test is regarded as one of the most effective and objective methods for crossvalidation in statistics because it can always yield an unique result and obtain a more accurate estimation of the prediction accuracy for a given benchmark dataset, and hence has been increasingly used and widely recognized by investigators for examining the accuracy of various predictors. [40][41][42]49,[51][52][53]57,58,60,70,71 Accordingly, in this study the jackknife test was adopted to evaluate the prediction method as well. In the jackknife test, each protein in the dataset is singled out in turn as an independent testing sample, and all the rule parameters are calculated without using this protein.…”

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

“…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;). In the jackknife or leave-one-out test each case in the database is predicted for the model constructed using all the cases except the one being predicted.…”

PseDNA‐Pro: DNA‐Binding Protein Identification by Combining Chou’s PseAAC and Physicochemical Distance Transformation

“…For a summary about its recent development and applications, please see a comprehensive review. [35] Ever since the concept of PseAAC was proposed by Chou [34] in 2001, it has rapidly penetrated into almost all the fields of protein attribute prediction, such as identifying bacterial virulent proteins, [36] predicting homo-oligomeric proteins, [37] predicting anticancer peptides, [38] predicting protein secondary structure content, [39] predicting supersecondary structure, [40] predicting protein structural classes, [41,42] predicting protein quaternary structure, [43] predicting enzyme family and subfamily classes, [44][45][46] predicting protein subcellular location, [47,48] predicting subcellular localization of apoptosis proteins, [49][50][51][52] predicting protein subnuclear location, [43] predicting protein submitochondria locations, [53][54][55] identifying cell wall lytic enzymes, [56] identifying risk type of human papillomaviruses, [57] identifying DNA-binding proteins, [3] predicting G-Protein-Coupled Receptor Classes, [58][59] predicting protein folding rates, [60] predicting outer membrane proteins, [61] predicting cyclin proteins, [62] predicting GABA(A) receptor proteins, [63] identifying bacterial secreted proteins, [64] identifying the cofactors of oxidoreductases, [65] identifying lipase types, [66] identifying protease family, [67] predicting Golgi protein types, [68] classifying amino acids, …”