Predicting protein structural class with pseudo-amino acid composition and support vector machine fusion network

GPCR‐CA: A cellular automaton image approach for predicting G‐protein–coupled receptor functional classes

“…According to its definition, the PseAA composition for a given protein sample is expressed by a set of 20 1 k discrete numbers, where the first 20 represent the 20 components of the classical amino acid composition while the additional k numbers incorporate some of its sequence-order information via various different kinds of coupling modes. Ever since the concept of PseAA composition was introduced, various PseAA composition approaches have been stimulated to deal with various different problems in proteins, such as protein structural class, [33][34][35][36][37][38][39][40] protein subcellular localization, 27,[41][42][43][44][45][46][47][48][49][50][51][52][53] protein subnuclear localization, 54 To successfully use the PseAA composition for predicting various attributes of proteins, the key is how to optimally extract the features for the PseAA components. In this study, a novel approach by combining the ''grey accumulative modeling'' and the ''cellular automaton image'' 78,79 was introduced to derive the PseAA components.…”

Use of fuzzy clustering technique and matrices to classify amino acids and its impact to Chou's pseudo amino acid composition

“…In an earlier paper (Chou 2000), the physicochemical distance among the 20 amino acids (Schnieder and Wrede 1994) was adopted to define PseAA. Subsequently, some investigators used complexity measure factor , some used the values derived from the cellular automata (Xiao et al 2005b(Xiao et al , 2005c(Xiao et al , 2006(Xiao et al , 2006b, some used hydrophobic and/or hydrophilic values , Feng 2002, Wang et al 2004, Gao et al 2005, Chen et al 2006, and some were through Fourier A c c e p t e d m a n u s c r i p t 3 transform (Guo et al 2006. In view of this, the author's finding might have a series of impacts to the aforementioned work.…”

“…The pseudo amino acid composition can be used to represent a protein sequence with a discrete model yet without completely losing its sequence-order information , and hence is particularly useful for analyzing a large amount of complicated protein sequences by means of the taxonomic approach. Actually, it has been widely used to study various protein attributes, such as protein structural class (Chen et al 2006a, Chen et al 2006b, Xiao et al 2006a There are several methods that are used in order to extract characteristics of genomes and one of them is trying to find some common characteristics along its constituents. A method that can serve in this direction is the clustering procedure and more specifically fuzzy clustering.…”

Prediction of protein structural class based on Linear Predictive Coding of PSI-BLAST profiles

“…For convenience, the PSSM is denoted as is to feed these features to an appropriate classification algorithm to efficiently and accurately predict structural class. Up to now, a lot of machine-learning algorithms have been proposed, such as neural network [21], support vector machine (SVM) [22][23][24][25], fuzzy clustering [26], fuzzy k-nearest neighbor [27,28], Bayesian classification [29], logistic regression [30], rough sets [31] and classifier fusion techniques [32][33][34][35][36]. Among the aforementioned classification algorithms, SVM is the most reliable and attained excellent performance on the SCOP problem [19].…”