Application of amino acid occurrence for discriminating different folding types of globular proteins

Abstract

BackgroundPredicting the three-dimensional structure of a protein from its amino acid sequence is a long-standing goal in computational/molecular biology. The discrimination of different structural classes and folding types are intermediate steps in protein structure prediction.ResultsIn this work, we have proposed a method based on linear discriminant analysis (LDA) for discriminating 30 different folding types of globular proteins using amino acid occurrence. Our method was tested with a non-redundant set of 1612 proteins and it discriminated them with the accuracy of 38%, which is comparable to or better than other methods in the literature. A web server has been developed for discriminating the folding type of a query protein from its amino acid sequence and it is available at http://granular.com/PROLDA/.ConclusionAmino acid occurrence has been successfully used to discriminate different folding types of globular proteins. The discrimination accuracy obtained with amino acid occurrence is better than that obtained with amino acid composition and/or amino acid properties. In addition, the method is very fast to obtain the results.

A Tri-Gram Based Feature Extraction Technique Using Linear Probabilities of Position Specific Scoring Matrix for Protein Fold Recognition

“…The RBF kernel parameters, gamma and , are optimized using LibSVM. The following feature sets are computed from the original protein sequences for the experiment: PF1, PF2 [21], PF [22], Occurrence (O) [19], AAC and [6]. We have used PSSM probabilities to find the consensus sequence for each of the original protein sequence in both of the datasets.…”

“…The TG dataset extracted by [19] consists of 1612 proteins belonging to 30 most populated folds from the SCOP 1.73. The sequence similarity of protein of TG datasets is no more than 25%.…”

“…These physicochemical attributes are usually selected in an arbitrary way and recently a systematic way of selecting physicochemical attributes was proposed by [18]. Taguchi and Gromiha [19] proposed features which are based on amino acids' occurrence; Shamim et al [20] have extracted features from the structural information of amino acid residues and amino acid residue pairs; Ghanty and Pal, [21] proposed pairwise frequencies of amino acids separated by one residue (PF1) and pairwise frequencies of adjacent amino acid residues (PF2). There are 400 features each in PF1 and PF2.…”

“…In experiment, we apply our procedure on two benchmarks namely Taguchi and Gromiha (TG), [19] dataset and extended Ding and Dubchak (EDD) [6] dataset. We performed -fold cross-validation on the datasets and obtained very promising recognition performance.…”

Protein Fold Recognition with Representation Learning and Long Short-Term Memory

“…Similarly, it has been pointed out that the co-occurrence information of amino acids in proteins is also important for capturing protein structures [6], [7], [24]. In addition, in most existing methods for PFR, feature vectors of amino acids typically include physicochemical information such as hydrophobicity, polarity, and van der Waals volume.…”