Predicting DNA-binding proteins: approached from Chou’s pseudo amino acid composition and other specific sequence features

Abstract

DNA-binding proteins play a pivotal role in gene regulation. It is vitally important to develop an automated and efficient method for timely identification of novel DNA-binding proteins. In this study, we proposed a method based on alone the primary sequences of proteins to predict the DNA-binding proteins. DNA-binding proteins were encoded by autocross-covariance transform, pseudo-amino acid composition, dipeptide composition, respectively and also the different combinations of the three encoded methods; further, these feature matrices were applied to support vector machine classifiers to predict the DNA-binding proteins. All modules were trained and validated by the jackknife cross-validation test. Through comparing the performance of these substituted modules, the best result was obtained from pseudo-amino acid composition with the overall accuracy of 96.6% and the sensitivity of 90.7%. The results suggest that it can efficiently predict the novel DNA-binding proteins only using the primary sequences.

Wavelet images and Chou’s pseudo amino acid composition for protein classification

“…Various methods have been developed for extracting features from proteins, including pseudo amino acid composition (Chen and Li 2007;Chou 2001;Ding and Zhang 2008) and Markov chains model (Bulashevska and Eils 2006). The Chou's pseudo amino acid composition (PseAAC) ) is one of the most widely used feature extractors for peptides and proteins (Chen et al 2009;Xiao et al 2011a, b;Fang et al 2008;Nanni and Lumini 2008). While maintaining much of the sequence order information, PseAAC represents a protein sequence using a discrete model that is composed of a set of more than 20 discrete factors.…”

Using Chou’s Pseudo Amino Acid Composition and Machine Learning Method to Predict the Antiviral Peptides

“…These parameters are also given by following equations (1-4) [77]: TN FP.FN ) (TP + FN ). (TP + FP).…”

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, …”

“…Amino acid composition of proteins associated with the biochemical properties are the commonly used sequence-based features, for example Cai and Lin [1] used protein's amino acid composition, limited range correlation of hydrophobicity and solvent accessible surface area to identify DBPs; Ahmad et al [2] found the specificity of sequence level and binding level and analyzed the relationship between them; Fang et al [3] encoded the feature space by autocross-covariance (ACC) transform, pseudoamino acid composition, dipeptide composition; Zou et al [4] adopted three different feature transformation methods to generate numeric feature vectors from protein sequences; Lin et al [5] represented each sequence as pseudo amino acid composition by applied grey model. For more accurately predictive performance, the combinations of different features were employed, for example Kumar et al [6] derived sequence properties by frequency of amino acid, amino acid groups, secondary structure, comAbstract: Identification of DNA-binding proteins is an important problem in biomedical research as DNA-binding proteins are crucial for various cellular processes.…”