iNuc-ext-PseTNC: an efficient ensemble model for identification of nucleosome positioning by extending the concept of Chou’s PseAAC to pseudo-tri-nucleotide composition
Nucleosome is a central element of eukaryotic chromatin, which composes of histone proteins and DNA molecules. It performs vital roles in many eukaryotic intra-nuclear processes, for instance, chromatin structure and transcriptional regulation formation. Identification of nucleosome positioning via wet lab is difficult; so, the attention is diverted towards the accurate intelligent automated prediction. In this regard, a novel intelligent automated model “iNuc-ext-PseTNC” is developed to identify the nucleosome positioning in genomes accurately. In this predictor, the sequences of DNA are mathematically represented by two different discrete feature extraction techniques, namely pseudo-tri-nucleotide composition (PseTNC) and pseudo-di-nucleotide composition. Several contemporary machine learning algorithms were examined. Further, the predictions of individual classifiers were integrated through an evolutionary genetic algorithm. The success rates of the ensemble model are higher than individual classifiers. After analyzing the prediction results, it is noticed that iNuc-ext-PseTNC model has achieved better performance in combination with PseTNC feature space, which are 94.3%, 93.14%, and 88.60% of accuracies using six-fold cross-validation test for the three benchmark datasets S1, S2, and S3, respectively. The achieved outcomes exposed that the results of iNuc-ext-PseTNC model are prominent compared to the existing methods so far notifiable in the literature. It is ascertained that the proposed model might be more fruitful and a practical tool for rudimentary academia and research.
KeywordsDNA SVM GA Tri-nucleotide composition
Compliance with ethical standards
Conflict of interest
The authors have no conflict of interest.
- Chen W, Feng P, Lin H, Chou K (2013b) iRSpot-PseDNC: identify recombination spots with pseudo dinucleotide composition. Nucleic Acids Res gks1450Google Scholar
- Mavrich TN, Ioshikhes IP, Venters BJ, Jiang C, Tomsho LP, Qi J, Schuster SC, Albert I, Pugh BF (2008c) A barrier nucleosome model for statistical positioning of nucleosomes throughout the yeast genome. Genome ResGoogle Scholar
- Xiao X, Cheng X, Su S, Mao Q, Chou K-C (2017) pLoc-mGpos: incorporate key gene ontology information into general PseAAC for predicting subcellular localization of Gram-positive bacterial proteins. Nat Sci 9:330Google Scholar
- Zhang W, Shi J, Tang G, Wu W, Yue X, Li D (2017) Predicting small RNAs in bacteria via sequence learning ensemble method. In: Bioinformatics and biomedicine (BIBM), 2017 IEEE international conference on, IEEE, pp 643–647Google Scholar