Development of a new oligonucleotide block location-based feature extraction (BLBFE) method for the classification of riboswitches

As knowledge of genetics and genome elements increases, the demand for the development of bioinformaticstools for analyzing these data are raised. Riboswitches are genetic components, usually located in theuntranslated regions of mRNAs, that regulate gene expression. Additionally, their interaction with antibioticshas been recently suggested, implying a role in antibiotic effects and resistance. Following a previouslypublished sequential block finding algorithm, herein, we report the development of a new block locationbasedfeature extraction strategy (BLBFE). This procedure utilizes the locations of family-specific sequentialblocks on riboswitch sequences as features. Furthermore, the performance of other feature extractionstrategies, including mono- and dinucleotide frequencies, k-mer, DAC, DCC, DACC, PC-PseDNC-Generaland SC-PseDNC-General methods, was investigated. KNN , LDA , naïve Bayes , PNN and decision treeclassifiers accompanied by V-fold cross-validation were applied for all methods of feature extraction, andtheir performances based on the defined feature extraction strategies were compared. Performance measuresof accuracy, sensitivity, specificity and F-score for each method of feature extraction were studied. Theproposed feature extraction strategy resulted in a classification of riboswitches with an average correctclassification rate (CCR) of ۹۰.۸%. Furthermore, the obtained data confirmed the performance of thedeveloped feature extraction method with an average accuracy of ۹۶.۱%, an average sensitivity of ۹۰.۸%, anaverage specificity of ۹۷.۵۲% and an average F-score of ۹۰.۶۹%. Our results implied that the proposedfeature extraction (BLBFE) method can classify and discriminate riboswitch families with high CCR,accuracy, sensitivity, specificity and F-score values.

Keywords:

Riboswitches , feature extraction , sequential blocks , block location-based feature extraction , classification , performance measures