Application of supervised machine learning algorithms for the classification of regulatory RNA riboswitches

Abstract

Riboswitches, the small structured RNA elements, were discovered about a decade ago. It has been the subject of intense interest to identify riboswitches, understand their mechanisms of action and use them in genetic engineering. The accumulation of genome and transcriptome sequence data and comparative genomics provide unprecedented opportunities to identify riboswitches in the genome. In the present study, we have evaluated the following six machine learning algorithms for their efficiency to classify riboswitches: J48, BayesNet, Naïve Bayes, Multilayer Perceptron, sequential minimal optimization, hidden Markov model (HMM). For determining effective classifier, the algorithms were compared on the statistical measures of specificity, sensitivity, accuracy, F-measure and receiver operating characteristic (ROC) plot analysis. The classifier Multilayer Perceptron achieved the best performance, with the highest specificity, sensitivity, F-score and accuracy, and with the largest area under the ROC curve, whereas HMM was the poorest performer. At present, the available tools for the prediction and classification of riboswitches are based on covariance model, support vector machine and HMM. The present study determines Multilayer Perceptron as a better classifier for the genome-wide riboswitch searches.

A Novel Riboswitch Classification based on Imbalanced Sequences achieved by Machine Learning

“…Dataset of imbalanced sequences in riboswitch showed different performances of classifiers ranked as: MLP -the best and NB -the poorest regarding their mean scores that range from 0.771 to 0.961. In Table 2, individual score results of this method have shown best result in RF00234, RF00522, RF01057 (1.00 in RF): greater values than reported in other study using BLAST + (26,56), which is most popular tools in analysis of sequence similarity (56) and others (25,26). Conversion of sequences into vector revealed good results in both groups used for analysis ( Table 1, 2 and Supplementary Table S2).…”

“…Numerous machine learning applications have been developed based on different methods to detect riboswitch. However, most riboswitch classification studies applied machine learning algorithms on the imbalanced dataset (25,26). Several findings revealed the impact of an imbalance dataset on correct classification and performance of algorithms (25,26,30).…”

“…However, most riboswitch classification studies applied machine learning algorithms on the imbalanced dataset (25,26). Several findings revealed the impact of an imbalance dataset on correct classification and performance of algorithms (25,26,30). Chawla and colleagues proposed SMOTE method of treating imbalanced datasets for better classification of majority and minority instances (30,34).…”

“…The dataset for this finding contains the imbalanced datasets ranging from 4,826 instances (RF00174) to 39 (RF01051) instances ( Supplementary Table S1). Learning from the imbalanced datasets that become critical concerns nowadays, particularly when minority class contains small instances in its dataset (25,26,74). Mainstream methods dealing with imbalance data can be roughly divided into two categories.…”

“…Most reported studies are limited for the specific types of riboswitches. However, conducted frequency-dependent research revealed its importance in the classification of riboswitch (25,26). Frequency-dependent classification uses k-mers counts.…”