MicroRNAs (miRNAs) play a major role in cancer development and also act as a key factor in many other diseases. In this investigation, we propose three methods for handling miRNA expressions. The first two methods determine whether a miRNA is indicating normal or cancer condition, and the third one determines how many miRNAs are supporting the cancer sample/patient. While Method 1 acts as a two-class classifier and is based on normalized average expression value, Method 2 also does the same and is based on the normalized average intraclass distance. Method 3 checks whether a miRNA belongs to the cancer class or not, provides the percentage of supporting miRNAs for a cancer patient, and is based on weighted normalized average intraclass distance. The values of the weights are determined using exhaustive search by maximizing the accuracy in training samples. The proposed methods are tested on the differentially regulated miRNAs in three types of cancers (breast, colon, and melanoma cancer). The performances of Method 1 and Method 2 are evaluated by F score, Matthews Correlation Coefficient (MCC), and plotting "1--specificity versus sensitivity" in Receiver Operating Characteristic (ROC) space and are found to be superior to the kNN and SVM classifiers for breast, colon, and melanoma cancer data sets. It is also observed that both the sensitivity and the specificity of Method 1 and Method 2 are higher than 0.5. For the same data sets, Method 3 achieved an average accuracy of more than 98% in detecting the miRNAs, supporting the cancer condition.
展开▼
