Year: 2021 | Month: June | Volume 9 | Issue 1
Identifying a novel microRNA biomarker for renal cell
carcinoma using a machine learning approach
In the United States, over 200,000 people live with RCC; the mortality of half these patients significantly increase due to the lack of adequate and rapid diagnosis (Campbell, 2014). MicroRNAs have been found to be strong biomarkers of tumors, easily detected in the bloodstream around the tumor (Moldovan et al., 2014). Many regulated microRNAs affect the outcome of cancers. There is limited previous research in microRNAs’ potential role in RCC. A total of 7223 isoform microRNA expressions of healthy and cancerous RCC samples were taken from the Gene Expression Omnibus. Of the microRNAs, the Best First Attribute Selector (BFAS) was used in the Weka interface to choose 53 microRNAs, which are most significant in predicting each patient’s outcome. The dataset was separated between training and testing data using a 4-fold cross-validation. Moreover, algorithms were run with the selected features to determine the highest classification accuracy, precision, and recall. The BFAS with the J48 decision tree algorithm and the BFAS with a Hoeffding Tree algorithm each had an accuracy of 91.89%. According to these models, bta-miR-200c_st and ACA39_st may be significant as biomarkers of RCC.
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
Print This Article
Email This Article to Your Friend