Support Vector Machine - Recursive Feature Elimination (SVM - RFE) for Selection of MicroRNA Expression Features of Breast Cancer

Abstract

Cancer is still a major problem for people today because it is one of the biggest causes of death in the world. Based on GLOBOCAN data in 2012, breast cancer accounted for the world's largest cancer mortality rate in women by 14.7% with total deaths amounting to 521,907 from 3,548,190 cases of cancer in the world. The high mortality rate is affected by the absence of sufficient early detection of cancer. MicroRNAs play an essential role in regulating cell division cycles, apoptosis, senescence, migration and cell invasion, and metastasis. The expression of microRNA in breast cancer shows a pattern compared to normal breasts, thus indicating its role as a potential diagnostic marker. However, not all microRNA profiles have a significant role in cancer detection. In this paper, we applied the support vector machine - recursive feature elimination (SVM-RFE) and univariate selection for feature selection of microRNA expression in breast cancer. Several experiments were conducted to select ten features with the highest ranking; therefore, it is expected to obtain a unique feature as a unique feature of breast cancer. Based on experimental results, this study obtained recommended the essential MicroRNA features for cancer analysis and biomarkers.