Optimization of neural network for cancer microRNA biomarkers classification

Abstract

Abstract Cancer is still a significant problem for people today because it is one of the biggest causes of death in the world. Based on GLOBOCAN data in 2018, breast cancer accounted for the world’s largest cancer mortality rate in women by 6.6% with total deaths amounting to 626,679 from 2,088,849 cases of cancer in the world. The high mortality rate of breast cancer is caused by the lack of effective early detection of the disease. 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. Cancer classification using microRNA as a feature has been done in previous studies using Neural Network Backpropagation, however without optimization and tuning parameters. In this paper, we investigated the best optimization algorithm and tuning parameter of neural network backpropagation for cancer classification using microRNA feature. The optimization algorithms were Gradient Descent, Momentum, AdaGrad, AdaDelta, RMSProp, and Adam. The result of the experiment showed that Adam and RMSPop optimizer produced high accuracy which reached 98.536% and 98.54762% accuracy.