Optimized gene selection and classification of cancer from microarray gene expression data using deep learning

Cancer is the major leading reason of death around the world. However, the early identification and prediction of a cancer type is very critical for patient's health. Recently, microarray gene expression data was utilized for efficient and early diagnosis of cancer. Previous work shows that microarray data has two major issues which are high dimensionality and small sample size. Several researchers have analyzed and evaluated the cancer classification problem using different statistical and machine learning-based approaches but there are still some issues with these approaches that make cancer classification a nontrivial task. Such as, the inability of certain machine learning algorithms to use unstructured data has limited their utility in the cancer classification process. Convolutional neural networks are proven to very suitable to analyze variety of unstructured data. This ability allowed the deep learning algorithms to play a vibrant part in early detection of cancer through data classification. In this research, a hybrid deep learning model based on Laplacian Score-Convolutional Neural Network (LS-CNN) is employed for the classification of given cancer's data. The performance of the proposed system was evaluated on 10 different benchmark datasets using various performance measurement metrics such as accuracy and confusion matrix. The experimental results conclude that proposed LS-CNN model outperformed compared to traditional machine learning and recently used deep learning approaches.