A Survey on Cancer Molecular Subtype Classification using Deep learning

Deep learning(DL) is a sub-field of artificial intelligence that mimics the human brain through computation. It has proven its proficiency in different domains, including healthcare. It has shown promising results in various health-care applications, including cancer classification, prognosis, and molecular sub-typing of cancer. Molecular sub-typing provides biological insights regarding cancer heterogeneity that may lead to personalized medicines. The objective of this review is to discuss and compare the different deep learning models used for molecular subtyping along with the different types of omics data used like gene expression data, RNA sequence data, mRNA, and miRNA. We compared and summarized the different models and data types used for the cancer molecular subtyping in a tabular format.