Clustering and classification for cancer subtype discovery and survival prediction

Abstract

Discovering diverse cancer classes or subclasses with a huge amount of diverse biological measurements provides a tough challenge and has significant implication in cancer analysis and treatment Cancer omics data such as Deoxyribonucleic Acid DNA methylation and messenger Ribonucleic acid mRNA expression can be used to discover new insights on identifying cancer subtypes However their high dimensional and multidimensional nature poses a problem Clustering methods are therefore used to find an effective low dimensional subspace of the original data and then cluster cancer samples in the reduced subspace Due to the challenge of data type diversity and big data volume only few methods can integrate these data and map them into an effective low dimensional subspace Accuracy even then remains to be a major issue Survival risk prediction and interpretation of the biological significance of different clusters is also a difficult task Therefore certain methods have been used to develop concordant structures to integrate different types of data Breast cancer is a highly heterogeneous disease and very common among western women The main cause of death is not the primary tumor but its metastases at distant sites such as lymph nodes and other organs especially the lung liver and bones The study of Circulating Tumor Cells CTCs in Peripheral Blood PB resulting from tumor cell invasion and intravascular filtration highlights their crucial role concerning tumor aggressiveness and metastasis newline