A SURVEY ON CANCER SUBTYPING BASED ON DEEP LEARNING USING PAN-CANCER AND MULTIOMIC DATA

Tumor subclasses with clinical implications are identified by breast cancer gene expression patterns. In this study, ROBERT TIBSHIRANI et al. make a suggestion. Based on changes in expression, the tumours were divided into three groups: basal epithelial-like, ERBB2-overexpressing, and normal breast-like. Two separate sets, one representing collection of 456 cDNA clones originally chosen to reflect intrinsic tumour features other being set that was highly correlated patient prognosis, clustered reveal both groupings quite robust. The basal-like subtype had dismal two oestrogen receptor-positive groups significantly different outcomes, according survival studies sub cohort patients. fibroadenomas 78 carcinomas examined. This comprises 40 have already been studied characterised. A total 85 tissue samples from 84 individuals