Skip to main content

Table 3 TCGA overall survival (OS) tasks

From: Standard machine learning approaches outperform deep representation learning on phenotype prediction from transcriptomics data

TCGA OS tasks   
ProjectDiseaseLabelLabel typeGroupSamples
CESCcervical squamous cell carcinomaOSsurvivaltrain304
COADcolon adenocarcinomaOSsurvivaltrain455
ESCAesophageal carcinomaOSsurvivaltrain184
KIRPkidney papillary cell carcinomaOSsurvivaltrain289
LUADlung adenocarcinomaOSsurvivaltrain507
OVovarian cancerOSsurvivaltrain420
PAADpancreatic adenocarcinomaOSsurvivaltrain178
SARCsarcomaOSsurvivaltrain259
STADstomach adenocarcinomaOSsurvivaltrain409
UCECuterine corpus endometrial carcinomaOSsurvivaltrain540
HNSChead-neck squamous cell carcinomaOSsurvivalvalidate501
BLCAbladder urothelial carcinomaOSsurvivaltest407
LUSClung squamous cell carcinomaOSsurvivaltest495
  1. The 13 overall survival tasks derived from TCGA used to train supervised models and validate the unsupervised embeddings. The project names correspond to those in Fig. 2