biostudies-literatureGrewal JKCanada's Michael Smith Genome Sciences CentreFoundation for the National Institutes of HealthNational Cancer InstituteNCI NIH HHSNational Institutes of Health103705https://www.ebi.ac.uk/biostudies/studies/S-EPMC12013717biostudies-literatureUnknown6(2)We present a protocol for obtaining cancer type and subtype predictions using a machine learning method (subSCOPE). We describe steps for data preparation, subSCOPE setup, and running subSCOPE inference on prepared data. The protocol supports five -omics data types as input (DNA methylation, gene expression, microRNA [miRNA] expression, point mutations, and copy-number variants) and allows individual cancer type and data type selection. For non-The Cancer Genome Atlas (TCGA) cancer samples, it provides subtype-level classification across 26 different TCGA cancer cohorts and 106 subtypes. For complete details on the use and execution of this protocol, please refer to Ellrott et al.¹.STAR protocolsProtocol for obtaining cancer type and subtype predictions using subSCOPE.PMC12013717U24 CA264021U24CA264023U24 CA264009U24 CA210990U24CA264029U24 CA264029U24 CA264007U24 CA264023Zenklusen JCTarnuzzer RLagani VLal ALee JAWang CDrill EChagas VSUzunangelov VFerguson MLRoh WCharonyktakis PAndersen JBAkbani RGao GFShen RWang ZYau CYang LShmulevich IChiotti KEFelau IHinoue TSchultz ARoberts LRCherniack ADHoyt SHCaesar-Johnson SJCastro MAAKarlberg BJOjesina AICancer Genome Atlas Analysis NetworkEllrott KLazar AJRobertson AGFriedl VKemal AGetz GJu ZStuart JMHoadley KAWestlake LBenz CCTsamardinos IWong CKGrewal JKKnijnenburg TAJones SJMLowenstein EApolonio VHBroom BMSpellman PTRamazzotti DTercan BStruck ALaird PWDemchok JAKim TKfalseProtocol for obtaining cancer type and subtype predictions using subSCOPE.We present a protocol for obtaining cancer type and subtype predictions using a machine learning method (subSCOPE). We describe steps for data preparation, subSCOPE setup, and running subSCOPE inference on prepared data. The protocol supports five -omics data types as input (DNA methylation, gene expression, microRNA [miRNA] expression, point mutations, and copy-number variants) and allows individual cancer type and data type selection. For non-The Cancer Genome Atlas (TCGA) cancer samples, it provides subtype-level classification across 26 different TCGA cancer cohorts and 106 subtypes. For complete details on the use and execution of this protocol, please refer to Ellrott et al.¹.2025-01-01T00:00:00Z2025 Jun2026-05-29T15:07:13.14Z2025-07-03T03:05:10.55ZS-EPMC120137174020283810.1016/j.xpro.2025.103705