Hidden-genome classifier to quantify heterogeneity of intrahepatic cholangiocarcinoma: retrospective review

Intrahepatic cholangiocarcinoma (IHC) is a heterogeneous tumor. The hidden-genome classifier is a supervised machine learning-based algorithm to quantify tumor heterogeneity and improve classification. Researchers at Memorial Sloan Kettering Cancer Center (New York, NY) conducted a retrospective review of 1,370 patients with IHC, extrahepatic cholangiocarcinoma (EHC), gallbladder cancer (GBC), hepatocellular carcinoma (HCC), of biphenotypic tumors. In this study, 410 IHC (78%) had > 50% genetic homology with EHC/GBC, while 122 (23%) had > 90% homology (‘biliary class’), characterized by alterations of KRAS, SMAD4, and CDKN2A loss; while 22% IHC had > 50% genetic homology with HCC, and 30 (5,7%) had > 90% homology (‘HCC class’), characterized by TERT alterations. Patients with biliary- versus non-biliary class IHC had median overall survival of 1 year (95%-bti 0,77-1,5) versus 1.8 years (1,6-2,0) for unresectable disease and 2,4 years (2,1-NR) versus 5,1 years (4,8-6,9) for resectable disease. Large-duct IHC was more common in the biliary class, while the HCC class was composed mostly of small-duct IHC. The hidden-genome classifier predicted OS independent of FGFR2 and IDH1 alterations. The histology subtype did not predict OS. The authors conclude that these results may explain the differential treatment responses seen in IHC.