CUPiD, a cfDNA methylation-based tissue-of-origin classifier for Cancers of Unknown Primary

Cancers of Unknown Primary (CUP) remains a diagnostic and therapeutic challenge due to biological heterogeneity and poor responses to standard chemotherapy. Predicting tissue-of-origin (TOO) molecularly could help refine this diagnosis, with tissue acquisition barriers mitigated via liquid biopsies. However, TOO liquid biopsies have yet to be explored in CUP cohorts. Using publicly available DNA methylation data, we developed a machine learning classifier termed CUPiD with accurate TOO predictions across 29 tumour classes. We tested CUPiD on 143 cfDNA samples from patients with 13 cancer types alongside 27 non-cancer controls, with overall sensitivity of 87.1% and specificity of 97.9%. CUPiD predictions for a further 41 patients with CUP were made for 78.0% of cases, of which 71.9% were clinically consistent with a subsequent or suspected primary tumour diagnosis. Combining CUPiD with cfDNA mutation data demonstrated potential diagnosis re-classification and/or treatment change in this hard-to-treat cancer group.EGA study EGAS00001007445