TY - JOUR
T1 - A cfDNA methylation-based tissue-of-origin classifier for cancers of unknown primary
AU - Conway, Alicia-Marie
AU - Pearce, Simon P.
AU - Clipson, Alexandra
AU - Hill, Steven
AU - Chemi, Francesca
AU - Slane-Tan, Dan
AU - Ferdous, Saba
AU - Hossain, A S Md Mukarram
AU - Kamieniecka, Katarzyna
AU - White, Daniel J.
AU - Mitchell, Claire
AU - Kerr, Alastair
AU - Krebs, Matthew G.
AU - Brady, Gerard
AU - Dive, Caroline
AU - Cook, Natalie
AU - Rothwell, Dominic
PY - 2024/4/17
Y1 - 2024/4/17
N2 - Abstract: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 are unexplored in CUP cohorts. Here we describe CUPiD, a machine learning classifier for accurate TOO predictions across 29 tumour classes using circulating cell-free DNA (cfDNA) methylation patterns. We tested CUPiD on 143 cfDNA samples from patients with 13 cancer types alongside 27 non-cancer controls, with overall sensitivity of 84.6% and TOO accuracy of 96.8%. In an additional cohort of 41 patients with CUP CUPiD predictions were made in 32/41 (78.0%) cases, with 88.5% of the predictions clinically consistent with a subsequent or suspected primary tumour diagnosis, when available (23/26 patients). Combining CUPiD with cfDNA mutation data demonstrated potential diagnosis re-classification and/or treatment change in this hard-to-treat cancer group.
AB - Abstract: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 are unexplored in CUP cohorts. Here we describe CUPiD, a machine learning classifier for accurate TOO predictions across 29 tumour classes using circulating cell-free DNA (cfDNA) methylation patterns. We tested CUPiD on 143 cfDNA samples from patients with 13 cancer types alongside 27 non-cancer controls, with overall sensitivity of 84.6% and TOO accuracy of 96.8%. In an additional cohort of 41 patients with CUP CUPiD predictions were made in 32/41 (78.0%) cases, with 88.5% of the predictions clinically consistent with a subsequent or suspected primary tumour diagnosis, when available (23/26 patients). Combining CUPiD with cfDNA mutation data demonstrated potential diagnosis re-classification and/or treatment change in this hard-to-treat cancer group.
KW - Biomarkers, Tumor/genetics
KW - Cell-Free Nucleic Acids/genetics
KW - DNA Methylation
KW - Humans
KW - Liquid Biopsy
KW - Neoplasms, Unknown Primary/genetics
UR - http://www.scopus.com/inward/record.url?scp=85190674435&partnerID=8YFLogxK
U2 - 10.1038/s41467-024-47195-7
DO - 10.1038/s41467-024-47195-7
M3 - Article
C2 - 38632274
SN - 2041-1723
VL - 15
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 3292
ER -
