This study introduces a stacked ensemble machine learning classifier designed to predict the tissue of origin for cancers using circulating tumor DNA (ctDNA). The model integrates 11 multidimensional ctDNA features, encompassing genomic, fragmentomic, methylation/repeat, and microbial signals, derived from low-pass whole-genome sequencing. It demonstrated robust performance, achieving top-1 and top-2 accuracies of 80% and 90% in an independent validation cohort of 1,221 samples. The classifier proved effective even with low tumor fractions and successfully identified the primary site in 73.3% of cancers of unknown primary (CUP) cases. This non-invasive approach holds significant potential for guiding clinical decision-making.
This study investigates a simplified approach to identify lung origin in cancers of unknown primary (CUP). Researchers found that the presence of SMARCA4 mutations, combined with a history of smoking, is strongly associated with lung-origin CUP (CUP-Lung). This combination offers a 76% probability of lung origin, even without detectable pulmonary involvement. This method could serve as a surrogate for whole-genome sequencing (WGS) to guide organ-directed treatments.
Otolaryngologia polska = The Polish otolaryngology ·
This study analyzed the genomic profile of 480 patients with metastatic adenocarcinoma of unknown primary (ACUP) using the FoundationOne CDx platform. The most frequent mutations included TP53, KRAS, and CDKN2A. Results showed that GNAS and PIK3CA mutations were associated with better overall survival. Conversely, ARID1A and NOTCH1 alterations were linked to a worse prognosis. These findings highlight the significance of specific genomic alterations as prognostic markers in ACUP.