What question did this study set out to answer?

The study aims to improve cancer classification by predicting the tissue of origin using cfDNA profiling.

August 6, 2026Molecular BiomedicineOpen Access

Integrative cfDNA profiling from low-pass whole-genome sequencing enables tissue-of-origin prediction in cancer

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates accurate cancer classification using cfDNA, indicating potential for improved treatment decisions.

The study aims to improve cancer classification by predicting the tissue of origin using cfDNA profiling.
Developed a stacked ensemble machine learning classifier using 11 cfDNA features.
Utilized five algorithms, including deep learning and gradient boosting, with five-fold cross-validation.
Evaluated performance across 17 cancer types with cohorts of 1,814 and 1,221 samples respectively.
Achieved top-1 accuracy of 78% in training and 80% in validation cohorts.
Notably predictive performance in low tumor fraction samples, retaining 71% top-1 accuracy.
In CUP cases, 73.3% of predictions aligned with clinically inferred primary sites.

Zhang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark