Pan-Cancer Detection and Typing by Mining Patterns in Large Genome-Wide Cell-Free DNA Sequencing Datasets
Jazyk angličtina Země Anglie, Velká Británie Médium print
Typ dokumentu časopisecké články, práce podpořená grantem
PubMed
35769009
DOI
10.1093/clinchem/hvac095
PII: 6621909
Knihovny.cz E-zdroje
- Klíčová slova
- cfDNA, ctDNA, hematological malignancies, liquid biopsy, machine learning, ovarian tumors, solid tumors,
- MeSH
- lidé MeSH
- nádorové biomarkery genetika MeSH
- nádory * diagnóza genetika MeSH
- sekvenování celého genomu MeSH
- volné cirkulující nukleové kyseliny * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- Názvy látek
- nádorové biomarkery MeSH
- volné cirkulující nukleové kyseliny * MeSH
BACKGROUND: Cell-free DNA (cfDNA) analysis holds great promise for non-invasive cancer screening, diagnosis, and monitoring. We hypothesized that mining the patterns of cfDNA shallow whole-genome sequencing datasets from patients with cancer could improve cancer detection. METHODS: By applying unsupervised clustering and supervised machine learning on large cfDNA shallow whole-genome sequencing datasets from healthy individuals (n = 367) and patients with different hematological (n = 238) and solid malignancies (n = 320), we identified cfDNA signatures that enabled cancer detection and typing. RESULTS: Unsupervised clustering revealed cancer type-specific sub-grouping. Classification using a supervised machine learning model yielded accuracies of 96% and 65% in discriminating hematological and solid malignancies from healthy controls, respectively. The accuracy of disease type prediction was 85% and 70% for the hematological and solid cancers, respectively. The potential utility of managing a specific cancer was demonstrated by classifying benign from invasive and borderline adnexal masses with an area under the curve of 0.87 and 0.74, respectively. CONCLUSIONS: This approach provides a generic analytical strategy for non-invasive pan-cancer detection and cancer type prediction.
Centre for Human Genetics University Hospitals Leuven Leuven Belgium
Department of Development and Regeneration Woman and Child KU Leuven Leuven Belgium
Department of Gynecology and Obstetrics University Hospitals Leuven Leuven Belgium
Department of Hematology University Hospitals Leuven Leuven Belgium
Department of Human Genetics Laboratory of Genetics of Malignant Diseases KU Leuven Leuven Belgium
Department of Human Genetics Laboratory of Translational Genetics VIB KU Leuven Leuven Belgium
Department of Oncology Laboratory of Experimental Oncology KU Leuven Leuven Belgium
Department of Oncology Laboratory of Gynecological Oncology KU Leuven Leuven Belgium
Department of Oncology Molecular Digestive Oncology KU Leuven Leuven Belgium
Department of Pneumology University Hospitals Leuven Leuven Belgium
Multidisciplinary Breast Centre Leuven Cancer Institute University Hospitals Leuven Leuven Belgium
Citace poskytuje Crossref.org