A deep-learning model for quantifying circulating tumour DNA from the density distribution of DNA-fragment lengths.

Journal: Nature biomedical engineering
PMID: 40055581

Abstract

The quantification of circulating tumour DNA (ctDNA) in blood enables non-invasive surveillance of cancer progression. Here we show that a deep-learning model can accurately quantify ctDNA from the density distribution of cell-free DNA-fragment lengths. We validated the model, which we named 'Fragle', by using low-pass whole-genome-sequencing data from multiple cancer types and healthy control cohorts. In independent cohorts, Fragle outperformed tumour-naive methods, achieving higher accuracy and lower detection limits. We also show that Fragle is compatible with targeted sequencing data. In plasma samples from patients with colorectal cancer, longitudinal analysis with Fragle revealed strong concordance between ctDNA dynamics and treatment responses. In patients with resected lung cancer, Fragle outperformed a tumour-naive gene panel in the prediction of minimal residual disease for risk stratification. The method's versatility, speed and accuracy for ctDNA quantification suggest that it may have broad clinical utility.

Authors

  • Guanhua Zhu
    Department of Urology, the First Affiliated Hospital of Soochow University, Suzhou, China.
  • Chowdhury Rafeed Rahman
    United International University, Dhaka, Bangladesh.
  • Victor Getty
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Denis Odinokov
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Probhonjon Baruah
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Hanaé Carrié
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Avril Joy Lim
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Yu Amanda Guo
    Computational and Systems Biology 3, Genome Institute of Singapore, A∗STAR (Agency for Science, Technology and Research), Singapore, Singapore.
  • Zhong Wee Poh
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Ngak Leng Sim
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Ahmed Abdelmoneim
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Yutong Cai
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Lakshmi Narayanan Lakshmanan
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Danliang Ho
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Saranya Thangaraju
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Polly Poon
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Yi Ting Lau
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Anna Gan
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Sarah Ng
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Si-Lin Koo
    National Cancer Center Singapore, Singapore, Singapore.
  • Dawn Q Chong
    Duke-NUS Medical School, National University of Singapore, Singapore, Singapore.
  • Brenda Tay
    National Cancer Center Singapore, Singapore, Singapore.
  • Tira J Tan
    National Cancer Center Singapore, Singapore, Singapore.
  • Yoon Sim Yap
    Duke-NUS Medical School, National University of Singapore, Singapore, Singapore.
  • Aik Yong Chok
    Singapore General Hospital, Singapore, Singapore.
  • Matthew Chau Hsien Ng
    Duke-NUS Medical School, National University of Singapore, Singapore, Singapore.
  • Patrick Tan
    Duke-NUS Medical School, National University of Singapore, Singapore.
  • Daniel Tan
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Limsoon Wong
    Department of Computer Science, National University of Singapore, Singapore; Department of Pathology, National University of Singapore, Singapore.
  • Pui Mun Wong
    Genome Institute of Singapore (GIS), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.
  • Iain Beehuat Tan
    Division of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore.
  • Anders Jacobsen Skanderup
    Computational and Systems Biology 3, Genome Institute of Singapore, A∗STAR (Agency for Science, Technology and Research), Singapore, Singapore.

Keywords

External Resources

Popular Topics
Recent Journals