Ultrasensitive detection of circulating tumour DNA via deep methylation sequencing aided by machine learning

Nat Biomed Eng. 2021 Jun;5(6):586-599. doi: 10.1038/s41551-021-00746-5. Epub 2021 Jun 15.

Abstract

The low abundance of circulating tumour DNA (ctDNA) in plasma samples makes the analysis of ctDNA biomarkers for the detection or monitoring of early-stage cancers challenging. Here we show that deep methylation sequencing aided by a machine-learning classifier of methylation patterns enables the detection of tumour-derived signals at dilution factors as low as 1 in 10,000. For a total of 308 patients with surgery-resectable lung cancer and 261 age- and sex-matched non-cancer control individuals recruited from two hospitals, the assay detected 52-81% of the patients at disease stages IA to III with a specificity of 96% (95% confidence interval (CI) 93-98%). In a subgroup of 115 individuals, the assay identified, at 100% specificity (95% CI 91-100%), nearly twice as many patients with cancer as those identified by ultradeep mutation sequencing analysis. The low amounts of ctDNA permitted by machine-learning-aided deep methylation sequencing could provide advantages in cancer screening and the assessment of treatment efficacy.

Publication types

  • Multicenter Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adult
  • Biomarkers, Tumor / blood
  • Biomarkers, Tumor / genetics*
  • Case-Control Studies
  • Circulating Tumor DNA / blood
  • Circulating Tumor DNA / genetics*
  • DNA Methylation
  • Early Detection of Cancer / methods
  • Female
  • High-Throughput Nucleotide Sequencing
  • Humans
  • Lung Neoplasms / blood
  • Lung Neoplasms / diagnosis*
  • Lung Neoplasms / genetics*
  • Lung Neoplasms / pathology
  • Machine Learning / statistics & numerical data*
  • Male
  • Middle Aged
  • Sequence Analysis, DNA / methods

Substances

  • Biomarkers, Tumor
  • Circulating Tumor DNA