Skip to main content
. 2023 Dec 19;14(12):843. doi: 10.1038/s41419-023-06329-3

Fig. 1. Sketch map of study design and research pipeline for early detection of ESCC.

Fig. 1

A 5hmC-based diagnostic model and low-pass WGS-based diagnostic model were developed to identify ctDNA from plasma cfDNA using a machine learning approach. A total of 171 subjects were involved as a Southern ESCC cohort, and blood samples were collected to perform 5hmC-seqeuncing and low-pass WGS, respectively. Two-thirds of the subjects were randomly selected as a training set, and the remaining one-third of the subjects were used as an independently internal Southern-ESCC test set to evaluate the model performance. A downloaded ESCC-5hmC dataset was used as an independent external Northern-ESCC test set. The research pipeline details are illustrated in supplementary Fig. S2. ctDNA cell-free tumor DNA, cfDNA cell-free DNA, HC healthy controls individuals, ESCC esophageal squamous cell carcinoma, Mid-Ad middle-advanced, 5hmC 5-hydroxymethylcytosines, WGS whole genome sequencing.