Finding new cancer epigenetic and genetic biomarkers from cell-free DNA by combining SALP-seq and machine learning.

摘要: The effective non-invasive diagnosis and prognosis are critical for cancer treatment. plasma cell-free DNA (cfDNA) provides a good material liquid biopsy its worth in this field is increasingly explored. Here we describe new pipeline effectively finding cfDNA-based biomarkers cancers by combining SALP-seq machine learning. Using the pipeline, 30 cfDNA samples from 26 esophageal (ESCA) patients 4 healthy people were analyzed as an example. As result, 103 epigenetic markers (including 54 genome-wide 49 promoter markers) 37 genetic identified cancer. These provide ESCA diagnosis, therapy. Importantly, these markers, especially not only shed important insights on regulatory mechanisms of cancer, but also could be used to classify samples. We therefore developed In study, discovered clinical distinct other reported characters.