Machine learning to detect the SINEs of cancer

We previously described an approach called RealSeqS to evaluate aneuploidy in plasma cell-free DNA (cfDNA) through the amplification of ~350,000 repeated elements with a single primer. We hypothesized that an unbiased evaluation of the large amount of sequencing data obtained with RealSeqS might reveal other differences between plasma samples from patients with and without cancer. This hypothesis was tested through the development of a novel machine-learning approach called Alu Profile Learning Using Sequencing (A-PLUS) and its application to samples from 5108 individuals, 2037 with cancer and the remainder without cancer. Samples from cancer patients and controls were pre-specified into four cohorts used for: 1) model training, 2) analyte integration and threshold determination, 3) validation, and 4) reproducibility. A-PLUS alone provided a sensitivity of 40.5% across 11 different cancer types in the Validation Cohort, at a specificity of 98.5%. Combining A-PLUS with aneuploidy and 8 common protein biomarkers detected 51% of 1167 cancers at 98.9% specificity. We found that part of the power of A-PLUS could be ascribed to a single feature – the global reduction of AluS sub-family elements in the circulating DNA of cancer patients. We confirmed this reduction through the analysis of another independent dataset obtained with a very different approach (whole genome sequencing). The evaluation of Alu elements therefore has the potential to enhance the performance of several methods designed for the earlier detection of cancer.

• Type: Other
• Archiver: European Genome-Phenome Archive (EGA)