DREAMS: deep read-level error model for sequencing data applied to low-frequency variant calling and circulating tumor DNA detection, Genome Biology

Circulating tumor DNA detection using next-generation sequencing (NGS) data of plasma DNA is promising for cancer identification and characterization. However, the tumor signal in the blood is often low and difficult to distinguish from errors. We present DREAMS (Deep Read-level Modelling of Sequencing-errors) for estimating error rates of individual read positions. Using DREAMS, we develop statistical methods for variant calling (DREAMS-vc) and cancer detection (DREAMS-cc). For evaluation, we generate deep targeted NGS data of matching tumor and plasma DNA from 85 colorectal cancer patients. The DREAMS approach performs better than state-of-the-art methods for variant calling and cancer detection.

Sequence motifs at systematic error sites. (a) The motif around

Systematic evaluation of error rates and causes in short samples

Computational analysis of cancer genome sequencing data

Genes, Free Full-Text

Identification of 12 cancer types through genome deep learning

Genes, Free Full-Text

Genome-wide cell-free DNA mutational integration enables ultra

Potential error sources in next-generation sequencing workflow. a

Systematic comparative analysis of single-nucleotide variant

Machine learning-based genome-wide interrogation of somatic copy

Phasing analysis of lung cancer genomes using a long read

PDF) DREAMS: deep read-level error model for sequencing data

Discovering the drivers of clonal hematopoiesis

Machine learning guided signal enrichment for ultrasensitive