RFcaller: a machine learning approach combined with read-level features to detect somatic mutations

The cost reduction in sequencing and the extensive genomic characterization of a wide variety of cancers are expanding tumor sequencing to a wide number of research groups and the clinical practice. Although specific pipelines have been generated for the identification of somatic mutations, their results usually differ considerably, and a common approach is to use several callers to achieve a more reliable set of mutations. This procedure is computationally expensive and time-consuming, and it suffers from the same limitations in sensitivity and specificity as other approaches. Expert revision of mutant calls is therefore required to verify calls that might be used for clinical diagnosis. This step could take advantage of machine learning techniques, as they provide a useful approach to incorporate expert-reviewed information for the identification of somatic mutations. Here we present RFcaller, a pipeline based on machine learning algorithms, for the detection of somatic mutations in tumor–normal paired samples that does not require large computing resources. RFcaller shows high accuracy for the detection of substitutions and insertions/deletions from whole genome or exome data. It allows the detection of mutations in driver genes missed by other approaches, and has been validated by comparison to deep and Sanger sequencing.