Fig. 2From: SNooPer: a machine learning-based method for somatic variant identification from low-pass next-generation sequencingDatasets used to develop and assess SNooPer. All 3 datasets were generated from real childhood acute lymphoblastic leukemia samples. Arrows indicate sequencing overlaps between datasets. Re-sequencing was used as orthogonal validation for the training phases of the algorithm. RF Models (1A, 1B, 1C and 2) resulting from these training phases are shown below the corresponding arrowsBack to article page