Skip to main content
Fig. 5 | BMC Genomics

Fig. 5

From: svclassify: a method to establish benchmark structural variant calls

Fig. 5

ROC curves for One-class classification using the L1 Distance, treating the 4000 Random regions as negatives and the Personalis or 1000 Genomes calls as positives. (a) ROC curves for one-class models for each dataset separately and for all combined for the Personalis validated deletion calls. (b) ROC curves for one-class models for each dataset separately and for all combined for the 1000 Genomes validated deletion calls. (c) ROC curves for one-class model requiring 1 or more, 2 or more, 3 or more, or all 4 technologies to have high classification scores for the Personalis validated deletion calls. (d) ROC curves for one-class model requiring 1 or more, 2 or more, 3 or more, or all 4 technologies to have high classification scores for the 1000 Genomes validated deletion calls. The 3 or more classification method is used to produce the final high-confidence SVs in this work. The horizontal axis shows the false positive rate (from the random set of regions matching the size distribution of the Personalis deletions) and the vertical axis shows the corresponding true positive rate (assuming all the validated/assembled calls are true). See original data at https://plot.ly/345/~parikhhm/, https://plot.ly/353/~parikhhm/, https://plot.ly/361/~parikhhm/, and https://plot.ly/369/~parikhhm/

Back to article page