Fig. 7From: Accurate prediction of metagenome-assembled genome completeness by MAGISTA, a random forest model built on alignment-free intra-bin statisticsPerformance of CheckM (a and b), MAGISTA (c and d) and MAGISTIC (e and f) on all test datasets for completeness (a, c and e) and purity (b, d and f). The black and blue lines indicate the ideal performance and best linear fit, respectively. Data points are coloured in accordance with their taxonomic relation to the most related genome in the training/reference set of the method whose performance is shownBack to article page