Fig. 7From: A comparison of machine learning and Bayesian modelling for molecular serotypingError rate in the high confidence group of samples against the percentage of the dataset in that group. The GBM results and a threshold on the percentage of a serotype’s cps genes significantly present were combined in order to divide the dataset into two groups of samples, a high confidence group of samples (Group C) and others (Group NC). The graph plots the error rate in Group C against the percentage of the dataset in that group, as the threshold is varied. For datasets D.36 and D.73Back to article page