Predicting Mycobacterium tuberculosis Complex Clades Using Knowledge-Based Bayesian Networks
Figure 2
(a) The spoligotype conformal Bayesian network uses a single rule based on the number of repeats at the MIRU24 locus as the first level of a hierarchical Bayesian network. It uses the 43 spacers as features. CBN predicts the major lineage with high accuracy. (b) The KBBN uses multiple rules based on the presence of characteristic deletions as the first level of a hierarchical Bayesian network. As with the CBN, it uses the 43 spoligotype spacers.
