minMLST is a machine-learning based methodology for identifying a minimal subset of genes
that preserves high discrimination among bacterial strains. It combines well known
machine-learning algorithms and approaches such as XGBoost, distance-based hierarchical
clustering, and SHAP.
minMLST quantifies the importance level of each gene in an MLST scheme and allows the user
to investigate the trade-off between minimizing the number of genes in the scheme vs preserving
a high resolution among strain types.