Table 2 Number of sequences, species, sequences/species for the considered seven categories of datasets. For instance, in the first category there are 3770 species with 11210 sequences, where each species has 3 sequences. Further, in the category with k sequences per species, a k-fold cross validation was adopted where k-1 sequences per species were used to train the model and rest one sequence was used to assess the model accuracy.

From: funbarRF: DNA barcode-based fungal species prediction using multiclass Random Forest supervised learning model