Table 4 Species identification success rates for different combinations of k-mer and g-spaced feature sets, where 4 and 5 sequences per species were used to train the prediction model. It can be seen that though the species identification success rates for both feature sets are at par, number of k-mer features used are larger than that of g-spaced features.

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