Figure 5From: Clustering protein sequences with a novel metric transformed from sequence similarity scores and sequence alignments with neural networksThe number of generated clusters and orphan clusters on the benchmarking dataset. Total clusters and orphan clusters for clugen and MCL at various specificities. With stricter parameter thresholds, overall specificity and the total number of clusters increases for both methods. The larger number of small clusters at higher specificities leads to a reduction in the number of orphan clusters in both methods.Back to article page