Table 6. Description of the dataset used in the current study (Obtained from Virco).

Target	Amino acids	Binding Site	Drug Class	Drugs	Mutant Sequences	Data points	Mean number of mutations
Reverse Transcriptase	400*	Orthosteric	NRTI	8	10,501	72,727	22 (±9)
Reverse Transcriptase	400*	Allosteric	NNRTI	4	10,723	35,249	22 (±9)
Protease	99	Orthosteric	PI	9	27,081	180,162	10 (±6)

^*For Reverse Transcriptase only the first 400 amino acids were sequenced. The total size of the dataset is unlike any other dataset used in PCM. The number of mutations shown in the last column is the average per sequence and standard deviation when compared to HXB2.