Prediction of HIV-1 protease cleavage site using a combination of sequence, structural, and physicochemical features

Table 7 Interpretable biological features selected by decision tree model based on Seq + Str features for the 746 dataset

Rank	Variable	Description	Importance
1	RSA_4	RSA at the 4^th position of an octamer	1.0000
2	MT	DipC of methionine & threonine	0.7855
3	C	AAC of cysteine	0.6060
4	RSA_5	RSA at the 5^th position of an octamer	0.5238
5	VH	DipC of valine & histidine	0.4059
6	AE	DipC of alanine & glutamic acid	0.3769
7	FL	DipC of phenylalanine & leucine	0.3268

ISSN: 1471-2105