Skip to main content

Table 2 The sequence and structural features extracted and the feature dimensionalities

From: SIMLIN: a bioinformatics tool for prediction of S-sulphenylation in the human proteome based on multi-stage ensemble-learning models

Feature type Feature Cluster Dimension
Sequence AAC 20
CKSAAP 2400
BLOSUM62 441
PSSM 400
AAindex 1344
Binary 441
Structural Predicted protein disordered region 20
Predicted protein secondary structure 84
Predicted surface accessibility 147
Total   5297