Skip to main content

Table 1 Summarization of different feature types and their vector representation dimensions

From: Predicting protein-ATP binding sites from primary sequence through fusing bi-profile sampling of multi-view features

Feature types Dimensionality
Position-specific scoring matrix (PSSM) 340
Position-specific scoring matrix normalized by logistic function (LogisticPSSM) 340
Bi-profiled binary amino acid composition (Bipro-aa) 34
Bi-profiled predicted secondary structure (BiPro-ss) 34
Bi-profiled predicted residue disorder (BiPro-dis) 34
Bi-profiled predicted residue solvent accessibility (Bipro-sa) 34