Research Article

DrugECs: An Ensemble System with Feature Subspaces for Accurate Drug-Target Interaction Prediction

Table 7

The most correlated properties in AAindex1 to the top component of PCA.

PCAAAindex1Data description

1NADH010104Hydropathy scale based on self-information values in the two-state model (20% accessibility) (Naderi-Manesh et al., 2001)
2RADA880103Transfer free energy from vap to chx (Radzicka-Wolfenden, 1988)
3NADH010107Hydropathy scale based on self-information values in the two-state model (50% accessibility) (Naderi-Manesh et al., 2001)
4RICJ880112Relative preference value at C3 (Richardson-Richardson, 1988)
5KHAG800101The Kerr-constant increments (Khanarian-Moore, 1980)
6RICJ880113Relative preference value at C2 (Richardson-Richardson, 1988)
7PRAM820103Correlation coefficient in regression analysis (Prabhakaran-Ponnuswamy, 1982)

The first column denotes the top components in PCA calculation; the second column denotes the property accessions in AAindex1 dataset.