Skip to main content

Table 2 The definition of the used molecular descriptors for modelling of two kinds of activities (3D7 and W2)

From: Quantitative structure–activity relationship to predict the anti-malarial activity in a set of new imidazolopiperazines based on artificial neural networks

Molecular descriptors

Definition

Descriptor category

Strain

GATS4m

Geary autocorrelation of lag 4 weighted by mass

2D autocorrelations

3D7

GATS7m

Geary autocorrelation of lag 7 weighted by mass

2D autocorrelations

3D7

Mor06u

Signal 06/unweighted

3D-MoRSE descriptors

3D7

Mor31u

3D-MoRSE, signal 31/unweighted

3D-MoRSE descriptors

3D7

+R3e

R maximal autocorrelation of lag 3/weighted by Sanderson electronegativity

GETAWAY descriptors

3D7

+R2p

R maximal autocorrelation of lag 2/weighted by polarizability

GETAWAY descriptors

3D7

BEHm3

Highest eigenvalue n.3 of Burden matrix/weighted by atomic masses

Burden eigenvalues

W2

MATS7m

Moran autocorrelation of lag 7 weighted by mass

2D autocorrelations

W2

RDF020m

Radial distribution function-020/weighted by mass

RDF descriptors

W2

Mor23u

3D-MoRSE signal 23/unweighted

3D-MoRSE descriptors

W2

Mor20p

3D-Morse signal 23/weighted by polarizability

3D-MoRSE descriptors

W2

MLOGP

Moriguchi octanol–water partition coefficient

Molecular properties

W2