Table 5 Statistical parameters and regression models for \({M_2(G)}\).

From: A graph-based computational approach for modeling physicochemical properties in drug design

Property

Models

Equations

R

\(R^2\)

\(S_{E}\)

F

p-value

BP

Linear

\(157.6296 + 2.5346 \times M_2\)

0.977

0.955

0.172

216.954

4.16424E-08

Quadratic

\(182.7138 + 2.0215 \times M_2 + 0.0022 \times M_2^2\)

0.977

0.957

27.046

99.566

7.27026E-07

ENP

Linear

\(36.4880 + 0.3200 \times M_2\)

0.944

0.891

0.035

82.224

3.8679E-06

Quadratic

\(49.2737 + 0.0585 \times M_2 + 0.0011 \times M_2^2\)

0.944

0.904

5.268

42.391

2.62732E-05

FP

Linear

\(50.5209 + 1.4520 \times M_2\)

0.933

0.871

0.176

67.859

9.103E-06

Quadratic

\(120.2526 + 0.0255 \times M_2 + 0.0060 \times M_2^2\)

0.933

0.889

25.978

36.104

5.02221E-05

MR

Linear

\(39.8439 + 0.3083 \times M_2\)

0.884

0.781

0.051

35.830

0.00013462

Quadratic

\(37.5926 + 0.3544 \times M_2 + -0.0002 \times M_2^2\)

0.884

0.782

8.165

16.158

0.001

POL

Linear

\(15.8151 + 0.1221 \times M_2\)

0.884

0.782

0.020

35.887

0.0001

Quadratic

\(14.8643 + 0.1416 \times M_2 + -0.0001 \times M_2^2\)

0.884

0.782

3.230

16.188

0.001

MW

Linear

\(169.4657 + 1.1531 \times M_2\)

0.888

0.789

0.188

37.463

0.0001

Quadratic

\(143.4164 + 1.6860 \times M_2 + -0.0023 \times M_2^2\)

0.888

0.792

29.637

17.222

0.0008

HAC

Linear

\(4.4529 + 0.1254 \times M_2\)

0.974

0.949

0.009

187.427

8.38367E-08

Quadratic

\(1.6039 + 0.1837 \times M_2 + -0.0002 \times M_2^2\)

0.974

0.953

1.390

92.565

9.94658E-07

Com

Linear

\(42.3828 + 2.8515 \times M_2\)

0.971

0.944

0.218

170.113

1.32945E-07

Quadratic

\(-7.7873 + 3.8779 \times M_2 + -0.0043 \times M_2^2\)

0.971

0.947

33.878

80.470

1.81026E-06

MV

Linear

\(143.0209 + 0.6395 \times M_2\)

0.772

0.596

0.166

14.761

0.003

Quadratic

\(85.2153 + 1.8221 \times M_2 + -0.0050 \times M_2^2\)

0.772

0.638

24.975

7.959

0.010

Back to article page