Table 12 Statistical parameters and regression models for SA(G).

From: Graph theoretic and machine learning approaches in molecular property prediction of bladder cancer therapeutics

Property

\(\text {Model}\)

\(\text {Equation}\)

R

\(R^2\)

\(S_E\)

F

\(p\text {-value}\)

BP

Linear

\(y = 303.2454 + 10.1581\,(\textrm{TI})\)

0.938

0.879

18.078

109.166

0.000

Cubic

\(y = 427.2545 - 1.5763\,(\textrm{TI}) + 0.3272\,(\textrm{TI})^2 - 0.0027\,(\textrm{TI})^3\)

0.939

0.882

65.335

32.304

0.000

EV

Linear

\(y = 52.0214 + 1.3963\,(\textrm{TI})\)

0.907

0.822

3.116

69.450

0.000

Cubic

\(y = 78.1633 - 0.5668\,(\textrm{TI}) + 0.0407\,(\textrm{TI})^2 - 0.0002\,(\textrm{TI})^3\)

0.917

0.841

10.770

22.903

0.000

FP

Linear

\(y = 134.0183 + 6.2771\,(\textrm{TI})\)

0.945

0.893

10.432

125.174

0.000

Cubic

\(y = 102.8677 + 8.5626\,(\textrm{TI}) - 0.0456\,(\textrm{TI})^2 + 0.0003\,(\textrm{TI})^3\)

0.946

0.895

37.819

36.773

0.000

MR

Linear

\(y = 0.8885 + 3.4138\,(\textrm{TI})\)

0.989

0.978

2.431

681.613

0.000

Cubic

\(y = 5.8356 + 2.4596\,(\textrm{TI}) + 0.0399\,(\textrm{TI})^2 - 0.0004\,(\textrm{TI})^3\)

0.990

0.981

8.388

221.224

0.000

SA

Linear

\(y = 17.7509 + 3.0648\,(\textrm{TI})\)

0.795

0.632

11.237

25.721

0.000

Cubic

\(y = 179.4027 - 9.4667\,(\textrm{TI}) + 0.2735\,(\textrm{TI})^2 - 0.0017\,(\textrm{TI})^3\)

0.852

0.726

35.378

11.499

0.001

MV

Linear

\(y = -1.5252 + 9.5605\,(\textrm{TI})\)

0.974

0.949

10.605

280.989

0.000

Cubic

\(y = 80.6425 + 0.9516\,(\textrm{TI}) + 0.2629\,(\textrm{TI})^2 - 0.0024\,(\textrm{TI})^3\)

0.975

0.951

37.903

84.972

0.000

P

Linear

\(y = 0.8819 + 1.3399\,(\textrm{TI})\)

0.987

0.975

1.034

581.083

0.000

Cubic

\(y = -3.4629 + 1.5614\,(\textrm{TI}) - 0.0010\,(\textrm{TI})^2 - 0.0000\,(\textrm{TI})^3\)

0.989

0.977

3.585

186.649

0.000