Table 9 Statistical parameters and regression models for ABC(G).

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

Property

Model

Equation

R

\(R^2\)

\(S_E\)

F

p-value

BP

Linear

\(y = 313.0270 + 13.2617(TI)\)

0.934

0.872

18.354

102.529

0.000

 

Cubic

\(y = 378.6721 + 4.0521(TI) + 0.3767(TI)^2 - 0.0045(TI)^3\)

0.935

0.873

69.495

29.922

0.000

EV

Linear

\(y = 53.0357 + 1.8363(TI)\)

0.910

0.828

3.028

72.210

0.000

Cubic

\(y = 69.6875 + 0.2893(TI) + 0.0373(TI)^2 - 0.0002(TI)^3\)

0.916

0.839

11.158

22.508

0.000

FP

Linear

\(y = 140.0399 + 8.1958(TI)\)

0.941

0.886

10.624

116.880

0.000

Cubic

\(y = 74.3682 + 14.9993(TI) - 0.1991(TI)^2 + 0.0017(TI)^3\)

0.944

0.891

39.481

35.567

0.000

MR

Linear

\(y = 4.2149 + 4.4552(TI)\)

0.985

0.970

2.826

488.105

0.000

Cubic

\(y = -6.9995 + 4.9111(TI) + 0.0181(TI)^2 - 0.0005(TI)^3\)

0.988

0.975

9.797

170.596

0.000

SA

Linear

\(y = 17.9351 + 4.1131(TI)\)

0.814

0.662

10.627

29.419

0.000

Cubic

\(y = 173.2169 - 12.0942(TI) + 0.4796(TI)^2 - 0.0042(TI)^3\)

0.863

0.744

35.192

12.592

0.000

MV

Linear

\(y = 7.4538 + 12.4907(TI)\)

0.971

0.943

11.076

249.749

0.000

Cubic

\(y = 43.4235 + 6.0594(TI) + 0.3086(TI)^2 - 0.0041(TI)^3\)

0.973

0.946

41.182

75.692

0.000

P

Linear

\(y = 2.2365 + 1.7467(TI)\)

0.982

0.964

1.214

406.331

0.000

Cubic

\(y = -8.9386 + 2.7946(TI) - 0.0258(TI)^2 + 0.0002(TI)^3\)

0.985

0.970

4.220

141.440

0.000