Table 10 Statistical parameters and regression models for RI(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

\(y = 300.7387 + 22.4485\,(\textrm{TI})\)

0.930

0.864

20.056

95.447

0.000

Cubic

\(y = 434.9741 - 3.6985\,(\textrm{TI}) + 1.5072\,(\textrm{TI})^2 - 0.0263\,(\textrm{TI})^3\)

0.931

0.867

89.558

28.204

0.000

EV

Linear

\(y = 51.6588 + 3.0869\,(\textrm{TI})\)

0.899

0.809

3.381

63.521

0.000

Cubic

\(y = 83.2309 - 2.0623\,(\textrm{TI}) + 0.2323\,(\textrm{TI})^2 - 0.0030\,(\textrm{TI})^3\)

0.913

0.833

14.266

21.568

0.000

FP

Linear

\(y = 132.4505 + 13.8729\,(\textrm{TI})\)

0.937

0.878

11.659

107.856

0.000

Cubic

\(y = 97.0749 + 20.4632\,(\textrm{TI}) - 0.3605\,(\textrm{TI})^2 + 0.0060\,(\textrm{TI})^3\)

0.937

0.879

52.435

31.351

0.000

MR

Linear

\(y = -1.1125 + 7.6207\,(\textrm{TI})\)

0.991

0.981

2.366

790.034

0.000

Cubic

\(y = -17.5766 + 10.0587\,(\textrm{TI}) - 0.0909\,(\textrm{TI})^2 + 0.0007\,(\textrm{TI})^3\)

0.992

0.983

10.061

257.319

0.000

SA

Linear

\(y = 17.1517 + 6.7625\,(\textrm{TI})\)

0.787

0.619

11.958

24.366

0.000

Cubic

\(y = 208.1255 - 25.5285\,(\textrm{TI}) + 1.5448\,(\textrm{TI})^2 - 0.0216\,(\textrm{TI})^3\)

0.855

0.731

45.345

11.748

0.001

MV

Linear

\(y = -8.2326 + 21.4148\,(\textrm{TI})\)

0.979

0.959

10.024

347.733

0.000

Cubic

\(y = 12.1001 + 15.5364\,(\textrm{TI}) + 0.4626\,(\textrm{TI})^2 - 0.0102\,(\textrm{TI})^3\)

0.979

0.959

44.797

102.350

0.000

P

Linear

\(y = 0.0795 + 2.9923\,(\textrm{TI})\)

0.989

0.978

1.001

681.344

0.000

Cubic

\(y = -14.0025 + 5.5056\,(\textrm{TI}) - 0.1301\,(\textrm{TI})^2 + 0.0020\,(\textrm{TI})^3\)

0.991

0.982

4.140

234.627

0.000