Table 13 Statistical parameters and regression models for HZ(G).

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

Property

Models

Equations

R

\(R^2\)

\(S_{E}\)

F

\(p-value\)

BP

Linear

\(y = 346.2330 + 0.3412(TI)\)

0.929

0.863

16.860

94.822

0.000

Cubic

\(y = 330.2336 + 0.2669(TI) + 0.0002(TI)^2 -0.0000(TI)^3\)

0.936

0.875

48.017

30.426

0.000

EV

Linear

\(y = 56.9822 + 0.0480(TI)\)

0.920

0.846

2.545

82.330

0.000

Cubic

\(y = 61.1586 + 0.0320(TI) + 0.0000(TI)^2 -0.0000(TI)^3\)

0.920

0.846

7.581

23.835

0.000

FP

Linear

\(y = 161.1328 + 0.2102(TI)\)

0.934

0.872

10.020

101.879

0.000

Cubic

\(y = 64.3816 + 0.4516(TI) -0.0001(TI)^2 + 0.0000(TI)^3\)

0.948

0.898

26.640

38.118

0.000

MR

Linear

\(y = 17.6540 + 0.1120(TI)\)

0.957

0.916

4.202

164.460

0.000

Cubic

\(y = -13.4410 + 0.1792(TI) -0.0000(TI)^2 -0.0000(TI)^3\)

0.965

0.932

11.310

59.250

0.000

SA

Linear

\(y = 21.5812 + 0.1135(TI)\)

0.869

0.754

8.047

46.088

0.000

Cubic

\(y = 157.2251 -0.3434(TI) + 0.0004(TI)^2 -0.0000(TI)^3\)

0.893

0.798

21.781

17.069

0.000

MV

Linear

\(y = 45.6253 + 0.3134(TI)\)

0.942

0.888

13.839

118.711

0.000

Cubic

\(y = 19.8828 + 0.3156(TI) + 0.0001(TI)^2 -0.0000(TI)^3\)

0.946

0.895

39.962

36.835

0.000

P

Linear

\(y = 7.6030 + 0.0438(TI)\)

0.952

0.906

1.750

145.028

0.000

Cubic

\(y = -9.8842 + 0.0905(TI) -0.0000(TI)^2 + 0.0000(TI)^3\)

0.960

0.922

4.752

51.353

0.000