Skip to main content

Table 2 Top ranked results according to various scenarios for the enthalpy of solution datasets

From: The influence of solid state information and descriptor selection on statistical models of temperature dependent aqueous solubility

Dataset

Rank

Molecular descriptors

3D descriptors from crystal structure?

Melting point descriptor included

Lattice energy descriptor included

Method

R2

RMSE (kJ/mol)

Avdeef_ExDPs_Cal_CS_False

1st

IntegSub, SiRMSSub

False

True

False

RFR

0.63

8.56

Avdeef_ExDPs_Cal_CS_False

2nd

IntegSub, SiRMSSub

False

False

False

RFR

0.63

8.58

Avdeef_ExDPs_Cal_CS_True

1st

IntegSub, SiRMSSub

False

True

False

RFR

0.26

11.45

Avdeef_ExDPs_Cal_CS_True

2nd

IntegSub, SiRMSSub

False

True

True

RFR

0.26

11.47

Avdeef_ExDPs_CS_False

1st

Rdk

False

False

False

RFR

0.34

13.82

Avdeef_ExDPs_CS_False

2nd

Rdk

False

True

False

RFR

0.34

13.84

Avdeef_ExDPs_CS_True

1st

3D

True

False

True

RFR

0.18

14.93

Avdeef_ExDPs_CS_True

2nd

3D

True

True

True

RFR

0.18

14.95

  1. All results were obtained without feature selection. All results are rounded to 2dp. The definitions of the 2D molecular descriptors subsets are provided in Additional file 1: Table S1. All references to R2 and RMSE denote arithmetic mean values obtained from cross-validation and all model rankings were generated based on the mean RMSE values