Skip to main content

Advertisement

Table 3 Prediction of the DFT DM by random forests using DMNBO or DMPEOE

From: Machine learning for the prediction of molecular dipole moments obtained by density functional theory

Descriptors Training seta Test set
MAE (D) R2/RMSE (D) MAE (D) R2/RMSE (D)
RDF_N + DM NBO b 0.639 0.747/0.930 0.638 0.761/0.929
RDF_P + DM PEOE c 0.624 0.740/0.946 0.615 0.765/0.929
PchmDM_N + DM NBO b 0.647 0.753/0.924 0.651 0.769/0.921
PchmDM_P + DM PEOE c 0.639 0.735/0.953 0.630 0.759/0.936
CDK + DM NBO d 0.713 0.705/1.00 0.700 0.724/0.990
CDK + DM PEOE e 0.708 0.685/1.03 0.704 0.705/1.02
MACCS + DMNBO 0.526 0.806/0.813 0.507 0.826/0.792
MACCS + DMPEOE 0.563 0.777/0.873 0.543 0.801/0.847
  1. aOOB estimation
  2. bDescriptors calculated using NBO charges, and DMNBO
  3. cDescriptors calculated using PEOE charges, and DMPEOE
  4. dGeometric CDK, and DMNBO
  5. eGeometric CDK, and DMPEOE