Skip to main content

Advertisement

Table 5 Prediction of the DFT DM by random forests using a combination of DMNBO and DMPEOE with different type of descriptors

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

Models Training seta Test set
MAE (D) R2/RMSE (D) MAE(D) R2/RMSE (D)
MACCSb 0.460 0.853/0.707 0.444 0.872/0.680
RDFb,c 0.533 0.817/0.791 0.522 0.839/0.767
PchmDMb,d 0.540 0.819/0.786 0.533 0.839/0.765
CDKb 0.538 0.815/0.793 0.525 0.837/0.765
  1. aOOB estimation
  2. bCombining DMPEOE, and DMNBO
  3. cRDF pairs NBO charges
  4. dPchmDM NBO charges