Skip to main content

Advertisement

Table 2 Prediction of the DFT DM by random forests on the basis of different molecular descriptors

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_Nb (384) 0.944 0.480/1.332 0.947 0.498/1.344
RDF_Pc (384) 0.890 0.512/1.295 0.882 0.549/1.287
PchmDM_Nb (360) 0.924 0.545/1.267 0.880 0.589/1.250
PchmDM_Pc (360) 0.873 0.569/1.240 0.931 0.566/1.278
CDKd (47) 0.983 0.434/1.385 0.985 0.445/1.402
MACCS FPe (166) 0.790 0.579/1.195 0.775 0.609/1.182
PubChem FPe (881) 0.817 0.547/1.238 0.801 0.584/1.217
CDK FPe (1024) 0.880 0.501/1.301 0.874 0.521/1.305
  1. aOOB estimation
  2. bDescriptors calculated using NBO charges
  3. cDescriptors calculated using PEOE charges
  4. dGeometric CDK descriptors
  5. eFingerprints