Noczio
commented
4 years ago Done.
Descriptors example:
m_name: ACETAZOLAMIDE n_atoms_without_Hydrogen: 13 n_atoms_with_Hydrogen: 19 m_weight: 221.988132052 m_avg_weigth: 216.203 m_weigth_without_Hydrogen: 222.251 n_radical_electrons: 0 n_valence_electrons: 72 n_aliphatic_carbocycles: 0 n_aliphatic_heterocycles: 0 n_aliphatic_rings: 0 n_amide_bonds: 1 n_aromatic_carbocycles: 0 n_aromatic_heterocycles: 1 n_aromatic_rings: 1 n_saturated_carbocycles: 0 n_saturated_heterocycles: 0 n_saturated_rings: 0 n_HBA: 6 n_HBD: 2 n_hetero_atoms: 9 n_hetero_cycles: 1 n_rings: 1 n_strict_rotable_bonds: 2 n_non_strict_rotable_bonds: 3 n_primary_carbon_atoms: 4 n_HOH: 3 n_O: 7 n_Hydrogen_acceptors: 6 n_Hydrogen_donnors: 2 n_briged_head_atoms: 0 n_atoms_stereo_centers: 0 n_atoms_unspecified_stereo_centers: 0 n_spiro_atoms: 0 m_logp: -0.8561000000000003 m_mr: 45.5859 fraction_CSP3: 0.25
Use the RDKit library to calculate the features (molecular descriptors) for both sets of molecules. Save the molecular descriptors in a text file (before saving the results, check the Scikit learn library to select the correct format to save the results).