A comparative study on the molecular descriptors for predicting drug-likeness of small molecules

Screening of "drug-like" molecule from the molecular database produced through high throughput techniques and their large repositories requires robust classification. In our work, a set of heuristically chosen nine molecular descriptors including four from Lipinski's rule, were used as classification parameter for screening "drug-like" molecules. The robustness of classification was compared with four fundamental descriptors of Lipinski. Back propagation neural network based classifier was applied on a database of 60000 molecules for classification of, "drug-like" and "non drug-like" molecules. Classification result using nine descriptors showed high classification accuracy of 96.1% in comparison to that using four Lipinski's descriptors which yielded an accuracy of 82.48%. Also a significant decrease of false positives resulted while using nine descriptors causing a sharp 18% increase of specificity of classification. From this study it appeared that Lipinski's descriptors which mainly deal with pharmacokinetic properties of molecules form the basis for identification of "drug-like" molecules that can be substantially improved by adding more descriptors representing pharmaco-dynamics properties of molecules.