Introduction
The OpenEye 3D QSAR Models floe package builds models for and make predictions of potency or binding affinity, based on descriptors generated from 3D conformers of molecules. By focusing on 3D conformations, the package can capture essential molecular features that influence biological activity. The integration of these advanced modeling techniques can lead to the identification of novel drug candidates with improved efficacy and reduced side effects.
Molecular similarity between aligned ligands, both in physical and chemical space, is used as the primary descriptor in this package. The 3D-QSAR model is built as a composition of multiple models that combines orthogonal sets of similarity descriptors and machine learning techniques. A prediction from the model is provided as the consensus of predictions from the individual models.
The 3D-QSAR model is also able to provide interpretation within the active site regarding regions where availability of groups containing specific interactions, such as hydrogen-bond donors/acceptors, anions/cations, and so forth, are preferred. Such interpretations can be used in generating new ideas, and they allow the model to be used as a potential generative design tool in the drug discovery cycle.
This package contains five floes: