ADME Prediction with KNIME: Development and Validation of a Publicly Available Workflow for the Prediction of Human Oral Bioavailability

In
silico prediction of human oral bioavailability is a relevant
tool for the selection of potential drug candidates and for the rejection
of those molecules with less probability of success during the early
stages of drug discovery and development. However, the high variability
and complexity of oral bioavailability and the limited experimental
data in the public domain have mainly restricted the development of
reliable in silico models to predict this property from the chemical
structure. In this study we present a KNIME automated workflow to
predict human oral bioavailability of new drug and drug-like molecules
based on five machine learning approaches combined into an ensemble
model. The workflow is freely accessible and allows the quick and
easy prediction of oral bioavailability for new molecules. Users do
not require any knowledge or advanced experience in machine learning
or statistical modeling to automatically obtain their predictions,
increasing the potential use of the present proposal.