MLDockKit a machine learning- based toolkit designed for computing Lipinski descriptors (measures of drug likeliness), predicting pIC50 values (a measure of drug potency) and conducting molecular docking (enables the understanding of protein-drug interactions at the atomic level) to target estrogen alpha receptor protein, whose presence promotes proliferation, inflammation, and migration of cancerous cells.

It is an innovative software engineered to revolutionize targeted prostate cancer therapies through in silico science. It is a collaborative project by a tripartite effort of Edwin Wuchenje (Department of Biological Sciences, MMUST), Dr. Clabe Wekesa (Max Plank Institute of Chemical Ecology) & Dr. Patrick Okoth (Department of Biological Sciences, MMUST). MLDockKit anticipates to fuel breakthrough in Prostate Cancer research and Drug Discovery.

The Link to the Package: https://pypi.org/project/MLDockKit/0.0.3/