Datasets of protein targets and ligands for benchmarking virtual screening methods.
This project contains datasets that I generated for my PhD thesis titled "Connecting chemical features of drugs to molecular, cellular, and organismal phenotypes". These data have been
used to developed methods to quantify the connections between chemical features of drugs at the molecular, cellular, and organismal level. Specifically, in the thesis I present methods for predicting activities among structurally diverse sets of drugs, for predicting up-regulation of genes based on chemical features of drugs, and a quantified approach to estimating clinical impacts of genotype guided therapies.