Honest QSAR Models Start With the Assay, Not the Algorithm
Tamsin Mansley and Mario Öeren's Optibrium webinar puts a QSAR in a fixed order: curate the assay, match regression or a class to the noise, hold out a test set that is scored once, and read the plot. A clearance label can still be the wrong target, because one number mixes several mechanisms.
Oct 25, 2026
EnsembleBBB
A machine learning ensemble for predicting drug blood-brain barrier permeability. The models, fingerprints, and prediction script are in the GitHub repository. The hosted Streamlit app currently asks visitors to sign in, so the repository is the public entry point.
Feb 13, 2024