Analyzing Compound and Project Progress Through Multi-Objective-Based Compound Quality Assessment
J. Willem M. Nissink, Sébastien L. Degorce · Future Medicinal Chemistry · 2013
BACKGROUND: Compound-quality scoring methods designed to evaluate multiple drug properties concurrently are useful to analyze and prioritize output from drug-design efforts. However, formalized multiparameter optimization approaches are not widely used in drug design. METHODS: We rank molecules synthesized in drug-discovery projects using simple and aggregated desirability functions reflecting medicinal chemistry 'rules'. Our quality score deals transparently with missing data, a key requirement in drug-hunting projects where data availability is often limited. We further estimate confidence in the interpretation of such a compound-quality measure. CONCLUSION: Scores and associated confidences provide systematic insight in the quality of emerging chemical equity. Tracking quality of synthetic output over time yields valuable insight into the progress of drug-design teams, with potential applications in risk and resource management of a drug portfolio.