Connected chemistry: How to choose the most promising drug candidates from your hit list

Watch On Demand

AI and machine learning (AI/ML) methods offer an alluring way to expedite the drug discovery process by delivering a large number of possible new candidates for any given therapeutic area. However, insight from medicinal chemists is still necessary to triage and prioritise the most promising molecules for synthesis, and progress these through the Design-Make-Test-Analyse (DMTA) cycle. A smooth interface between data and humans drives down DMTA cycle times and shortens the path to clinical candidates. 

Mari Goldsmith, Application Scientist at Torx Software and John Kratunis, Manager, Customer Success Specialists, NA at CAS demonstrates the power of combining Torx with CAS SciFinder to ensure the correct decisions are made quickly to deliver new drugs faster.

Related Articles