BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Transferable Machine Learning Interatomic Potential for Bond Disso
 ciation Energy Prediction of Drug-like Molecules - Elena Gelzinyte\, Unive
 rsity of Cambridge
DTSTART:20230612T130000Z
DTEND:20230612T133000Z
UID:TALK202327@talks.cam.ac.uk
CONTACT:Dr Venkat Kapil
DESCRIPTION:We present a transferable MACE interatomic potential that is a
 pplicable for open- and closed-shell drug-like molecules containing C\, H\
 , O chemical elements. We explore MACE transferability to the COMP6 datase
 t and show that it reaches accuracy on par with state-of-the-art transfera
 ble ANI2x potential for closed shell molecules. An accurate description of
  radical species extends the scope of possible applications to reaction en
 ergy prediction\, for example in the context of Cytochrome P450 (CYP) meta
 bolism. MACE potential reaches similar accuracy on two CYP substrate datas
 ets\, with open-and closed-shell structures relevant to CYP metabolism. We
  apply MACE to aliphatic C-H bond dissociation energy prediction where it 
 reaches RMSE below 1.6 kcal/mol and a better rank prediction than currentl
 y used AM1 semi-empirical method. 
LOCATION:Zoom link: https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHpt
 UXlRSkppQT09
END:VEVENT
END:VCALENDAR