BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Found In Translation: Using Language Models To Predict C–H Boryl
 ation Regioselectivity - Ruslan Kotlyarov\, University of Cambridge
DTSTART:20230208T143000Z
DTEND:20230208T150000Z
UID:TALK193822@talks.cam.ac.uk
CONTACT:Lisa Masters
DESCRIPTION:By treating chemical reactions as a machine translation task\,
  it is possible to predict products across wide range of reactions using r
 eaction SMILES as only input (Schwaller 2019). Such models can be fine-tun
 ed to domain-specific data such as reactions of carbohydrates (Pesciullesi
  2020). We investigated how encoder-decoder transformer models can be appl
 ied to predicting regioselectivity of iridium-catalysed C–H borylation. 
 We found our model performance is comparable to state of the art deep lear
 ning models trained on the same amount of data but further investigation i
 s needed on how well it generalises to new substrates.
LOCATION:Unilever Lecture Theatre\, Yusuf Hamied Department of Chemistry
END:VEVENT
END:VCALENDAR