University of Cambridge > Talks.cam > Theory - Chemistry Research Interest Group > Found In Translation: Using Language Models To Predict Cā€“H Borylation Regioselectivity

  Browse A-Z

Log in

University Account External (via Google)

šŸ” Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ā„¹ļø Information

Found In Translation: Using Language Models To Predict Cā€“H Borylation Regioselectivity

Download to your calendar using vCal

If you have a question about this talk, please contact Lisa Masters.

First Year PhD Report

By treating chemical reactions as a machine translation task, it is possible to predict products across wide range of reactions using reaction SMILES as only input (Schwaller 2019). Such models can be fine-tuned to domain-specific data such as reactions of carbohydrates (Pesciullesi 2020). We investigated how encoder-decoder transformer models can be applied to predicting regioselectivity of iridium-catalysed Cā€“H borylation. We found our model performance is comparable to state of the art deep learning models trained on the same amount of data but further investigation is needed on how well it generalises to new substrates.

This talk is part of the Theory - Chemistry Research Interest Group series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

The Royal College of Pathologists,2 Carlton House Terrace,London,SW1Y 5AF North British Functional Analysis (NBFAS) Greaves Room, Dept. of Pathology, Tennis Court Road

Other talks

Talk title TBC The Magic of Magnetism The rise of local cartography in Europe, 12th-14th century Title TBC Group Presentation 3 Cooperation in Nature
 

Ā© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity