BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Conditional enzyme design with unsupervised language models
DTSTART:20240904T153000
DTEND:20240904T163000
DTSTAMP:20260511T073023Z
UID:97da015b043af0c505d31e2ac2d347f342548a20586b0948dff47202
CATEGORIES:Conferences - Seminars
DESCRIPTION:Noelia Ferruz\nArtificial Intelligence (AI) methods are emergi
 ng as powerful tools in fields such as Natural Language Processing (NLP) a
 nd Computer Vision (CV)\, impacting the applications we use in our daily l
 ives. Language models have recently shown incredible performance at unders
 tanding and generating human text\, producing text often indistinguishable
  from that written by humans. Inspired by these recent advances\, we train
 ed a language model\, ZymCTRL\, a model trained on enzyme sequences and th
 eir associated Enzymatic Commission (EC) numbers. By combining each sequen
 ce with its respective catalytic function\, the model has learned a joint 
 distribution of the sequence patterns that govern function. To assess the 
 quality of generation and their validity in real-life scenarios\, we thoro
 ughly tested the model using carbonic anhydrases and lactate dehydrogenase
 s. In all cases\, the model generated enzymes whose activities aligned wit
 h their natural counterparts\, even with sequence identities as low as 40%
 . Lastly\, we have trained REXzyme\, a translation machine capable of desi
 gning enzyme sequences for user-defined chemical reactions.\n\nLab website
 : https://www.aiproteindesign.com/
LOCATION:CH G1 495
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR