BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Machine learning for biological sequence design with therapeutic a
 pplications
DTSTART:20210923T160000
DTSTAMP:20260408T033946Z
UID:5deb857b52c91c57d64103e418c30745d2c474ea4a0fbf8bc061e6c4
CATEGORIES:Conferences - Seminars
DESCRIPTION:Lucy Colwell\, Cambridge University – Google\n \nExperiment
 al breakthroughs allow data on the relationship between sequence and funct
 ion to be rapidly acquired. This data can be used to train and validate ma
 chine learning models that predict protein function directly from sequence
 . However\, the cost and latency of wet-lab experiments require methods th
 at find good sequences in few experimental rounds\, though each round can 
 contain large batches of sequence designs. In this setting\, I will discus
 s model-based optimization approaches that allow us to take advantage of s
 ample inefficient methods and find diverse optimal sequence candidates for
  experimental evaluation. The potential of this approach is illustrated th
 rough the design and experimental validation of viable AAV capsid protein 
 variants for gene therapy applications in addition to the design and valid
 ation of peptides as potential therapeutics. \n 
LOCATION:https://epfl.zoom.us/j/85131999647?pwd=TUpoYWE4MnQ4KzZnbDVhSTRBZH
 h4UT09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR