BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:"Machine learning in chemistry and beyond" (ChE-651) seminar by An
 irudh Nambiar "Bayesian Reaction Optimization on a Robotic Flow Synthesis 
 Platform"
DTSTART:20221025T153000
DTEND:20221025T163000
DTSTAMP:20261005T184151Z
UID:34cfffcf7c11f007d05e0f191000e545a900832c62120cf4a6a307b8
CATEGORIES:Conferences - Seminars
DESCRIPTION:Anirudh Nambiar is a Senior Engineer in the Synthetics Process
  Development Department at Amgen in Cambridge\, Massachusetts. He complete
 d his PhD in Chemical Engineering at MIT working with Klavs Jensen where h
 e developed robotic flow synthesis platforms equipped with decision-making
  algorithms to optimise reaction outcomes.\nMachine assistance has helped 
 automate and accelerate steps in the synthesis of organic compounds\, acce
 lerating the discovery and development of new medicines and materials. Dur
 ing reaction development\, the design space can consist of both continuous
  (e.g.\, time\, temperature) and categorical (e.g.\, reagent choice) react
 ion variables that must be tuned to optimize a desired objective function 
 (e.g.\, yield). This typically time- and labor-intensive task can be accel
 erated by leveraging automated synthesis platforms orchestrated by optimiz
 ation algorithms which efficiently navigate the reaction design space.\n\n
 This talk will describe my Ph.D. work where we developed a robotic flow sy
 nthesis platform with integrated process analytical technology (PAT) to me
 asure reaction outcomes directly on the system. Closed-loop experimentatio
 n was established through automated feedback of experimental results to a 
 Bayesian optimization algorithm that suggested which experiment to run nex
 t based on prior data.\n\nThe first case study will focus on a multi-step 
 synthesis of a small molecule API where the route was proposed by a comput
 er-aided synthesis planning software. Both continuous and categorical vari
 ables suggested by the software were optimized using the Bayesian algorith
 m with respect to multiple objectives simultaneously. In the second case s
 tudy\, Bayesian optimization helped identify optimal continuous variable s
 ettings for a photochemical transformation. By generating response surface
 s using the algorithm’s mathematical model\, the input-output relationsh
 ip learned by the algorithm will be visualized.
LOCATION:https://epfl.zoom.us/j/68447908297?pwd=OU5JUGJUSUhZc0ZNYjQ2WENvYl
 NRdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR