BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Machine learning in chemistry and beyond" (ChE-651) seminar by Pro
 f. Kim Jelfs: "Remembering the lab in computational molecular material dis
 covery"
DTSTART:20241001T151500
DTEND:20241001T161500
DTSTAMP:20260513T005722Z
UID:2d11375a80d25d660aa3aa85ea6c96b0b3dc122d5d0c660c07fff21e
CATEGORIES:Conferences - Seminars
DESCRIPTION:Kim Jelfs completed her PhD in Computational Chemistry at Univ
 ersity College London\, working on the development and application of mode
 lling to understand zeolite crystal growth and was awarded the Ramsay Meda
 l for the best completing PhD student. She then went on research visits at
  the Universitat de Barcelona\, the University of Liverpool\, and finally 
 Imperial as a research fellow\, where she is now a Professor since 2022.\n
 \nKim was awarded a 2018 Royal Society of Chemistry Harrison-Meldola Memor
 ial Prize\, a 2019 Philip Leverhulme Prize in Chemistry and was named the 
 2022 UK Blavatnik Awards Laureate in Chemistry. Kim holds an ERC Starting 
 Grant and is an Associate Editor for Chemical Communications.      
   \nWe have been developing computational software towards assisting in 
 the discovery of molecular materials with targeted structures and properti
 es. While initially we have focused upon porous molecular materials\, we w
 ill also address the ways in which our approach is generalisable to other 
 molecular materials and their applications\, including as organic semicond
 uctors or for photocatalysis. Our evolutionary algorithm automates the ass
 embly of\nhypothetical molecules from a library of precursors. Our approac
 h has already suggested promising targets that have been synthetically rea
 lised. We have also examined the application of both supervised machine le
 arning and explainable graph neural networks for the rapid prediction of p
 orous molecules’ properties. Finally\, we have trained a model (the Mate
 rials Precursor Score\, MPScore) to guide our predictions to select materi
 als that have a high chance of being synthesisable in the laboratory. We w
 ill also discuss our experimental work to gather data for improved models.
LOCATION:https://epfl.zoom.us/j/68447908297?pwd=OU5JUGJUSUhZc0ZNYjQ2WENvYl
 NRdz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR