BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine-Learning a Transferable Coarse-grained Protein Force Field
  - Felix Musil\, Free University Berlin\, Germany
DTSTART:20220627T133000Z
DTEND:20220627T140000Z
UID:TALK173222@talks.cam.ac.uk
CONTACT:Dr Venkat Kapil
DESCRIPTION:Recent developments and applications of machine learning to ph
 ysical systems have led to significant advances in the construction of coa
 rse-grained force fields for efficient simulation and sampling [1]. Yet\, 
 transferability and extrapolation between different systems of interest re
 main an outstanding limitation for machine-learned models. Using force mat
 ching\, a bottom-up coarse-graining approach\, and a database of chemicall
 y diverse peptides\, we present a coarse-grained force field that is trans
 ferable across protein sequences enabling us to explore their conformation
 al landscape. Our model\, based on a graph neural network architecture\, i
 s validated/tested against all-atom simulations of unseen proteins [2].\n\
 n[1] Wang\, J. et al. Machine Learning of Coarse-Grained Molecular Dynamic
 s Force Fields. ACS Cent. Sci. 5\, 755–767 (2019).\n\n[2] Lindorff-Larse
 n\, K. et al. How fast-folding proteins fold. Science (80-. ). 334\, 517
 –520 (2011).\n\n
LOCATION:see in special message
END:VEVENT
END:VCALENDAR