BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ZContent.net//ZapCalLib 1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
SUMMARY:Deep Learning to Decompose Macromolecules Into Independent Markovia
 n Domains
LOCATION:Chemistry A101
TZID:America/Denver
DTSTART:20221110T160000
UID:2026-04-16-20-43-13@natsci.colostate.edu
DTSTAMP:20260416T204313
Description:About the Seminar\n\nDespite advances in software algorithms an
 d computer hardware\, the simulation of long timescale processes involving
  biological macromolecules remains prohibitively computationally expensive
 . Thus\, there is a pressing need for novel computational techniques capab
 le of resolving this issue. Harnessing recent advances in neural network-b
 ased machine learning algorithms\, NoƩ and coworkers propose an improveme
 nt to the previously proposed VAMPNet computational framework (1) for the 
 simulation of long duration events in molecular systems. By learning both 
 a means of dividing up the system studied into independent domains and an 
 approximation of the kinetics of the independent macromolecular domains\, 
 the new iVAMPNet architecture extends the utility of VAMPNets\, allowing f
 or the study of larger and more complex systems (2). The iVAMPNet architec
 ture is tested on model systems and its accuracy in predicting the timesca
 les of long-duration processes from short molecular dynamics simulations i
 s assessed.\n\n&nbsp\;\n\n 	(1) Mardt\, A.\; Pasquali\, L.\; Wu\, H.\; NoĆ
 ©\, F. VAMPnets for Deep Learning of Molecular Kinetics. Nat Commun 2018\,
 \n9 (1)\, 5. https://doi.org/10.1038/s41467-017-02388-1.\n 	Mardt\, A.\; H
 empel\, T.\; Clementi\, C.\; NoƩ\, F. Deep Learning to Decompose Macromol
 ecules into Independent\nMarkovian Domains. bioRxiv March 31\, 2022\, p 20
 22.03.30.486366.\nhttps://doi.org/10.1101/2022.03.30.486366.\n 4:00 pm
END:VEVENT
END:VCALENDAR