BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210916T132451Z
LOCATION:Henry Dunant
DTSTART;TZID=Europe/Stockholm:20210707T143000
DTEND;TZID=Europe/Stockholm:20210707T150000
UID:submissions.pasc-conference.org_PASC21_sess152_msa337@linklings.com
SUMMARY:Targeting Billion-Scale Compound Libraries with Deep Learning: A S
 ARS-Cov-2 Example
DESCRIPTION:Minisymposium\n\nTargeting Billion-Scale Compound Libraries wi
 th Deep Learning: A SARS-Cov-2 Example\n\nBrettin, Babuji, Clyde, Jain, Li
 u...\n\nDeep learning-based surrogate models can be effective approaches t
 o speed up costly computations in large workflows. In this work, we presen
 t the evaluation of compounds from a large chemical database using surroga
 te DL models in place of the slower traditional docking approaches. Our wo
 rk demonstrates significant improvement of the surrogate of over tradition
 al approaches in speed, while maintaining an acceptable level of error.  T
 his workflow faced challenges in scaling the inference problem to reduce o
 verall time in searching billions of compounds for potential COVID-19 inhi
 bitors. We present different types of deep learning models that can be use
 d as surrogates. We show the impact of using images, 2-D and 3-D drug desc
 riptors in the feature set. We explore the sample size on which to train t
 he models using two different approaches to construct the training set, an
 d we illustrate the effect of different model optimization strategies. The
 se models were subsequently used to search a much larger space of compound
 s and provided input into the selection of compounds for whole cell viral 
 inhibition assays.\n\nDomain: CS and Math, Life Sciences
END:VEVENT
END:VCALENDAR