BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160552Z
LOCATION:Track 3
DTSTART;TZID=America/New_York:20201113T121500
DTEND;TZID=America/New_York:20201113T123000
UID:submissions.supercomputing.org_SC20_sess222_ws_cafcw138@linklings.com
SUMMARY:Scaffold-Induced Molecular Subgraphs (SIMSG): Effective Graph Samp
 ling Methods for High-Throughput Computational Drug Discovery
DESCRIPTION:Workshop\n\nScaffold-Induced Molecular Subgraphs (SIMSG): Effe
 ctive Graph Sampling Methods for High-Throughput Computational Drug Discov
 ery\n\nClyde, Shah, Zvyagin, Ramanathan, Stevens\n\nHistorically, drugs ha
 ve been discovered serendipitously based on active chemicals known to inte
 ract with and bind to protein targets. Combinatorial chemistry has enabled
  an explosion of diverse chemical libraries which potentially have drug-li
 ke properties; however, the main issue that is still faced by drug discove
 ry community is the need to efficiently navigate the high dimensional chem
 ical space to identify viable molecules that can target proteins of intere
 st. Ongoing pandemics such as the novel coronavirus disease 2019 (COVID-19
 ) further emphasize the need for such effective methods to sample these ch
 emical spaces and quickly identify effective drugs against the virus. Simi
 lar needs are also emerging within the context of other diseases such as c
 ancer, where intrinsic heterogeneity of gene expression within tumor cells
  and the cancer type can result in similar challenges. Current techniques 
 assume enumeration of large compound libraries coupled with GPU- accelerat
 ed machine learning (ML) models will be an effective tool for screening th
 rough datasets. However, these techniques still face inherent limitations 
 where inference or physics-based simulations become computational bottlene
 cks for spanning large chemical spaces (beyond 10**12 molecules). To overc
 ome these limitations, we propose a graph based structure of chemical spac
 e, opposed to a static library of compounds. By embracing this inherent st
 ructure of chemical space for small molecule design, we show an enhanced s
 ampling technique that exploits random walk theory and intrinsic relations
 hips between chemical "scaffolds" for ultra high-throughput docking studie
 s.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR