BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T054723Z
LOCATION:240-241-242
DTSTART;TZID=America/Chicago:20211117T110000
DTEND;TZID=America/Chicago:20211117T113000
UID:submissions.supercomputing.org_SC21_sess248_gbv102@linklings.com
SUMMARY:Language Models for the Prediction of SARS-CoV-2 Inhibitors
DESCRIPTION:ACM Gordon Bell Finalist, Awards Presentation\n\nLanguage Mode
 ls for the Prediction of SARS-CoV-2 Inhibitors\n\nBlanchard, Gounley, Bhow
 mik, Shekar, Lyngaas...\n\nThe COVID-19 pandemic highlights the need for c
 omputational tools to automate and accelerate drug design for novel protei
 n targets. We leverage deep learning language models to generate and score
  drug candidates based on predicted protein binding affinity. We pre-train
 ed a deep learning language model (BERT) on ∼9.6 billion molecules, 
 achieving peak performance of 603 petaflops in mixed precision. Our work r
 educes pre-training time from days to hours, compared to previous efforts 
 with this architecture, while also increasing the dataset size by nearly a
 n order of magnitude. For scoring, we fine-tuned the language model using 
 an assembled set of thousands of protein targets with binding affinity dat
 a and searched for inhibitors of specific protein targets, SARS-CoV-2 Mpro
  and PLpro. We utilized a genetic algorithm approach for finding optimal c
 andidates using the generation and scoring capabilities of the language mo
 del. Our generalizable models accelerate the identification of inhibitors 
 for emerging therapeutic targets.\n\nTag: AI-HPC Convergence, Computationa
 l Science, Extreme Scale Computing, Performance, Scientific Computing\n\nR
 egistration Category: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR