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:20190719T085743Z
LOCATION:HG E 3
DTSTART;TZID=Europe/Stockholm:20190612T143000
DTEND;TZID=Europe/Stockholm:20190612T150000
UID:submissions.pasc-conference.org_PASC19_sess126_msa105@linklings.com
SUMMARY:Using Deep Learning to Accurately Detect Cancer Mutations
DESCRIPTION:Minisymposium\nComputer Science and Applied Mathematics, Emerg
 ing Application Domains, Physics, Life Sciences\n\nUsing Deep Learning to 
 Accurately Detect Cancer Mutations\n\nEbrahim Sahraeian, Liu, Lau, Podesta
 , Miroslaw...\n\nWe present NeuSomatic, the first convolutional neural net
 work-based approach for identifying cancer mutations. NeuSomatic’s v
 ersatility enables its use on DNA sequence data generated from different s
 equencing platforms, sequencing strategies, and tumor purities while signi
 ficantly outperforming state of the art cancer mutation detection tools. I
 t summarizes sequence alignments into small matrices and incorporates more
  than a hundred features to capture mutation signals effectively. It can a
 lso incorporate mutation signals reported by other cancer mutation callers
  for enhanced accuracy. Thus, it can be used universally as a stand-alone 
 somatic mutation detection method or with an ensemble of existing methods 
 to achieve the highest accuracy. NeuSomatic leverages multiple software te
 chnologies including containers and efficient machine-learning libraries f
 or portability and scalability. It can be run on multiple compute platform
 s including local high-performance compute cluster and cloud computing inf
 rastructure. We processed over 250 whole-exome sequenced samples across mu
 ltiple cancer types from The Cancer Genome Atlas project on the Microsoft 
 Azure platform to demonstrate the scalability and compute efficiency of Ne
 uSomatic. It took, on average, less than 3 hours to process each sample wh
 ile costing less than one US dollar. Overall, we believe NeuSomatic is an 
 accurate, versatile, efficient and scalable approach for detecting cancer 
 mutations.
END:VEVENT
END:VCALENDAR