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:20181221T160906Z
LOCATION:D165
DTSTART;TZID=America/Chicago:20181111T090000
DTEND;TZID=America/Chicago:20181111T173000
UID:submissions.supercomputing.org_SC18_sess147@linklings.com
SUMMARY:Fourth Computational Approaches for Cancer Workshop (CAFCW18)
DESCRIPTION:Workshop\nApplications, Deep Learning, Exascale, Workshop Reg 
 Pass\n\nIntroduction – Fourth Computational Approaches for Cancer Workshop
  (CAFCW18)\n\nStahlberg, Kovatch, Barr, Chandrasekaran\n\nAs the drive tow
 ards precision medicine has accelerated, the opportunities and challenges 
 in using computational approaches in cancer research and clinical applicat
 ion are rapidly growing. The expanding development of new approaches are r
 eshaping the way computation is being applied in cancer applic...\n\n-----
 ----------------\nScalable Deep Ensemble Learning for Cancer Drug Discover
 y\n\nJacobs, Moon, Van Essen\n\nIn this work, we demonstrate how the Liver
 more Tournament Fast Batch (LTFB) ensemble algorithm is able to efficientl
 y tune hyperparameters and accelerate the time to solution for several can
 cer drug discovery networks.  Drawn from the DOE-NCI Pilot 1 and ECP CANDL
 E projects we show significantly imp...\n\n---------------------\nHPC-Base
 d Hyperparameter Search of MT-CNN for Information Extraction from Cancer P
 athology Reports\n\nYoon, Alawad, Christian, Hinkle, Ramanathan...\n\nFind
 ing optimal hyperparameters is necessary to identify the best performing d
 eep learning models, but the process is costly. In this paper, we applied 
 model-based optimization, also known as Bayesian optimization, using the C
 ANDLE framework implemented on a High-Performance Computing environment. A
 ...\n\n---------------------\nHummingbird: Efficient Performance Predictio
 n for Executing Genomics Applications in the Cloud\n\nRay, Mueller, Bahman
 i, Krishnan\n\nA major drawback of executing existing genomics pipelines o
 n cloud computing facilities is that the onus of efficiently executing it 
 on the best configuration lies on the user. Lack of knowledge regarding wh
 ich cloud configuration is best to execute a pipeline often results in an 
 unnecessary increas...\n\n---------------------\nSafety, Reproducibility, 
 Performance: Accelerating Cancer Drug Discovery with Cloud, ML, and HPC Te
 chnologies\n\nMinnich\n\nNew computational opportunities and challenges ha
 ve emerged within the cancer research and clinical application areas as th
 e size, number, variety and complexity of cancer datasets have grown in re
 cent years. Simultaneously, advances in computational capabilities have gr
 own and are expected to conti...\n\n---------------------\nToward a Comput
 ational Simulation of Circulating Tumor Cell Transport in Vascular Geometr
 ies\n\nGounley, Draeger, Randles\n\nComputational models can provide much 
 needed insight into the mechanisms driving cancer cell trajectory. However
 , capabilities must be expanded to enable simulations in larger sections o
 f micro- and meso-vasculature and account for the more complex fluid dynam
 ic patterns that occur in patient-derive...\n\n---------------------\nDeve
 loping a Reproducible WDL-Based Workflow for RNASeq Data Using Modular, So
 ftware Engineering-Based Approaches\n\nCukras, Pettersson, Zhang, Cen, Tee
 r...\n\nComputational workflows have become standard in many disciplines, 
 including bioinformatics and genomics. Workflow languages, such as the Wor
 kflow Description Language (WDL) and Common Workflow Language (CWL) have b
 een developed to express workflow processing syntax. These languages can b
 e highly exp...\n\n---------------------\nThe Gen3 Approach to Portability
  and  Repeatability for Cancer Genomics Projects\n\nFlamig, Tang, Grossman
 \n\nThe Gen3 software stack is a open-source platform for managing, analyz
 ing, and sharing petabyte-scale research data. In this note, we describe t
 he approach that we have used with Gen3 to support portability and repeati
 bility for cancer genomics projects. Data in a Gen3 data commons is divide
 d into p...\n\n---------------------\nToward a Pre-Cancer Image Atlas thro
 ugh Crowdsourcing and Machine Learning\n\nMahabal, Liu, Cinquini, Crichton
 , Kincaid...\n\nWe describe how crowdsourcing can be combined with advance
 d machine learning for early cancer detection. We demonstrate our system f
 or lung cancer (using data from the National Lung cancer Screen Trial), bu
 t in such a fashion that it can easily be replicated for other organs. Thu
 s this becomes a ste...\n\n---------------------\nMorning Keynote – Comput
 ational Approaches in Clinical Applications\n\nParanjape\n\n--------------
 -------\nWorkshop Morning Break\n\n\n\n---------------------\nWorkshop Lun
 ch (on your own)\n\n\n\n---------------------\nWorkshop Afternoon Break\n\
 n\n\n---------------------\nAfternoon Keynote – Genomic Profiling of Norma
 l, Premalignant, and Heterogeneous Tissues in Cancer Patients\n\nScheet\n\
 nNormal tissues adjacent to tumor and premalignant lesions present an oppo
 rtunity for in vivo human models of early disease pathology.  Genomic stud
 ies of such “at risk” tissues may identify molecular pathways involved in 
 a transition to malignant phenotypes and/or targets for personalized preve
 ntion...\n\n---------------------\nPanel Discussion:  Reproducibility and 
 Accessibility - Challenges and Opportunities\n\n\n\nInteractive panel disc
 ussion on frontiers and perspectives for computation in cancer research an
 d clinical applications\n\n---------------------\nExtending Frontiers for 
 Computing in Cancer – Special Session\n\n\n\nProvide a glimpse into the la
 test developments at the frontiers of computing in cancer. Highlight effor
 ts underway with Joint Design of Advanced Computing Solutions for Cancer a
 nd other efforts at the cutting-edge of cancer research and high performan
 ce computing.\n
END:VEVENT
END:VCALENDAR