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:20260522T150120Z
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 Afternoon Break\n---------------------\nHummingbird: 
 Efficient Performance Prediction for Executing Genomics Applications in th
 e Cloud\n\nA major drawback of executing existing genomics pipelines on cl
 oud computing facilities is that the onus of efficiently executing it on t
 he best configuration lies on the user. Lack of knowledge regarding which 
 cloud configuration is best to execute a pipeline often results in an unne
 cessary increas...\n\n\nUtsab Ray and Frank Mueller (North Carolina State 
 University) and Amir Bahmani and Vandhana Krishnan (Stanford University)\n
 ---------------------\nPanel Discussion:  Reproducibility and Accessibilit
 y - Challenges and Opportunities\n\nInteractive panel discussion on fronti
 ers and perspectives for computation in cancer research and clinical appli
 cations\n\n---------------------\nWorkshop Lunch (on your own)\n----------
 -----------\nHPC-Based Hyperparameter Search of MT-CNN for Information Ext
 raction from Cancer Pathology Reports\n\nFinding optimal hyperparameters i
 s necessary to identify the best performing deep learning models, but the 
 process is costly. In this paper, we applied model-based optimization, als
 o known as Bayesian optimization, using the CANDLE framework implemented o
 n a High-Performance Computing environment. A...\n\n\nHong-Jun Yoon, Moham
 med Alawad, Blair Christian, Jacob Hinkle, Arvind Ramanathan, and Georgia 
 Tourassi (Oak Ridge National Laboratory)\n---------------------\nMorning K
 eynote – Computational Approaches in Clinical Applications\n\nKetan Paranj
 ape (Roche - Diagnostic Information Solutions)\n---------------------\nInt
 roduction – Fourth Computational Approaches for Cancer Workshop (CAFCW18)\
 n\nAs the drive towards precision medicine has accelerated, the opportunit
 ies and challenges in using computational approaches in cancer research an
 d clinical application are rapidly growing. The expanding development of n
 ew approaches are reshaping the way computation is being applied in cancer
  applic...\n\n\nEric Stahlberg (Frederick National Laboratory for Cancer R
 esearch), Patricia Kovatch (Icahn School of Medicine at Mount Sinai), Thom
 as Barr (Nationwide Children's Hospital), and Sunita Chandrasekaran (Unive
 rsity of Delaware)\n---------------------\nThe Gen3 Approach to Portabilit
 y and  Repeatability for Cancer Genomics Projects\n\nThe Gen3 software sta
 ck is a open-source platform for managing, analyzing, and sharing petabyte
 -scale research data. In this note, we describe the approach that we have 
 used with Gen3 to support portability and repeatibility for cancer genomic
 s projects. Data in a Gen3 data commons is divided into p...\n\n\nZac Flam
 ig, Yajing Tang, and Robert L. Grossman (University of Chicago)\n---------
 ------------\nSafety, Reproducibility, Performance: Accelerating Cancer Dr
 ug Discovery with Cloud, ML, and HPC Technologies\n\nNew computational opp
 ortunities and challenges have emerged within the cancer research and clin
 ical application areas as the size, number, variety and complexity of canc
 er datasets have grown in recent years. Simultaneously, advances in comput
 ational capabilities have grown and are expected to conti...\n\n\nAmanda J
 . Minnich (Lawrence Livermore National Laboratory)\n---------------------\
 nDeveloping a Reproducible WDL-Based Workflow for RNASeq Data Using Modula
 r, Software Engineering-Based Approaches\n\nComputational workflows have b
 ecome standard in many disciplines, including bioinformatics and genomics.
  Workflow languages, such as the Workflow Description Language (WDL) and C
 ommon Workflow Language (CWL) have been developed to express workflow proc
 essing syntax. These languages can be highly exp...\n\n\nScott Cukras, Fre
 drik Pettersson, Yonghong Zhang, Ling Cen, Jamie Teer, and Steven Eschrich
  (Moffitt Cancer Center)\n---------------------\nScalable Deep Ensemble Le
 arning for Cancer Drug Discovery\n\nIn this work, we demonstrate how the L
 ivermore Tournament Fast Batch (LTFB) ensemble algorithm is able to effici
 ently tune hyperparameters and accelerate the time to solution for several
  cancer drug discovery networks.  Drawn from the DOE-NCI Pilot 1 and ECP C
 ANDLE projects we show significantly imp...\n\n\nSam Ade Jacobs, Tim Moon,
  and Brian C. Van Essen (Lawrence Livermore National Laboratory)\n--------
 -------------\nExtending Frontiers for Computing in Cancer – Special Sessi
 on\n\nProvide a glimpse into the latest developments at the frontiers of c
 omputing in cancer. Highlight efforts underway with Joint Design of Advanc
 ed Computing Solutions for Cancer and other efforts at the cutting-edge of
  cancer research and high performance computing.\n\n---------------------\
 nWorkshop Morning Break\n---------------------\nToward a Pre-Cancer Image 
 Atlas through Crowdsourcing and Machine Learning\n\nWe describe how crowds
 ourcing can be combined with advanced machine learning for early cancer de
 tection. We demonstrate our system for lung cancer (using data from the Na
 tional Lung cancer Screen Trial), but in such a fashion that it can easily
  be replicated for other organs. Thus this becomes a ste...\n\n\nAshish Ma
 habal (California Institute of Technology); David Liu, Luca Cinquini, Dani
 el Crichton, Heather Kincaid, and Sean Kelly (Jet Propulsion Laboratory); 
 Kristen Anton and Maureen Colbert (Dartmouth Medical School); Christopher 
 Amos (Baylor College of Medicine); Matthew Schabath (Moffitt Cancer Center
 ); and Christos Patriotis and Sudhir Srivastava (National Cancer Institute
 )\n---------------------\nToward a Computational Simulation of Circulating
  Tumor Cell Transport in Vascular Geometries\n\nComputational models can p
 rovide much needed insight into the mechanisms driving cancer cell traject
 ory. However, capabilities must be expanded to enable simulations in large
 r sections of micro- and meso-vasculature and account for the more complex
  fluid dynamic patterns that occur in patient-derive...\n\n\nJohn Gounley 
 (Duke University), Erik W. Draeger (Lawrence Livermore National Laboratory
 ), and Amanda Randles (Duke University)\n---------------------\nAfternoon 
 Keynote – Genomic Profiling of Normal, Premalignant, and Heterogeneous Tis
 sues in Cancer Patients\n\nNormal tissues adjacent to tumor and premaligna
 nt lesions present an opportunity for in vivo human models of early diseas
 e pathology.  Genomic studies of such “at risk” tissues may identify molec
 ular pathways involved in a transition to malignant phenotypes and/or targ
 ets for personalized prevention...\n\n\nPaul Scheet (MD Anderson Cancer Ce
 nter)\n\nTag: Applications, Deep Learning, Exascale\n\nRegistration Catego
 ry: Workshop Reg Pass\n\nSession Chairs: Thomas J. Barr (Nationwide Childr
 en's Hospital); Patricia Kovatch (Icahn School of Medicine at Mount Sinai)
 ; and Eric Stahlberg (MD Anderson Cancer Center, University of Texas)
END:VEVENT
END:VCALENDAR