Close
FINDING CURES TOGETHER<sup>SM</sup>

30th Anniversary AACR Special Conference Convergence: Artificial Intelligence, Big Data, and Prediction in Cancer

​Program   

Sunday, Oct. 14 

Monday, Oct. 15

Tuesday, Oct. 16

Wednesday, Oct. 17


Sunday, Oct. 14

Welcome
6-6:30 p.m.

Welcome  
Margaret Foti, American Association for Cancer Research, Philadelphia, Pennsylvania

Conference Overview
Phillip A. Sharp, David H. Koch Institute for Integrative Cancer Research at MIT, Cambridge, Massachusetts


Keynote Lectures

6:30-8 p.m.

Detection of cancer with circulating nucleic acids
Richard Klausner, Mindstrong Health, Palo Alto, California

Using single cell atlases to study the tumor ecosystem
Aviv Regev, Massachusetts Institute of Technology, Cambridge, Massachusetts


Opening Reception
8-9:30 p.m.


Top of page


Monday, Oct. 15  

Continental Breakfast
7-8 a.m.


Plenary Session 1: Predicting the Genetic/Environmental  Causes of Cancer

8-10 a.m.

The fourth revolution in cancer research: From phenotype to molecular biology to omics to data science
Alan Bernstein, Canadian Institute for Advanced Research (CIFAR), Toronto, ON, Canada

Models of pancreatic cancer risk
Alison P. Klein, Johns Hopkins Sidney Kimmel Comprehensive Cancer Center, Baltimore, Maryland

The challenge of characterizing cancer susceptibility
Stephen J. Chanock, National Cancer Institute, Rockville, Maryland

Title to be announced
Anna Goldenberg, University of Toronto, Toronto, ON, Canada

 
Break
10-10:30 a.m.


Plenary Session 2: Predicting Cancer Phenotype through Images

10:30 a.m.-12 p.m.

Title to be announced
Josephine Bunch, National Physical Laboratory, Middlesex, England

Assignment of surgical margins with PARP imaging agents in the oral cavity
Thomas Reiner, Memorial Sloan Kettering Cancer Center, New York, New York

Learning disease progression models from images and text
Regina Barzilay, MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Massachusetts


Lunch on Own / Free Time

12-2 p.m.


Plenary Session 3: Predicting Cancer Phenotype through  Histology and Pathology

2:15-4:15 p.m.

Predicting cancer phenotype through histology and pathology
Thomas J. Fuchs, Memorial Sloan Kettering Cancer Center, New York, New York

Machine learning approaches to annotate pathology images with high-dimensional cellular state information
Barbara E. Engelhardt, Princeton University, Princeton, New Jersey

Bringing it all together: AI-powered pathology for immuno-oncology
Andrew H. Beck, PathAI, Cambridge, Massachusetts

Title to be announced
Dana Pe'er, Memorial Sloan Kettering Cancer Center, New York, New York

 
Short Talks from Proffered Papers Session 1 
4:30-5:10 p.m.

Computed tomography textures machine learning classifiers predict response to immunotherapy in patients with lung cancer*
Harini Veeraraghavan, Memorial Sloan Kettering Cancer Center, New York, New York

Identification of relevant alterations in cancer using topological data analysis*
Pablo Camara, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania

Systematic network-based analysis reveals novel molecular subtypes conserved in multiple pancreatic cancer cohorts and at the single cell level*
Pasquale Laise, Columbia  University, New York, New York

An integrative genetic epidemiologic approach to analysis of multiomics data identifies low and medium risk susceptibility genes for breast cancer*
Roxana Moslehi, University at Albany, Albany, New York


Poster Session A / Reception

5:30-7:30 p.m.


Free Time / Evening on Own

7:30 p.m.-

Top of page


Tuesday, Oct. 16 

Continental Breakfast
7-8 a.m.
 
Plenary Session 4: Predicting Cancer Response Using Patient-Centric Data Platforms 
8-10 a.m.

Partnering with patients to advance cancer research
Nikhil Wagle, Dana-Farber Cancer Institute, Boston, Massachusetts

An integrated omic and multi scale image view of breast cancer progression
Joe W. Gray, Oregon Health & Science University, Portland, Oregon

Emerging opportunities at the intersection of computational oncology and precision cancer medicine
Eliezer M. Van Allen, Dana-Farber Cancer Institute, Boston, Massachusetts

The reality of complexity when using knowns to query unknowns: From yeast and omics to humans and forecasting symptom transitions
Stephen M. Friend, Visiting Professor Oxford University, 4YouandMe, Sage Bionetworks, Seattle, Washington


Break
10-10:30 a.m.

 
Plenary Session 5: Predicting Cancer Response to Precision Therapy 
10:30 a.m.-12:30 p.m.

Identification of breast cancer drivers and therapy resistance mechanisms in mouse models
Jos Jonkers, Netherlands Cancer Institute, Amsterdam, Netherlands

Defining a cancer dependency map
William C. Hahn, Dana-Farber Cancer Institute, Boston, Massachusetts

Tumor evolution and heterogeneity: Optimizing precision therapy in lung cancer
Alice T. Shaw, Massachusetts General Hospital Cancer Center, Boston, Massachusetts

 
Lunch on Own / Free Time
12:30-2:30 p.m.

Special Session: New Funding Opportunities from the NCI Center for Cancer Training  
1:45-2:30 p.m.

Michele McGuirl, Center for Cancer Training, National Cancer Institute, Bethesda, Maryland

A new NCI funding opportunity is expected to be published in late 2018 for early-stage postdocs who wish to pursue careers as independent cancer researchers, and those in data and population sciences are especially encouraged to apply. Mentors and potential applicants (including international students and postdocs) are invited to learn more about this new pilot program and other funding opportunities offered by NCI.


Plenary Session 6: Predicting the Impact of Early Intervention in Cancer  
2:45-4:45 p.m.

RNA-based elucidation of pharmacologically actionable dependencies in human malignancies
Andrea Califano, Columbia University, New York, New York

Title to be announced
Franziska Michor, Dana-Farber Cancer Institute, Boston, Massachusetts

Making hay of needles: Connecting clinical and physical parameters in the search for early cancer
Imran S. Haque, Freenome, South San Francisco, California

The convergence of data streams for pancreatic cancer earlier detection
Brian M. Wolpin, Dana-Farber Cancer Institute, Boston, Massachusetts

Short Talks from Proffered Papers Session 2  
4:45-5:15 p.m.

Incorporating breast anatomy in radiomic machine learning for breast cancer risk estimation with digital mammograms*
Aimilia Gastounioti, University of Pennsylvania, Philadelphia, Pennsylvania

DeepAbstractor: A scalable deep learning framework for automated information extraction from free-text pathology reports*
Georgia Tourassi, Oak Ridge National Laboratory, Oak Ridge, Tennessee

Mammogram-derived texture features and risk of breast cancer*
Oana A. Zeleznik, Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts

 
Poster Session B / Reception
5:15-7:15 p.m.

 
Evening on Own / Free Time
7:15 p.m.-

Top of page


Wednesday, Oct. 17    

Continental Breakfast

7-8 a.m.
 
Plenary Session 7: Predicting Immune Response to Cancer 
8-10 a.m.

Immunotherapy induced immune responses to pancreatic cancer
Elizabeth M. Jaffee, Johns Hopkins Sidney Kimmel Comprehensive Cancer Center, Baltimore, Maryland

Multi-omic, dynamic data clouds for early detection of cancer or cancer recurrence
James R. Heath, Institute of Systems Biology, Seattle, Washington

The predictive value of the pre-existing immune contexture and Immunoscore
Jerome Galon, INSERM UMRS1138, Cordeliers Research Center, Paris, France

Identifying and tracking tumor-specific T-cell clones
Harlan Robins, Adaptive Biotechnologies Corporation, Seattle, Washington


Break

10-10:15 a.m.


Plenary Session 8: Predicting Cancer Status by Metabolic  Changes

10:15-12:15 p.m.

Metabolic modeling of single-cell RNA-Seq reveals cell-to-cell metabolic heterogeneity and actionable targets in autoimmunity
Nir Yosef, UC Berkeley Center for Computational Biology, Berkeley, California

Metabolic reprogramming in human tumors in vivo
Ralph J. DeBerardinis, UT Southwestern Medical Center, Dallas, Texas

Leveraging metabolic limitations of tumor growth to treat cancer
Matthew G. Vander Heiden, David H. Koch Institute for Integrative Cancer Research at MIT, Cambridge, Massachusetts

Urea cycle dysregulation, emerging pyrimidines mutation bias, and enhanced response to immunotherapy in cancer
Eytan Ruppin, National Cancer Institute, Bethesda, Maryland


Closing Remarks
12:15-12:30 p.m.

Phillip A. Sharp, David H. Koch Institute for Integrative Cancer Research at MIT, Cambridge, Massachusetts

William C. Hahn, Dana-Farber Cancer Institute, Boston, Massachusetts

 
Departure


*Short talk from proffered abstract

Top of page