Sage Bionetworks / DREAM Breast Cancer Prognosis Challenge

Last year at the Sage Congress, we announced a contest to create a computational model that more accurately predicts breast cancer survival than existing models.

It was called the Sage Bionetworks / DREAM Breast Cancer Prognosis Challenge, and we built it on the following basis information:

•    Training data set: genomic and clinical data from 2000 women diagnosed with breast cancer (the METABRIC data set)
•    Data access and analysis tools: Synapse
•    Compute resources: each participant provided with a standardized virtual machine donated by Google
•    Model scoring: models submitted to Synapse for scoring on a real-time leaderboard

This Challenge was open source and encouraged code-sharing to forge innovative computational models. The standardized and shared computational infrastructure enabled participants to use code submitted by others in their own model building, and the winning code must be reproducible.

We’re using a brand new dataset to select the winning model, derived from approximately 180 breast cancer samples, with data generation funded by Avon. The winning model will be the one that, having been trained using METABRIC data, is most accurate for survival prediction when applied to a brand new dataset.

The winner gets, in addition to peer acclaim, the right to submit a pre-approved article about his/her winning model to Science Translational Medicine.

354 participants from 35 countries registered for the challenge.  Throughout the model-training period, more than 1700 models were submitted to the leaderboard on Synapse for scoring (the code for all the models on the leaderboard was accessible to all to use to evolve new models).

Each participant was invited to submit up to 5 of their models, from all of those that they had generated, for final scoring against the METABRIC data set. The top two teams were recognized at the Nov 2012 DREAM conference.

•    Top Scoring Team: Attractor Metagenes
–    Team Members: Wei-Yi Cheng, Tai-Hsien Ou Yang, and Dimitris Anastassiou
–    Affiliation: Center for Computational Biology and Bioinformatics and Department of Electrical Engineering, Columbia University
•    Second Best Scoring Team: PittTransMed
–    Team Members: Dr. Songjian Lu, Dr. Chunhui Cai, Ms. Hatice Ulku Osmanbeyoglu, Ms. Lujia Chen, Dr. Roger Day, Dr. Gregory Cooper and Dr. Xinghua Lu
–    Affiliation: Department of Biomedical Informatics, School of Medicine, University of Pittsburgh

The same or different of their models are now being tested against the newly generated Oslo-Val data set, and a single winner will publish in STM and to be invited to speak at the Congress.

For final scoring, 46 individuals or teams ended up submitting models.  So in total, there were about 170 final models to score against Metabric and then against Oslo-Val.

We’ll be announcing the final winner soon. To stay up on this and other Sage Bionetworks news, follow us on Twitter.

Sage Bionetworks’ “Model Challenge” is still open to all new comers!

12 September 2012 – Kelly LaMarco has published a Science Translational Medicine Editor’s Choice Report describing the Sage Bionetworks/DREAM Breast Cancer Prognosis Challenge that continues to welcome new participants until October 15, 2012.  Winners of the Challenge will be invited to San Francisco (with their travel costs paid for by DREAM and Sage Bionetworks) to present in either the November, 2012 DREAM conference or Sage Bionetwork’s April, 2013 4th Annual Congress.

Sage Bionetworks named one of the two best places in the world to work

It is wonderful to report that Sage Bionetworks has been ranked #2 in The Scientist’s tenth international survey of best places to work in academia. The Scientist noted that in this year’s survey, researchers around the world said they valued the personal satisfaction their workplace offers above all else. Sage Bionetworks was profiled by Hayley Dunning who noted that with fewer than 30 researchers, each with a different specialty, Sage Bionetworks was an “incubator for innovation,” quoting Senior Scientist Brian Bot, who feels that weekly interactions with software engineers as well as oncologists with direct patient contact help him put “a different spin on things.”

Dr. Stephen Friend, President of Sage Bionetworks, remarked, “This unanticipated recognition for our young endeavor illustrates the increasing importance of collective biomedical research and is reflected in recent large number of outstanding researchers wanting to work here.

The survey complied over 1,000 responses from full-time life scientists working in academic and non-profit research institutions around the world. The Gladstone Institutes in San Francisco ranked first for the second year in a row. Sage Bionetworks was cited as a newcomer in the top 25 institutions that also included the Massachusetts General Hospital, Cleveland Clinic and Scripps Institute of Oceanography.

A New Model

“Sage Bionetworks does not follow traditional research organization models”, Stephen Friend noted. “We have an outstanding interdisciplinary team of experts working towards a common strategic goal rather than individual academic recognition.” Building from its computation biology roots, Sage Bionetworks is also increasingly working with patient advocates and communities to help build better models of disease.

Sage Bionetworks is focused on changing how medical researchers and citizens collaborate on large datasets to create useful models of disease with initiatives such as Synapse, an open access analysis and collaboration platform, and the DREAM breast cancer prognosis challenge that enables research community interaction.

It should be noted that Sage Bionetworks partners with a broad array of academic and commercial entities to accomplish its goals. We have been especially fortunate to have the support of the NCI’s Integrative Cancer Biology Program and the Washington Life Sciences Discovery fund for this start-up enterprise as well as ongoing partnerships with organizations such as IBM, Google, Amazon and the Fred Hutchinson Cancer Research Center.”

download Sage Bionetworks media release

About The Scientist:

The Scientist has informed and entertained life science professionals around the world for over 25 years. The title provides innovative print and online coverage of the latest innovations in life science research and industry developments including trends in research, new technology, news, business and careers. We reach the leading researchers in academia and industry that are interested in maintaining a broad view of the life sciences by reading insightful articles that are current, concise, accurate and entertaining. For more information about The Scientist, visit www.the-scientist.com

CommonMind – New Open Research Resource

Press Release: CommonMind Consortium Launched as a Public-Private Effort to Generate and Broadly Share Molecular Data on Neuropsychiatric Disease.

Date: April 9th, 2012
Contact: Jonathan Derry, Vice-President, Sage Bionetworks
Tel: (206) 667-2101   email: info@CommonMind.org

SEATTLE, WA.  Sage Bionetworks, Mount Sinai School of Medicine (MSSM), University of Pennsylvania (Penn), the National Institute of Mental Health (NIMH), and Takeda Pharmaceuticals Company Limited (TAKEDA) have launched a Public-Private Pre-Competitive Consortium to generate and analyze large-scale genomic data from human subjects with neuropsychiatric disease and to make this data and the associated analytical results broadly available to the public. This collaboration brings together disease area expertise, large scale and well curated brain sample collections, and data management and analysis expertise from the respective institutions.

As many as 450 million people worldwide are believed to be living with a mental or behavioral disorder: schizophrenia and bipolar disorder are two of the top six leading causes of years lived with disability according to the World Health Organization. The burden on the individual as well as on society is significant with estimates for the health care costs for these individuals as high as four percent GNP. This highlights a grave need for new therapies to alleviate this suffering.

Researchers from MSSM including Dr. Pamela Sklar, Dr. Joseph Buxbaum and Dr. Eric Schadt will join with Dr. Raquel Gur and Dr. Chang-Gyu Hahn from Penn to combine their extensive brain bank collections for the generation of whole genome scale RNA and DNA sequence data. Dr. Pamela Sklar, Professor of Psychiatry and Neuroscience at MSSM commented “this is an exciting opportunity for us to use the newest genomic methods to really expand our understanding of the molecular underpinnings of neuropsychiatric disease”, while Dr Raquel Gur, Professor of Psychiatry from Penn observed “this will be a great complement to some of the large-scale genetic analyses that have been carried out to date because it will give a more complete mechanistic picture”.

Dr. Jonathan Derry, Vice President of Research at Sage Bionetworks noted, “We are truly thrilled to be partnering with some of the best brain researchers to generate an unprecedented scale of molecular data that we will make broadly available as a resource to the community through our data analysis and management platform Synapse.”  Dr Thomas Lehner, Chief Genomics Research Branch at NIMH added, “The NIMH is particularly excited about this partnership that will leverage resources and expertise in both the public and the private sector to accelerate research into the causes and treatments of major mental illness”.

TAKEDA has provided seed funding for the effort that will look to expand in the future. The CommonMind Consortium is committed to generating an open resource for the community and invites others with common goals to contact us at info@CommonMind.org.

Download PDF of Press Release

Young Investigator Travel Awards

Sage Bionetworks is offering 10 travel awards to the 2012 Commons Congress in San Francisco to grad students, postdocs and early stage investigators. Details and an on line application form are available on the Congress website.  This is a fantastic opportunity for young clinicians, biologists, software engineers and computational scientists who are passionate about open science and data-intensive science to participate and contribute.

Application deadline is February 29, so act quickly. Please forward this information on to outstanding candidates!

 

Conversations

network building in the Big Data Deluge

Sage Bionetworks is holding an interactive colloquium with the Hutchinson Cancer Research Center on collective approaches to analyzing the tsunami of medical research data and translate it into healthcare advances. Come find out what you need to take advantage of high performance, cloud-based computing and the development of predictive models of disease within a collaborative platform.

Presentations and Roundtable:
FHCRC – david hockenbery • soheil meshinchi • pete nelson • jim olson • riki peters • jerry radich
UW – kelly edwards
SAGE BIONETWORKS – jonathan derry • stephen friend • erich huang • lara mangravite • adam margolin
GUEST SPEAKER – eric schadt
synapse demonstrations • sage bionetworks software platform team
poster presentations • sage bionetworks scientists & engineers

Questions? contact conversations@sagebase.org

Monday 23 January 2012 – 2 PM – 5 PM

Pelton Auditorium • Thomas Building • Fred Hutchinson Cancer Research Center • 1100 Fairview Ave. N. • Seattle WA

Download PDF of Program