OUS researchers contribute to pioneering approach of crowdsourced research competition

April 17 cover of Sci Transl Med
April 17 cover of Sci Transl Med

In an extensive collaboration with the Department of Pathology (Hege G. Russnes) and Department of Oncology (Lars Ottestad and Hans Kristian Vollan), scientists from the Department of Genetics lead by Anne-Lise Børresen contributed to a pioneering approach of crowdsourced research competition — the Sage Bionetworks–DREAM Breast Cancer Prognosis Challenge. In this competition computational biologist from the whole world made use of gene expression, gene copy number, and clinical data to develop prognostic models for breast cancer survival in an open challenge environment.
In the April 17 issue of Science Translational Medicine, the Challenge’s conception and execution as well as insights derived from its outcome are described.

The BCC comprised multiple rounds of blinded evaluations on held-out portions of data on 1981 patients from the METABRIC cohort, resulting in more than 1400 models submitted. All models were submitted as open source code available for all participants. Participants then retrained their models on the full data set of 1981 samples and submitted up to five models for validation. The validation set represented newly generated molecular and clinical data of 184 breast cancer patients from Oslo.

Links:

Science Translation Research April 17 issue - cover expansion

Systematic Analysis of Challenge-Driven Improvements in Molecular Prognostic Models for Breast Cancer
Science Translation Medicine, April 17 2013
PDF format

In a companion Research Article, Cheng et al. outline the development of the prognostic computational model that won the Challenge:
Development of a Prognostic Model for Breast Cancer Survival in an Open Challenge Environment
Science Translation Medicine, April 17 2013
PDF format

Editor's summary - Dreaming of biomedicine's future (Word format)


Home page of Anne-Lise Børresen-Dale's group - Integrated Genomics of Breast Cancer

Department of Genetics

 
Page visits: 3707