Browse views: by Year, by Function, by GLF, by Subfunction, by Conference, by Journal

Systematic analysis of challenge-driven improvements in molecular prognostic models for breast cancer

Margolin, AA and Bilal, E and Huang, E and Norman, TC and Ottestad, L and Mecham, BH and Sauerwine, B and Kellen, MR and Mangravite, LM and Furia, MD and Vollan, HKM and Rueda, OM and Guinney, J and Deflaux, NA and Hoff, B and Schildwachter, X and Russnes, HG and Park, D and Vang, VO and Pirtle, T and Youseff, L and Citro, C and Curtis, C and Kristensen, VN and Hellerstein, J and Friend, SH and Stolovitzky, G and Aparicio, S and Caldas, C and Borresen-Dale, A (2013) Systematic analysis of challenge-driven improvements in molecular prognostic models for breast cancer. Science Translational Medicine.

Abstract

Although molecular prognostics in breast cancer are among the most successful examples of translating genomic analysis to clinical applications, optimal approaches to breast cancer clinical risk prediction remain controversial. The Sage Bionetworks-DREAM Breast Cancer Prognosis Challenge (BCC) is a crowdsourced research study for breast cancer prognostic modeling using genome-scale data. The BCC provided a community of data analysts with a common platform for data access and blinded evaluation of model accuracy in predicting breast cancer survival on the basis of gene expression data, copy number data, and clinical covariates. This approach offered the opportunity to assess whether a crowdsourced community Challenge would generate models of breast cancer prognosis commensurate with or exceeding current best-in-class approaches. The BCC comprised multiple rounds of blinded evaluations on held-out portions of data on 1981 patients, resulting in more than 1400 models submitted as open source code. Participants then retrained their models on the full data set of 1981 samples and submitted up to five models for validation in a newly generated data set of 184 breast cancer patients. Analysis of the BCC results suggests that the best-performing modeling strategy outperformed previously reported methods in blinded evaluations; model performance was consistent across several independent evaluations; and aggregating community-developed models achieved performance on par with the best-performing individual models. Copyright 2013 by the American Association for the Advancement of Science; all rights reserved

Item Type: Article
Additional Information: pubid: 212 nvp_institute: NIBR contributor_address: (Margolin, Huang, Norman, Mecham, Kellen, Mangravite, Furia, Guinney, Deflaux, Hoff, Schildwachter, Friend) Sage Bionetworks, 1100 Fairview Avenue North, MS: M1-C108, Seattle, WA 98109, United States (Bilal, Stolovitzky) Functional Genomics and Systems Biology, IBM Computational Biology Center, P. O. Box 218, Yorktown Heights, NY 10598, United States (Huang) Institute for Genome Sciences and Policy, Duke University, Durham, NC 27708, United States (Huang) Department of Surgery, Duke University School of Medicine, Durham, NC 27710, United States (Ottestad, Vollan) Department of Oncology, Division of Cancer, Surgery and Transplantation, Oslo University Hospital, 0450 Oslo, Norway (Mecham) Trialomics, LLC, Seattle, WA 98103, United States (Sauerwine, Pirtle, Youseff, Citro, Hellerstein) Google Inc., 651 North 34th Street, Seattle, WA 98103, United States (Furia) Genomics Institute of the Novartis Research Foundation, San Diego, CA 92121, United States (Vollan, Russnes, Vang, Kristensen, Borresen-Dale) Department of Genetics, Institute for Cancer Research, Oslo University Hospital, Montebello, 0310 Oslo, Norway (Vollan, Russnes, Vang, Kristensen, Borresen-Dale) K.G. Jebsen Centre for Breast Cancer Research, Institute for Clinical Medicine, Faculty of Medicine, 0313 Oslo, Norway (Vollan, Rueda, Caldas) Cancer Research UK, Cambridge Research Institute, Li Ka Shing Centre, Robinson Way, Cambridge CB2 0RE, United Kingdom (Russnes) Department of Pathology, Oslo University Hospital, 0450 Oslo, Norway (Park) Department of Pathology, Drammen Hospital, Vestre Viken HF, 3004 Drammen, Norway (Curtis) Department of Preventive Medicine, Keck School of Medicine, University of Southern California, Los Angeles, CA 90033, United States (Kristensen) Department of Clinical MolecularOncology, Division of Medicine, AkershusUniversity Hospital, 1478 Ahus, Norway (Aparicio) Molecular Oncology, British Columbia Cancer Research Centre, Vancouver, BC V5Z 1L3, Canada (Aparicio) Department of Pathology and LaboratoryMedicine, University of British Columbia, Vancouver, BC V6T 1Z4, Canada (Aparicio) Genome Sciences Centre, BC Cancer Agency, 675 West 10th Avenue, Vancouver, BC V5Z 1L3, Canada (Caldas) Cambridge Breast Unit, Addenbrooke's Hospital, Cambridge University Hospital NHS Foundation Trust and NIHR Cambridge Biomedical Research Centre, Cambridge CB2 2QQ, United Kingdom (Caldas) Cambridge Experimental Cancer Medicine Centre, Cambridge CB2 0RE, United Kingdom
Date Deposited: 13 Oct 2015 13:12
Last Modified: 13 Oct 2015 13:12
URI: https://oak.novartis.com/id/eprint/22030

Search

Email Alerts

Register with OAK to receive email alerts for saved searches.