A Crowdsourcing Approach to Developing and Assessing Prediction Algorithms for AML Prognosis

Simple item page
dc.citation.articleNumbere1004890
dc.citation.issueNumber6
dc.citation.journalTitlePLoS Computational Biology
dc.citation.volumeNumber12
dc.contributor.authorNoren, David P.
dc.contributor.authorLong, Byron L.
dc.contributor.authorNorel, Raquel
dc.contributor.authorRrhissorrakrai, Kahn
dc.contributor.authorHess, Kenneth
dc.contributor.authorHu, Chenyue Wendy
dc.contributor.authorBisberg, Alex J.
dc.contributor.authorSchultz, Andre
dc.contributor.authorEngquist, Erik
dc.contributor.authorLiu, Li
dc.contributor.authorLin, Xihui
dc.contributor.authorChen, Gregory M.
dc.contributor.authorXie, Honglei
dc.contributor.authorHunter, Geoffrey A.M.
dc.contributor.authorBoutros, Paul C.
dc.contributor.authorStepanov, Oleg
dc.contributor.authorDREAM 9 AML-OPC Consortium
dc.contributor.authorNorman, Thea
dc.contributor.authorFriend, Stephen H.
dc.contributor.authorStolovitzky, Gustavo
dc.contributor.authorKornblau, Steven
dc.contributor.authorQutub, Amina A.
dc.date.accessioned2016-09-30T20:52:23Z
dc.date.available2016-09-30T20:52:23Z
dc.date.issued2016
dc.description.abstractAcute Myeloid Leukemia (AML) is a fatal hematological cancer. The genetic abnormalities underlying AML are extremely heterogeneous among patients, making prognosis and treatment selection very difficult. While clinical proteomics data has the potential to improve prognosis accuracy, thus far, the quantitative means to do so have yet to be developed. Here we report the results and insights gained from the DREAM 9 Acute Myeloid Prediction Outcome Prediction Challenge (AML-OPC), a crowdsourcing effort designed to promote the development of quantitative methods for AML prognosis prediction. We identify the most accurate and robust models in predicting patient response to therapy, remission duration, and overall survival. We further investigate patient response to therapy, a clinically actionable prediction, and find that patients that are classified as resistant to therapy are harder to predict than responsive patients across the 31 models submitted to the challenge. The top two performing models, which held a high sensitivity to these patients, substantially utilized the proteomics data to make predictions. Using these models, we also identify which signaling proteins were useful in predicting patient therapeutic response.
dc.identifier.citationNoren, David P., Long, Byron L., Norel, Raquel, et al.. "A Crowdsourcing Approach to Developing and Assessing Prediction Algorithms for AML Prognosis." <i>PLoS Computational Biology,</i> 12, no. 6 (2016) Public Library of Science: http://dx.doi.org/10.1371/journal.pcbi.1004890.
dc.identifier.doihttp://dx.doi.org/10.1371/journal.pcbi.1004890
dc.identifier.urihttps://hdl.handle.net/1911/91645
dc.language.isoeng
dc.publisherPublic Library of Science
dc.rightsThis is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleA Crowdsourcing Approach to Developing and Assessing Prediction Algorithms for AML Prognosis
dc.typeJournal article
dc.type.dcmiText
dc.type.publicationpublisher version
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
journal.pcbi.1004890.pdf
Size:
2.24 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Faculty Publications
Bioengineering Publications
Center for Research Computing