Crowdsourcing biomedical research: leveraging communities as innovation engines

Sáez-Rodríguez, Julio; Costello, James C.; Friend, Stephen H.; Kellen, Michael R.; Mangravite, Lara M.; Meyer, Pablo; Norman, Thea; Stolovitzky, Gustavo

doi:10.1038/nrg.2016.69

Cited by 151 publications

(140 citation statements)

References 86 publications

(115 reference statements)

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…25–30 To our knowledge, this DREAM challenge represented the first public collaborative competition 31 to use open-access registration trial datasets in cancer with the intention of improving outcome predictions. In total, 163 individuals comprising 50 teams participated in the challenge, applying state-of-the-art machine learning and statistical modelling methods.…”

Section: Discussionmentioning

confidence: 99%

Prediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data

Guinney¹,

Wang²,

Laajala³

et al. 2017

The Lancet Oncology

Self Cite

128

127

View full text Add to dashboard Cite

Summary Background Improvements to prognostic models in metastatic castration-resistant prostate cancer have the potential to augment clinical trial design and guide treatment strategies. In partnership with Project Data Sphere, a not-for-profit initiative allowing data from cancer clinical trials to be shared broadly with researchers, we designed an open-data, crowdsourced, DREAM (Dialogue for Reverse Engineering Assessments and Methods) challenge to not only identify a better prognostic model for prediction of survival in patients with metastatic castration-resistant prostate cancer but also engage a community of international data scientists to study this disease. Methods Data from the comparator arms of four phase 3 clinical trials in first-line metastatic castration-resistant prostate cancer were obtained from Project Data Sphere, comprising 476 patients treated with docetaxel and prednisone from the ASCENT2 trial, 526 patients treated with docetaxel, prednisone, and placebo in the MAINSAIL trial, 598 patients treated with docetaxel, prednisone or prednisolone, and placebo in the VENICE trial, and 470 patients treated with docetaxel and placebo in the ENTHUSE 33 trial. Datasets consisting of more than 150 clinical variables were curated centrally, including demographics, laboratory values, medical history, lesion sites, and previous treatments. Data from ASCENT2, MAINSAIL, and VENICE were released publicly to be used as training data to predict the outcome of interest—namely, overall survival. Clinical data were also released for ENTHUSE 33, but data for outcome variables (overall survival and event status) were hidden from the challenge participants so that ENTHUSE 33 could be used for independent validation. Methods were evaluated using the integrated time-dependent area under the curve (iAUC). The reference model, based on eight clinical variables and a penalised Cox proportional-hazards model, was used to compare method performance. Further validation was done using data from a fifth trial—ENTHUSE M1—in which 266 patients with metastatic castration-resistant prostate cancer were treated with placebo alone. Findings 50 independent methods were developed to predict overall survival and were evaluated through the DREAM challenge. The top performer was based on an ensemble of penalised Cox regression models (ePCR), which uniquely identified predictive interaction effects with immune biomarkers and markers of hepatic and renal function. Overall, ePCR outperformed all other methods (iAUC 0·791; Bayes factor >5) and surpassed the reference model (iAUC 0·743; Bayes factor >20). Both the ePCR model and reference models stratified patients in the ENTHUSE 33 trial into high-risk and low-risk groups with significantly different overall survival (ePCR: hazard ratio 3·32, 95% CI 2·39–4·62, p<0·0001; reference model: 2·56, 1·85–3·53, p<0·0001). The new model was validated further on the ENTHUSE M1 cohort with similarly high performance (iAUC 0·768). Meta-analysis across all methods confirmed previously identified...

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data

Guinney¹,

Wang²,

Laajala³

et al. 2017

The Lancet Oncology

Self Cite

128

127

View full text Add to dashboard Cite

show abstract

“…Given the limited performance of SC2, we assessed whether an ensemble method -based on an aggregation of all submitted models -could yield a better overall model, a phenomenon called "wisdom of the crowd" 9,12 . We used a Spectral Meta-Learner (SML) 13 approach, and observed a marginal improvement in performance (BAC=0.693) over the best performing individual team (BAC=0.688) and an ensemble of any number of randomly chosen models ( Figure 2D).…”

Section: High-throughput Screen Covering Diverse Disease and Drug Commentioning

confidence: 99%

“…DREAM Challenges (dreamchallenges.org) are collaborative competitions that pose important biomedical questions to the scientific community, and evaluate participants' responses in a statistically rigorous and unbiased way, while also emphasizing model reproducibility and methodological transparency 9 . To accelerate the understanding of drug combination synergy, DREAM Challenges partnered with AstraZeneca and the Sanger Institute to launch the AstraZeneca-Sanger Drug Combination Prediction DREAM Challenge.…”

Section: Introductionmentioning

confidence: 99%

A cancer pharmacogenomic screen powering crowd-sourced advancement of drug combination prediction

Wang

Guan

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

In the last decade advances in genomics, uptake of targeted therapies, and the advent of personalized treatments have fueled a dramatic change in cancer care. However, the effectiveness of most targeted therapies is short lived, as tumors evolve and develop resistance. Combinations of drugs offer the potential to overcome resistance. The space of possible combinations is vast, and significant advances are required to effectively find optimal treatment regimens tailored to a patient's tumor. DREAM and AstraZeneca hosted a Challenge open to the scientific community aimed at computational prediction of synergistic drug combinations and predictive biomarkers associated to these combinations. We released a data set comprising ~11,500 experimentally tested drug combinations, coupled to deep molecular characterization of the respective 85 cancer cell lines. Among 150 submitted approaches, those that incorporated prior knowledge of putative drug targets showed superior performance predicting drug synergy across independent data. Genomic features of best-performing models revealed putative mechanisms of drug synergy for multiple drugs in combination with PI3K/AKT pathway inhibitors.All rights reserved. No reuse allowed without permission.(which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.

show abstract

“…Since then, community-driven benchmarking efforts have been recognized as effective tools that are capable of enabling the evaluation of novel or existing computational methods 23 . The limitations and challenges of competition-based benchmarking have been reviewed elsewhere 10,[23][24][25] .…”

Section: Individual Versus Competition-based Benchmarkingmentioning

confidence: 99%

Towards reproducible, transparent, and systematic benchmarking of omics computational tools

Mangul¹,

Martin²,

Hill³

et al. 2018

Preprint

View full text Add to dashboard Cite

Rapid technological advances, such as the development of next-generation sequencing, are driving the need for comprehensive computational tools to analyze the wealth of generated genomic data. Systematic benchmarking has been successful in many research disciplines to help non-computational researchers evaluate the accuracy and applicability of new computational tools. Adopting a standardized benchmarking practice and following established principles for the design of new benchmarking studies could help researchers using omics data to better leverage technological innovation. In this Review, we propose step-by-step instructions for increasing reusability, transparency, and reproducibility of benchmarking studies by using containerization, common data representation, open data, and systematic parameter description.

show abstract

Crowdsourcing biomedical research: leveraging communities as innovation engines

Cited by 151 publications

References 86 publications

Prediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data

Prediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data

A cancer pharmacogenomic screen powering crowd-sourced advancement of drug combination prediction

Towards reproducible, transparent, and systematic benchmarking of omics computational tools

Contact Info

Product

Resources

About