Past Issues of the DREAM Newsletter

*|MC:SUBJECT|*
View this email in your browser
December 1, 2020
Share Share
Tweet Tweet
Forward Forward

Friday, Dec. 4, 11 a.m. PST - Webinar

Join the free webinar for the Anti-PD-1 Response Prediction DREAM Challenge – the first Challenge in immuno-oncology 

Date: Friday, Dec. 4, 2020
Time: 11 a.m. PST
No need to register.
Webinar Info
ABOUT THE CHALLENGE: This DREAM Challenge aims to crowdsource machine learning algorithms to help predict the response to checkpoint inhibition therapy.

Immuno-oncology (I-O) therapy targeting the PD-1 pathway has transformed the treatment landscape in advanced non-small cell lung cancer (NSCLC), with the combination of I-O with or without chemotherapy being the current standard of care in the first-line setting for those patients who are ineligible for targeted therapy.1-5 While durable responses and prolonged survival have been demonstrated in some patients treated with I-O, there remains a high disease burden and a need to improve the ability to predict which patients are more likely to receive benefit from treatment with I-O. 

The Bristol Myers Squibb-Sage Bionetworks Anti–PD-1 Response Prediction DREAM Challenge is the first DREAM initiative and collaboration in the I-O space. Like other DREAM Challenges, the Anti–PD-1 Challenge is a crowdsourced effort that looks to advance our understanding of foundational questions in biomedicine through open-science collaboration. We invite experts and innovators in genomics, computational biology, and translational biomarker development to participate in this Challenge that aims to identify predictive biomarkers for I-O therapy in lung cancer. The deidentified, validation dataset for this Challenge comes from an international, randomized, open-label phase 3 trial (CheckMate 026) of anti-PD-1 nivolumab vs platinum-based chemotherapy in patients with previously untreated advanced NSCLC.6 By exploring RNA-sequencing data for predictive signals of efficacy and resistance to nivolumab, the Anti–PD-1 Challenge seeks to improve our ability to appropriately select patients most likely to benefit from I-O treatment and to gain insights that may facilitate potential novel monotherapies or combinations with I-O.
Webinar Info
Twitter
Website
Copyright © *|CURRENT_YEAR|* *|LIST:COMPANY|*, All rights reserved.
*|IFNOT:ARCHIVE_PAGE|* *|LIST:DESCRIPTION|*

Our mailing address is:
*|HTML:LIST_ADDRESS_HTML|* *|END:IF|*

Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

*|IF:REWARDS|* *|HTML:REWARDS|* *|END:IF|*
*|MC:SUBJECT|*
View this email in your browser
September 20, 2020
Share Share
Tweet Tweet
Forward Forward

NeurIPS Workshop: Abstracts Due Oct. 2!

ML Competitions at the Grassroots

The Challenges in Machine Learning Workshop at NeurIPS invites you to submit your two-page abstracts for oral or poster presentations on a diversity of topics pertaining to competitions in machine learning, including but not limited to:
  • strategies for addressing behavioral barriers to participation in ML competitions from under-represented communities
  • strategies for measuring the long-term impact of participation in an ML competition
  • novel competition protocols
  • ML hackathons and datathons, etc.
We look forward to your participation. Visit the link below for guidelines and registration information.

Virtual Workshop: Dec. 11
Abstract Submission Deadline: Oct. 2
INFO & REGISTRATION

DREAM RSG Nov. 16-18

13th annual RECOMB/ISCB Conference on Regulatory & Systems Genomics
The RECOMB/ISCB Conference on Regulatory and Systems Genomics with DREAM Challenges is one of the premier annual meetings in the fields of regulatory genomics, systems biology, and network visualization. You are invited to submit an abstract and poster for past DREAM Challenges. Learn more about submission guidelines here.

Virtual Conference: Nov. 16-19
INFO & REGISTRATION

Hack for NF! Oct. 2-Nov. 13

$30,000 Prize Pool


The Children’s Tumor Foundation is hosting Hack for NF 2020! They’re calling for healthcare startups, developers, solutions architects, and hackathon enthusiasts to join researchers, clinicians, and patients to develop solutions built around neurofibromatosis. Bring your data science, ML, and AI skills to the table and help make a difference. The winning teams will claim from the $30,000 prize pool with additional incubation opportunities after the hackathon. Help spread the word so we can recruit participants!
LEARN MORE
Twitter
Website
Copyright © *|CURRENT_YEAR|* *|LIST:COMPANY|*, All rights reserved.
*|IFNOT:ARCHIVE_PAGE|* *|LIST:DESCRIPTION|*

Our mailing address is:
*|HTML:LIST_ADDRESS_HTML|* *|END:IF|*

Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

*|IF:REWARDS|* *|HTML:REWARDS|* *|END:IF|*
*|MC:SUBJECT|*
View this email in your browser

FOR IMMEDIATE RELEASE
 

The Michael J. Fox Foundation and Sage Bionetworks Announce Winners of the $25,000 BEAT-PD DREAM Challenge

NEW YORK (June 17, 2020) – The Michael J. Fox Foundation for Parkinson’s Research (MJFF) and Sage Bionetworks announce the winners of the BEAT-PD DREAM Challenge. BEAT-PD (Biomarker and Endpoint Assessment to Track Parkinson’s Disease) is a data challenge designed to benchmark new methods to predict Parkinson’s disease severity in patients in their homes. MJFF and Sage partnered with Evidation Health, Northwestern University, Radboud University Medical Center, and the BRAIN Commons to host the BEAT-PD Challenge.

Forty-three teams participated in the Challenge with data hosted by the BRAIN Commons. The teams received access to raw sensor (accelerometer and gyroscope) time-series data, which they used to predict individual medication state and symptom severity. Winners from the Challenge share a $25,000 prize.

The winners of the BEAT-PD Challenge are: 

  • dbmi (Yidi Huang, Brett Beaulieu-Jones, Mark Keller, Mohammed Saqib) from Harvard Medical School, Department of Biomedical Informatics 

  • ROC BEATPD (Alex Page, Monica Javidnia, Greta Smith, Robbie Zielinski, and Charles Venuto) from the University of Rochester Medical Center

  • Yuanfang Guan from University of Michigan

  • HaProzdor (Ayala Matzner, Yuval El-Hanany, Izhar Bar-Gad) from the Gonda Brain Research Center at Bar Ilan University

“We congratulate all the winners. The Foundation has supported research into sensors and other digital tools for Parkinson’s for many years,” says Mark Frasier, PhD, Senior Vice President, Research Programs at MJFF. “The BEAT-PD projects are unlocking the potential of data collected by digital devices to help people with Parkinson’s, their physicians, and researchers. Now, more than ever, we understand the critical importance of remote monitoring for the safe and effective delivery of healthcare and the progress of clinical research.”

In a previous data challenge, teams proved that disease status and symptom severity could be predicted using data collected during the completion of specific tasks while monitored by a physician. The BEAT-PD Challenge built on this to determine whether disease severity can be assessed from passive sensor data from consumer electronics, collected during daily life, not pre-set tasks, which will bring us closer to the promise of at-home monitoring of disease progression.

Three of the teams (dbmi, ROC BEATPD and HaProzdor) approached the problem by applying signal processing methods to the smartwatch and smartphone sensor data, the results of which were then used in machine learning models which allowed for patient-specific characteristics. The fourth solution, by Yuanfang Guan, applied a deep-learning model incorporating spatial and temporal data augmentation of the sensor data.

BEAT-PD data used in the DREAM Challenge is available on the BRAIN Commons. For more information and to apply for access to these data, please visit: https://www.braincommons.org/beat-pd-data-release/.

The winning teams have been invited to collaborate to improve upon their individual models, as well as to test them against clinician-validated symptom severity ratings and to co-author a manuscript based on their findings.

Learn more about the BEAT-PD Challenge: www.synapse.org/beatpdchallenge

 

Contacts: 

Kristina Magana
The Michael J. Fox Foundation
kmagana@michaeljfox.org 

 

Hsiao-Ching Chou
Sage Bionetworks
chou@sagebionetworks.org 

 

ABOUT THE MICHAEL J. FOX FOUNDATION

As the world's largest nonprofit funder of Parkinson's research, The Michael J. Fox Foundation is dedicated to accelerating a cure for Parkinson's disease and improved therapies for those living with the condition today. The Foundation pursues its goals through an aggressively funded, highly targeted research program coupled with active global engagement of scientists, Parkinson's patients, business leaders, clinical trial participants, donors and volunteers. In addition to funding more than $900 million in research to date, the Foundation has fundamentally altered the trajectory of progress toward a cure. Operating at the hub of worldwide Parkinson's research, the Foundation forges groundbreaking collaborations with industry leaders, academic scientists and government research funders; increases the flow of participants into Parkinson's disease clinical trials with its online tool, Fox Trial Finder; promotes Parkinson's awareness through high-profile advocacy, events and outreach; and coordinates the grassroots involvement of thousands of Team Fox members around the world. For more information, visit us at michaeljfox.org, on Facebook or Twitter.

ABOUT SAGE BIONETWORKS

Sage Bionetworks is a nonprofit biomedical research and technology development organization that was founded in Seattle in 2009. Our focus is to develop and apply open practices to data-driven research for the advancement of human health. Our interdisciplinary team of scientists and engineers work together to provide researchers access to technology tools and scientific approaches to share data, benchmark methods, and explore collective insights, all backed by Sage’s gold-standard governance protocols and commitment to user-centered design. Sage is a 501c3 and is supported through a portfolio of competitive research grants, commercial partnerships, and philanthropic contributions.
 

ABOUT DREAM CHALLENGES

DREAM (Dialogue on Reverse Engineering and Assessment Methods) Challenges emerged in 2006 to leverage the wisdom of the multidisciplinary scientific community to solve fundamental and difficult questions in biomedical research. DREAM’s methodology is based on crowd-sourcing scientific Challenges, fostering open and collaborative research, and promoting data sharing. In 2013, DREAM partnered with Sage Bionetworks, which developed and administers the technology platform that underpins DREAM Challenges.

ABOUT BRAIN COMMONS 

The BRAIN Commons is a scalable cloud based platform for computational discovery designed for the brain health community. The BRAIN Commons empowers the global research community by providing access to multi-modal data, state-of-the-art analytic tools and a secure interoperable system for data sharing. The BRAIN Commons is spearheaded by Cohen Veterans Bioscience, a non-profit research biotech dedicated to advancing brain health through data driven science. In partnership with The Michael J. Fox Foundation, the BRAIN Commons hosts the DREAM challenge data. www.braincommons.org

Twitter
Facebook
Website
Copyright © *|CURRENT_YEAR|* *|LIST:COMPANY|*, All rights reserved.
*|IFNOT:ARCHIVE_PAGE|* *|LIST:DESCRIPTION|*

Our mailing address is:
*|HTML:LIST_ADDRESS_HTML|* *|END:IF|*

Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

*|IF:REWARDS|* *|HTML:REWARDS|* *|END:IF|*
*|MC:SUBJECT|*
Forward Forward
Share Share
Share Share
Share Share

How Can We Help?

Dear DREAM Community, 

We are solvers. What draws us to DREAM Challenges is our collective mission to solve complex biomedical questions – and to do so together. Our resolve remains strong even as some Challenges have had to pause. For those who can shift their efforts, we are pleased to announce the launch of the COVID-19 DREAM  Challenge, a collaboration with the University of Washington and the Center for Data to Health (CD2H) to use electronic healthcare data to advance important COVID-related questions.

If you have suggestions for other Challenges related to COVID-19, or you have questions about any ongoing Challenge, please contact us.

- Justin Guinney, DREAM Chair

Upcoming Events

Mark Your Calendars: Nov. 16-18, 2020

What: Join DREAM for the 13th Annual RECOMB/ISCB Regulatory and Systems Genomics Conference, with a special session on Regulatory and Systems Genetics in Immunology
When: Nov. 16-18, 2020
Where: Carnegie Mellon University, Pittsburgh, PA
Details: Visit the event site here.

Truth Challenge V2:

Calling Variants from Short and Long Reads in Difficult-to-Map Regions

Launching May 1

Overview: In the context of whole human genome sequencing, software pipelines typically rely on (1) mapping sequencing reads or assemblies to a reference genome, and (2) the subsequent identification of variants. One way of assessing the performance of such pipelines is by using well-characterized reference datasets such as Genome in a Bottle’s 7 human genome benchmarks. Two of these benchmarks were used in the first precisionFDA Truth Challenge, which assessed variant calling accuracy in “easier-to-map” regions of the genome. The Genome in a Bottle Consortium led by the National Institute of Standards and Technology (NIST) has developed expanded benchmarks for HG003 and HG004, the parents of an Ashkenazi trio. Before their release, precisionFDA and NIST are running a new truth challenge focused on variant calling in more challenging genomic regions.

Join this challenge to assess variant calling pipeline performance on a common frame of reference consisting of difficult-to-map regions, segmental duplications, and the Major Histocompatibility Complex (MHC). Ilumina, PacBio HiFi, and Oxford Nanopore sequencing datasets will be made available for this challenge. 

The challenge submission period runs from May 1 to June 1. For more information and to pre-register, visit the challenge site.

New COVID-19 Dream Challenge

REGISTRATION IS NOW OPEN: The rapid rise of COVID-19 has challenged healthcare globally. The underlying risks and outcomes of infection are still incompletely characterized even as the world surpasses 1 million infections. Due to the importance and emergent need for better understanding of the condition and the development of patient-specific clinical risk scores and early warning tools, we have developed a platform to support testing analytic and machine learning hypotheses on clinical data without data sharing as a platform to rapidly discover and implement approaches for care. We have previously applied this approach in the successful EHR DREAM Challenge focusing on Patient Mortality Prediction with UW Medicine.

Initially, we are asking the following challenge question: Of patients who have at least one clinical encounter/visit at UW Medicine and who were tested for Covid-19, can we predict who is positive? In addition to the initial challenge question, we have identified nine total questions of interest, four of which we hope to adapt if the first Challenge is successful.

The EHR COVID-19 DREAM challenge is made possible by funding from the National Center for Advancing Translational Sciences (NCATS) and partnerships with the University of Washington School of Medicine Departments (Anesthesiology and Pain Medicine, Radiology and Biomedical Informatics and Medical Education), UW Medicine Information Technology Services, the Institute of Translational Health Sciences, the Center for Data To Health, and the CLEAR Center.

Register Now
Challenge Updates

The Biomarker and Endpoint Assessment to Track Parkinson's Disease (BEAT-PD) Challenge is a first-of-its-kind challenge, designed to benchmark methods for the processing of unstructured (free-living) sensor data, in order to be predictive of Parkinson's Disease severity. Participants will be provided with raw sensor (accelerometer and gyroscope) time series data recorded during the course of daily living, and will be asked to predict individuals' medication state and symptom severity.

Final Submissions Due: May 13, 2020

Learn More

We aim to significantly lower the burden of adding coherent metadata annotations across the data ecosystem to streamline and enable both retrospective harmonization as well as data query, discovery and interpretation. This challenge addresses this time-consuming task with automated metadata annotation of structured data.

Final Submissions Due: May 22, 2020, at 5 p.m. PST

Winners Announced: Early June 2020

Learn More

The goal of the Beat AML DREAM Challenge is to define patient subpopulations tailored to individual treatments by discovering (genomic and transcriptomic) biomarkers of drug sensitivity, as evaluated on an unpublished cohort of patients from the Beat AML project.

Validation Phase: 3/2/2020 - 4/28/2020

Winners Announced: May 2020

Learn More

Over the last two years, the Columbia CTD2 Center developed PANACEA (Pancancer Analysis of Chemical Entity Activity), a comprehensive repertoire of dose-response curves and molecular profiles representative of cellular responses to drug perturbations. PANACEA covers a broad spectrum of cellular contexts representative of poor outcome malignancies, including rare ones such as GIST sarcoma and gastroenteropancreatic neuroendocrine tumors (GEP-NETs). PANACEA is uniquely suited to support DREAM Challenges related to the elucidation of drug mechanism of action (MOA), drug sensitivity, and drug synergy.

The goal of this Challenge is to foster development and benchmarking of algorithms to predict the sensitivity, as measured by the area under the dose-response curve, of the sensitivity of a cell line to a compound based on the baseline transcriptional profiles of the cell line.

Registration: OPEN

Closes: July 2020

Register

The extent of stromal and immune cell infiltration within solid tumors has prognostic and predictive significance. Unfortunately, expression profiling of tumors has, until very recently, largely been undertaken using bulk techniques (e.g., microarray and RNA-seq). The goal of this Challenge is to evaluate the ability of computational methods to deconvolve bulk expression data, reflecting a mixture of cell types, into individual immune components. Methods will be assessed based on in vitro and in silico admixtures specifically generated for this Challenge.

Validation Phase: April 1-30, 2020

Learn More

Rheumatoid Arthritis (RA) is a debilitating disease that causes joint damage in the hands and feet due to inflammation. Accurate measuring of joint damage and progression of disease is essential in assessing the severity of disease, along with being able to monitor patient response to treatment. Scoring of X-ray images is tedious and there can be a great deal of variability between rheumatologists when applying scoring methods. We will leverage nearly 1000 images across a range of disease severities to challenge participants to develop an automated scoring algorithm with the goal of making clinical scoring fast and consistent; this will aid rheumatologists in making the best decisions for patients.

Leaderboard Closes, Final Scoring Round Opens: May 14, 2020

Final Scoring Round Closes: June 11, 2020

Winners Announced: July 31, 2020

Learn more

Upcoming Challenges

Natural Language Processing

A critical bottleneck in translational research is access to large volumes of high-quality clinical data. A large portion of patient information including patient status, treatments, and outcomes is contained in unstructured text fields. Research in Natural Language Processing (NLP) aims to unlock this often inaccessible information. However, numerous challenges exist in developing and evaluating NLP methods, much of it centered on having “gold-standard” metrics for evaluation, and access to data that may contain personal health information (PHI).  This DREAM challenge will be focused on the development and evaluation of NLP algorithms that can improve clinical trial matching and recruitment.

Anticipated Launch: Summer 2020

Immuno-oncology

Immuno-oncology (I-O) therapy targeting the PD-1 pathway has transformed the treatment landscape in advanced non-small cell lung cancer (NSCLC), with the combination of I-O with or without chemotherapy being the current standard of care in the first-line setting for those patients who are ineligible for targeted therapy. While durable responses and prolonged survival have been demonstrated in patients treated with I-O, there remains a high disease burden and a need to improve the ability to predict which patients are more likely to receive benefit from treatment with I-O.

DREAM will soon launch an exciting new collaboration to identify predictive biomarkers for I-O therapy in lung cancer to advance our ability to appropriately select patients most likely to benefit from I-O treatment and to gain insights that may facilitate potential novel therapies or combinations with I-O.

Anticipated Launch: Summer 2020

Recently Closed Challenges

Eleven international teams competed in this open science competition to reconstruct cell lineages from datasets of different sizes and types. The best performers included three teams that tied for Subchallenge 1, which asked teams to reconstruct a small cell lineage tree of less than 100 cells based in part on video microscopy data.
  • Jingyuan Hu and Zhandong Liu, Ph.D., both of Baylor College of Medicine. 

  • Hanrui Zhang and Yuanfang Guan, Ph.D., both of the University of Michigan. 

  • Matthew G. Jones of the University of California, Berkeley, and UC San Francisco and Alex Khodaverdian, Richard Zhang, Suhas Rao, Robert Wang and Nir Yosef, Ph.D., of the University of California, Berkeley.

One team won both Subchallenges 2 and 3, which comprised computer-generated mutations for a thousand-cell lineage tree of the microscopic worm, C. elegans, and a computer-generated tree of 10,000 cells, respectively:

Wuming Gong, Ph.D., of Lillehei Heart Institute, University of Minnesota, and Il-Youp Kwak, Ph.D., of Chung-Ang University. 

To learn more about this challenge challenge, see this Q&A with Shendure, Elowitz and Meyer

The final results of the Patient Mortality Prediction Challenge are now available. The goal of this challenge was to predict patients who have at least one hospital visit who will pass away within 180 days of their last visit. The top performing teams in this first EHR DREAM Challenge are UW-biostat, Ivan Brugere and ProActa. The top performing teams will be invited to collaborate on analyzing the results of the Challenge and preparing the Challenge manuscript. We are extremely grateful to all the teams who have participated in this Challenge, and look forward to working with you in future DREAM Challenges.

Publications

Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms
Schaffter, T., et al., JAMA Netw Open. 2020;3(3):e200265. doi:10.1001/jamanetworkopen.2020.0265

Crowdsourced mapping of unexplored target space of kinase inhibitors
Cichonska, A., et al., Biorxiv; 10.1101/2019.12.31.891812

A community effort to create standards for evaluating tumor subclonal reconstructions
Salcedo, A. et al, Nature Biotechnology, 38, 27-107. DOI: 10.1038/s41587-019-0364-z

Crowdsourcing digital health measures to predict Parkinson’s disease severity: the Parkinson’s Disease Digital Biomarker DREAM Challenge
Sieberts, S. K., et al., Biorxiv; 10.1101/2020.01.13.904722

Multiple Myeloma DREAM Challenge reveals epigenetic regulator PHF19 as marker of aggressive disease
Mason MJ, et al. Leukemia. 2020;10.1038/s41375-020-0742-z. doi:10.1038/s41375-020-0742-z


DREAM Channel on bioRxiv
 






This email was sent to *|EMAIL|*
why did I get this?    unsubscribe from this list    update subscription preferences
*|LIST:ADDRESSLINE|*

*|MC:SUBJECT|*
View this email in your browser
Tweet Tweet
Forward Forward
Share Share
January 14, 2020

Registration Now Open

The Cancer Research Data Commons (CRDC) aims to collate data across diverse groups of cancer researchers, each collecting biomedical data in different formats. This means the data must be retrospectively harmonized and transformed to enable this data to be submitted. In addition, to be findable by the broader scientific community, coherent information (metadata) is necessary about the data fields and values.

Coherent metadata annotation of the data fields and their values can enable computational data transformation, query, and analysis. Creation of this type of descriptive metadata can require biomedical expertise to determine the best annotations and thus is a time-consuming and manual task which is both an obstacle and a bottleneck in data sharing and submissions.

Timeline

Challenge Launch: Jan. 14, 2020
Webinar: Jan. 30, 2020, at 9 am PST
Challenge Close: April 24, 2020
Winners Announced: Early May, 2020

Goal
Using structured biomedical data files, challenge participants will develop tools to automate annotation of metadata fields and values, using available research data annotations (e.g., caDSR Common Data Elements (CDEs)) as well as established terminologies and ontologies (e.g., NCI Thesaurus (NCIt)Logical Observation Identifiers Names and Codes (LOINC)Mondo Disease Ontology (Mondo)International Classification of Diseases (ICD)).
 

Motivation
We aim to significantly lower the burden of adding these annotations across the data ecosystem to streamline and enable both retrospective harmonization as well as data query, discovery and interpretation. This challenge addresses this time-consuming task with automated metadata annotation of structured data.

Register Now
Twitter
Website
Copyright © *|CURRENT_YEAR|* *|LIST:COMPANY|*, All rights reserved.
*|IFNOT:ARCHIVE_PAGE|* *|LIST:DESCRIPTION|*

Our mailing address is:
*|HTML:LIST_ADDRESS_HTML|* *|END:IF|*

Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

*|IF:REWARDS|* *|HTML:REWARDS|* *|END:IF|*

Subscribe

* indicates required