Dear ENCODE-DREAM Challenge Participants,   The queues for the second phase of the Challenge are now open. Listed below are a few important points for the second phase of the Challenge:   * Each team will be given 10 submission per TF/Cell type combination for the leaderboard. For the final round submission, there is no limit, but we will only score your final submission when the final round closes on January 11, 2017. Both submission queues will be open until January 11, 2017. * During the first phase of the challenge, a few datasets were flagged as potentially problematic. Specifically, the SK-N-SH DNase dataset was found to be from a stimulated condition whereas theChIP-seq datasets were in unstimulated conditions. Hence, we have removed all SK-N-SH datasets. These were all restricted to training datasets. Second, some of the newer, unreleased ATF2 ChIP-seq datasets showed irregular overlap fractions with DNase peaks in the matched cell type. To be on the safe side, we have eliminated this TF from the competition. ATF2 was also not used in the final round 1 evaluation and ranking. We have eliminated these datasets in Phase 2 of the challenge. * All teams will that make submissions, provide their code and method write-up, along with participating in some post challenge benchmarking will be part of the "ENCODE-DREAM Community" which will be listed as a coauthor on the overview paper. Community members will be indexed as "Collaborators" in Pubmed. If your team participated in the Conference round and supplied your code and write-ups, you are already in the Community author list; the organizers will contact you at the end of the challenge with more details. * The Conference Round resulted in two teams, autosome.ru and J-TEAM, that performed robustly better than all other teams, thus they will be included as byline authors on the overivew paper with their methods highlighted in the manuscript. For the Final Submission Round, the top two teams that robustly outperform autosome.ru or J-TEAM will be invited to be authors on the overview paper as well. * The RSG with DREAM Challenge Conference will be Nov. 6-9, with DREAM Challenges being presented on Nov. 9. Stay tuned for more details on the presentations from the top 2 teams for the Conference Round. https://www.iscb.org/recomb-regsysgen2016   ** Please provide your feedback on the Challenge forum below ** The organizers are thinking of running a webinar after the DREAM Conference to invite the top two teams to provide a short summary of their methods, review the Challenge details, and to provide a forum for teams to ask questions. Please indicate if you feel this would be helpful and if you have any other suggestions for topics that you would like to discuss.   We wish you the best of luck for the remainder of the Challenge and please post questions/concerns to the forum.   Kind Regards, -ENCODE-DREAM Organizers

Created by James Costello james.costello
Sorry. I'm going to revert what James initially replied and disallow the use of the SKNSH data. We know the Chip samples are mismatched with the DNase. We don't want all kinds of non uniformity in the training set ups between methods. Please don't use those samples in training.
If we are allowed to use the SK-N-SH DNase data at our own risk, then why can't we download them anymore? Can you please put the data back?
Dear Maximus/Yichao, Please check now. You should be able to see the dates in the leaderboards now. Best, Thomas
Hi, Thomas. There is a date column, but no date inside the cells.
Dear Yichao, Please kindly post a link to what you are talking about. From what I see here: https://www.synapse.org/#!Synapse:syn6131484/wiki/402488 I do in fact see a Date column. Best, Thomas
Hi David, yes you can use them at your own risk.
I'm talking about the leaderboard. Thank you, Yichao
Dear Yichao, Thank you for your patience. Are you talking about the Final Round pages like this page? https://www.synapse.org/#!Synapse:syn6131484/wiki/405278 Best, Thomas
Can you show us the date of our submission in the scoring table? For example, add one more column for date. Thank you!
Quick question: are we still allowed to use the SK-N-SH DNase data if we choose to do so at our own risk?
For me it would be very helpful to have a webinar on the winning methods since I'm still lagging way behind the state-of-the-art methods.

Phase 2 Live!! page is loading…