General rules

The participants submit predicted transcription initiation efficiency at particular genomic positions, that is, the absolute or relative counts of 5' ends of the csRNA-Seq reads. The participants must rely on the training data provided by the challenge organizers (the genome sequences and the preprocessed csRNA-Seq and sRNA-Seq tracks). The usage of external data is not allowed, except for the pre-trained genomic models such as AlphaGenome or Evo2. The test data will not be published until the announcement of the winners. The organizers reserve the right to assess their own solutions at the post-challenge stage, but these solutions will not be included in the model ranking nor affect the selection of the winners of the challenge. All teams must provide a method write-up accompanying the Final submission. The winning and runner-up teams must provide a reproducible pipeline/code to derive the submitted solutions from the training data and to score the test data. The winners will be invited to co-author the post-challenge manuscript aiming at a high-impact journal. All participants of the challenge will be included in the EPIC consortium as a joint author of the post-challenge paper.

Each participating team should register online with a single spokesperson submitting solutions on behalf of the team, which can include from 1 to 10 members. Registration is possible only by authorizing with an active GitHub account. We kindly ask you to avoid using multiple accounts for a single team and registering with provocative, impolite, or offensive team names.