Data are now live. Good luck!
- Each team must have a github handle associated with it in order to participate. Make sure you edit your registration or email the organizers to provide this, if you haven't yet.
- You may add team members up to noon EDT on 8/19 by editing your response to the google form or emailing the organizers.
- Teams of entirely undergraduates will be in the undergraduate division, else they will be in the open division.
- Predictions on test data set are submitted by pushing to
github. A repository with the name
Hackathon-Summer-2021, owned by the team captain, will be queried for a file named prediction/prediction.csv. If the team captain forks this repository and writes predictions there everything should work (as long as the predictions are formatted correctly). - Predictions will be scored at least once daily, starting 8/18, with scores posted by noon. At the organizers' option, predictions may be scored more frequently than this.
- General questions/problems can be directed to issues page. We encourage other hackathon participants to respond to issues.
- The scoreboard will be located here, and will be updated starting noon on 8/18. We cannot provide support beyond the diagnostic output included on the scoreboard if an error is encountered in scoring your predictions.
- Interim scoring may employ forms of randomization (e.g. bootstrapping) from the test data set. The final scores will use all the data and not be randomized.
- Competition runs through 11:59 PM EDT 22-August-2021. The predictions each team has committed to their repository at that time will be used to determine their final score.
- Training data are here. The label you are to predict is
ageand is available in train_data/train_labels.csv. Thegroupcovariate indicates what cohort (study) thesample_idwas from. The features available for prediction are in train_data/train_expression.csv.gz--rows are samples and are in the same order as train_labels.csv. Columns are features. train_data/train_features_names.csv contain gene symbol names for all the features. The data are also available as an R SummarizedExperiment, train_data/train_summarized_experiment.rds. - Test data are here, and are the same format as train data.
- Your predictions should be in the order of the
sample_ids listed here. The first column will be examined, regardless of column name. No join is performed on thesample_idcolumn.
The data are unnormalized counts of various genes from RNASeq performed on various patients. The goal is to predict the patient's age at sampling from their RNAseq profile.
- First place in each division: $300 + $75*(team size)
- Second place in each division: 0 + $50*(team size)
- Predictions will be scored based on mean square error, lower values are better.
- In order to claim your prize, you will need to fill out a post-competition survey.
In addition, winning teams will have the opportunity to present their solutions at a meeting of participants and faculty this fall.