## Can I use external datasets? 
Yes, without limits. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.

## What about private datasets? 
Private datasets are allowed. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.

## Do I need to submit/licence/publish my code/model/data ? 
No. You only grant us the permission to use the predicted values you submit. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.

## Even if I'm eligible for a prize? 
Still no. Winners are only asked to submit a high-level description of the methods and data used. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.

## How does the public/private leaderboard work? 
The public leaderboard is based on predictions of 60 perturbations. The private leaderboard (final evaluation) will be based on 60 different perturbations, whose gene symbols will be released one week before the end of the challenge. See the [data](https://www.kaggle.com/competitions/echoes-of-silenced-genes/data) section for details.

## What type of values should I submit?
Delta expression on log2 scale. See the [data](https://www.kaggle.com/competitions/echoes-of-silenced-genes/data) section for details.

## How are the training and ground-truth datasets normalized?
Log1p-normalization, followed by simple arithmetic mean per perturbation. See the [data](https://www.kaggle.com/competitions/echoes-of-silenced-genes/data) section for details.

## Will you release the ground-truth data after the end of the contest? 
Yes, we will release the test dataset ground-truth, as well as the winning predictions. 

## Will you publish the high-level methods descriptions submitted by the winners? 
Yes.