{
  "fetched_at": "2026-10-19T22:26:33Z",
  "source_url": "https://www.kaggle.com/competitions/compomics2018/data",
  "pages": [
    {
      "name": "rules",
      "content": "    <h3>One account per participant</h3>\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n    <h3>Submission Limits</h3>\n    <p>You may submit a maximum of 10 entries per day.</p>\n    <p>You may select up to 4 final submissions for judging.</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>data_train.csv</strong> - the train set</li>\n<li><strong>data_test.csv</strong> - the test set</li>\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Histone modifications play an important role in affecting gene regulation. Specific histone modifications at specific locations in or near the gene can alter the expression of genes. Predicting gene expression from histone modification signals is a widely studied research topic.\n\nIn this competition you will predict gene expression levels (low=0, high=1) based on the presence of histone modifications at specific locations in the gene. You will try to find the model that learns the true underlying model best.  \n\nFor each gene a region of 10.000bp around the transcription start site of the gene is extracted (5000bp upstream and 5000bp downstream).  This region is binned in 100 bins of 100bp. For each bin  five core histone modification marks are counted [1].\n\nThe dataset is compiled from the \"E047\" (Primary T CD8+ naive cells from peripheral blood) celltype from Roadmap Epigenomics Mapping Consortium (REMC) database. \n\n[1] Kundaje, A. et al. Integrative analysis of 111 reference human epige-\nnomes. Nature, 518, 317–330, 2015.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"http://scikit-learn.org/stable/modules/generated/sklearn.metrics.log_loss.html\"> log-loss</a>. \n\n<h2>Submission Format</h2>\n<p><strong>For every gene in the test set</strong>, submission files should contain two columns: GeneId and Label. GeneId should match the GeneId in the test set and Label is the corresponding predicted probability for class 1 (high).</p>\n\n<p>You can download the sample_submission.csv for an example.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}