{
  "id": 440677,
  "title": "Kaggle datasets - single cell data under similar compounds, but different cell types",
  "url": "/competitions/open-problems-single-cell-perturbations/discussion/440677",
  "author_name": "",
  "post_date": "2023-09-15T19:21:28.615373900Z",
  "votes": 13,
  "comment_count": 1,
  "views": 0,
  "content": "<p><a href=\"https://www.kaggle.com/datasets/alexandervc/scrnaseq-exposed-to-multiple-compounds\" target=\"_blank\">https://www.kaggle.com/datasets/alexandervc/scrnaseq-exposed-to-multiple-compounds</a><br>\n<a href=\"https://www.kaggle.com/datasets/alexandervc/singlecell-rnaseq-exposed-to-multiple-compounds\" target=\"_blank\">https://www.kaggle.com/datasets/alexandervc/singlecell-rnaseq-exposed-to-multiple-compounds</a><br>\nBoth datasets with same data in slightly different format. <br>\nMore that 700K cells.  <br>\nOriginal source: <a href=\"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139944\" target=\"_blank\">https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139944</a></p>\n<p>The compounds somewhat similar to the present challenge, but cell types are quite different.<br>\nAlso the processing provided in the present challenge is not done for the data above. </p>\n<p>Theoretically one may try to use these and several similar datasets for data augmentation, practically due to different processing it might be quite complicated if possible. </p>",
  "messages": [
    {
      "id": "2440858",
      "postDate": "09/15/2023 19:21:28",
      "content": "<p><a href=\"https://www.kaggle.com/datasets/alexandervc/scrnaseq-exposed-to-multiple-compounds\" target=\"_blank\">https://www.kaggle.com/datasets/alexandervc/scrnaseq-exposed-to-multiple-compounds</a><br>\n<a href=\"https://www.kaggle.com/datasets/alexandervc/singlecell-rnaseq-exposed-to-multiple-compounds\" target=\"_blank\">https://www.kaggle.com/datasets/alexandervc/singlecell-rnaseq-exposed-to-multiple-compounds</a><br>\nBoth datasets with same data in slightly different format. <br>\nMore that 700K cells.  <br>\nOriginal source: <a href=\"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139944\" target=\"_blank\">https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139944</a></p>\n<p>The compounds somewhat similar to the present challenge, but cell types are quite different.<br>\nAlso the processing provided in the present challenge is not done for the data above. </p>\n<p>Theoretically one may try to use these and several similar datasets for data augmentation, practically due to different processing it might be quite complicated if possible. </p>",
      "rawMarkdown": "https://www.kaggle.com/datasets/alexandervc/scrnaseq-exposed-to-multiple-compounds\nhttps://www.kaggle.com/datasets/alexandervc/singlecell-rnaseq-exposed-to-multiple-compounds\nBoth datasets with same data in slightly different format. \nMore that 700K cells.  \nOriginal source: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139944\n\nThe compounds somewhat similar to the present challenge, but cell types are quite different.\nAlso the processing provided in the present challenge is not done for the data above. \n\nTheoretically one may try to use these and several similar datasets for data augmentation, practically due to different processing it might be quite complicated if possible.",
      "votes": null
    },
    {
      "id": "2441012",
      "postDate": "09/16/2023 00:01:50",
      "content": "<p>Thanks for sharing!</p>",
      "rawMarkdown": "Thanks for sharing!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2441012,
      "author_name": "yupenghe",
      "author_url": "",
      "post_date": "09/16/2023 00:01:50",
      "content": "<p>Thanks for sharing!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2440858": "https://www.kaggle.com/datasets/alexandervc/scrnaseq-exposed-to-multiple-compounds\nhttps://www.kaggle.com/datasets/alexandervc/singlecell-rnaseq-exposed-to-multiple-compounds\nBoth datasets with same data in slightly different format. \nMore that 700K cells.  \nOriginal source: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139944\n\nThe compounds somewhat similar to the present challenge, but cell types are quite different.\nAlso the processing provided in the present challenge is not done for the data above. \n\nTheoretically one may try to use these and several similar datasets for data augmentation, practically due to different processing it might be quite complicated if possible.",
    "2441012": "Thanks for sharing!"
  },
  "source": "meta"
}