{
  "id": 347897,
  "title": "Any plan to release the raw counts?",
  "url": "/competitions/open-problems-multimodal/discussion/347897",
  "author_name": "",
  "post_date": "2022-08-25T21:17:13.598564Z",
  "votes": 10,
  "comment_count": 8,
  "views": 0,
  "content": "<p>Hi there,</p>\n<p>I remember in one discussion the host mentioned that raw counts will probably be released?<br>\nGuess it will be really useful for QC and preprocessing it as one wants to.<br>\nThanks in advance!</p>",
  "messages": [
    {
      "id": "1914229",
      "postDate": "08/25/2022 21:17:13",
      "content": "<p>Hi there,</p>\n<p>I remember in one discussion the host mentioned that raw counts will probably be released?<br>\nGuess it will be really useful for QC and preprocessing it as one wants to.<br>\nThanks in advance!</p>",
      "rawMarkdown": "Hi there,\n\nI remember in one discussion the host mentioned that raw counts will probably be released?\nGuess it will be really useful for QC and preprocessing it as one wants to.\nThanks in advance!",
      "votes": null
    },
    {
      "id": "1914910",
      "postDate": "08/26/2022 14:26:06",
      "content": "<p>What do you mean by raw counts?</p>",
      "rawMarkdown": "What do you mean by raw counts?",
      "votes": null
    },
    {
      "id": "1914919",
      "postDate": "08/26/2022 14:33:59",
      "content": "<p>The matrix we have now are all under some normalization and transformation (You can check the detail in the Data section).<br>\nThese matrix are derived from raw (unprocessed) counts, which is usually the start point for quality control. Besides, researchers can do their own preprocessing with the raw counts matrix. Does this answer your question? xD</p>",
      "rawMarkdown": "The matrix we have now are all under some normalization and transformation (You can check the detail in the Data section).\nThese matrix are derived from raw (unprocessed) counts, which is usually the start point for quality control. Besides, researchers can do their own preprocessing with the raw counts matrix. Does this answer your question? xD",
      "votes": null
    },
    {
      "id": "1914920",
      "postDate": "08/26/2022 14:35:01",
      "content": "<p>Thx.<br>\nI didn't realize that the data is transformed/normalized.</p>",
      "rawMarkdown": "Thx.\nI didn't realize that the data is transformed/normalized.",
      "votes": null
    },
    {
      "id": "1914962",
      "postDate": "08/26/2022 15:06:27",
      "content": "<p>Yes, we will release the counts soon. We were actually hoping to release them today, but as noted in another thread, there's an issue with one of the samples being duplicated that we want to resolve before we release the raw counts.</p>",
      "rawMarkdown": "Yes, we will release the counts soon. We were actually hoping to release them today, but as noted in another thread, there's an issue with one of the samples being duplicated that we want to resolve before we release the raw counts.",
      "votes": null
    },
    {
      "id": "1914967",
      "postDate": "08/26/2022 15:10:59",
      "content": "<p>Thanks a lot! I know there must be a lot of stuffs on the to-do list, take your time! xD<br>\nBTW, can I know which reference genome was used in the analysis?</p>",
      "rawMarkdown": "Thanks a lot! I know there must be a lot of stuffs on the to-do list, take your time! xD\nBTW, can I know which reference genome was used in the analysis?",
      "votes": null
    },
    {
      "id": "1915993",
      "postDate": "08/27/2022 14:55:20",
      "content": "<p>Thanks a lot ! </p>\n<p><a href=\"https://www.kaggle.com/danielburkhardt\" target=\"_blank\">@danielburkhardt</a> Аny chance to release spliced/unspliced counts - to use RNA velocity ? </p>",
      "rawMarkdown": "Thanks a lot ! \n\n@danielburkhardt Аny chance to release spliced/unspliced counts - to use RNA velocity ?",
      "votes": null
    },
    {
      "id": "1931602",
      "postDate": "09/08/2022 20:54:12",
      "content": "<p>so it's been about 2 weeks now - what's the word on raw counts? <br>\nAre we definitely doing that or not? ETA?</p>\n<p>I don't really want to invest a bunch of time in the working with the normalized data if i'm just going to end up throwing it out later.</p>",
      "rawMarkdown": "so it's been about 2 weeks now - what's the word on raw counts? \nAre we definitely doing that or not? ETA?\n\nI don't really want to invest a bunch of time in the working with the normalized data if i'm just going to end up throwing it out later.",
      "votes": null
    },
    {
      "id": "1944493",
      "postDate": "09/18/2022 10:36:42",
      "content": "<p><a href=\"https://www.kaggle.com/danielburkhardt\" target=\"_blank\">@danielburkhardt</a> , any news on this?</p>",
      "rawMarkdown": "danielburkhardt , any news on this?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1914910,
      "author_name": "nandodmelo",
      "author_url": "",
      "post_date": "08/26/2022 14:26:06",
      "content": "<p>What do you mean by raw counts?</p>",
      "votes": null,
      "replies": [
        {
          "id": 1914919,
          "author_name": "comp540cl123",
          "author_url": "",
          "post_date": "08/26/2022 14:33:59",
          "content": "<p>The matrix we have now are all under some normalization and transformation (You can check the detail in the Data section).<br>\nThese matrix are derived from raw (unprocessed) counts, which is usually the start point for quality control. Besides, researchers can do their own preprocessing with the raw counts matrix. Does this answer your question? xD</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1914920,
          "author_name": "nandodmelo",
          "author_url": "",
          "post_date": "08/26/2022 14:35:01",
          "content": "<p>Thx.<br>\nI didn't realize that the data is transformed/normalized.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1914962,
      "author_name": "danielburkhardt",
      "author_url": "",
      "post_date": "08/26/2022 15:06:27",
      "content": "<p>Yes, we will release the counts soon. We were actually hoping to release them today, but as noted in another thread, there's an issue with one of the samples being duplicated that we want to resolve before we release the raw counts.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1914967,
          "author_name": "comp540cl123",
          "author_url": "",
          "post_date": "08/26/2022 15:10:59",
          "content": "<p>Thanks a lot! I know there must be a lot of stuffs on the to-do list, take your time! xD<br>\nBTW, can I know which reference genome was used in the analysis?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1915993,
          "author_name": "alexandervc",
          "author_url": "",
          "post_date": "08/27/2022 14:55:20",
          "content": "<p>Thanks a lot ! </p>\n<p><a href=\"https://www.kaggle.com/danielburkhardt\" target=\"_blank\">@danielburkhardt</a> Аny chance to release spliced/unspliced counts - to use RNA velocity ? </p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1931602,
      "author_name": "splatai",
      "author_url": "",
      "post_date": "09/08/2022 20:54:12",
      "content": "<p>so it's been about 2 weeks now - what's the word on raw counts? <br>\nAre we definitely doing that or not? ETA?</p>\n<p>I don't really want to invest a bunch of time in the working with the normalized data if i'm just going to end up throwing it out later.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1944493,
      "author_name": "agenlu",
      "author_url": "",
      "post_date": "09/18/2022 10:36:42",
      "content": "<p><a href=\"https://www.kaggle.com/danielburkhardt\" target=\"_blank\">@danielburkhardt</a> , any news on this?</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1914229": "Hi there,\n\nI remember in one discussion the host mentioned that raw counts will probably be released?\nGuess it will be really useful for QC and preprocessing it as one wants to.\nThanks in advance!",
    "1914910": "What do you mean by raw counts?",
    "1914919": "The matrix we have now are all under some normalization and transformation (You can check the detail in the Data section).\nThese matrix are derived from raw (unprocessed) counts, which is usually the start point for quality control. Besides, researchers can do their own preprocessing with the raw counts matrix. Does this answer your question? xD",
    "1914920": "Thx.\nI didn't realize that the data is transformed/normalized.",
    "1914962": "Yes, we will release the counts soon. We were actually hoping to release them today, but as noted in another thread, there's an issue with one of the samples being duplicated that we want to resolve before we release the raw counts.",
    "1914967": "Thanks a lot! I know there must be a lot of stuffs on the to-do list, take your time! xD\nBTW, can I know which reference genome was used in the analysis?",
    "1915993": "Thanks a lot ! \n\n@danielburkhardt Аny chance to release spliced/unspliced counts - to use RNA velocity ?",
    "1931602": "so it's been about 2 weeks now - what's the word on raw counts? \nAre we definitely doing that or not? ETA?\n\nI don't really want to invest a bunch of time in the working with the normalized data if i'm just going to end up throwing it out later.",
    "1944493": "danielburkhardt , any news on this?"
  },
  "source": "meta"
}