{
  "id": 439155,
  "title": "Confused about variables used to predict reactivity",
  "url": "/competitions/stanford-ribonanza-rna-folding/discussion/439155",
  "author_name": "",
  "post_date": "2023-09-13T21:17:20.507056400Z",
  "votes": null,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Hi! I'm really interested to work on this Kaggle project, but I'm a bit confused: do we use the actual RNA \"Sequence\" string variable to predict the reactivity numbers, or the \"reads<br>\n and \"signal-to-noise\" variables? </p>\n<p>Thanks!</p>",
  "messages": [
    {
      "id": "2436922",
      "postDate": "09/13/2023 21:17:20",
      "content": "<p>Hi! I'm really interested to work on this Kaggle project, but I'm a bit confused: do we use the actual RNA \"Sequence\" string variable to predict the reactivity numbers, or the \"reads<br>\n and \"signal-to-noise\" variables? </p>\n<p>Thanks!</p>",
      "rawMarkdown": "Hi! I'm really interested to work on this Kaggle project, but I'm a bit confused: do we use the actual RNA \"Sequence\" string variable to predict the reactivity numbers, or the \"reads\n and \"signal-to-noise\" variables? \n\nThanks!",
      "votes": null
    },
    {
      "id": "2436935",
      "postDate": "09/13/2023 21:44:47",
      "content": "<p>Reads and signal-to-noise variables are not in the test data, so I think we only use the sequence string.</p>",
      "rawMarkdown": "Reads and signal-to-noise variables are not in the test data, so I think we only use the sequence string.",
      "votes": null
    },
    {
      "id": "2436961",
      "postDate": "09/13/2023 23:19:36",
      "content": "<p>The reads and signal-to-noise variables speak to the quality of the reactivity data. The quality of the experimental result for some sequences is high while the quality for other sequences is medium or low.</p>",
      "rawMarkdown": "The reads and signal-to-noise variables speak to the quality of the reactivity data. The quality of the experimental result for some sequences is high while the quality for other sequences is medium or low.",
      "votes": null
    },
    {
      "id": "2438056",
      "postDate": "09/14/2023 02:52:39",
      "content": "<p>How do the number of reads relate?  Is it that there were low-quality results so more reads needed to be accomplished, or that typically more reads yield smoother results? </p>",
      "rawMarkdown": "How do the number of reads relate?  Is it that there were low-quality results so more reads needed to be accomplished, or that typically more reads yield smoother results?",
      "votes": null
    },
    {
      "id": "2439391",
      "postDate": "09/14/2023 19:53:48",
      "content": "<blockquote>\n  <p>Is it that there were low-quality results so more reads needed to be accomplished</p>\n</blockquote>\n<p>No, the experiment is only performed once for each group. The data are single run.</p>",
      "rawMarkdown": "> Is it that there were low-quality results so more reads needed to be accomplished\n\nNo, the experiment is only performed once for each group. The data are single run.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2436935,
      "author_name": "markyoukey",
      "author_url": "",
      "post_date": "09/13/2023 21:44:47",
      "content": "<p>Reads and signal-to-noise variables are not in the test data, so I think we only use the sequence string.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2436961,
      "author_name": "digitalembrace",
      "author_url": "",
      "post_date": "09/13/2023 23:19:36",
      "content": "<p>The reads and signal-to-noise variables speak to the quality of the reactivity data. The quality of the experimental result for some sequences is high while the quality for other sequences is medium or low.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2438056,
          "author_name": "markyoukey",
          "author_url": "",
          "post_date": "09/14/2023 02:52:39",
          "content": "<p>How do the number of reads relate?  Is it that there were low-quality results so more reads needed to be accomplished, or that typically more reads yield smoother results? </p>",
          "votes": null,
          "replies": [
            {
              "id": 2439391,
              "author_name": "digitalembrace",
              "author_url": "",
              "post_date": "09/14/2023 19:53:48",
              "content": "<blockquote>\n  <p>Is it that there were low-quality results so more reads needed to be accomplished</p>\n</blockquote>\n<p>No, the experiment is only performed once for each group. The data are single run.</p>",
              "votes": null,
              "replies": []
            }
          ]
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2436922": "Hi! I'm really interested to work on this Kaggle project, but I'm a bit confused: do we use the actual RNA \"Sequence\" string variable to predict the reactivity numbers, or the \"reads\n and \"signal-to-noise\" variables? \n\nThanks!",
    "2436935": "Reads and signal-to-noise variables are not in the test data, so I think we only use the sequence string.",
    "2436961": "The reads and signal-to-noise variables speak to the quality of the reactivity data. The quality of the experimental result for some sequences is high while the quality for other sequences is medium or low.",
    "2438056": "How do the number of reads relate?  Is it that there were low-quality results so more reads needed to be accomplished, or that typically more reads yield smoother results?",
    "2439391": "> Is it that there were low-quality results so more reads needed to be accomplished\n\nNo, the experiment is only performed once for each group. The data are single run."
  },
  "source": "meta"
}