{
  "id": 567825,
  "title": "Replicate TM Score locally",
  "url": "/competitions/stanford-rna-3d-folding/discussion/567825",
  "author_name": "",
  "post_date": "2025-03-12T09:30:54.334855600Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Trying to replicate the TM metric locally, the functions take three arguments;</p>\n<pre><code>Args:\n        solution (pd.DataFrame): A DataFrame containing the native RNA structures.\n        submission (pd.DataFrame): A DataFrame containing the predicted RNA structures.\n        row_id_column_name (): The name of the column containing unique row identifiers.\n</code></pre>\n<p>I'm assuming that <code>submission</code> is expected to have the same form as <code>submission.csv</code> and that the <code>row_id_column_name</code> is <code>ID</code>. Testing this out with the validation data, I assumed that the <code>validation_labels</code> is good for the solution argument (after stripping away x_2, y_2, z_2, ….., y_40, z_40). This is not really working. Has anyone done this successfully?</p>",
  "messages": [
    {
      "id": "3147678",
      "postDate": "03/12/2025 09:30:54",
      "content": "<p>Trying to replicate the TM metric locally, the functions take three arguments;</p>\n<pre><code>Args:\n        solution (pd.DataFrame): A DataFrame containing the native RNA structures.\n        submission (pd.DataFrame): A DataFrame containing the predicted RNA structures.\n        row_id_column_name (): The name of the column containing unique row identifiers.\n</code></pre>\n<p>I'm assuming that <code>submission</code> is expected to have the same form as <code>submission.csv</code> and that the <code>row_id_column_name</code> is <code>ID</code>. Testing this out with the validation data, I assumed that the <code>validation_labels</code> is good for the solution argument (after stripping away x_2, y_2, z_2, ….., y_40, z_40). This is not really working. Has anyone done this successfully?</p>",
      "rawMarkdown": "Trying to replicate the TM metric locally, the functions take three arguments;\n```python\n    \nArgs:\n        solution (pd.DataFrame): A DataFrame containing the native RNA structures.\n        submission (pd.DataFrame): A DataFrame containing the predicted RNA structures.\n        row_id_column_name (str): The name of the column containing unique row identifiers.\n\n```\nI'm assuming that `submission` is expected to have the same form as `submission.csv` and that the `row_id_column_name` is `ID`. Testing this out with the validation data, I assumed that the `validation_labels` is good for the solution argument (after stripping away x_2, y_2, z_2, ....., y_40, z_40). This is not really working. Has anyone done this successfully?",
      "votes": null
    },
    {
      "id": "3147873",
      "postDate": "03/12/2025 13:58:02",
      "content": "<p>yeah, i have made the notebook public here: <a href=\"https://www.kaggle.com/code/jaejohn/rna-3d-folding-evaluation\" target=\"_blank\">https://www.kaggle.com/code/jaejohn/rna-3d-folding-evaluation</a></p>",
      "rawMarkdown": "yeah, i have made the notebook public here: https://www.kaggle.com/code/jaejohn/rna-3d-folding-evaluation",
      "votes": null
    },
    {
      "id": "3148540",
      "postDate": "03/13/2025 09:06:20",
      "content": "<p>Thanks!    </p>",
      "rawMarkdown": "Thanks!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3147873,
      "author_name": "jaejohn",
      "author_url": "",
      "post_date": "03/12/2025 13:58:02",
      "content": "<p>yeah, i have made the notebook public here: <a href=\"https://www.kaggle.com/code/jaejohn/rna-3d-folding-evaluation\" target=\"_blank\">https://www.kaggle.com/code/jaejohn/rna-3d-folding-evaluation</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 3148540,
          "author_name": "olemagnushiback",
          "author_url": "",
          "post_date": "03/13/2025 09:06:20",
          "content": "<p>Thanks!    </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "3147678": "Trying to replicate the TM metric locally, the functions take three arguments;\n```python\n    \nArgs:\n        solution (pd.DataFrame): A DataFrame containing the native RNA structures.\n        submission (pd.DataFrame): A DataFrame containing the predicted RNA structures.\n        row_id_column_name (str): The name of the column containing unique row identifiers.\n\n```\nI'm assuming that `submission` is expected to have the same form as `submission.csv` and that the `row_id_column_name` is `ID`. Testing this out with the validation data, I assumed that the `validation_labels` is good for the solution argument (after stripping away x_2, y_2, z_2, ....., y_40, z_40). This is not really working. Has anyone done this successfully?",
    "3147873": "yeah, i have made the notebook public here: https://www.kaggle.com/code/jaejohn/rna-3d-folding-evaluation",
    "3148540": "Thanks!"
  },
  "source": "meta"
}