{
  "id": 509074,
  "title": "Key words definations for layman understanding",
  "url": "/competitions/leash-BELKA/discussion/509074",
  "author_name": "",
  "post_date": "2024-06-01T04:10:11.588467300Z",
  "votes": -6,
  "comment_count": 7,
  "views": 0,
  "content": "<p>To understand &amp; get started its important to know keywords:</p>\n<ol>\n<li><p>buildingblock_smiles : small molecule in computer understanding unique version.<br>\n   a. what is shared BB &amp; non shareBB is it train &amp; test small molecule ?</p></li>\n<li><p>what is triazine core  in molecule_smiles:<br>\n   a. what is triazine core ?<br>\n   b. what is non triazine core?<br>\n   c. how to find triazine core in molecule smiles.</p></li>\n<li><p>protein target name : mixed with BB if bind success than used to drug discovery<br>\n  a. what is difference between BB &amp; protein ?</p></li>\n</ol>\n<p>Well appreciated if you can share any articles or related discussions , notebooks  on above questions &amp; using analogy to explain above question will help more !!</p>\n<p>Thank you for commenting in this discussion to share your knowledge..</p>",
  "messages": [
    {
      "id": "2848493",
      "postDate": "06/01/2024 04:10:11",
      "content": "<p>To understand &amp; get started its important to know keywords:</p>\n<ol>\n<li><p>buildingblock_smiles : small molecule in computer understanding unique version.<br>\n   a. what is shared BB &amp; non shareBB is it train &amp; test small molecule ?</p></li>\n<li><p>what is triazine core  in molecule_smiles:<br>\n   a. what is triazine core ?<br>\n   b. what is non triazine core?<br>\n   c. how to find triazine core in molecule smiles.</p></li>\n<li><p>protein target name : mixed with BB if bind success than used to drug discovery<br>\n  a. what is difference between BB &amp; protein ?</p></li>\n</ol>\n<p>Well appreciated if you can share any articles or related discussions , notebooks  on above questions &amp; using analogy to explain above question will help more !!</p>\n<p>Thank you for commenting in this discussion to share your knowledge..</p>",
      "rawMarkdown": "To understand & get started its important to know keywords:\n\n1. buildingblock_smiles : small molecule in computer understanding unique version.\n       a. what is shared BB & non shareBB is it train & test small molecule ?\n\n2. what is triazine core  in molecule_smiles:\n       a. what is triazine core ?\n       b. what is non triazine core?\n       c. how to find triazine core in molecule smiles.\n\n3.  protein target name : mixed with BB if bind success than used to drug discovery\n      a. what is difference between BB & protein ?\n     \n\nWell appreciated if you can share any articles or related discussions , notebooks  on above questions & using analogy to explain above question will help more !!\n\nThank you for commenting in this discussion to share your knowledge..",
      "votes": null
    },
    {
      "id": "2848499",
      "postDate": "06/01/2024 04:19:23",
      "content": "<p>in the new age of AI, you could ask chatgpt for help.<br>\nmost of the answer is already in the discussion forum, you should read it.</p>\n<p>layman:<br>\ni read in the forum that ….. my understanding is that … is it correct?</p>\n<p>lazyman:<br>\nplease tell me what is …</p>",
      "rawMarkdown": "in the new age of AI, you could ask chatgpt for help.\nmost of the answer is already in the discussion forum, you should read it.\n\nlayman:\ni read in the forum that ..... my understanding is that ... is it correct?\n\nlazyman:\nplease tell me what is ...",
      "votes": null
    },
    {
      "id": "2848507",
      "postDate": "06/01/2024 04:31:47",
      "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2F8896ae82b5473bcbf909d99c8c44546a%2FSelection_168.png?generation=1717216290331951&amp;alt=media\"><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fc8eaa73d1c3d5191d680287297ee5498%2FSelection_167.png?generation=1717216303724934&amp;alt=media\"></p>",
      "rawMarkdown": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2F8896ae82b5473bcbf909d99c8c44546a%2FSelection_168.png?generation=1717216290331951&alt=media)\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fc8eaa73d1c3d5191d680287297ee5498%2FSelection_167.png?generation=1717216303724934&alt=media)",
      "votes": null
    },
    {
      "id": "2848809",
      "postDate": "06/01/2024 08:18:22",
      "content": "<p>3 a. small molecule(BB) vs protein :</p>\n<p><strong>small molecule(BB)</strong> : Think of small molecules like Legos. They are individual building blocks with relatively simple structures. <img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F96acad32808729e376160877a6de11dc%2FGettyImages-521952820.webp?generation=1717230051014533&amp;alt=media\"></p>\n<p><strong>Proteins</strong> are like intricate machines built from Legos. The specific sequence and arrangement of Legos (amino acids) determine the final form and function of the machine (protein). <img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F16a72ecdb73cce76a4f31f9e5255171e%2F44_mechanism_lego_machine_t.webp?generation=1717230068568139&amp;alt=media\"></p>",
      "rawMarkdown": "3 a. small molecule(BB) vs protein :\n\n**small molecule(BB)** : Think of small molecules like Legos. They are individual building blocks with relatively simple structures. ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F96acad32808729e376160877a6de11dc%2FGettyImages-521952820.webp?generation=1717230051014533&alt=media)\n\n\n**Proteins** are like intricate machines built from Legos. The specific sequence and arrangement of Legos (amino acids) determine the final form and function of the machine (protein). ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F16a72ecdb73cce76a4f31f9e5255171e%2F44_mechanism_lego_machine_t.webp?generation=1717230068568139&alt=media)",
      "votes": null
    },
    {
      "id": "2848909",
      "postDate": "06/01/2024 09:17:45",
      "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fd6384bb6c60389215c68b57007a48445%2FSelection_171.png?generation=1717233443356406&amp;alt=media\"></p>\n<p>they are indeed similiar</p>",
      "rawMarkdown": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fd6384bb6c60389215c68b57007a48445%2FSelection_171.png?generation=1717233443356406&alt=media)\n\nthey are indeed similiar",
      "votes": null
    },
    {
      "id": "2852179",
      "postDate": "06/03/2024 07:08:22",
      "content": "<p>Yeah , my comment with Legos is good analogy to understand small molecules &amp; proteins !!</p>",
      "rawMarkdown": "Yeah , my comment with Legos is good analogy to understand small molecules & proteins !!",
      "votes": null
    },
    {
      "id": "2852330",
      "postDate": "06/03/2024 08:10:28",
      "content": "<p><a href=\"https://www.kaggle.com/hengck23\" target=\"_blank\">@hengck23</a>  can you please validate this is how we get triazine core from molecule smiles ?</p>\n<p>unique_molecule_smiles_from_head = ['C#CCOc1ccc(CNc2nc(NCC3CCCN3c3cccnn3)nc(N<a href=\"CC#C\" target=\"_blank\">C@@H</a>CC(=O)N[Dy])n2)cc1', <br>\n                                    'C#CCOc1ccc(CNc2nc(NCc3cccc(Br)n3)nc(N<a href=\"CC#C\" target=\"_blank\">C@@H</a>CC(=O)N[Dy])n2)cc1']</p>\n<h1>Function to extract the triazine core from a molecule</h1>\n<p>def extract_triazine_core(smiles):</p>\n<pre><code># Define the triazine core  a SMARTS pattern\ntriazine_smarts = \n\n# Convert the SMILES   an RDKit molecule \nmol = Chem.\n not mol:\n    return None, None\n\n# Use the SMARTS pattern  search  the triazine core\ntriazine_pattern = Chem.\nmatches = mol.\n\n not matches:\n    return None\n\n# Create a  molecule  only the triazine core\natom_indices = matches  # Assuming there's only one \ntriazine_core = Chem.\n\ntriazine_core_smiles = Chem.\n\nreturn triazine_core_smiles\n</code></pre>\n<p>for smiles in unique_molecule_smiles_from_head:<br>\n    print(extract_triazine_core(smiles))</p>\n<p>cc.cncN.ncN<br>\ncc.cncN.ncN</p>",
      "rawMarkdown": "hengck23  can you please validate this is how we get triazine core from molecule smiles ?\n\nunique_molecule_smiles_from_head = ['C#CCOc1ccc(CNc2nc(NCC3CCCN3c3cccnn3)nc(N[C@@H](CC#C)CC(=O)N[Dy])n2)cc1', \n                                    'C#CCOc1ccc(CNc2nc(NCc3cccc(Br)n3)nc(N[C@@H](CC#C)CC(=O)N[Dy])n2)cc1']\n\n# Function to extract the triazine core from a molecule\ndef extract_triazine_core(smiles):\n    \n    # Define the triazine core as a SMARTS pattern\n    triazine_smarts = \"c1ncncn1\"\n    \n    # Convert the SMILES string to an RDKit molecule object\n    mol = Chem.MolFromSmiles(smiles)\n    if not mol:\n        return None, None\n\n    # Use the SMARTS pattern to search for the triazine core\n    triazine_pattern = Chem.MolFromSmarts(triazine_smarts)\n    matches = mol.GetSubstructMatches(triazine_pattern)\n\n    if not matches:\n        return None\n\n    # Create a new molecule with only the triazine core\n    atom_indices = matches[0]  # Assuming there's only one match\n    triazine_core = Chem.PathToSubmol(mol, atom_indices)\n    \n    triazine_core_smiles = Chem.MolToSmiles(triazine_core)\n\n    return triazine_core_smiles\n\nfor smiles in unique_molecule_smiles_from_head:\n    print(extract_triazine_core(smiles))\n\ncc.cncN.ncN\ncc.cncN.ncN",
      "votes": null
    },
    {
      "id": "2852473",
      "postDate": "06/03/2024 10:07:11",
      "content": "<p>you should check this:<br>\n<a href=\"https://www.kaggle.com/code/chemdatafarmer/scaffold-exploration\" target=\"_blank\">https://www.kaggle.com/code/chemdatafarmer/scaffold-exploration</a></p>\n<pre><code>triazine = Chem.MolFromSmiles('C1=NC=NC=N1')\ndef check_for_triazine(smiles):\n   = Chem.MolFromSmiles(smiles).HasSubstructMatch(triazine)\n   check\n</code></pre>",
      "rawMarkdown": "you should check this:\nhttps://www.kaggle.com/code/chemdatafarmer/scaffold-exploration\n\n```\n\ntriazine = Chem.MolFromSmiles('C1=NC=NC=N1')\ndef check_for_triazine(smiles):\n    check = Chem.MolFromSmiles(smiles).HasSubstructMatch(triazine)\n    return check\n\n\n\n```",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2848499,
      "author_name": "hengck23",
      "author_url": "",
      "post_date": "06/01/2024 04:19:23",
      "content": "<p>in the new age of AI, you could ask chatgpt for help.<br>\nmost of the answer is already in the discussion forum, you should read it.</p>\n<p>layman:<br>\ni read in the forum that ….. my understanding is that … is it correct?</p>\n<p>lazyman:<br>\nplease tell me what is …</p>",
      "votes": null,
      "replies": [
        {
          "id": 2848507,
          "author_name": "hengck23",
          "author_url": "",
          "post_date": "06/01/2024 04:31:47",
          "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2F8896ae82b5473bcbf909d99c8c44546a%2FSelection_168.png?generation=1717216290331951&amp;alt=media\"><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fc8eaa73d1c3d5191d680287297ee5498%2FSelection_167.png?generation=1717216303724934&amp;alt=media\"></p>",
          "votes": null,
          "replies": [
            {
              "id": 2852330,
              "author_name": "kunduruanil",
              "author_url": "",
              "post_date": "06/03/2024 08:10:28",
              "content": "<p><a href=\"https://www.kaggle.com/hengck23\" target=\"_blank\">@hengck23</a>  can you please validate this is how we get triazine core from molecule smiles ?</p>\n<p>unique_molecule_smiles_from_head = ['C#CCOc1ccc(CNc2nc(NCC3CCCN3c3cccnn3)nc(N<a href=\"CC#C\" target=\"_blank\">C@@H</a>CC(=O)N[Dy])n2)cc1', <br>\n                                    'C#CCOc1ccc(CNc2nc(NCc3cccc(Br)n3)nc(N<a href=\"CC#C\" target=\"_blank\">C@@H</a>CC(=O)N[Dy])n2)cc1']</p>\n<h1>Function to extract the triazine core from a molecule</h1>\n<p>def extract_triazine_core(smiles):</p>\n<pre><code># Define the triazine core  a SMARTS pattern\ntriazine_smarts = \n\n# Convert the SMILES   an RDKit molecule \nmol = Chem.\n not mol:\n    return None, None\n\n# Use the SMARTS pattern  search  the triazine core\ntriazine_pattern = Chem.\nmatches = mol.\n\n not matches:\n    return None\n\n# Create a  molecule  only the triazine core\natom_indices = matches  # Assuming there's only one \ntriazine_core = Chem.\n\ntriazine_core_smiles = Chem.\n\nreturn triazine_core_smiles\n</code></pre>\n<p>for smiles in unique_molecule_smiles_from_head:<br>\n    print(extract_triazine_core(smiles))</p>\n<p>cc.cncN.ncN<br>\ncc.cncN.ncN</p>",
              "votes": null,
              "replies": []
            }
          ]
        }
      ]
    },
    {
      "id": 2848809,
      "author_name": "kunduruanil",
      "author_url": "",
      "post_date": "06/01/2024 08:18:22",
      "content": "<p>3 a. small molecule(BB) vs protein :</p>\n<p><strong>small molecule(BB)</strong> : Think of small molecules like Legos. They are individual building blocks with relatively simple structures. <img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F96acad32808729e376160877a6de11dc%2FGettyImages-521952820.webp?generation=1717230051014533&amp;alt=media\"></p>\n<p><strong>Proteins</strong> are like intricate machines built from Legos. The specific sequence and arrangement of Legos (amino acids) determine the final form and function of the machine (protein). <img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F16a72ecdb73cce76a4f31f9e5255171e%2F44_mechanism_lego_machine_t.webp?generation=1717230068568139&amp;alt=media\"></p>",
      "votes": null,
      "replies": [
        {
          "id": 2848909,
          "author_name": "hengck23",
          "author_url": "",
          "post_date": "06/01/2024 09:17:45",
          "content": "<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fd6384bb6c60389215c68b57007a48445%2FSelection_171.png?generation=1717233443356406&amp;alt=media\"></p>\n<p>they are indeed similiar</p>",
          "votes": null,
          "replies": [
            {
              "id": 2852179,
              "author_name": "kunduruanil",
              "author_url": "",
              "post_date": "06/03/2024 07:08:22",
              "content": "<p>Yeah , my comment with Legos is good analogy to understand small molecules &amp; proteins !!</p>",
              "votes": null,
              "replies": []
            }
          ]
        }
      ]
    },
    {
      "id": 2852473,
      "author_name": "hengck23",
      "author_url": "",
      "post_date": "06/03/2024 10:07:11",
      "content": "<p>you should check this:<br>\n<a href=\"https://www.kaggle.com/code/chemdatafarmer/scaffold-exploration\" target=\"_blank\">https://www.kaggle.com/code/chemdatafarmer/scaffold-exploration</a></p>\n<pre><code>triazine = Chem.MolFromSmiles('C1=NC=NC=N1')\ndef check_for_triazine(smiles):\n   = Chem.MolFromSmiles(smiles).HasSubstructMatch(triazine)\n   check\n</code></pre>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2848493": "To understand & get started its important to know keywords:\n\n1. buildingblock_smiles : small molecule in computer understanding unique version.\n       a. what is shared BB & non shareBB is it train & test small molecule ?\n\n2. what is triazine core  in molecule_smiles:\n       a. what is triazine core ?\n       b. what is non triazine core?\n       c. how to find triazine core in molecule smiles.\n\n3.  protein target name : mixed with BB if bind success than used to drug discovery\n      a. what is difference between BB & protein ?\n     \n\nWell appreciated if you can share any articles or related discussions , notebooks  on above questions & using analogy to explain above question will help more !!\n\nThank you for commenting in this discussion to share your knowledge..",
    "2848499": "in the new age of AI, you could ask chatgpt for help.\nmost of the answer is already in the discussion forum, you should read it.\n\nlayman:\ni read in the forum that ..... my understanding is that ... is it correct?\n\nlazyman:\nplease tell me what is ...",
    "2848507": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2F8896ae82b5473bcbf909d99c8c44546a%2FSelection_168.png?generation=1717216290331951&alt=media)\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fc8eaa73d1c3d5191d680287297ee5498%2FSelection_167.png?generation=1717216303724934&alt=media)",
    "2848809": "3 a. small molecule(BB) vs protein :\n\n**small molecule(BB)** : Think of small molecules like Legos. They are individual building blocks with relatively simple structures. ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F96acad32808729e376160877a6de11dc%2FGettyImages-521952820.webp?generation=1717230051014533&alt=media)\n\n\n**Proteins** are like intricate machines built from Legos. The specific sequence and arrangement of Legos (amino acids) determine the final form and function of the machine (protein). ![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2058006%2F16a72ecdb73cce76a4f31f9e5255171e%2F44_mechanism_lego_machine_t.webp?generation=1717230068568139&alt=media)",
    "2848909": "![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F113660%2Fd6384bb6c60389215c68b57007a48445%2FSelection_171.png?generation=1717233443356406&alt=media)\n\nthey are indeed similiar",
    "2852179": "Yeah , my comment with Legos is good analogy to understand small molecules & proteins !!",
    "2852330": "hengck23  can you please validate this is how we get triazine core from molecule smiles ?\n\nunique_molecule_smiles_from_head = ['C#CCOc1ccc(CNc2nc(NCC3CCCN3c3cccnn3)nc(N[C@@H](CC#C)CC(=O)N[Dy])n2)cc1', \n                                    'C#CCOc1ccc(CNc2nc(NCc3cccc(Br)n3)nc(N[C@@H](CC#C)CC(=O)N[Dy])n2)cc1']\n\n# Function to extract the triazine core from a molecule\ndef extract_triazine_core(smiles):\n    \n    # Define the triazine core as a SMARTS pattern\n    triazine_smarts = \"c1ncncn1\"\n    \n    # Convert the SMILES string to an RDKit molecule object\n    mol = Chem.MolFromSmiles(smiles)\n    if not mol:\n        return None, None\n\n    # Use the SMARTS pattern to search for the triazine core\n    triazine_pattern = Chem.MolFromSmarts(triazine_smarts)\n    matches = mol.GetSubstructMatches(triazine_pattern)\n\n    if not matches:\n        return None\n\n    # Create a new molecule with only the triazine core\n    atom_indices = matches[0]  # Assuming there's only one match\n    triazine_core = Chem.PathToSubmol(mol, atom_indices)\n    \n    triazine_core_smiles = Chem.MolToSmiles(triazine_core)\n\n    return triazine_core_smiles\n\nfor smiles in unique_molecule_smiles_from_head:\n    print(extract_triazine_core(smiles))\n\ncc.cncN.ncN\ncc.cncN.ncN",
    "2852473": "you should check this:\nhttps://www.kaggle.com/code/chemdatafarmer/scaffold-exploration\n\n```\n\ntriazine = Chem.MolFromSmiles('C1=NC=NC=N1')\ndef check_for_triazine(smiles):\n    check = Chem.MolFromSmiles(smiles).HasSubstructMatch(triazine)\n    return check\n\n\n\n```"
  },
  "source": "meta"
}