{
  "id": 403495,
  "title": "Top Papers on Automated Function Prediction (AFP)",
  "url": "/competitions/cafa-5-protein-function-prediction/discussion/403495",
  "author_name": "Dhruv_K",
  "post_date": "2023-04-23T12:55:30.271000",
  "votes": 23,
  "comment_count": 5,
  "views": 0,
  "content": "<ol>\n<li>GoLabeller: <a href=\"https://doi.org/10.1093/bioinformatics/bty130\" target=\"_blank\">https://doi.org/10.1093/bioinformatics/bty130</a></li>\n<li>NetGo: <a href=\"https://doi.org/10.1093/nar/gkz388\" target=\"_blank\">https://doi.org/10.1093/nar/gkz388</a> </li>\n<li>GoFDR: <a href=\"https://doi.org/10.1016/j.ymeth.2015.08.009\" target=\"_blank\">https://doi.org/10.1016/j.ymeth.2015.08.009</a></li>\n<li>DeepGO: <a href=\"https://doi.org/10.1093/bioinformatics/btx624\" target=\"_blank\">https://doi.org/10.1093/bioinformatics/btx624</a></li>\n</ol>\n<p>The paper for NetGo also presents a comparison of all methods in a validation dataset described as</p>\n<blockquote>\n  <p>The validation datasets were generated by following the procedures of CAFA1 (4), CAFA2 (5) and CAFA3. Specifically, protein sequences were downloaded from UniProt (3), while experimental annotations were extracted from SwissProt (7), GOA(<a href=\"http://www.ebi.ac.uk/GOA\" target=\"_blank\">http://www.ebi.ac.uk/GOA</a>) (21), and GO (<a href=\"http://geneontology.org/page/download-annotations\" target=\"_blank\">http://geneontology.org/page/download-annotations</a>)</p>\n</blockquote>\n<p>Will add more information as it comes up. </p>\n<ol>\n<li>goPredSim: <a href=\"https://www.nature.com/articles/s41598-020-80786-0\" target=\"_blank\">https://www.nature.com/articles/s41598-020-80786-0</a></li>\n<li>ProLanGO: <a href=\"https://doi.org/10.3390/molecules22101732\" target=\"_blank\">https://doi.org/10.3390/molecules22101732</a></li>\n<li>2013  Review on protein function prediction: <a href=\"https://doi.org/10.1038/nmeth.2340\" target=\"_blank\">https://doi.org/10.1038/nmeth.2340</a></li>\n<li>DeepGOPlus: 10.1093/bioinformatics/btz595</li>\n<li>CFAGO: cross-fusion of network and attributes based on attention mechanism for protein function prediction (2023)</li>\n<li>PANNZER—A practical tool for protein function prediction (2021)</li>\n<li>Accurate protein function prediction via graph attention networks with predicted structure information  (2021)</li>\n<li>I-TASSER-MTD: a deep-learning-based platform for multi-domain protein structure and function prediction (2022)</li>\n<li>PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods (2022)</li>\n<li>OntoProtein: Protein Pretraining With Gene Ontology Embedding (2022)</li>\n<li>Gene Ontology Capsule GAN: an improved architecture for protein function prediction (2022)</li>\n<li>ProTranslator: Zero-Shot Protein Function Prediction Using Textual Description (2022)</li>\n<li>DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms  (2022)</li>\n<li>PANDA2: protein function prediction using graph neural networks (2022)</li>\n</ol>\n<p>There are many papers here, it will take a while to go through them. I will keep you posted. For now, it looks like GoLabeller is first place contender. (Please correct if it isn't)</p>",
  "messages": [
    {
      "id": 2231581,
      "postDate": "2023-04-23T12:55:30.270Z",
      "content": "<ol>\n<li>GoLabeller: <a href=\"https://doi.org/10.1093/bioinformatics/bty130\" target=\"_blank\">https://doi.org/10.1093/bioinformatics/bty130</a></li>\n<li>NetGo: <a href=\"https://doi.org/10.1093/nar/gkz388\" target=\"_blank\">https://doi.org/10.1093/nar/gkz388</a> </li>\n<li>GoFDR: <a href=\"https://doi.org/10.1016/j.ymeth.2015.08.009\" target=\"_blank\">https://doi.org/10.1016/j.ymeth.2015.08.009</a></li>\n<li>DeepGO: <a href=\"https://doi.org/10.1093/bioinformatics/btx624\" target=\"_blank\">https://doi.org/10.1093/bioinformatics/btx624</a></li>\n</ol>\n<p>The paper for NetGo also presents a comparison of all methods in a validation dataset described as</p>\n<blockquote>\n  <p>The validation datasets were generated by following the procedures of CAFA1 (4), CAFA2 (5) and CAFA3. Specifically, protein sequences were downloaded from UniProt (3), while experimental annotations were extracted from SwissProt (7), GOA(<a href=\"http://www.ebi.ac.uk/GOA\" target=\"_blank\">http://www.ebi.ac.uk/GOA</a>) (21), and GO (<a href=\"http://geneontology.org/page/download-annotations\" target=\"_blank\">http://geneontology.org/page/download-annotations</a>)</p>\n</blockquote>\n<p>Will add more information as it comes up. </p>\n<ol>\n<li>goPredSim: <a href=\"https://www.nature.com/articles/s41598-020-80786-0\" target=\"_blank\">https://www.nature.com/articles/s41598-020-80786-0</a></li>\n<li>ProLanGO: <a href=\"https://doi.org/10.3390/molecules22101732\" target=\"_blank\">https://doi.org/10.3390/molecules22101732</a></li>\n<li>2013  Review on protein function prediction: <a href=\"https://doi.org/10.1038/nmeth.2340\" target=\"_blank\">https://doi.org/10.1038/nmeth.2340</a></li>\n<li>DeepGOPlus: 10.1093/bioinformatics/btz595</li>\n<li>CFAGO: cross-fusion of network and attributes based on attention mechanism for protein function prediction (2023)</li>\n<li>PANNZER—A practical tool for protein function prediction (2021)</li>\n<li>Accurate protein function prediction via graph attention networks with predicted structure information  (2021)</li>\n<li>I-TASSER-MTD: a deep-learning-based platform for multi-domain protein structure and function prediction (2022)</li>\n<li>PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods (2022)</li>\n<li>OntoProtein: Protein Pretraining With Gene Ontology Embedding (2022)</li>\n<li>Gene Ontology Capsule GAN: an improved architecture for protein function prediction (2022)</li>\n<li>ProTranslator: Zero-Shot Protein Function Prediction Using Textual Description (2022)</li>\n<li>DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms  (2022)</li>\n<li>PANDA2: protein function prediction using graph neural networks (2022)</li>\n</ol>\n<p>There are many papers here, it will take a while to go through them. I will keep you posted. For now, it looks like GoLabeller is first place contender. (Please correct if it isn't)</p>",
      "rawMarkdown": "1. GoLabeller: https://doi.org/10.1093/bioinformatics/bty130\n2. NetGo: https://doi.org/10.1093/nar/gkz388 \n3. GoFDR: https://doi.org/10.1016/j.ymeth.2015.08.009\n4. DeepGO: https://doi.org/10.1093/bioinformatics/btx624\n\nThe paper for NetGo also presents a comparison of all methods in a validation dataset described as\n\n >The validation datasets were generated by following the procedures of CAFA1 (4), CAFA2 (5) and CAFA3. Specifically, protein sequences were downloaded from UniProt (3), while experimental annotations were extracted from SwissProt (7), GOA(http://www.ebi.ac.uk/GOA) (21), and GO (http://geneontology.org/page/download-annotations)\n\nWill add more information as it comes up. \n5. goPredSim: https://www.nature.com/articles/s41598-020-80786-0\n6. ProLanGO: https://doi.org/10.3390/molecules22101732\n7. 2013  Review on protein function prediction: https://doi.org/10.1038/nmeth.2340\n8.  DeepGOPlus: 10.1093/bioinformatics/btz595\n9. CFAGO: cross-fusion of network and attributes based on attention mechanism for protein function prediction (2023)\n10.  PANNZER—A practical tool for protein function prediction (2021)\n11.  Accurate protein function prediction via graph attention networks with predicted structure information  (2021)\n12. I-TASSER-MTD: a deep-learning-based platform for multi-domain protein structure and function prediction (2022)\n13. PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods (2022)\n14. OntoProtein: Protein Pretraining With Gene Ontology Embedding (2022)\n15. Gene Ontology Capsule GAN: an improved architecture for protein function prediction (2022)\n16. ProTranslator: Zero-Shot Protein Function Prediction Using Textual Description (2022)\n17. DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms  (2022)\n18. PANDA2: protein function prediction using graph neural networks (2022)\n\nThere are many papers here, it will take a while to go through them. I will keep you posted. For now, it looks like GoLabeller is first place contender. (Please correct if it isn't)",
      "votes": 23
    },
    {
      "id": 2231690,
      "postDate": "2023-04-23T14:56:17.557Z",
      "content": "<p>more recent NetGo <a href=\"https://www.sciencedirect.com/science/article/pii/S1672022923000669\" target=\"_blank\">https://www.sciencedirect.com/science/article/pii/S1672022923000669</a> </p>",
      "rawMarkdown": "more recent NetGo https://www.sciencedirect.com/science/article/pii/S1672022923000669 ",
      "votes": 7
    },
    {
      "id": 2255994,
      "postDate": "2023-05-12T07:23:15.477Z",
      "content": "<p>DeepFRI <br>\n<a href=\"https://beta.deepfri.flatironinstitute.org/\" target=\"_blank\">https://beta.deepfri.flatironinstitute.org/</a>.  (web server, accept fasta file for input)<br>\n<a href=\"https://www.nature.com/articles/s41467-021-23303-9\" target=\"_blank\">https://www.nature.com/articles/s41467-021-23303-9</a> (2021 Nat Com) </p>",
      "rawMarkdown": "DeepFRI \nhttps://beta.deepfri.flatironinstitute.org/.  (web server, accept fasta file for input)\nhttps://www.nature.com/articles/s41467-021-23303-9 (2021 Nat Com) ",
      "votes": 3
    },
    {
      "id": 2236336,
      "postDate": "2023-04-26T19:01:30.490Z",
      "content": "<p>A plethora of papers to go through, I will try to generate some common aspects and share with the community. Best!</p>",
      "rawMarkdown": "A plethora of papers to go through, I will try to generate some common aspects and share with the community. Best!",
      "votes": 4
    },
    {
      "id": 2273850,
      "postDate": "2023-05-25T13:02:45.463Z",
      "content": "<p>PFresGO</p>\n<p><a href=\"https://doi.org/10.1093/bioinformatics/btad094\" target=\"_blank\">https://doi.org/10.1093/bioinformatics/btad094</a> (2023 Bioinformatics)</p>",
      "rawMarkdown": "PFresGO\n\nhttps://doi.org/10.1093/bioinformatics/btad094 (2023 Bioinformatics)"
    },
    {
      "id": 2231584,
      "postDate": "2023-04-23T12:57:31.973Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 2231690,
      "author_name": "MT",
      "author_url": "",
      "post_date": "2023-04-23T14:56:17.557000",
      "content": "<p>more recent NetGo <a href=\"https://www.sciencedirect.com/science/article/pii/S1672022923000669\" target=\"_blank\">https://www.sciencedirect.com/science/article/pii/S1672022923000669</a> </p>",
      "votes": 7,
      "replies": []
    },
    {
      "id": 2255994,
      "author_name": "FsheriF",
      "author_url": "",
      "post_date": "2023-05-12T07:23:15.477000",
      "content": "<p>DeepFRI <br>\n<a href=\"https://beta.deepfri.flatironinstitute.org/\" target=\"_blank\">https://beta.deepfri.flatironinstitute.org/</a>.  (web server, accept fasta file for input)<br>\n<a href=\"https://www.nature.com/articles/s41467-021-23303-9\" target=\"_blank\">https://www.nature.com/articles/s41467-021-23303-9</a> (2021 Nat Com) </p>",
      "votes": 3,
      "replies": []
    },
    {
      "id": 2236336,
      "author_name": "Dhruv_K",
      "author_url": "",
      "post_date": "2023-04-26T19:01:30.490000",
      "content": "<p>A plethora of papers to go through, I will try to generate some common aspects and share with the community. Best!</p>",
      "votes": 4,
      "replies": []
    },
    {
      "id": 2273850,
      "author_name": "Yumeng717",
      "author_url": "",
      "post_date": "2023-05-25T13:02:45.463000",
      "content": "<p>PFresGO</p>\n<p><a href=\"https://doi.org/10.1093/bioinformatics/btad094\" target=\"_blank\">https://doi.org/10.1093/bioinformatics/btad094</a> (2023 Bioinformatics)</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 2231584,
      "author_name": "",
      "author_url": "",
      "post_date": "2023-04-23T12:57:31.973000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2231581": "1. GoLabeller: https://doi.org/10.1093/bioinformatics/bty130\n2. NetGo: https://doi.org/10.1093/nar/gkz388 \n3. GoFDR: https://doi.org/10.1016/j.ymeth.2015.08.009\n4. DeepGO: https://doi.org/10.1093/bioinformatics/btx624\n\nThe paper for NetGo also presents a comparison of all methods in a validation dataset described as\n\n >The validation datasets were generated by following the procedures of CAFA1 (4), CAFA2 (5) and CAFA3. Specifically, protein sequences were downloaded from UniProt (3), while experimental annotations were extracted from SwissProt (7), GOA(http://www.ebi.ac.uk/GOA) (21), and GO (http://geneontology.org/page/download-annotations)\n\nWill add more information as it comes up. \n5. goPredSim: https://www.nature.com/articles/s41598-020-80786-0\n6. ProLanGO: https://doi.org/10.3390/molecules22101732\n7. 2013  Review on protein function prediction: https://doi.org/10.1038/nmeth.2340\n8.  DeepGOPlus: 10.1093/bioinformatics/btz595\n9. CFAGO: cross-fusion of network and attributes based on attention mechanism for protein function prediction (2023)\n10.  PANNZER—A practical tool for protein function prediction (2021)\n11.  Accurate protein function prediction via graph attention networks with predicted structure information  (2021)\n12. I-TASSER-MTD: a deep-learning-based platform for multi-domain protein structure and function prediction (2022)\n13. PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods (2022)\n14. OntoProtein: Protein Pretraining With Gene Ontology Embedding (2022)\n15. Gene Ontology Capsule GAN: an improved architecture for protein function prediction (2022)\n16. ProTranslator: Zero-Shot Protein Function Prediction Using Textual Description (2022)\n17. DeepGOZero: improving protein function prediction from sequence and zero-shot learning based on ontology axioms  (2022)\n18. PANDA2: protein function prediction using graph neural networks (2022)\n\nThere are many papers here, it will take a while to go through them. I will keep you posted. For now, it looks like GoLabeller is first place contender. (Please correct if it isn't)",
    "2231690": "more recent NetGo https://www.sciencedirect.com/science/article/pii/S1672022923000669 ",
    "2255994": "DeepFRI \nhttps://beta.deepfri.flatironinstitute.org/.  (web server, accept fasta file for input)\nhttps://www.nature.com/articles/s41467-021-23303-9 (2021 Nat Com) ",
    "2236336": "A plethora of papers to go through, I will try to generate some common aspects and share with the community. Best!",
    "2273850": "PFresGO\n\nhttps://doi.org/10.1093/bioinformatics/btad094 (2023 Bioinformatics)",
    "2231584": ""
  }
}