{ "id": 567046, "title": "Good starter pack for Stanford RNA 3D Folding Contest - 2025", "url": "/competitions/stanford-rna-3d-folding/discussion/567046", "author_name": "", "post_date": "2025-03-08T04:36:38.177301500Z", "votes": 21, "comment_count": 1, "views": 0, "content": "

Here are some good starter pack for Stanford RNA 3D Folding Contest - 2025

\n

Research Papers

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Title & LinkAuthorsYearKey Contribution
trRosettaRNA: automated prediction of RNA 3D structureWang et al.2023Deep learning pipeline combining transformer networks and Rosetta energy minimization for RNA 3D structure prediction. Outperformed traditional methods in CASP15 and RNA-Puzzles.
RoseTTAFoldNA: Protein–nucleic acid complexes predictionBaek et al.2024Single-model network for predicting protein–RNA/DNA complexes with high accuracy, even for targets without homologs.
GraphDTA: Drug–target binding affinity predictionNguyen et al.2019Graph convolutional networks (GCNs) for drug–target affinity prediction using molecular graph representations.
RhoFold+: RNA 3D prediction with language modelsShen et al.2024Language model-based method for single-chain RNA structure prediction, improving on RhoFold’s automation and accuracy.
\n

Models & Tools

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Model/Tool & LinkTypeDescription
trRosettaRNADeep Learning + RosettaPredicts RNA 3D structures via transformer-based 1D/2D geometry prediction and Rosetta energy minimization.
RoseTTAFoldNAHybrid DLPredicts protein–RNA/DNA complexes with confidence estimates, outperforming FARFAR2 and DeepFoldRNA.
GraphDTAGraph Neural NetworkRepresents drugs as graphs (atoms as nodes, bonds as edges) for affinity prediction.
RhoFold+Language ModelFully automated RNA 3D prediction using improved integration of MSAs and sequence features.
\n

Papers with Code

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Title & LinkKey FeaturesCode Availability
trRosettaRNACode for transformer network and Rosetta-based folding.Server/Code
GraphDTAPython implementation of GCNs for drug-target affinity.GitHub
RoseTTAFoldNAIntegrates protein and nucleic acid structure prediction.Code available via RoseTTAFoldNA repo (not explicitly linked in paper).
\n

Hope you find them useful

", "messages": [ { "id": "3144193", "postDate": "03/08/2025 04:36:38", "content": "

Here are some good starter pack for Stanford RNA 3D Folding Contest - 2025

\n

Research Papers

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Title & LinkAuthorsYearKey Contribution
trRosettaRNA: automated prediction of RNA 3D structureWang et al.2023Deep learning pipeline combining transformer networks and Rosetta energy minimization for RNA 3D structure prediction. Outperformed traditional methods in CASP15 and RNA-Puzzles.
RoseTTAFoldNA: Protein–nucleic acid complexes predictionBaek et al.2024Single-model network for predicting protein–RNA/DNA complexes with high accuracy, even for targets without homologs.
GraphDTA: Drug–target binding affinity predictionNguyen et al.2019Graph convolutional networks (GCNs) for drug–target affinity prediction using molecular graph representations.
RhoFold+: RNA 3D prediction with language modelsShen et al.2024Language model-based method for single-chain RNA structure prediction, improving on RhoFold’s automation and accuracy.
\n

Models & Tools

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Model/Tool & LinkTypeDescription
trRosettaRNADeep Learning + RosettaPredicts RNA 3D structures via transformer-based 1D/2D geometry prediction and Rosetta energy minimization.
RoseTTAFoldNAHybrid DLPredicts protein–RNA/DNA complexes with confidence estimates, outperforming FARFAR2 and DeepFoldRNA.
GraphDTAGraph Neural NetworkRepresents drugs as graphs (atoms as nodes, bonds as edges) for affinity prediction.
RhoFold+Language ModelFully automated RNA 3D prediction using improved integration of MSAs and sequence features.
\n

Papers with Code

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Title & LinkKey FeaturesCode Availability
trRosettaRNACode for transformer network and Rosetta-based folding.Server/Code
GraphDTAPython implementation of GCNs for drug-target affinity.GitHub
RoseTTAFoldNAIntegrates protein and nucleic acid structure prediction.Code available via RoseTTAFoldNA repo (not explicitly linked in paper).
\n

Hope you find them useful

", "rawMarkdown": "# Here are some good starter pack for Stanford RNA 3D Folding Contest - 2025\n\n### **Research Papers**\n\n| Title & Link | Authors | Year | Key Contribution |\n|--------------------------------------------------------------------------------------------------|-----------------------|------|---------------------------------------------------------------------------------|\n| **[trRosettaRNA: automated prediction of RNA 3D structure**](https://www.nature.com/articles/s41467-023-42528-4) | Wang et al. | 2023 | Deep learning pipeline combining transformer networks and Rosetta energy minimization for RNA 3D structure prediction. Outperformed traditional methods in CASP15 and RNA-Puzzles. |\n| **[RoseTTAFoldNA: Protein–nucleic acid complexes prediction**](https://www.nature.com/articles/s41592-023-02086-5) | Baek et al. | 2024 | Single-model network for predicting protein–RNA/DNA complexes with high accuracy, even for targets without homologs. |\n| **[GraphDTA: Drug–target binding affinity prediction**](https://www.biorxiv.org/content/10.1101/684662v3.full.pdf) | Nguyen et al. | 2019 | Graph convolutional networks (GCNs) for drug–target affinity prediction using molecular graph representations. |\n| **[RhoFold+: RNA 3D prediction with language models**](https://www.nature.com/articles/s41592-024-02487-0) | Shen et al. | 2024 | Language model-based method for single-chain RNA structure prediction, improving on RhoFold’s automation and accuracy. |\n\n\n### **Models & Tools**\n\n| Model/Tool & Link | Type | Description |\n|--------------------------------------------------------------------------------------------------|-----------------------|-----------------------------------------------------------------------------|\n| **[trRosettaRNA**](https://yanglab.qd.sdu.edu.cn/trRosettaRNA) | Deep Learning + Rosetta | Predicts RNA 3D structures via transformer-based 1D/2D geometry prediction and Rosetta energy minimization. |\n| **[RoseTTAFoldNA**](https://www.nature.com/articles/s41592-023-02086-5) | Hybrid DL | Predicts protein–RNA/DNA complexes with confidence estimates, outperforming FARFAR2 and DeepFoldRNA. |\n| **[GraphDTA**](https://github.com/thinng/GraphDTA) | Graph Neural Network | Represents drugs as graphs (atoms as nodes, bonds as edges) for affinity prediction. |\n| **[RhoFold+**](https://www.nature.com/articles/s41592-024-02487-0) | Language Model | Fully automated RNA 3D prediction using improved integration of MSAs and sequence features. |\n\n\n### **Papers with Code**\n\n| Title & Link | Key Features | Code Availability |\n|--------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------|----------------------------------------------------------------------------------|\n| **[trRosettaRNA**](https://yanglab.qd.sdu.edu.cn/trRosettaRNA) | Code for transformer network and Rosetta-based folding. | [Server/Code](https://yanglab.qd.sdu.edu.cn/trRosettaRNA) |\n| **[GraphDTA**](https://github.com/thinng/GraphDTA) | Python implementation of GCNs for drug-target affinity. | [GitHub](https://github.com/thinng/GraphDTA) |\n| **[RoseTTAFoldNA**](https://www.nature.com/articles/s41592-023-02086-5) | Integrates protein and nucleic acid structure prediction. | Code available via [RoseTTAFoldNA repo](https://github.com/RosettaCommons/RoseTTAFoldNA) (not explicitly linked in paper). |\n\n\n## Hope you find them useful", "votes": null }, { "id": "3191536", "postDate": "05/01/2025 20:20:19", "content": "

Thank you!

", "rawMarkdown": "Thank you!", "votes": null } ], "comments": [ { "id": 3191536, "author_name": "judahszammit", "author_url": "", "post_date": "05/01/2025 20:20:19", "content": "

Thank you!

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "3144193": "# Here are some good starter pack for Stanford RNA 3D Folding Contest - 2025\n\n### **Research Papers**\n\n| Title & Link | Authors | Year | Key Contribution |\n|--------------------------------------------------------------------------------------------------|-----------------------|------|---------------------------------------------------------------------------------|\n| **[trRosettaRNA: automated prediction of RNA 3D structure**](https://www.nature.com/articles/s41467-023-42528-4) | Wang et al. | 2023 | Deep learning pipeline combining transformer networks and Rosetta energy minimization for RNA 3D structure prediction. Outperformed traditional methods in CASP15 and RNA-Puzzles. |\n| **[RoseTTAFoldNA: Protein–nucleic acid complexes prediction**](https://www.nature.com/articles/s41592-023-02086-5) | Baek et al. | 2024 | Single-model network for predicting protein–RNA/DNA complexes with high accuracy, even for targets without homologs. |\n| **[GraphDTA: Drug–target binding affinity prediction**](https://www.biorxiv.org/content/10.1101/684662v3.full.pdf) | Nguyen et al. | 2019 | Graph convolutional networks (GCNs) for drug–target affinity prediction using molecular graph representations. |\n| **[RhoFold+: RNA 3D prediction with language models**](https://www.nature.com/articles/s41592-024-02487-0) | Shen et al. | 2024 | Language model-based method for single-chain RNA structure prediction, improving on RhoFold’s automation and accuracy. |\n\n\n### **Models & Tools**\n\n| Model/Tool & Link | Type | Description |\n|--------------------------------------------------------------------------------------------------|-----------------------|-----------------------------------------------------------------------------|\n| **[trRosettaRNA**](https://yanglab.qd.sdu.edu.cn/trRosettaRNA) | Deep Learning + Rosetta | Predicts RNA 3D structures via transformer-based 1D/2D geometry prediction and Rosetta energy minimization. |\n| **[RoseTTAFoldNA**](https://www.nature.com/articles/s41592-023-02086-5) | Hybrid DL | Predicts protein–RNA/DNA complexes with confidence estimates, outperforming FARFAR2 and DeepFoldRNA. |\n| **[GraphDTA**](https://github.com/thinng/GraphDTA) | Graph Neural Network | Represents drugs as graphs (atoms as nodes, bonds as edges) for affinity prediction. |\n| **[RhoFold+**](https://www.nature.com/articles/s41592-024-02487-0) | Language Model | Fully automated RNA 3D prediction using improved integration of MSAs and sequence features. |\n\n\n### **Papers with Code**\n\n| Title & Link | Key Features | Code Availability |\n|--------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------|----------------------------------------------------------------------------------|\n| **[trRosettaRNA**](https://yanglab.qd.sdu.edu.cn/trRosettaRNA) | Code for transformer network and Rosetta-based folding. | [Server/Code](https://yanglab.qd.sdu.edu.cn/trRosettaRNA) |\n| **[GraphDTA**](https://github.com/thinng/GraphDTA) | Python implementation of GCNs for drug-target affinity. | [GitHub](https://github.com/thinng/GraphDTA) |\n| **[RoseTTAFoldNA**](https://www.nature.com/articles/s41592-023-02086-5) | Integrates protein and nucleic acid structure prediction. | Code available via [RoseTTAFoldNA repo](https://github.com/RosettaCommons/RoseTTAFoldNA) (not explicitly linked in paper). |\n\n\n## Hope you find them useful", "3191536": "Thank you!" }, "source": "meta" }