Published November 14, 2026 | Version v5

GraphaRNA model & RNA3Desc dataset

  • 1. ROR icon Poznań University of Technology
  • 2. ROR icon Bowling Green State University

Description

Graph Neural Network and Diffusion Model for Modeling RNA Interatomic Interactions and dataset of RNA 3D descriptors (RNA3Desc)

This repository contains the dataset (RNA3Desc) and the pre-trained model associated with GraphaRNA, a diffusion-based graph neural network for RNA 3D structure prediction. The data is organized into multiple files, each providing key resources for training, validation, and testing the model, as well as a pre-trained model ready for inference.

Data Overview:

  1. rRNA_tRNA.tar.gz:

    • Contains raw PDB files with extracted descriptors from ribosomal RNA (rRNA) and transfer RNA (tRNA) structures.
  2. non_rRNA_tRNA.tar.gz:

    • Contains raw PDB files with extracted descriptors from RNA molecules that are non-rRNA and non-tRNA. These serve as a separate test set.
  3. train-pkl.tar.gz:

    • Contains the filtered and preprocessed pickle files for the training set, derived from the rRNA_tRNA dataset. These files are used to train GraphaRNA.
  4. val-pkl.tar.gz:

    • Contains the validation set, which is a subset of the training data from train-pkl.tar.gz.
  5. test-pkl.tar.gz:

    • Contains the preprocessed pickle files for the test set, derived from the non_rRNA_tRNA dataset. This set includes RNA descriptors that are not rRNA or tRNA, providing a challenging test scenario.
  6. model_epoch_800.tar.gz:

    • Contains the pre-trained GraphaRNA model after 800 epochs of training on the train-pkl dataset. This model is ready for inference and evaluation.
  7.  all-outputs.txt:
    • Contains basic metadata about all descriptors: name of file, number of segments, number of nucleotides, sequence of each segment, and positions of segments in original PDB files.
  8. grapharna.tar:
    • Docker image of GraphaRNA instance.

Use of Data and Model:

  • The raw PDB files can be used for RNA descriptor extraction, while the pickle files are preprocessed for direct use in training, validation, and testing workflows.
  • The GraphaRNA model in model_epoch_800.tar.gz can be used to run inference on new RNA data or to reproduce results from the associated paper.

How to Use:

  • Training: The train-pkl.tar.gz contains data that can be used to retrain the GraphaRNA model from scratch.
  • Validation: The val-pkl.tar.gz can be used to validate the model during or after training.
  • Testing: Use the test-pkl.tar.gz to evaluate the model's performance on RNA types that it wasn't trained on (non-rRNA and non-tRNA).
  • Inference: The model_epoch_800.tar.gz is ready for inference on new RNA sequences.

Citing:

If you use this dataset or the pre-trained model in your research, please cite the associated paper.

@article{10.1093/bioinformatics/btaf515,
    author = {Justyna, Marek and Zirbel, Craig and Antczak, Maciej and Szachniuk, Marta},
    title = {Graph neural network and diffusion model for modeling RNA interatomic interactions},
    journal = {Bioinformatics},
    volume = {41},
    number = {9},
    pages = {btaf515},
    year = {2025},
    month = {09},
    issn = {1367-4811},
    doi = {10.1093/bioinformatics/btaf515},
    url = {https://doi.org/10.1093/bioinformatics/btaf515},
}

 

Funding

Project supported by the National Science Center, Poland [grants 2020/39/O/ST6/01488 and 2024/53/B/ST6/02789 to M.S.]

Files

all-output.txt

Files (14.4 GB)

Name Size
md5:0a81392311912ac953cf64ac770b741b
33.5 MB Preview Download
md5:01c5074c71f7df8d5a1955c12b953d72
9.2 GB Download
md5:4d53e950852d618c9104a8834e9e463f
2.8 GB Download
md5:e58d972760f0ebd44b440771eb46a560
194.0 MB Download
md5:aaa2ac0e9c8869268939a0a8fb05a1cc
2.2 GB Download
md5:1e702ebcbec1deed93c6c877dfcc5a7f
19.6 MB Download
md5:5e27133fee6b8eb57c1542de3d852ca0
34.9 MB Download
md5:f72e71365f16969f4d41f5ca9ecd8994
784.9 kB Download

Additional details