https://github.com/aqlaboratory/rgn2

https://github.com/aqlaboratory/rgn2

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/aqlaboratory/rgn2
• Owner: aqlaboratory
• Created: 2019-07-22T16:23:41.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2023-11-28T17:16:23.000Z (about 1 year ago)
• Last Synced: 2024-08-03T09:04:09.063Z (5 months ago)
• Language: Python
• Size: 17.1 MB
• Stars: 98
• Watchers: 11
• Forks: 29
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• top-life-sciences - **aqlaboratory/rgn2** - 11-28 17:16:23 | (Ranked by starred repositories)

README

        
# RGN2

This is the reference implementation of recurrent geometric network-2 (RGN2), described in the paper _Single-sequence protein structure prediction using a language model and deep learning_.

**Note:** We recommend using RGN2 primarily for prediction of orphan or de novo proteins. For proteins with known homologs we suggest using

[AlphaFold2](https://colab.research.google.com/github/sokrypton/ColabFold/blob/main/AlphaFold2.ipynb) or 

[OpenFold](https://colab.research.google.com/github/aqlaboratory/openfold/blob/main/notebooks/OpenFold.ipynb).

## Usage

Use the [RGN2 Colab notebook](https://colab.research.google.com/github/aqlaboratory/rgn2/blob/master/rgn2_prediction.ipynb) to predict the 3D structures for orphan or de novo protein sequences.

## Reference

[Single-sequence protein structure prediction using a language model and deep learning, Nature Biotechnology 2022](https://rdcu.be/cWPgh)