search

gongtiansu / SASA-Net

A deep learning based approach that directly learns protein 3D structure from estimated inter-residue distances
MIT License
1 stars 0 forks source link

readme

SASA-Net

About The Project

The implementation of the paper "SASA-Net: A spatial-aware self-attention mechanism for building protein 3D structure directly from inter-residue distances".

Getting Started

Prerequisites

Install PyTorch 1.6+, python 3.7+

Installation

  1. Clone the repo

    git clone https://github.com/gongtiansu/SASA-Net.git

  2. Install python packages

    cd SASA-Net
pip install -r requirements.txt

Usage

  1. Generate estimated inter-residue distance using ProFOLD
  2. Run SASA-Net 
    run_SA.sh --fasta <fasta> --feat <profold_npz> --output <output_pdb>

Example

cd example
./run_example.sh

License

Distributed under the MIT License. See LICENSE for more information.