Metadata-Version: 2.1
Name: BGCfinder
Version: 0.0.13
Summary: Biosynthetic Gene Cluster finder with Graph Neural Network
Home-page: https://github.com/jihunni/BGCfinder
Author: Jihun Jeung
Author-email: jihun@gm.gist.ac.kr
License: MIT
Keywords: Biosynthetic Gene Cluster
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Scientific/Engineering :: Chemistry
Requires-Python: >=3
License-File: LICENSE.txt
Requires-Dist: argparse
Requires-Dist: biopython (>=1.79)
Requires-Dist: rdkit-pypi (==2022.3.2.1)
Requires-Dist: pandas (==1.3.4)
Requires-Dist: numpy (==1.20.3)
Requires-Dist: appdirs (>=1.4.4)

# BGCfinder : Biosynthetic Gene Cluster detection with Graph Neural Network

BGCfinder detects biosynthetic gene clusters in bacterial genomes using deep learning. 
BGCfinder takes a fasta file containing bacterial protein coding sequences and embed each protein sequence into a graph. 
Graph Neural Network takes the graphs to detect biosynthetic gene cluster.

Author : Jihun Jeung, jihun@gm.gist.ac.kr, jeung4705@gmail.com, https://github.com/jihunni/BGCfinder

To construct the conda environment,
```bash
$ conda create --name BGCfinder --clone base
$ conda init bash
$ conda activate BGCfinder
$ conda install pytorch cudatoolkit=11.3 -c pytorch
$ conda install pyg -c pyg
$ pip install 
```

To run BGCfinder with a fasta file containing amino acid sequence with CPU,
```bash
python BGCfinder/main.py data/test_run.fasta -o test_run.tsv -l test_run.log -d False
```

To run BGCfinder with a fasta file containing amino acid sequence with GPU,
```bash
python BGCfinder/main.py data/test_run.fasta -o test_run.tsv -l test_run.log -d True
```

The development environment of BGCfinder : 
```
'torch==1.10.0',
'torch-geometric==2.0.2',
'torch-scatter==2.0.9',
'torch-sparse==0.6.12'
```


