Metadata-Version: 2.1
Name: deepconpkg
Version: 0.0.2
Summary: Protein Contact Prediction using Dilated Convolutional Neural Networks with Dropout
Home-page: https://github.com/Chaserich1/deepconpkg
Author: Badri Adhikari
Author-email: adhikarib@umsl.edu
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python
Classifier: License :: OSI Approved :: MIT License
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: pyYAML
Requires-Dist: tensorflow
Requires-Dist: keras

## DEEPCON: Protein Contact Prediction using Dilated Convolutional Neural Networks with Dropout  


#### Contact:
Email: adhikarib@umsl.edu  
Homepage: https://badriadhikari.github.io/  
Paper: https://www.biorxiv.org/content/10.1101/590455v1 

### DEEPCON using Covariance features as input

Trained and validated using the 3456 proteins in the DeepCov dataset with the covariance features (441 channels) as input.


#### Installation Instructions:


You need a deep learing backend that is Keras compatible:

    pip3 install -U tensorflow
    pip3 install pyyaml

Install DEEPCON-Covariance package

    pip3 install deepcon


#### Intstructions for User:

Inside Python:

	import deepcon


#### Predict
```bash
python ../deepcon-covariance.py --aln ./16pkA0.aln --rr ./16pkA0.rr
```

#### Evaluate
```bash
./coneva-lite.pl -pdb ./16pkA.pdb -rr ./16pkA0.rr
```



