Metadata-Version: 2.4
Name: paras
Version: 2.0.0
Summary: Predictive algorithm for resolving A-domain specificity featurising enzyme and compound in tandem.
Home-page: https://github.com/BTheDragonMaster/parasect
Author: Barbara Terlouw
Author-email: barbara.terlouw@wur.nl
Maintainer: David Meijer
Maintainer-email: david.meijer@wur.nl
Keywords: paras,parasect,non-ribosomal peptide,substrate specificity,prediction
Classifier: Development Status :: 1 - Planning
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Framework :: Pytest
Classifier: Framework :: tox
Classifier: Framework :: Sphinx
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3 :: Only
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE.txt
Requires-Dist: scipy
Requires-Dist: biopython
Requires-Dist: joblib
Requires-Dist: pikachu-chem
Requires-Dist: numpy==1.23.0
Requires-Dist: scikit-learn==1.2.0
Requires-Dist: ncbi-acc-download>=0.2.5
Requires-Dist: sqlalchemy
Requires-Dist: iterative-stratification==0.1.9
Requires-Dist: imblearn
Requires-Dist: pandas
Requires-Dist: seaborn
Provides-Extra: tests
Requires-Dist: coverage; extra == "tests"
Requires-Dist: pytest; extra == "tests"
Requires-Dist: tox; extra == "tests"
Dynamic: license-file

# PARASECT

Welcome to PARASECT: Predictive Algorithm for Resolving A-domain Specificity featurising Enzyme and Compound in Tandem. Detect NRPS AMP-binding domains from an amino acid sequence and predict their substrate specificity profile.

## Web application

You can find a live version of the web application [here](https://paras.bioinformatics.nl/).

## Database

Browse the data that PARAS and PARASECT were trained on [here](https://paras.bioinformatics.nl/query_database).

## Data submission

Do you have new datapoints that you think PARAS/PARASECT could benefit from in future versions? Submit your data [here](https://paras.bioinformatics.nl/data_annotation).

## Trained models

The trained models for PARAS and PARASECT can be found on Zenodo [here](https://zenodo.org/records/13165500).

## Command line installation

To install PARAS/PARASECT on the command line, run:

```angular2html
conda create -n paras python=3.9
conda activate paras

pip install paras
conda install -c bioconda hmmer
conda install -c bioconda hmmer2
conda install -c bioconda muscle==3.8.1551
```

For usage instructions, see our [wiki](https://github.com/BTheDragonMaster/parasect/wiki).
Note that the command line tool will download the models from zenodo upon the first run.
