Metadata-Version: 1.2
Name: stVAE
Version: 0.1
Summary: Style transfer variational autoencoder
Home-page: https://github.com/NRshka/stvae/source
Author: ['N. Russkikh', 'A. Makarov', 'D. Antonets', 'D. Shtokalo']
Author-email: makarov.alxr@yandex.ru
License: MIT license
Description: # stvae-source
        [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
        [![Build Status](https://travis-ci.org/NRshka/stvae-source.svg?branch=master)](https://travis-ci.org/NRshka/stvae-source)
        
        This repository contains the code for training and evaluating adversarial style transfer models on gene expression data from paper "Style transfer with variational autoencoders is a promising approach to RNA-Seq data harmonization and analysis" by  N. Russkikh, D. Antonets,  D. Shtokalo, A. Makarov, A. Zakharov, E. Terentyev. The paper is accessible by link
         https://t.co/sbjHbSzocn 
         
        The main script is run.py, which contains both training and testing procedures. Testing includes transferring the style of test set expression data to all possible style categories and evaluating the accuracy of prediction of style and pre-defined semantic categories by MLP trained on the raw expression data.
        
        Training hyperparameters can be set in config.py file
         
        
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
Classifier: Natural Language :: Russian
Classifier: Programming Language :: Python :: 3.7
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Requires-Python: >=3.6
