deepbiome 1.0.0

Deep Learning package using the phylogenetic tree information for microbiome data analysis.

Deep Learning package using the phylogenetic tree information for microbiome abandunce data analysis.

• Free software: 3-clause BSD license

• Documentation: https://Young-won.github.io/deepbiome

Installation

Prerequisites

• python >= 3.5

• Tensorflow

• Keras

Install DeepBiome

At the command line:

# for python 3.x

$ pip3 install git+https://github.com/Young-won/deepbiome.git

Features

• deepbiome.deepbiome_train(log, network_info, path_info, number_of_fold=None, max_queue_size=10, workers=1, use_multiprocessing=False)

  Function for training the deep neural network with phylogenetic tree weight regularizer.

  It uses microbiome abundance data as input and uses the phylogenetic taxonomy to guide the decision of the optimal number of layers and neurons in the deep learning architecture.

• deepbiome.deepbiome_test(log, network_info, path_info, number_of_fold=None, max_queue_size=10, workers=1, use_multiprocessing=False)

  Function for testing the pretrained deep neural network with phylogenetic tree weight regularizer.

  If you use the index file, this function provide the evaluation using test index (index set not included in the index file) for each fold. If not, this function provide the evaluation using the whole samples.

• deepbiome.deepbiome.deepbiome_prediction(log, network_info, path_info, num_classes, number_of_fold=None, max_queue_size=10, workers=1, use_multiprocessing=False)

  Function for prediction by the pretrained deep neural network with phylogenetic tree weight regularizer.

Credits

This package was builded on the Keras and the Tensorflow packages.

This package was created with Cookiecutter and the NSLS-II/scientific-python-cookiecutter project template.