Skip to main content

Deep Multimodal Autoencoder

Project description

# deep-mae
Deep multi-modal autoencoder

# Installation
conda create -n mae tensorflow keras numpy scipy pandas scikit-bio biom-format
source activate mae
pip install git+

# Getting started

First split up your data into training and testing sets.
You can also use this to filter out features observed in few samples.
The number of examples that you would like to cross-validate against
can be specified by `num_test` as follows
``` split \
--otu-table-file data/otu.biom \
--metabolite-table-file data/ms.biom \
--num_test 20 \
--min_samples 10 \
--output_dir split_data

Once the data is splitted, you can then run the model and perform
``` autoencoder \
--otu-train-file split_data/train_otu.biom \
--metabolite-train-file split_data/train_ms.biom \
--otu-test-file split_data/test_otu.biom \
--metabolite-test-file split_data/test_ms.biom \
--summary-dir summary \
--results-file cv-results.csv \
--ranks-file ranks.csv

Finally we can use the results from the autoencoder to build a
network as follows
``` network \
--ranks-file ranks.csv \
--node-metadata cytoscape-nodes.txt \
--edge-metadata cytoscape-edges.sif

This information can be directly feed into cytoscape.

Project details

Release history Release notifications

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
minstrel-0.1.0.tar.gz (9.5 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page