The official pytorch implementation of “Style transfer with variational autoencoders is a promising approach to RNA-Seq data harmonization and analysis”. The package contains a code for training and testing the model, as well as a code for working with different types of datasets.
Installation
To install the latest version from PyPI, use:
>>> pip install stvae
Benchmarks
The original code containing code with testing several models can be found here.
Example
ds = stvae.datasets.MouseDataset(download=True) # download data to the current directory
cfg = stvae.Config()
train, test, classif = ds.split(0.15, True, 0.15)
cfg.count_classes = ds.n_labels
cfg.count_classes = ds.n_batches
cfg.input_dim = ds.nb_genes
cfg.use_cuda = True # if you have a CUDA compatibility gpu
cfg.epochs = 600 # number of training epocs
cfg.classifier_epochs = 450 # number of epochs for testing classifirs training
model = stvae.stVAE(cfg)
model.train(train, None)
d = model.test(test, classif)1 maintainer
Release files for stVAE 0.2.10
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| stVAE-0.2.10.tar.gz | 33.5 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| stVAE-0.2.10-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 73.5 kB
Release files / stVAE-0.2.10.tar.gz
| Download URL | stVAE-0.2.10.tar.gz |
|---|---|
| Size | 33.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1f0c1c2e0fca3feb5c00c09b70282016f872d7649ef569a01fa4183721e09485
|
|
BLAKE2b-256 checksum How to use checksums |
0ef3a7ff19bff1cde5538ee214fe97302799c826c3b1ea773fddfb055bdfdb97
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.7.0 requests/2.25.1 setuptools/52.0.0.post20210125 requests-toolbelt/0.8.0 tqdm/4.61.1 CPython/3.8.3
|
Release files / stVAE-0.2.10-py3-none-any.whl
| Download URL | stVAE-0.2.10-py3-none-any.whl |
|---|---|
| Size | 40.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b3e0d1fd7df67f9f5cfadfa4b7ff6a4b54bb36d13718e748286514eac45273ad
|
|
BLAKE2b-256 checksum How to use checksums |
f9320bf2a0516d0a49e92c383146b1da7073b5dca7557bc5ba0139435645260f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.7.0 requests/2.25.1 setuptools/52.0.0.post20210125 requests-toolbelt/0.8.0 tqdm/4.61.1 CPython/3.8.3
|
