torch-adata 0.0.14

torch-adata

Create pytorch Datasets from AnnData

Installation

Install from PYPI:

pip install torch-adata

Install the developer version:

git clone https://github.com/mvinyard/torch-adata.git; cd torch-adata;
pip install -e .

Example use of the base class

The base class, AnnDataset is a subclass of the widely-used torch.utils.data.Dataset.

import anndata as a
import torch_adata

adata = a.read_h5ad("/path/to/data.h5ad")
dataset = torch_adata.AnnDataset(adata)

Returns sampled data X_batch as a torch.Tensor.

# create a dummy index
idx = np.random.choice(range(dataset.__len__()), 5)
X_batch = dataset[idx]

TimeResolvedAnnDataset

Specialized class for time-resolved datasets. A subclass of the class, AnnDataset.

import anndata as a
import torch_adata as ta

adata = a.read_h5ad("/path/to/data.h5ad")
dataset = torch_adata.TimeResolvedAnnDataset(
    adata,
    time_key="Time point",
    use_key="X_pca",
    obs_key="weight_key",
    return_t=True,
)

When return_t == True:

X, y, t = dataset[idx]

When return_t == False:

X, y = dataset[idx]