Metadata-Version: 2.4
Name: cell-load
Version: 0.7.1
Summary: Dataloaders for training models on huge single-cell datasets
Author-email: Abhinav Adduri <abhinav.adduri@arcinstitute.org>, Yusuf Roohani <yusuf.roohani@arcinstitute.org>, Noam Teyssier <noam.teyssier@arcinstitute.org>
License-File: LICENSE
Requires-Python: <3.13,>=3.10
Requires-Dist: anndata>=0.9.1
Requires-Dist: lightning>=2.0.0
Requires-Dist: toml>=0.10.2
Requires-Dist: torch>=1.13.0
Description-Content-Type: text/markdown

# cell-load

> Dataloaders for state-sets models

## Installation

Distributed via [`uv`](https://docs.astral.sh/uv).

```bash
uv pip install cell-load
```

## Data Module Usage

This is currently set up to do context generalization - users can specify multiple AnnData files,
and can identify specific cell lines to add to the test set. For those test cell lines, users can
identify specific perturbations to hold out for testing.

For example usage please see the [`State`](https://github.com/ArcInstitute/state) repository.
