Metadata-Version: 2.4
Name: seqchromloader
Version: 0.12.4
Summary: Utilities for training DL models using DNA sequence and chromatin inputs
Home-page: https://github.com/yztxwd/seqchromloader
Author-email: Jianyu Yang <yztxwd@gmail.com>
License-Expression: MIT AND (Apache-2.0 OR BSD-2-Clause)
Project-URL: Homepage, https://github.com/seqcode/seqchromloader
Keywords: interpretation,attribution,concept,genomics,deep learning
Requires-Python: <3.14,>=3.8
Description-Content-Type: text/markdown
Requires-Dist: biopython>=1.8.0
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: pyfaidx>=0.7.0
Requires-Dist: pybedtools>=0.9.0
Requires-Dist: pysam>=0.19.0
Requires-Dist: pybigwig>=0.3.0
Requires-Dist: torch>=1.10.0
Requires-Dist: webdataset>=0.2.0
Dynamic: home-page

# seqchromloader

seqchromloader aims to provide versatile and ready-to-use writer/loader for applying deep learning to bioinformatics study.

Plan to support dataset formats including:
- webdataset (done)
- tfrecord (x)

Training framework support:
- pytorch dataloader (done)
- pytorch-lightning datamodule (done)
- NVIDIA-DALI (x)

## Installation

### conda (suggested):

`mamba install -c bioconda -c conda-forge seqchromloader`

or

`conda install -c bioconda -c conda-forge seqchromloader`

### pip

`pip install seqchromloader`

## Usage

For detailed usage, please refer to [documentation](https://seqchromloader.readthedocs.io/en/latest/)
