arrp-dataset 1.0.0

Simple python tool to create dataset for arrps.

Simple python tool to render dataset that can be used for training models for active regulatory regions prediction.

How to get the dataset?

Just clone the repo.

How to get the package?

Just type into your terminal:

pip install arrp_dataset

Which genome does it use by default?

By default it uses hg19, as it is the genome used in the labeled data currently available from the Wasserman team.

Dependencies

This package will use the package bedtools to elaborate the bed files. A setup for the package is available here.

Rendering the dataset

Just type into your terminal:

python run.py