regLM

regLM is a toolkit for training hyenaDNA-based autoregressive language models on DNA sequences and generating novel regulatory elements.

regLM schematic

Documentation

Documentation

Tutorials

Tutorials

Installation

1. Install HyenaDNA

To use regLM, first install HyenaDNA from GitHub following the instructions: https://github.com/HazyResearch/hyena-dna

2. Install regLM

git clone https://github.com/Genentech/regLM.git
cd regLM
pip install .

Preprint

https://www.biorxiv.org/content/10.1101/2024.02.14.580373

Code used to perform the experiments in the regLM paper, along with trained model weights and synthetic sequences, are available at Zenodo.