GLM-Nullsette-Benchmark

This is a repository of scripts for reproducing benchmarking GLM on Nullsette.

Installation

git clone https://github.com/cellethology/GLM-Nullsette-Benchmark.git
cd GLM-Nullsette-Benchmark
conda env create -f environment.yml
conda activate glm_eval

Inference data

Example data is in data/ directory. For inference data used in the paper, please unzip the data/processed_data.zip file.

Expression cassette data

You will find expression cassette data stored in database directory. It can be easily imported using the following script.

from database import deboer_database, zahm_database, kosuri_database, lagator_database

Model inference script

Inference script for several representation models are in model directory.

Acknowledgements

We acknowledge the valuable contributions to genomic language modeling made by the authors of the following repositories: Evo1, Evo2, Nucleotide Transformer, DNABERT-2, GENERator, METAGENE-1, Caduceus, GPN, GENA-LM, gLM2, PDLLM.