GPN — Genomic Pretrained Network

Quick start · Model families · Demos · Documentation

Code and resources for genomic language models GPN, GPN-MSA, PhyloGPN and GPN-Star.

Quick start

pip install gpn

Load GPN-Star, our latest model, with standard Transformers AutoClasses:

from gpn import register_auto_classes
from transformers import AutoModelForMaskedLM

register_auto_classes("star")
model = AutoModelForMaskedLM.from_pretrained("songlab/gpn-star-hg38-v100-200m")

Explore the GPN-Star models, alignments, scores, and benchmark datasets.

Model families

Command line

Install file-backed inference dependencies with pip install "gpn[inference]" or training dependencies with pip install "gpn[train]".

gpn ss {train,vep,logits,embedding} ...
gpn msa {vep,logits,embedding} ...
gpn star {train,vep,logits,embedding} ...

See the CLI guide for inputs, outputs, and multi-GPU inference.

Training

GPN and GPN-Star can be trained on prepared data using the maintained GPN and GPN-Star recipes.

Demos

• Precomputed GPN-Star scores ·
• GPN-Star ·
• GPN ·
• PhyloGPN ·

Historical analyses

The paper analyses and retired research workflows are preserved in the analysis-archive-2026-08-18 archive.

Development and help

See the documentation, ask questions in Discussions, or report problems in Issues.

GPN is developed in the Song Lab at UC Berkeley and distributed under the MIT License.

Citation

GPN:

@article{benegas2023dna,
  title={DNA language models are powerful predictors of genome-wide variant effects},
  author={Benegas, Gonzalo and Batra, Sanjit Singh and Song, Yun S},
  journal={Proceedings of the National Academy of Sciences},
  volume={120},
  number={44},
  pages={e2311219120},
  year={2023},
  publisher={National Acad Sciences}
}

GPN-MSA:

@article{benegas2025dna,
  title={A DNA language model based on multispecies alignment predicts the effects of genome-wide variants},
  author={Benegas, Gonzalo and Albors, Carlos and Aw, Alan J and Ye, Chengzhong and Song, Yun S},
  journal={Nature Biotechnology},
  pages={1--6},
  year={2025},
  publisher={Nature Publishing Group US New York}
}

PhyloGPN:

@inproceedings{albors2025phylogenetic,
  title={A Phylogenetic Approach to Genomic Language Modeling},
  author={Albors, Carlos and Li, Jianan Canal and Benegas, Gonzalo and Ye, Chengzhong and Song, Yun S},
  booktitle={International Conference on Research in Computational Molecular Biology},
  pages={99--117},
  year={2025},
  organization={Springer}
}

GPN-Star:

@article{ye2025predicting,
  title={Predicting functional constraints across evolutionary timescales with phylogeny-informed genomic language models},
  author={Ye, Chengzhong and Benegas, Gonzalo and Albors, Carlos and Li, Jianan Canal and Prillo, Sebastian and Fields, Peter D and Clarke, Brian and Song, Yun S},
  journal={bioRxiv},
  pages={2025--09},
  year={2025},
  publisher={Cold Spring Harbor Laboratory}
}

Sorghum gene expression prediction:

@article{groover2026mapping,
  title={Mapping cis-regulatory mutations at scale in sorghum enables modulation of gene expression},
  author={Groover, Evan D and Ding, David and Wang, Flora Z and Benegas, Gonzalo and Rivera, Joseph and Schwartz, Shahar and Chen, Stephen and Moubarak, Michael F and Georgieva, Viktoriya and Lemaux, Peggy G and others},
  journal={Nature Biotechnology},
  pages={1--11},
  year={2026},
  publisher={Nature Publishing Group US New York}
}