This is the official implementation of the ICML 2025 poster paper "SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model".

Usage

You should first download the source code from github:

git clone https://github.com/ZhuJiwei111/SPACE
cd SPACE

Then you can access the model through:

from model.modeling_space import Space

model_name_or_path = "yangyz1230/space"
model = Space.from_pretrained(model_name_or_path)

Citation

@misc{yang2025spacegenomicprofilepredictor,
      title={SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model}, 
      author={Zhao Yang and Jiwei Zhu and Bing Su},
      year={2025},
      eprint={2506.01833},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2506.01833}, 
}
Downloads last month
22
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Dataset used to train yangyz1230/space