References

This package is based on the core research and methods developed for Genos, a framework for genomic sequence modeling and analysis.

If you use Genos SDK or its models in your research or production work, please cite the following publications:

Primary Paper

Genos: A Human-Centric Genomic Foundation Model

Adi Lin¹, Bin Xie¹, Cheng Ye¹,Cheng Wang¹, Duoyuan Chen¹, Ercheng Wang¹, Fanfeng Lu¹, Guirong Xue¹, Haiqiang Zhang¹, Jiajie Zhan¹, Jianfeng Zhang¹, Jiangshuan Pang¹, Jianqiang Liang¹, Jiawei Lin¹, Jiaxin Ma¹, Jie Hu¹, Jing Ma¹,Jingni Dong¹, Jiongzhen Li, Junchen Liu¹, Junhong Chen¹, Junyou Li¹, Kai Ding¹, Kaiwen Deng¹, Kui Chen¹, Lihui Wang¹, Longqi Liu¹, Ling Guo¹, Liwen Xiong¹, Luhao Yang¹, Ming Cheng¹, Nanning Chen¹, Renzhong Chen¹, Shanxin Sun¹, Shaoshuai Li¹, Shicheng Chen¹, Shiping Liu¹, Siwei Xie¹, Suyan Liu¹, Tao Zhou¹, Wangyang Tang¹, Weiqiang Zhang¹, Xianyue Jiang¹, Xianzhi Qi¹, Xin Jin¹, Xinjiang Tan¹, Xinyue Hu¹, Xun Xu¹, Xuyang Feng¹, Yafei Lu¹ ,Yifan Gao¹, Yong Shang¹, Youzhe He¹, Yue Yuan¹, Yufan Wang¹, Yuqi Liu1, Zhan Xiao¹, Zhangyuan Meng¹, Zhaorong Li¹, Zhe Zhao¹, Zheng Yang¹, Zilin Wang¹

GigaScience, 2025. https://doi.org/10.1093/gigascience/giaf132

Related Works

[1] The Human Genome Project. (2003). Finishing the euchromatic sequence of the human genome. Nature, 431(7011), 931 - 945.

[2] 1000 Genomes Project Consortium. (2010). A map of human genome variation from population - scale sequencing. Nature, 467(7319), 1061 - 1073.

[3] Grešová, K., Martinek, V., Čechák, D., Šimeček, P. & Alexiou, P. Genomic benchmarks: a collection of datasets for genomic sequence classification. BMC Genomic Data 24, (2023).

[4] Dalla-Torre, H. et al. Nucleotide Transformer: building and evaluating robust foundation models for human genomics. Nature Methods (2024) doi:10.1038/s41592-024-02523-z.

[5] Trop, E. et al. The Genomics Long-Range Benchmark: Advancing DNA Language Models. OpenReview https://openreview.net/forum?id=8O9HLDrmtq.

[6] Gao, Y. et al. A pangenome reference of 36 Chinese populations. Nature 619, 112–121 (2023).

[7] Fallahpour, Adibvafa, et al. BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model. arXiv preprint arXiv:2505.23579 (2025).

[8] Liao, W.W. et al. A draft human pangenome reference. Nature 617, 312–324 (2023). —

How to Cite

If you use the SDK, please include the following citation in your work:

 @article{he2025genos,
title   = {Genos: A Human-Centric Genomic Foundation Model},
author  = {Adi Lin¹, Bin Xie¹, Cheng Ye¹,Cheng Wang¹, Duoyuan Chen¹, Ercheng Wang¹, Fanfeng Lu¹, Guirong Xue¹, Haiqiang Zhang¹, Jiajie Zhan¹, Jianfeng Zhang¹, Jiangshuan Pang¹, Jianqiang Liang¹, Jiawei Lin¹, Jiaxin Ma¹, Jie Hu¹, Jing Ma¹,Jingni Dong¹, Jiongzhen Li, Junchen Liu¹, Junhong Chen¹, Junyou Li¹, Kai Ding¹, Kaiwen Deng¹, Kui Chen¹, Lihui Wang¹, Longqi Liu¹, Ling Guo¹, Liwen Xiong¹, Luhao Yang¹, Ming Cheng¹, Nanning Chen¹, Renzhong Chen¹, Shanxin Sun¹, Shaoshuai Li¹, Shicheng Chen¹, Shiping Liu¹, Siwei Xie¹, Suyan Liu¹, Tao Zhou¹, Wangyang Tang¹, Weiqiang Zhang¹, Xianyue Jiang¹, Xianzhi Qi¹, Xin Jin¹, Xinjiang Tan¹, Xinyue Hu¹, Xun Xu¹, Xuyang Feng¹, Yafei Lu¹ ,Yifan Gao¹, Yong Shang¹, Youzhe He¹, Yue Yuan¹, Yufan Wang¹, Yuqi Liu1, Zhan Xiao¹, Zhangyuan Meng¹, Zhaorong Li¹, Zhe Zhao¹, Zheng Yang¹, Zilin Wang¹},
journal = {GigaSience},
year    = {2025},
doi     = {10.1093/gigascience/giaf132}

}

Acknowledgements

Genos SDK builds upon the open-source ecosystems of:

• PyTorch

• Hugging Face Transformers

• Megatron-LM

We thank these projects for their contributions to the open science community.