This is repo containing all advanced De Novo peptide sequencing models developed by Beam Lab.
It includes:
| Model | Model Checkpoint | Category | Brief Introduction |
|---|---|---|---|
| ContraNovo | ContraNovo | AT | Autoregressive multimodal contrastive learning model for de novo sequencing. |
| PrimeNovo | PrimeNovo | NAT | First NAT biological sequences model for fast sequencing. |
| RefineNovo | coming soon | NAT | An ultra-stable NAT model framework that can adapt to any data distributions. (most stable training so far, guaranteed successful training). |
| RankNovo | RankNovo | - | A framework for combining any set of de novo models for combined power of accurate predictions. |
(N)AT refers to (Non)-Autoregressive Transformer.
Test MGF File: Bacillus.10k.mgf
Feel free to open Issues or start a Discussion to share your results!
- [2025-05] RefineNovo and RankNovo have been accepted by ICML'2025. 🎉
- [2024-11] PrimeNovo has been accepted by Nature Communications. 🎉
- [2023-12] ContraNovo has been accepted by AAAI'2024. 🎉
Refer to AT Denovo for AT denovo environment preparation.
Refer to NAT Denovo for NAT denovo environment preparation.
Refer to RankNovo for RankNovo environment preparation.
If you use this project, please cite:
@inproceedings{jin2024contranovo,
title={Contranovo: A contrastive learning approach to enhance de novo peptide sequencing},
author={Jin, Zhi and Xu, Sheng and Zhang, Xiang and Ling, Tianze and Dong, Nanqing and Ouyang, Wanli and Gao, Zhiqiang and Chang, Cheng and Sun, Siqi},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={38},
number={1},
pages={144--152},
year={2024}
}
@article{zhang2025pi,
title={$\pi$-PrimeNovo: an accurate and efficient non-autoregressive deep learning model for de novo peptide sequencing},
author={Zhang, Xiang and Ling, Tianze and Jin, Zhi and Xu, Sheng and Gao, Zhiqiang and Sun, Boyan and Qiu, Zijie and Wei, Jiaqi and Dong, Nanqing and Wang, Guangshuai and others},
journal={Nature Communications},
volume={16},
number={1},
pages={267},
year={2025},
publisher={Nature Publishing Group UK London}
}
@article{zhang2025curriculum,
title={Curriculum Learning for Biological Sequence Prediction: The Case of De Novo Peptide Sequencing},
author={Zhang, Xiang and Wei, Jiaqi and Qiu, Zijie and Xu, Sheng and Dong, Nanqing and Gao, Zhiqiang and Sun, Siqi},
journal={arXiv preprint arXiv:2506.13485},
year={2025}
}
@article{qiu2025universal,
title={Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing},
author={Qiu, Zijie and Wei, Jiaqi and Zhang, Xiang and Xu, Sheng and Zou, Kai and Jin, Zhi and Gao, Zhiqiang and Dong, Nanqing and Sun, Siqi},
journal={arXiv preprint arXiv:2505.17552},
year={2025}
}