Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.00087 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915366322569216 |
|---|---|
| author | Zhao, Jiale Mao, Pengzhi Wang, Kaifei Li, Yiming Peng, Yaping Chen, Ranfei Lu, Shuqi Ji, Xiaohong Ding, Jiaxiang Zhang, Xin Liao, Yucheng E, Weinan Zhang, Weijie Wen, Han Chi, Hao |
| author_facet | Zhao, Jiale Mao, Pengzhi Wang, Kaifei Li, Yiming Peng, Yaping Chen, Ranfei Lu, Shuqi Ji, Xiaohong Ding, Jiaxiang Zhang, Xin Liao, Yucheng E, Weinan Zhang, Weijie Wen, Han Chi, Hao |
| contents | Deep learning has advanced mass spectrometry data interpretation, yet most models remain feature extractors rather than unified scoring frameworks. We present pUniFind, the first large-scale multimodal pre-trained model in proteomics that integrates end-to-end peptide-spectrum scoring with open, zero-shot de novo sequencing. Trained on over 100 million open search-derived spectra, pUniFind aligns spectral and peptide modalities via cross modality prediction and outperforms traditional engines across diverse datasets, particularly achieving a 42.6 percent increase in the number of identified peptides in immunopeptidomics. Supporting over 1,300 modifications, pUniFind identifies 60 percent more PSMs than existing de novo methods despite a 300-fold larger search space. A deep learning based quality control module further recovers 38.5 percent additional peptides including 1,891 mapped to the genome but absent from reference proteomes while preserving full fragment ion coverage. These results establish a unified, scalable deep learning framework for proteomic analysis, offering improved sensitivity, modification coverage, and interpretability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00087 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | pUniFind: a unified large pre-trained deep learning model pushing the limit of mass spectra interpretation Zhao, Jiale Mao, Pengzhi Wang, Kaifei Li, Yiming Peng, Yaping Chen, Ranfei Lu, Shuqi Ji, Xiaohong Ding, Jiaxiang Zhang, Xin Liao, Yucheng E, Weinan Zhang, Weijie Wen, Han Chi, Hao Machine Learning Artificial Intelligence Deep learning has advanced mass spectrometry data interpretation, yet most models remain feature extractors rather than unified scoring frameworks. We present pUniFind, the first large-scale multimodal pre-trained model in proteomics that integrates end-to-end peptide-spectrum scoring with open, zero-shot de novo sequencing. Trained on over 100 million open search-derived spectra, pUniFind aligns spectral and peptide modalities via cross modality prediction and outperforms traditional engines across diverse datasets, particularly achieving a 42.6 percent increase in the number of identified peptides in immunopeptidomics. Supporting over 1,300 modifications, pUniFind identifies 60 percent more PSMs than existing de novo methods despite a 300-fold larger search space. A deep learning based quality control module further recovers 38.5 percent additional peptides including 1,891 mapped to the genome but absent from reference proteomes while preserving full fragment ion coverage. These results establish a unified, scalable deep learning framework for proteomic analysis, offering improved sensitivity, modification coverage, and interpretability. |
| title | pUniFind: a unified large pre-trained deep learning model pushing the limit of mass spectra interpretation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.00087 |