A deep learning framework for hepatocellular carcinoma diagnosis using MS1 data
Clinical proteomics analysis is of great significance for analyzing pathological mechanisms and discovering disease-related biomarkers. Using computational methods to accurately predict disease types can effectively improve patient disease diagnosis and prognosis. However, how to eliminate the errors introduced by peptide precursor identification and protein identification for pathological diagnosis remains a major unresolved issue. Here, we develop a powerful end-to-end deep learning model, termed "MS1Former", that is able to classify hepatocellular carcinoma tumors and adjacent non-tumor (normal) tissues directly using raw MS1 spectra without peptide precursor identification. Our model provides accurate discrimination of subtle m/z differences in MS1 between tumor and adjacent non-tumor tissue, as well as more general performance predictions for data-dependent acquisition, data-independent acquisition, and full-scan data. Our model achieves the best performance on multiple external validation datasets. Additionally, we perform a detailed exploration of the model's interpretability. Prospectively, we expect that the advanced end-to-end framework will be more applicable to the classification of other tumors.
Authors
- Xiaoping Zheng (ORCID: https://orcid.org/0000-0002-7556-130X)
- Xiaoliang Qian (ORCID: https://orcid.org/0000-0002-4328-6411)
- Kunkai Su (ORCID: https://orcid.org/0000-0001-7075-3153)
- Bin Ju (ORCID: https://orcid.org/0000-0003-0768-6327)
- Yinjia Wang
- Wei Xu (ORCID: https://orcid.org/0000-0001-8005-4372)
- Keda Yang (ORCID: https://orcid.org/0000-0002-3470-0414)
- Nannan Sun (ORCID: https://orcid.org/0000-0002-5255-9784)
- Liying Zhang (ORCID: https://orcid.org/0000-0003-3276-8009)
- Dengfeng Zhou (ORCID: https://orcid.org/0009-0005-5654-3973)
- Xiao Tu (ORCID: https://orcid.org/0000-0002-6482-5138)
- Jia Chen (ORCID: https://orcid.org/0009-0003-4685-8125)
- Zewen Xie
- Shugang Qu
- Tao He
- Shan Feng
Institutions
- Zhejiang Chinese Medical University (CN)
- Westlake University (CN)
- Abterra Biosciences (United States) (US)
- The First Hospital of Kunming (CN)
- Zhejiang Shuren University (CN)
- Hangzhou Red Cross Hospital (CN)
- First Affiliated Hospital Zhejiang University (CN)
- State Key Laboratory of Diagnosis and Treatment of Infectious Diseases
- Zhejiang University (CN)
Publication Details
- Journal
- Scientific Reports
- Published
- 2024-11-04
- DOI
- https://doi.org/10.1038/s41598-024-77494-4
- Citations
- 3
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 1.04
Funders
- Westlake University
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities