Decoding ascitic immunological niches with multi-modal machine learning reveals prognostic and chemoresistant determinants in ovarian cancer
Integrating ascitic immunophenotyping with clinical factors improves risk prediction in HGSOC, with RSF offering robust performance under rigorous, leakage-safe validation. Ascites-resident T-cell states provide complementary, reproducible prognostic signals for survival and platinum response, supporting their potential utility for patient stratification and hypothesis generation for immunomodulatory strategies.
Authors
- Xiaolan Zhang (ORCID: https://orcid.org/0009-0003-0436-7360)
- Tianhui He (ORCID: https://orcid.org/0000-0002-2835-0702)
- Xinran Gao
- Lin Zeng (ORCID: https://orcid.org/0000-0001-8707-5854)
- Yufei Nie
- Qinkun Sun
- Yuelin Song (ORCID: https://orcid.org/0000-0001-8424-2418)
- Chunliang Shang (ORCID: https://orcid.org/0000-0003-0275-7894)
- Jing Wang (ORCID: https://orcid.org/0000-0003-1580-1356)
- Lin Yang (ORCID: https://orcid.org/0000-0002-1922-0519)
- Hongyan Guo (ORCID: https://orcid.org/0009-0005-8863-3236)
Institutions
- Peking University (CN)
- Massachusetts General Hospital (US)
- Peking University Third Hospital (CN)
- Center for Cancer Research (US)
Publication Details
- Journal
- Frontiers in Immunology
- Published
- 2025-12-03
- DOI
- https://doi.org/10.3389/fimmu.2025.1698793
- Primary Topic
- Ferroptosis and cancer prognosis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Peking University
- Peking University Third Hospital
- National Key Research and Development Program of China