Abstract
This study developed and validated a mitochondrial apoptosis-related pathology transfer learning model (MAR-PTL) for ovarian cancer prognosis by integrating digital pathology features with mitochondrial apoptosis gene expression. We constructed a transfer learning framework combining deep learning features extracted from H&E slides using ResNet50 architecture with transcriptomic data. Patients were categorized into high- and low-risk groups based on model-generated risk scores, and functional enrichment analysis along with single-cell RNA sequencing were performed to elucidate underlying mechanisms. The MAR-PTL model demonstrated superior prognostic performance (C-index = 0.78) compared to conventional methods. Notably, BCL2L2 emerged as the core prognostic gene, showing significant correlations with specific ResNet features, including a negative correlation with ResNet592 and positive correlations with ResNet373, 737, and 938. Mechanistically, high-risk groups exhibited downregulated ribosomal pathways and upregulated immune-inflammatory pathways. Furthermore, single-cell analysis revealed that BCL2L2 + tumor cells displayed distinct metabolic profiles enriched in respirasome assembly pathways and preferentially interacted with fibroblasts and endothelial cells via MDK-NCL and PPIA-BSG ligand-receptor pairs. Collectively, the MAR-PTL model provides a novel approach for prognostication by capturing the interplay between mitochondrial apoptosis and pathological features, identifying BCL2L2 as a key regulator of progression through metabolic reprogramming and tumor-stromal interactions, thereby offering potential therapeutic targets for high-risk patients.
Data availability
All data generated or analyzed during this study are included in this article.
References
Wang, C-W. et al. ATEC23 challenge: automated prediction of treatment effectiveness in ovarian cancer using histopathological images. Med. Image Anal. 99, 103342. https://doi.org/10.1016/j.media.2024.103342 (2025).
Casey, N. P. et al. Efficient CAR T cell targeting of the CA125 extracellular repeat domain of MUC16. J. ImmunoTher Cancer. 12, e008179. https://doi.org/10.1136/jitc-2023-008179 (2024).
Sekar, Y., Ishwar, D., Tan, B. & Venkatakrishnan, K. Nano biosensor unlocks tumor derived immune signals for the early detection of ovarian cancer. Biosens. Bioelectron. 278, 117368. https://doi.org/10.1016/j.bios.2025.117368 (2025).
Smith, A. J. B. et al. Cancer antigen 125 levels at time of ovarian cancer diagnosis by race and ethnicity. JAMA Netw. Open. 8, e251292. https://doi.org/10.1001/jamanetworkopen.2025.1292 (2025).
Salas-Lloret, D. et al. BRCA1/BARD1 ubiquitinates PCNA in unperturbed conditions to promote continuous DNA synthesis. Nat. Commun. 15, 4292. https://doi.org/10.1038/s41467-024-48427-6 (2024).
Gjorgoska, M. & Rižner, T. L. From fallopian tube epithelium to high-grade serous ovarian cancer: a single-cell resolution review of sex steroid hormone signaling. Prog Lipid Res. 96, 101302. https://doi.org/10.1016/j.plipres.2024.101302 (2024).
Li, W. et al. Halofuginone disrupted collagen deposition via mTOR-eIF2α-ATF4 axis to enhance chemosensitivity in ovarian cancer. Adv. Sci. (weinh Baden-wurtt Ger) https://doi.org/10.1002/advs.202416523 (2025).
Spear, S. et al. PTEN loss shapes macrophage dynamics in high-grade serous ovarian carcinoma. Cancer Res. 84, 3772–3787. https://doi.org/10.1158/0008-5472.CAN-23-3890 (2024).
Sun, C. et al. Targeting platinum-resistant ovarian cancer by disrupting histone and RAD51 lactylation. Theranostics 15, 3055–3075. https://doi.org/10.7150/thno.104858 (2025).
Chen, S. et al. Folate-targeted nanoparticles for glutamine metabolism Inhibition enhance anti-tumor immunity and suppress tumor growth in ovarian cancer. J. Control Release: Off J. Control Release Soc. 379, 89–104. https://doi.org/10.1016/j.jconrel.2024.12.073 (2025).
Dai, W., Zhou, J. & Chen, T. Unraveling the extracellular vesicle network: insights into ovarian cancer metastasis and chemoresistance. Mol. Cancer. 23, 201. https://doi.org/10.1186/s12943-024-02103-x (2024).
Zhao, Y., Agyemang, D., Liu, Y., Mahoney, M. & Li, S. Quantifying interpretation reproducibility in vision transformer models with TAVAC. Sci. Adv. 10, eabg0264. https://doi.org/10.1126/sciadv.abg0264 (2024).
Pizurica, M. et al. Digital profiling of gene expression from histology images with linearized attention. Nat. Commun. 15, 9886. https://doi.org/10.1038/s41467-024-54182-5 (2024).
Chen, Y. et al. Convolutional neural network quantification of Gleason pattern 4 and association with biochemical recurrence in intermediate-grade prostate tumors. Mod. Pathol: Off J. U S Can. Acad. Pathol. Inc. 36, 100157. https://doi.org/10.1016/j.modpat.2023.100157 (2023).
Cho, H. et al. A nuclei-focused strategy for automated histopathology grading of renal cell carcinoma. IEEE J. Biomed. Health Inform. https://doi.org/10.1109/JBHI.2024.3487004 (2024).
Ding, H. et al. ContransGAN: convolutional neural network coupling global swin-transformer network for high-resolution quantitative phase imaging with unpaired data. Cells 11, 2394. https://doi.org/10.3390/cells11152394 (2022).
Huang, K-B. et al. A multi-classifier system integrated by clinico-histology-genomic analysis for predicting recurrence of papillary renal cell carcinoma. Nat. Commun. 15, 6215. https://doi.org/10.1038/s41467-024-50369-y (2024).
Rühl, S. et al. Inhibition of BAK-mediated apoptosis by the BH3-only protein BNIP5. Cell. Death Differ. 32, 320–336. https://doi.org/10.1038/s41418-024-01386-3 (2025).
Srivastava, S. et al. Structural basis of BAK sequestration by MCL-1 in apoptosis. Mol. Cell. https://doi.org/10.1016/j.molcel.2025.03.013 (2025). S1097-2765(25)251-5.
Wei, H. et al. Deciphering molecular specificity in MCL-1/BAK interaction and its implications for designing potent MCL-1 inhibitors. Cell. Death Differ. https://doi.org/10.1038/s41418-025-01454-2 (2025).
Diepstraten, S. T. et al. Putting the STING back into BH3-mimetic drugs for TP53-mutant blood cancers. Cancer Cell. 42, 850–868e9. https://doi.org/10.1016/j.ccell.2024.04.004 (2024).
Zhu, Y. et al. Carnitine palmitoyltransferase 1A promotes mitochondrial fission by enhancing MFF succinylation in ovarian cancer. Commun. Biol. 6, 618. https://doi.org/10.1038/s42003-023-04993-x (2023).
Kolozali, S., White, S. L., Norris, S., Fasli, M. & van Heerden, A. Explainable early prediction of gestational diabetes biomarkers by combining medical background and wearable devices: A pilot study with a cohort group in South Africa. IEEE J. Biomed. Health Inf. 28, 1860–1871. https://doi.org/10.1109/JBHI.2024.3361505 (2024).
Sun, D. et al. TISCH: A comprehensive web resource enabling interactive single-cell transcriptome visualization of tumor microenvironment. Nucleic Acids Res. 49, D1420–D1430. https://doi.org/10.1093/nar/gkaa1020 (2021).
Kanehisa, M., Furumichi, M., Sato, Y., Matsuura, Y. & Ishiguro-Watanabe, M. KEGG: biological systems database as a model of the real world. Nucleic Acids Res. 53, D672–D677. https://doi.org/10.1093/nar/gkae909 (2025).
Kanehisa, M. Toward Understanding the origin and evolution of cellular organisms. Protein Sci: Publ Protein Soc. 28, 1947–1951. https://doi.org/10.1002/pro.3715 (2019).
Yunyun, Z., Guihu, W. & An, J. Explore the expression of mitochondria-related genes to construct prognostic risk model for ovarian cancer and validate it, so as to provide optimized treatment for ovarian cancer. Front. Immunol. 15, 1458264. https://doi.org/10.3389/fimmu.2024.1458264 (2024).
Chen, J. et al. Non-apoptotic cell death in ovarian cancer: treatment, resistance and prognosis. Biomed. Pharmacother = Biomed. Pharmacother. 150, 112929. https://doi.org/10.1016/j.biopha.2022.112929 (2022).
Liu, X. et al. Development of prognostic biomarkers by TMB-guided WSI analysis: a two-step approach. IEEE J. Biomed. Health Inf. 27, 1780–1789. https://doi.org/10.1109/JBHI.2023.3249354 (2023).
Chen, M., Wang, K. & Wang, J. Vision transformer-based multilabel survival prediction for oropharynx cancer after radiation therapy. Int. J. Radiat. Oncol. Biol. Phys. 118, 1123–1134. https://doi.org/10.1016/j.ijrobp.2023.10.022 (2024).
Xie, F. et al. Mutational profiling of mitochondrial DNA reveals an epithelial ovarian cancer-specific evolutionary pattern contributing to high oxidative metabolism. Clin. Transl Med. 14, e1523. https://doi.org/10.1002/ctm2.1523 (2024).
Zeng, W., Wang, M., Zhang, Y., Zhou, T. & Zong, Z. Targeting mitochondrial damage: shining a new light on immunotherapy. Front. Immunol. 15, 1432633. https://doi.org/10.3389/fimmu.2024.1432633 (2024).
Dumas, L. et al. RNA G-quadruplexes control mitochondria-localized mRNA translation and energy metabolism. Nat. Commun. 16, 3292. https://doi.org/10.1038/s41467-025-58118-5 (2025).
Kao, Y-R. & Will, B. The cost of competency? Cell 186, 685–687. https://doi.org/10.1016/j.cell.2023.01.010 (2023).
Feng, W-Q. et al. IL-17A-mediated mitochondrial dysfunction induces pyroptosis in colorectal cancer cells and promotes CD8 + T-cell tumour infiltration. J. Transl Med. 21, 335. https://doi.org/10.1186/s12967-023-04187-3 (2023).
Li, J. et al. Reactive oxygen species modulation in the current landscape of anticancer therapies. Antioxid. Redox Signal. 41, 322–341. https://doi.org/10.1089/ars.2023.0445 (2024).
Zhang, Y. et al. Complement C3 of tumor-derived extracellular vesicles promotes metastasis of RCC via recruitment of immunosuppressive myeloid cells. Proc. Natl. Acad. Sci. U S A. 122, e2420005122. https://doi.org/10.1073/pnas.2420005122 (2025).
Yue, B., Gao, W., Lovell, J. F., Jin, H. & Huang, J. The cGAS-STING pathway in cancer immunity: dual roles, therapeutic strategies, and clinical challenges. Essays Biochem. 69, EBC20253006. https://doi.org/10.1042/EBC20253006 (2025).
Janneh, A. H., Atkinson, C., Tomlinson, S. & Ogretmen, B. Sphingolipid metabolism and complement signaling in cancer progression. Trends Cancer. 9, 782–787. https://doi.org/10.1016/j.trecan.2023.07.001 (2023).
Del Bufalo, D. & Damia, G. Overview of BH3 mimetics in ovarian cancer. Cancer Treat. Rev. 129, 102771. https://doi.org/10.1016/j.ctrv.2024.102771 (2024).
Izumi, M. et al. Integrative single-cell RNA-seq and Spatial transcriptomics analyses reveal diverse apoptosis-related gene expression profiles in EGFR-mutated lung cancer. Cell. Death Dis. 15, 580. https://doi.org/10.1038/s41419-024-06940-y (2024).
Xing, Y. et al. Impact of mitochondrial damage on tumor microenvironment and immune response: A comprehensive bibliometric analysis. Front. Immunol. 15, 1442027. https://doi.org/10.3389/fimmu.2024.1442027 (2024).
Oh, J. M. et al. A micro-metabolic rewiring assay for assessing hypoxia-associated cancer metabolic heterogeneity. Bioact Mater. 48, 493–509. https://doi.org/10.1016/j.bioactmat.2025.02.030 (2025).
Jin, H-R. et al. Lipid metabolic reprogramming in tumor microenvironment: from mechanisms to therapeutics. J. Hematol. Oncol. 16, 103. https://doi.org/10.1186/s13045-023-01498-2 (2023).
Wang, X. et al. SLC1A1-mediated cellular and mitochondrial influx of R-2-hydroxyglutarate in vascular endothelial cells promotes tumor angiogenesis in IDH1-mutant solid tumors. Cell. Res. 32, 638–658. https://doi.org/10.1038/s41422-022-00650-w (2022).
Monroe, T. B. et al. Lipid peroxidation products induce carbonyl stress, mitochondrial dysfunction, and cellular senescence in human and murine cells. Aging Cell. 24, e14367. https://doi.org/10.1111/acel.14367 (2025).
Carvalho, R. F. et al. Single-cell and bulk RNA sequencing reveal ligands and receptors associated with worse overall survival in serous ovarian cancer. Cell. Commun. Signal: CCS. 20, 176. https://doi.org/10.1186/s12964-022-00991-4 (2022).
Li, Y. et al. CypA/TAF15/STAT5A/miR-514a-3p feedback loop drives ovarian cancer metastasis. Oncogene 43, 3570–3585. https://doi.org/10.1038/s41388-024-03188-w (2024).
Luo, F. et al. The BCL-2 inhibitor APG-2575 resets tumor-associated macrophages toward the M1 phenotype, promoting a favorable response to anti-PD-1 therapy via NLRP3 activation. Cell. Mol. Immunol. 21, 60–79. https://doi.org/10.1038/s41423-023-01112-y (2024).
Author information
Authors and Affiliations
Contributions
LHQ, XFH and CZY contributed to study conceptualization, data curation, preparation of the original draft, and reviewing and editing of the manuscript. RS, and PYC discussed the methodology and software utilized. ZJJ, WHX and GZZ possesses expertise in the fields of imaging. LLL and HC specialize in the areas of supervision, review writing, and editing.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Qin, Lh., Huang, X., Yang, C. et al. Mitochondrial apoptosis gene-based pathomics for ovarian cancer prognosis. Sci Rep (2026). https://doi.org/10.1038/s41598-026-40121-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-40121-5
