Deep Learning Enabled 3D Multi-Omic Analysis Reveals Molecular Signatures of Heterogeneous Response to Chemotherapy in Pancreatic Cancer

Forjaz, A.; Mojdeganlou, H.; Valentin, A.; Wetzel, M.; Lvovs, D.; Deshpande, A.; Shin, S. M.; Piya, S.; Rajapakshe, K. I.; Guerrero, P. A.; Pedro, B. A.; Sidiropoulos, D. N.; Wu, P.-H.; Bernard Pagan, V.; Demystifying Pancreatic Cancer Therapies TeamLab,; Wirtz, D.; Fertig, E. J.; Kagohara, L. T.; Ho, W. J.; Kiemen, A. L.; Wood, L. D.

doi:10.64898/2026.03.03.709150

Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.03.03.709150

Deep Learning Enabled 3D Multi-Omic Analysis Reveals Molecular Signatures of Heterogeneous Response to Chemotherapy in Pancreatic Cancer

View original source ↗Export metadata ↓

Abstract

Resistance to systemic therapy is a major unmet challenge in pancreatic cancer. To identify potential mechanisms of resistance, we developed a novel 3D pipeline in clinical samples that uses deep learning to classify sensitive and persistent tumor cell populations based on morphological features, enabling subsequent molecular characterization of intratumoral heterogeneity. We applied this automated 3D pipeline to a cohort of human pancreatic cancer samples treated with neoadjuvant chemotherapy, identifying heterogeneity in response to therapy both between and within tumors. Application of spatial proteomics to these sensitive and persistent regions identified enhanced epithelial-to-mesenchymal transition and non-classical cell states in persistent cells, confirming our morphological classification. Integration of spatial transcriptomics in multiple pancreatic cancer cohorts associated fibroblast-cancer crosstalk via syndecans with resistance to cytotoxic therapy. Our validated 3D multi-omic pipeline is now poised for application to clinical trials, enabling discovery of resistance mechanisms and design of new therapeutic combinations to circumvent resistance. Statement of significanceWe developed a novel 3D multi-omic pipeline to identify mechanisms of resistance to chemotherapy in clinical samples. This approach associated fibroblast-cancer crosstalk via syndecans with resistance to cytotoxic therapy and is poised for broader application in neoadjuvant clinical trials.

Explore related subjects

cancer biology Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Forjaz, A., Mojdeganlou, H., Valentin, A., Wetzel, M., Lvovs, D., Deshpande, A., Shin, S. M., Piya, S., Rajapakshe, K. I., Guerrero, P. A., Pedro, B. A., Sidiropoulos, D. N., Wu, P.-H., Bernard Pagan, V., Demystifying Pancreatic Cancer Therapies TeamLab,, Wirtz, D., Fertig, E. J., Kagohara, L. T., Ho, W. J., Kiemen, A. L., Wood, L. D.. 2026-03-05. Deep Learning Enabled 3D Multi-Omic Analysis Reveals Molecular Signatures of Heterogeneous Response to Chemotherapy in Pancreatic Cancer. https://doi.org/10.64898/2026.03.03.709150

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Tet2-Clonal Hematopoiesis Promotes Whereas Dnmt3a-CH Inhibits Breast Cancer Progression During Aging

Clonal hematopoiesis of indeterminate potential (CHIP) driven by somatic mutations in blood cells increases with age and is associated with adverse outcomes in cancer patients. How CHIP mutations influence solid tumor progression remains unclear. Using inducible murine models of Dnmt3a- or Tet2-mutant CHIP combined with orthotopic syngeneic breast cancer models, we demonstrate that upon aging Dnmt3a-mutant CHIP prevents whereas Tet2-mutant CHIP drives breast cancer progression. Dnmt3a-mutant immune infiltrates established interferon-mediated MHCIIhigh tumor-associated macrophages (TAMs) that supported cytotoxic CD8+ T cell-mediated tumor rejection. In contrast, Tet2-mutant TAMs exhibited an inflammatory, immunosuppressive phenotype characterized by increased IL-1 and CXCL2 production, reduced MHCII expression, and impaired T cell recruitment and activation. Therapeutic blockade of IL-1R1 or CXCR2 reduced tumor progression in aged Tet2-mutant CHIP mice and partially restored anti-tumor immunity. These findings establish that the effects of CHIP on cancer are mutation- and age-dependent and identify IL-1/CXCL2-driven inflammation as a therapeutic vulnerability of tumor-promoting Tet2-mutant CHIP.

cancer biology↗

bioRxiv2026

Single Nucleus Profiling Reveals Rewired Tumor-Immune-Stromal Cell Communication in Plasmacytoid Urothelial Carcinoma

Plasmacytoid urothelial carcinoma (PUC) is an aggressive histologic subtype of bladder cancer associated with worse patient outcomes and therapeutic response compared to conventional urothelial carcinoma (CUC). While recent work has demonstrated metastatic lymph nodes from PUC tumors have an inflamed phenotype, how the tumor microenvironment (TME) and crosstalk between tumor, stromal, and immune cells in primary PUC bladder tumors differs from those in CUC remains poorly understood. The impact of these differences on response to immunotherapy is also unknown. To understand TME differences between CUC and PUC and their impact on cell signaling, we performed single nucleus RNA sequencing on PUC and CUC tumors, as well as Xenium spatial transcriptomics on a mixed CUC / PUC tumor. We identified increased signaling between PUC-enriched, CDH1-low urothelial cells, immunosuppressive lipid-associated macrophages, and SFRP2+/CTHRC1+ fibroblasts in PUC tumors compared to CUC. Spatial transcriptomics identified increased macrophage infiltration in PUC histology and colocalization of PUC tumor cells, immunosuppressive macrophages, and SFRP2+ fibroblasts. Taken together, this study delineates PUC architecture and demonstrates interplay CDH1-low tumor cells, EMT, and immunosuppressive macrophages, identifying possible therapeutic vulnerabilities in PUC.

cancer biology↗

bioRxiv2026

The Phospholipase A2 Activity of Peroxiredoxin 6 Protects Hepatocarcinoma Cells Against Ferroptosis and Mitophagy Impairment

Peroxiredoxin 6 (PRDX6) is a moonlighting protein that plays a key role in regulating redox homeostasis and lipid metabolism through its unique dual peroxidase and calcium-independent phospholipase A2 (iPLA2) activities. Here, we generated a stable HepG2 cell line harboring a D140A mutation to selectively ablate iPLA2 activity, and we compared its phenotype with that of wild-type (WT) and PRDX6-knockout (KO) cells. D140A exhibited low ROS leves, similar to WT cells, confirming that oxidative stress is due to peroxidase deficiency. In contrast, D140A cells displayed higher lipid peroxidation than WT cells, though significantly lower than that of KO cells. Furthermore, the D140A mutant mirrored the KO phenotype regarding intracellular ferrous iron accumulation, impaired lipid droplet biogenesis, and the downregulation of the key ferroptosis regulator GPX4. Mechanistically, integrated proteomic, lipidomic, and enzymatic analyses revealed that a deficiency in iPLA2 activity of PRDX6 disrupted the release of key lipid species necessary for cell structure and signaling. Consequently, organelles involved in lipid synthesis and trafficking, such as peroxisomes, endoplasmic reticulum, mitochondria and lipid droplet, were affected. Specifically, we found that mitochondria exhibited a reduction in cristae and a diminished capacity for mitophagy and autophagy, which ultimately makes cells much more susceptible to erastin-induced ferroptotic cell death. Taken together, our findings demonstrate that PRDX6 iPLA2 activity uniquely coordinates organelle lipid homeostasis and mitophagy to protect cancer cells from ferroptotic cell death. Consequently, the use of iPLA2 inhibitors such as MJ33, which decreased PRDX6 iPLA2 activity to a level comparable to the mutant D140A, could represent a promising therapeutic strategy for inducing ferroptotic cell death in hepatocellular carcinoma.

cancer biology↗