2025 Hyper Recent •CC0 1.0 Universal

This work is dedicated to the public domain. No rights reserved.

Access Preprint From Server
June 3rd, 2025
Version: 1
University of Nebraska-Lincoln
cancer biology
biorxiv

GAN-Enhanced Machine Learning and Metabolic Modeling Identify Reprogramming in Pancreatic Cancer

Razmpour, T.Open in Google Scholar•Tabibian, M.Open in Google Scholar•Roohi, A.Open in Google Scholar•Saha, R.Open in Google Scholar

Pancreatic Ductal Adenocarcinoma (PDAC) is one of the deadliest forms of cancer and presents a significant clinical challenge due to poor prognosis and limited treatment options. In this study, we developed a novel framework integrating genome-scale metabolic modeling (GSM) with machine learning to identify metabolic biomarkers and vulnerabilities in PDAC. We addressed the inherent class imbalance in cancer datasets by generating synthetic healthy samples using a Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), implementing a three-step biological filtration process to ensure their validity. Our approach achieved 94.83% accuracy in distinguishing between healthy and cancerous metabolic states. Systems-level analysis revealed three key dysregulated pathways: heparan sulfate degradation, O-glycan metabolism, and heme degradation. We identified impaired lysosomal degradation of heparan sulfate proteoglycans as a potential contributor to PDAC pathogenesis, providing a mechanistic explanation for the previously observed association between lysosomal storage disorders and pancreatic cancer. Additionally, we found that nervonic acid transport (MAR00336) was the most discriminative reaction between healthy and cancerous states, with gene-level analysis highlighting FABPs, SLC27As, ACSLs, and ACSBGs as key molecular drivers of metabolic reprogramming in PDAC. Overall, our multi-level approach connected genetic drivers to functional metabolic consequences, revealing coordinated upregulation of fatty acid transport and activation processes. These findings enhance our understanding of PDAC metabolism and present potential therapeutic targets, demonstrating the value of integrated computational approaches in cancer research.

Similar Papers

biorxiv
Thu Jun 05 2025
Leveraging autophagy and pyrimidine metabolism to target pancreatic cancer
Autophagy inhibitors are promising compounds to treat pancreatic ductal adenocarcinoma (PDA) but their efficacy in patients is unclear, highlighting a need to understand mechanisms of resistance. We used a novel approach to uncover metabolic adaptations that bypass autophagy inhibition. Utilizing PDA cells with acquired resistance to different autophagy inhibitors, we found that severe autophagy d...
Dufresne, S.
•
Kuna, R. S.
•
Wong, K.
•
Komarla, A.
...•
Towers, C. G.
biorxiv
Thu Jun 05 2025
Association of GADD45A and favorable outcome in hormone positive breast cancer
Background: Hormone receptor-positive (HR(+)) breast cancer is the most prevalent subtype in breast cancer, and although treatment options are rapidly increasing, still poses as an unmet need in advanced cases. Growth arrest and DNA damage-inducible alpha (GADD45A) is a gene with known relationship with the cell cycle and DNA damage pathways. Conflicting roles in breast cancer biology have been re...
Lin, C.-Y.
•
Liu, C.-Y.
•
Chao, T.-C.
•
Huang, C.-C.
...•
Lai, J.-I.
biorxiv
Thu Jun 05 2025
Inferring cell dynamics in stress-induced neuroblastoma cell cultures
Neuroblastoma is characterised by significant intratumoural heterogeneity which complicates treatments. Phenotypic plasticity, i.e., the ability of cells to alter their phenotype without genetic mutations, is a key factor contributing to this heterogeneity. In this study, we quantify cell actions and cell-to-cell interactions that lead to phenotypic adaptation in vitro under stress, specifically l...
Hafiichuk, K.
•
Hamis, S.
•
Karlsson, J.
•
Gisselsson, D.
•
Chattopadhyay, S.
biorxiv
Thu Jun 05 2025
Contrastive Learning-Enhanced Drug Metabolite Prediction Drives the Discovery of an Orally Bioavailable RSK4 Inhibitor for Esophageal Cancer
Drug metabolism liabilities are a major bottleneck in drug development, necessitating accurate metabolite prediction tools. While AI-driven methods have advanced, challenges remain in achieving high-precision, robustness, broad reaction coverage and seamless integration into the drug development workflow. To address this, we first constructed the most comprehensive human-specific drug metabolism d...
He, H.
•
Zhang, M.
•
Yang, X.
•
He, S.
...•
Li, S.
biorxiv
Thu Jun 05 2025
Biologically-informed machine learning identifies a new clinically-actionable bladder cancer subgroup characterised by NRF2 overactivity
Muscle-invasive bladder cancer is a diverse disease where subtyping is ambiguous. Gene expression profiling followed by unsupervised machine learning (ML) has broadened our understanding of tumour biology, but has failed to provide high-confidence clinically-actionable subgroups. To focus on tissue-specific urothelial biology, we generated co-expression networks from histologically normal bladder,...
Ungureanu, V. V.
•
Gawne, R. T.
•
Baker, S. C.
•
Eriksson, P.
...•
Mason, A. S.
biorxiv
Thu Jun 05 2025
Hepatocyte expression of fetal insulin receptor isoform contributes to the promotion of liver cancer through non-cell autonomous mechanisms
The insulin receptor (INSR) exists in two isoforms, INSR-A and INSR-B, resulting from alternative splicing of the INSR pre-mRNA. INSR-B mediates the metabolic and mitogenic effects of insulin in the adult liver, while INSR-A is expressed during development. Recently, INSR-A has been detected in pathological murine and human livers. Here, we develop an in vivo CRISPR/Cas9 strategy to assess the imp...
Leandre, F.
•
Iddir, A.
•
Godart, C.
•
Lagoutte, I.
...•
Desbois-Mouthon, C.
biorxiv
Thu Jun 05 2025
Primary tumor microbiomes predict distant metastasis of colorectal cancer
Metastasis causes most cancer-related deaths in colorectal carcinoma (CRC), and microbiome markers may have prognostic value. We hypothesized that primary tumor microbiomes predict distant metastases. We analyzed 5-year metastasis-free survival (MFS) in a retrospective cohort of 900 ORIEN CRC tumor microbiomes (RNAseq). ORIEN findings were validated on an independent cohort using 16S rDNA sequenci...
Parajuli, B.
•
Midya, V.
•
Kiddle, R.
•
De Jager, N.
...•
Bosch, D. E.
biorxiv
Thu Jun 05 2025
Identifying Space-Resolved Proteins of the Murine Thymus, by Combining MALDI Mass Spectrometry Imaging and Proteomics
The identification of spatially resolved proteomes has recently seen significant breakthroughs, yet challenges persist, particularly in integrating protein identification with precise spatial localiza-tion within a single experimental workflow. Matrix-assisted laser desorption ionization mass spec-trometry imaging (MALDI-MSI) enables spatial protein mapping on tissue sections without the need for ...
Aguilan, J. T.
•
Madrid-Aliste, C.
•
Lagou, M. K.
•
Sidoli, S.
•
Karagiannis, G. S.
biorxiv
Wed Jun 04 2025
Artemether and Euphorbia Factor L9 suppress kynurenine production through distinct effects on Tryptophan metabolism.
L-Tryptophan (Trp) is an essential amino acid, catabolised through the kynurenine pathway, which is mediated by the enzymes indoleamine-2,3-dioxygenase 1 (IDO1), IDO2, or Trp-2,3-deoxygenase (TDO). Therapeutic targeting of Trp metabolism could be relevant to several pathologies. In cancer, IDO1 acts as an immune checkpoint suppressing effector T cell function. Yet, direct inhibition of IDO1 has ha...
Capatina, A. L. L.
•
Czechowski, T.
•
Plunkett-Jones, C.
•
Tonon, T.
...•
Lagos, D.
biorxiv
Wed Jun 04 2025
Isoform-Specific Gene Regulation by Progesterone Receptors Drives Divergent Phenotypes in Breast Cancer Cells
Exposure to progesterone is a recognized risk factor for breast cancer, and PGR polymorphisms are associated with various malignancies. Two progesterone receptor (PR) isoforms, full length PR-B and truncated PR-A, are expressed from the PGR gene in breast tissue and play crucial roles in normal physiology and breast cancer progression. An imbalance in the expression ratio of these isoforms, favori...
Gillis, N. E.
•
Truong, T. H.
•
Diep, C. H.
•
Spartz, A.
...•
Lange, C. A.