Related Experiment Video
Updated: Jun 6, 2026
Oncogene Expression Analysis with Alterations in pH in a Pancreatic Ductal Cell Line
Published on: April 11, 2025
Active learning-guided mechanistic modeling reveals context-specific regulators of CXCL9 expression in pancreatic
Bi-Rong Wang1,2,3, Maaruthy Yelleswarapu1,2, Lucie Descamps1,2
1Department of Biomedical Engineering, Eindhoven University of Technology, PO Box 513, Eindhoven, 5600MB, the Netherlands.
Abstract:
Cold tumors like pancreatic cancer suffer from poor immune infiltration, limiting effective anti-tumor responses. The chemokine CXCL9 promotes immune cell recruitment, but the signaling mechanisms regulating its expression in tumor cells remain poorly understood and underexplored as targets for modulation. We present a framework that integrates active learning with mechanistic logic-ODE models to guide perturbation screenings and uncover regulators of CXCL9 in pancreatic cancer cells. Using perturbation-response data and curated prior knowledge, we trained interpretable models to identify signaling mechanisms that enhance CXCL9 expression and prioritize drug combinations. Active learning enabled data-efficient model refinement and guided informative experiments under resource constraints. Benchmarking on synthetic data and experimental validation confirmed the performance of different acquisition strategies and its applicability to feasible iterative wet lab experiments. Our results demonstrate how combining active learning with mechanistic modeling supports rational, targeted experimental design.
Insights
This study introduces a novel framework combining active learning and mechanistic modeling to identify key regulators of CXCL9 chemokine expression in pancreatic cancer. This approach enhances immune cell infiltration for improved anti-tumor responses.
Area of Science:
- Computational Biology
- Cancer Research
- Immunology
Background:
- Pancreatic cancer exhibits poor immune infiltration, hindering effective anti-tumor immunity.
- The chemokine CXCL9 is crucial for immune cell recruitment but its regulatory mechanisms in tumor cells are poorly understood.
Purpose of the Study:
- To develop and validate an integrated framework using active learning and mechanistic logic-ODE models.
- To identify signaling pathways and drug combinations that enhance CXCL9 expression in pancreatic cancer cells.
Main Methods:
- Integration of active learning with mechanistic logic-ODE models.
- Utilizing perturbation-response data and curated prior knowledge to train interpretable models.
- Guiding iterative experimental screenings for data efficiency.
Main Results:
- Identification of signaling mechanisms that upregulate CXCL9 expression.
- Prioritization of effective drug combinations for modulating CXCL9.
- Demonstration of active learning's efficiency in resource-constrained experimental settings.
Conclusions:
- The combined active learning and mechanistic modeling framework facilitates rational, targeted experimental design.
- This approach can uncover novel regulators of CXCL9 and guide therapeutic strategies for pancreatic cancer.
- The study highlights the potential for computational methods to accelerate discovery in cancer immunology.
