Related Experiment Video
Updated: Oct 28, 2025
Monitoring PD-1-Blocking Antibodies Bound to T Cells Derived from a Drop of Peripheral Blood
Published on: February 5, 2020
Systems biology informed neural networks (SBINN) predict response and novel combinations for PD-1 checkpoint blockade
Michelle Przedborski1, Munisha Smalley2, Saravanan Thiyagarajan2
1Department of Applied Mathematics, University of Waterloo, Waterloo, ON, Canada. mprzedborski@uwaterloo.ca.
Abstract:
Anti-PD-1 immunotherapy has recently shown tremendous success for the treatment of several aggressive cancers. However, variability and unpredictability in treatment outcome have been observed, and are thought to be driven by patient-specific biology and interactions of the patient's immune system with the tumor. Here we develop an integrative systems biology and machine learning approach, built around clinical data, to predict patient response to anti-PD-1 immunotherapy and to improve the response rate. Using this approach, we determine biomarkers of patient response and identify potential mechanisms of drug resistance. We develop systems biology informed neural networks (SBINN) to calculate patient-specific kinetic parameter values and to predict clinical outcome. We show how transfer learning can be leveraged with simulated clinical data to significantly improve the response prediction accuracy of the SBINN. Further, we identify novel drug combinations and optimize the treatment protocol for triple combination therapy consisting of IL-6 inhibition, recombinant IL-12, and anti-PD-1 immunotherapy in order to maximize patient response. We also find unexpected differences in protein expression levels between response phenotypes which complement recent clinical findings. Our approach has the potential to aid in the development of targeted experiments for patient drug screening as well as identify novel therapeutic targets.
Insights
Predicting patient response to anti-PD-1 immunotherapy is crucial for cancer treatment. This study introduces a systems biology and machine learning approach to enhance prediction accuracy and identify novel therapeutic strategies for improved patient outcomes.
Area of Science:
- Oncology
- Immunotherapy
- Systems Biology
- Machine Learning
Background:
- Anti-programmed cell death protein 1 (anti-PD-1) immunotherapy shows promise for aggressive cancers but exhibits variable patient response.
- Patient-specific factors and immune-tumor interactions contribute to unpredictable treatment outcomes.
- Developing predictive models and personalized treatment strategies is essential to improve anti-PD-1 therapy efficacy.
Purpose of the Study:
- To develop an integrative systems biology and machine learning approach to predict patient response to anti-PD-1 immunotherapy.
- To identify biomarkers for patient response and mechanisms of drug resistance.
- To optimize combination therapies for enhanced treatment outcomes.
Main Methods:
- Utilized clinical data within an integrative systems biology and machine learning framework.
- Developed systems biology informed neural networks (SBINN) for patient-specific kinetic parameter calculation and outcome prediction.
- Employed transfer learning with simulated data to improve SBINN prediction accuracy.
- Identified novel drug combinations and optimized a triple therapy regimen (IL-6 inhibition, IL-12, anti-PD-1).
Main Results:
- Successfully predicted patient response to anti-PD-1 immunotherapy with improved accuracy using SBINN and transfer learning.
- Identified potential biomarkers and mechanisms underlying drug resistance.
- Determined an optimized triple combination therapy protocol to maximize patient response.
- Observed distinct protein expression differences between response phenotypes.
Conclusions:
- The developed integrative approach enhances the prediction of anti-PD-1 immunotherapy response.
- Identified novel therapeutic targets and optimized combination strategies, including triple therapy.
- Findings support the development of targeted patient drug screening and personalized treatment protocols.
- The study provides a framework for improving immunotherapy efficacy in aggressive cancers.
More Related Videos
Related Concept Videos
01:19Interactions Between Signaling Pathways
Convergence and divergence, and cross-talk between signaling pathways
Two distinct signaling pathways can converge on a single functional unit, which may either be a single protein or a complex of proteins. The response is either functionally distinct or synergistic between the two pathways but different from the response...
01:21EPS and iPS Cells in Disease Research
02:26Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
02:50Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...