Date of Graduation
5-2026
Document Type
Thesis
Degree Name
Bachelor of Science in Chemical Engineering
Degree Level
Undergraduate
Department
Chemical Engineering
Advisor/Mentor
William Richardson
Abstract
Myocardial fibrosis is a key driver of heart failure progression and exhibits substantial patient-to-patient variability, complicating the development of effective personalized therapies. In this study, we present an integrated computational framework that combines a mechanistic signaling network model with patient-specific proteomic data to predict individualized fibrotic responses and therapeutic strategies. Using proteomic measurements from the Framingham Heart Study, we generated personalized baseline states and performed systematic in silico perturbation screens to evaluate candidate drug targets across 132 signaling nodes. Results reveal that while global network response structure is conserved, therapeutic efficacy varies widely between patients in both magnitude and breadth, supporting the need for personalized treatment approaches. Population-level analysis using principal covariates classification demonstrates that variability in drug response is driven by coordinated, multivariate interactions among biochemical and biomechanical inputs rather than single biomarkers. Finally, we introduce a graph neural network framework designed to incorporate mechanistic network structure for predicting long-term clinical outcomes. Together, this work establishes a scalable approach for integrating mechanistic modeling and machine learning to advance precision medicine in myocardial fibrosis.
Keywords
computational modeling, fibrosis, biochemical reaction network
Citation
Noel, J. (2026). Predicting personalized myocardial fibrosis response patterns using a mechanistic signaling network model. Chemical Engineering Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/cheguht/229
