Bazargan, S. | bioRxiv Science

bioRxiv2026

A virtual cohort framework with applications to adoptive cell therapy in bladder cancer

Even under the same treatment, responses can vary. Virtual cohorts build on an available, often limited, dataset can capture these differences and enable the discovery of treatment protocols that work well for a wide variety of individuals. In this paper, we refined current virtual cohort pipelines by improving data handling, ensuring the virtual cohort can be used to stratify individuals into treatment subgroups based on their data, and validating that the virtual cohort matches the observed data variability. To illustrate, we applied this pipeline to a murine data set of orthotopic bladder cancer treated with gemcitabine (Gem) and immunotherapy with OT-1 cells. We generated over 10,000 virtual mice that replicate the dynamics of three cell subpopulations in the tumor (cancer cells, T cells, and myeloid-derived suppressor cells) and data from four experimental cohorts (control, Gem, OT-1, and Gem+OT-1). We also provided a guide for using this pipeline for other treatments.

cancer biology↗

bioRxiv2025

A Machine Learning Model Optimized for Local Data Stratifies Patients for the Adoptive Cell Therapy with Tumor Infiltrating Lymphocytes in Bladder Tumors

Adoptive cell therapy (ACT) with tumor-infiltrating lymphocytes (TIL) is a form of personalized immunotherapy that requires ex vivo expansion of autologous TILs and their reinfusion back into the patient. Predicting TIL expansion at the time of diagnosis may improve selection of patients that can benefit from ACT-TIL. It can also prevent high treatment-related costs and delays in treatment of patients whose cancer specimens would not yield successful TIL growth. We developed PETIL, a machine-learning model optimized for data of a medium size to determine a minimal combination of features (demographic, clinical, and biological specimen-based) that is predictive of expansion of TILs from a resected bladder cancer. We used a retrospectively identified set of data from bladder cancer patients at Moffitt Cancer Center for the training and testing cohorts. Additionally, we used data from a recent feasibility clinical trial at Moffitt Cancer Center as a blinded validation cohort. PETIL uses random forest method to identify a combination of robust predictive features, support vector machine model to determine the optimal classification hyperparameters, and Matthews correlation coefficient method to adjust the decision-boundary threshold for imbalanced data. Our model yielded AUC=0.740 for the testing cohort and AUC=0.857 for blinded validation cohort. Thus, our PETIL model optimized for data of medium size has favorable performance metrics for predicting TIL expansion from a given tumor. Authors SummaryTreatment with autologous tumor-infiltrating lymphocytes (TIL) that are expanded ex vivo from a given tumor and then reinfused into the patient is a promising personalized immunotherapy. However, the TIL expansion takes about 4-6 weeks, thus developing tools that predict whether TIL growth will be successful can help to avoid delays in treatment of patients whose cancer specimens would not yield successful TIL expansion. Our Predictor of Expansion of TIL (PETIL) is a machine-learning model that uses patients demographic information, clinical tumor classification, and biological tumor specimen-based measurements to determine a minimal set of these data features that are predictive of TIL expansion outcome. We applied this model to data from bladder cancer patients collected at Moffitt Cancer Center and showed that PETIL has favorable performance metrics for the dataset of a moderate size. This computational predictor can support clinicians in determining which patients are candidates for TIL immunotherapy. The developed PETIL pipeline can also be adjusted to data from other solid tumors.

immunology↗

bioRxiv2024

Histology-guided mathematical model of tumor oxygenation: sensitivity analysis of physical and computational parameters

A hybrid off-lattice agent-based model has been developed to reconstruct the tumor tissue oxygenation landscape based on histology images and simulated interactions between vasculature and cells with microenvironment metabolites. Here, we performed a robustness sensitivity analysis of that models physical and computational parameters. We found that changes in the domain boundary conditions, the initial conditions, and the Michaelis constant are negligible and, thus, do not affect the model outputs. The model is also not sensitive to small perturbations of the vascular influx or the maximum consumption rate of oxygen. However, the model is sensitive to large perturbations of these parameters and changes in the tissue boundary condition, emphasizing an imperative aim to measure these parameters experimentally.

systems biology↗