Dutta Lab - Cybernetics

Controlled BCG Immunotherapy. In this study, we propose the Reparameterized Multiobjective Control approach for seeking an optimal drug dosing regimen and apply it to the design of BCG treatment. This approach utilizes constrained optimization based on a nonlinear bladder cancer model with impulsive drug instillation in effectively treating bladder cancer by stimulating the immune response of patients.

Yue R., Dutta A. Reparameterized Multiobjective Control of BCG Immunotherapy. Scientific Reports, 13(1):1–12, Nature Portfolio, 2023.

Controlled Cancer Differentiation. We designed three new controllers for cancer differentiation therapy. The sigmoid-based controller can reduce the amount of drug dosage to complete state transition. The polynomial dynamic inversion-based controller uses less time for differentiation therapy. The PID impulsive controller can increase the time interval between each drug dosage and show better robustness.

Hsiao, YC, Dutta, A. Nonlinear Control Designs and Their Application to Cancer Differentiation Therapy. Mathematical Biosciences, 366:1-8, 2023.

Cancer Vaccine Generator. We introduce a novel immunogenicity goal-directed peptide sequence generator in a Wasserstein generative adversarial network with gradient penalty. The convolutional neural network-based generator is guided by a critic incorporated with an immunogenicity predictor to generate immunogenic epitopes for bladder cancer vaccines.

Hsiao, YC, Dutta, A. Network Modeling and Control of Dynamic Disease Pathways, Review and Perspectives. IEEE/ACM Transactions on Computational Biology and Bioinformatics, pp. 1-20, 2024.

Page updated

Google Sites

Report abuse