loading page

Reinforcement learning-guided control strategies for CAR T-cell activation and expansion
  • +1
  • Nigel Reuel,
  • Sakib Ferdous,
  • Ibne Farabi Shihab,
  • Ratul Chowdhury
Nigel Reuel
Iowa State University Department of Chemical and Biological Engineering

Corresponding Author:[email protected]

Author Profile
Sakib Ferdous
Iowa State University Department of Chemical and Biological Engineering
Author Profile
Ibne Farabi Shihab
Iowa State University Department of Computer Science
Author Profile
Ratul Chowdhury
Iowa State University Department of Chemical and Biological Engineering
Author Profile

Abstract

Reinforcement learning (RL), a subset of machine learning (ML), can potentially optimize and control biomanufacturing processes, such as improved production of therapeutic cells. Here, the process of CAR-T cell activation by antigen presenting beads and their subsequent expansion is formulated in-silico. The simulation is used as an environment to train RL-agents to dynamically control the number of beads in culture with the objective of maximizing the population of robust effector cells at the end of the culture. We make periodic decisions of incremental bead addition or complete removal. The simulation is designed to operate in OpenAI Gym which enables testing of different environments, cell types, agent algorithms and state-inputs to the RL-agent. Agent training is demonstrated with three different algorithms (PPO, A2C and DQN) each sampling three different state input types (tabular, image, mixed); PPO-tabular performs best for this simulation environment. Using this approach, training of the RL-agent on different cell types is demonstrated, resulting in unique control strategies for each type. Sensitivity to input-noise (sensor performance), number of control step interventions, and advantage of pre-trained agents are also evaluated. Therefore, we present a general computational framework to maximize the population of robust effector cells in CAR-T cell therapy production.
23 Aug 2023Submitted to Biotechnology and Bioengineering
31 Aug 2023Submission Checks Completed
31 Aug 2023Assigned to Editor
31 Aug 2023Review(s) Completed, Editorial Evaluation Pending
29 Sep 2023Reviewer(s) Assigned
05 Feb 20241st Revision Received
05 Feb 2024Assigned to Editor
05 Feb 2024Submission Checks Completed
05 Feb 2024Review(s) Completed, Editorial Evaluation Pending
20 Feb 2024Reviewer(s) Assigned
14 Mar 2024Editorial Decision: Revise Major
15 Apr 20242nd Revision Received
15 Apr 2024Submission Checks Completed
15 Apr 2024Assigned to Editor
15 Apr 2024Review(s) Completed, Editorial Evaluation Pending
12 May 2024Editorial Decision: Accept