Facilities and processes to produce biotherapeutics

Inventors

Shaver, Jeremy Martin • Amimeur, Tileli • Ketchem, Randal Robert • Vandiver, Michael W. • Horman, Brian W. • Garcia Morales, Fernando

Assignees

Just Evotec Biologics Inc

Abstract

The concepts described herein are directed to implementations of production facilities that can produce molecules used to treat biological conditions, such as biotherapeutics. The biotherapeutics can include various molecules, such as proteins, enzymes, and antibodies. The production facilities can include a number of separate modular cleanrooms that comprise particular pieces of equipment to perform one or more aspects of the processes used to manufacture biotherapeutics. The modular cleanrooms are arranged such that material that is produced by the equipment of one modular cleanroom can be transferred to another modular cleanroom for additional processing. Additionally, systems and processes are described to generate models using machine learning techniques, where the models can be used to predict productivity and/or efficiency metrics for production lines of biotherapeutics. Further, models can be generated to control the operation of pieces of equipment included in the production lines.

Core Innovation

The patent describes a modular production facility to produce one or more biotherapeutics, using multiple modular cleanrooms arranged so that intermediate material is transferred between cleanrooms for successive processing. A first modular cleanroom includes a first plurality of pieces of equipment including a bioreactor to produce an effluent that includes a biotherapeutic. A second modular cleanroom includes a second plurality of pieces of equipment including at least a filter system to purify the effluent produced in the first modular cleanroom.

The production facility includes a staging area with a plurality of storage containers that store cell culture media and cell growth material for the bioreactor and store buffer solution for equipment in the first and second modular cleanrooms. The system and method obtain a first set of data indicating conditions of the bioreactor via at least one sensor or one or more external assays measured at different points in time during operation. The data is analyzed utilizing one or more inferential modeling techniques to determine process variables with at least a first threshold impact on a productivity metric related to the bioreactor effluent, and to determine control variables with at least a second threshold impact on the process variables.

The patent further describes generating a model that includes variables corresponding to the process variables and control variables, wherein the model predicts the productivity metric. Process data obtained from first and second pieces of equipment is applied to the model to determine values of the productivity metric, and responsive to values outside a threshold range, machine learning techniques are applied to determine at least one process variable to modify and at least one control variable to modify to cause additional values of the at least one process variable to change.

Control signals indicating control settings are sent to one or more pieces of equipment to modify the control variable in a manner that modifies the productivity metric, and operation of the pieces of equipment is caused to change based on the control signals.

Claims Coverage

The partial content provides two independent claims, covering a system and a method, each centered on modular cleanrooms plus inferential modeling and machine-learning-driven model-based control using threshold impacts on a productivity metric. Across the independent claims, the core inventive features number at least 5 per claim: modular cleanroom architecture, staging storage containers, inferential modeling to identify threshold-impact variables, a model predicting a productivity metric, and closed-loop threshold-responsive control via machine learning and control signals.

In the provided partial content, the independent claims share a common combination of modular cleanroom system architecture with a computational closed-loop control framework. The inventive core is identifying threshold-impact process variables and control variables through inferential modeling, generating a model to predict a productivity metric, and using machine learning plus threshold checks to determine variable modifications and send control signals that change equipment operation in order to modify the productivity metric.

Stated Advantages

Documented Applications