Computer-based system for controlling and monitoring metabolic rate and environmental factors of at least one bioreactor and method of use thereof

Abstract

A bioreactor chamber for growing a cell culture in a liquid medium includes a controller, sensors coupled to the bioreactor chamber, and a control device for varying gas and / or fluid flow within the bioreactor chamber. The sensors measure a plurality of sensor parameters in the liquid medium. Sensor data from each sensor is received at predetermined time intervals. The desired cell growth configuration and the sensor data from each sensor are input into a cell culture control machine learning model. Based on output data from the cell culture control machine learning model, control circuit commands are sent to the control device to control at least one of displaying a cell culture parameter prediction, gas flow, liquid flow of nutrient solution, or removal of waste from the liquid medium.

Description

[Technical Field]

[0001] The present disclosure relates generally to computer-based systems, and more particularly to computer-based systems for controlling and monitoring the metabolic rate and environmental factors of at least one bioreactor and methods of use thereof.

[0002] Various embodiments of the present disclosure can be further described with reference to the accompanying drawings, in which like structures are referenced by like numerals throughout the several views. The drawings shown are not necessarily to scale, with emphasis instead generally being placed on illustrating the principles of the present disclosure. Therefore, specific structural and functional details disclosed herein should not be construed as limiting, but merely as a representative basis for teaching those skilled in the art how to variously use one or more exemplary embodiments. [Brief explanation of the drawings]

[0003] [Figure 1A]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 1B]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 1C]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 2]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 3]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 4]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 5]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 6]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 7]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 8]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 9A]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 9B]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 9C]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 9D]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 9E]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 9F]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 10]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 11]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 12]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 13]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 14]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 15]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 16A]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 16B]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. [Figure 17]

[0023] Figure 1 shows one or more schematic flow diagrams, particular computer-based architectures, and / or screenshots of various specialized graphical user interfaces illustrating some example aspects of at least some embodiments of the present disclosure. Summary of the Invention

[0004] In some embodiments, the present disclosure provides an exemplary technically improved computer-based method, including at least the following steps: providing a bioreactor arrangement, the bioreactor arrangement including: a bioreactor chamber for growing a cell culture, which may include a plurality of cells or microorganisms in a liquid medium; a controller; a plurality of sensors coupled to the bioreactor chamber; a plurality of control devices for varying gas flow, fluid flow, or both within the bioreactor chamber; and a control circuit that may receive control circuit commands from the controller to control the plurality of control devices. The plurality of sensors may measure a plurality of sensor parameters in the liquid medium, which may include a dissolved oxygen (DO) level, a glucose level, and a lactate level. A desired cell growth configuration may be received by the controller via an input device. The desired cell growth configuration may include at least one desired value range, at least one set point, or any combination thereof, for each of a plurality of sensor parameters measured by the plurality of sensors at predetermined time intervals for each of the plurality of cell culture growth parameters during growth of the cell culture. Sensor data from each of the plurality of sensors may be received by the controller at predetermined time intervals. The desired cell growth configuration and sensor data from each of the plurality of sensors can be input into at least one cell culture control machine learning model. The at least one cell culture control machine learning model can be trained using a dataset based at least in part on time-dependent correlations between the plurality of sensor parameters and the plurality of cell culture growth parameters.Based on output data from the at least one cell culture control machine learning model, the controller may perform at least one of: transmitting at least one control circuit command for display on a display; transmitting at least one cell culture parameter prediction from the plurality of cell culture growth parameters; transmitting at least one control circuit command to control a gas control device to vary a gas level in the bioreactor chamber; transmitting at least one control circuit command to control a device that controls liquid flow of a nutrient fluid into the bioreactor chamber; or transmitting at least one control circuit command to open a device coupled to the bioreactor chamber to remove waste from the liquid medium.

[0005] In some embodiments, the present disclosure provides an exemplary technically improved computer-based system including at least the following components of a bioreactor chamber for growing a cell culture including a plurality of cells or microorganisms in a liquid medium: a controller; a reservoir chamber for holding a nutrient fluid including at least one nutrient for the plurality of cells or microorganisms; a plurality of sensors coupled to the bioreactor chamber; a plurality of control devices for varying gas flow, fluid flow, or both within the bioreactor chamber; and a control circuit for receiving control circuit commands from the controller to control the plurality of control devices. The plurality of sensors may measure a plurality of sensor parameters in the liquid medium, which may include dissolved oxygen (DO) level, glucose level, and lactate level.The controller is configured to receive a desired cell growth configuration via an input device, the desired cell growth configuration may include at least one desired value range, at least one set point, or any combination thereof, for each of a plurality of sensor parameters measured by a plurality of sensors at a predetermined time interval for each of a plurality of cell culture growth parameters during growth of the cell culture; receive sensor data from each of the plurality of sensors at the predetermined time interval; input the desired cell growth configuration and the sensor data from each of the plurality of sensors into a cell culture control machine learning model, the at least one cell culture control machine learning model being a data set based at least in part on a time-dependent correlation between the plurality of sensor parameters and the plurality of cell culture growth parameters. the cell culture control machine learning model may be trained using the model; and based on output data from the cell culture control machine learning model, perform at least one of: sending at least one control circuit command to display at least one cell culture parameter prediction from the plurality of cell culture growth parameters on a display; sending at least one control circuit command to a gas control device that changes a gas level in the bioreactor chamber; sending at least one control circuit command to control a device that controls liquid flow of a nutrient fluid into the bioreactor chamber; or sending at least one control circuit command to open a device coupled to the bioreactor chamber to remove waste from the liquid medium. DETAILED DESCRIPTION OF THE INVENTION

[0006] Various detailed embodiments of the present disclosure are disclosed herein in conjunction with the accompanying drawings. However, it should be understood that the disclosed embodiments are merely exemplary. Additionally, each of the examples given in connection with the various embodiments of the present disclosure are intended to be illustrative and not limiting.

[0007] Throughout this specification, the following terms take on the meanings explicitly associated therewith unless the context clearly dictates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Additionally, as used herein, the phrases "in another embodiment" and "in some other embodiments" do not necessarily refer to different embodiments, although they may. Thus, as described below, various embodiments can be readily combined without departing from the scope or spirit of the present disclosure.

[0008] Furthermore, the term "based on" is not exclusive and allows for based on additional unrecited factors unless the context clearly dictates otherwise. Furthermore, throughout this specification, the meanings of "a," "an," and "the" include plural references. The meaning of "in" includes "in" and "on."

[0009] It is understood that at least one aspect / function of the various embodiments described herein can be performed in real time and / or dynamically. As used herein, the term "real time" refers to an event / action that can occur instantaneously or near-instantaneously when another event / action occurs. For example, "real-time processing," "real-time computation," and "real-time execution" all relate to the performance of a computation during the actual time that an associated physical process (e.g., a user interacting with an application on a mobile device) occurs, and the results of the computation can be used to guide the physical process.

[0010] As used herein, the terms "dynamically" and "automatically," as well as their logical and / or linguistic related and / or derivative terms, mean that a particular event and / or action can be triggered and / or occur without human intervention. In some embodiments, the event and / or action according to the present disclosure can occur in real time and / or based on at least one predetermined periodicity of nanoseconds, nanoseconds, milliseconds, milliseconds, seconds, seconds, minutes, minutes, hours, hours, daily, daily, weekly, monthly, etc.

[0011] As used herein, the term "runtime" corresponds to any behavior that is dynamically determined during the execution of a software application or at least a portion of a software application.

[0012] Embodiments of the present disclosure herein disclose computer-based methods and systems for a bioreactor that can be controlled by at least one real-time cell culture control machine learning model (MLM) executed by a controller. The MLM can learn to use, in part, a plurality of sensor data output parameters generated from a plurality of sensors monitoring the bioreactor at its inputs, map them, and output control commands that can dynamically operate various hardware components of the bioreactor system to control various parameters of the bioreactor and / or predict a plurality of cell culture parameter predictions for a plurality of cells growing in a fluid medium within the bioreactor.

[0013] 1A is a schematic block diagram illustrating various components of a first embodiment of a bioreactor system 100A according to some embodiments of the bioreactor system of the present disclosure. In some embodiments, the exemplary bioreactor system 100A can include a bioreactor 103, which can also include an outlet 105, two pumps 109a and 109b, a plurality of sensors 104a and 104b coupled to the bioreactor 103, a controller 106, an imaging camera 102, and an inner chamber 103a, which contains at least a plurality of cells.

[0014] 1B is a schematic block diagram illustrating various components of a second embodiment of a bioreactor system 100B according to some embodiments of the bioreactor system of the present disclosure. Bioreactor system 100B can include all of the elements of bioreactor system 100A. Bioreactor system 100B can further include a reservoir chamber 107 fluidly connected to bioreactor chamber 103 by a fluid circuit (e.g., a pump system) including at least two portions (e.g., two pumps 109a, 109b). The fluid circuit of the exemplary bioreactor system includes at least two portions, each portion including, for example, a pump (109a, 109b), and the fluid circuit or pump system will be collectively referred to hereinafter as 109.

[0015] In some embodiments, the exemplary bioreactor system 100B can include multiple sensors 104a and 104b coupled to the bioreactor 103 and multiple sensors 104c coupled to the reservoir chamber 107.

[0016] In some embodiments, reservoir chamber 107 may further include inlet 111. In some embodiments, reservoir chamber 107 may be a separate chamber having a fluid medium. In some embodiments, the fluid medium in the reservoir may be the same as the fluid medium in the bioreactor. In some embodiments, the fluid medium in the reservoir may be different from the fluid medium in the bioreactor. In some embodiments, reservoir chamber 107 does not contain cells. In some embodiments, the reservoir is a container that contains a medium that provides for delivery of fluid to bioreactor 103. In some embodiments, the reservoir is a container that receives and contains waste from bioreactor 103. In some embodiments, the bioreactor system 100B includes at least two reservoirs: a first reservoir chamber 107 that contains a medium that supplies fluid to the bioreactor 103, and in which the fluid is received via an inlet 111; and a second reservoir (not shown in FIG. 1A) that receives and stores waste from the bioreactor 103 via a fluid circuit (not shown in FIG. 1A) or via an outlet 105.

[0017] In some embodiments, bioreactor 103 may include a first fluid medium. In some embodiments, the first fluid medium may include at least one gas, at least one nutrient, and the at least one nutrient may be present in an amount sufficient to supply a plurality of cells, a liquid, or any combination thereof. The liquid of the first fluid medium may further include the volume of liquid within bioreactor 103.

[0018] In some embodiments, the liquid may have a temperature ranging from 37° C. to 42° C. In some embodiments, the liquid may have a temperature ranging from 24° C. to 42° C. In some embodiments, the liquid may have a temperature ranging from 2° C. to 70° C. In some embodiments, the liquid may have a pH level ranging from 6.5 pH to 7.5 pH. In some embodiments, the liquid may have a pH level ranging from 5 pH to 8 pH.

[0019] In some embodiments of the exemplary bioreactor system 100, the reservoir may have an inner chamber 107a containing at least a second fluid medium. The second fluid medium may include at least one gas, at least one nutrient in an amount sufficient to supply at least a plurality of cells, a liquid, or any combination thereof. The liquid of the second medium may further include the volume, temperature, and pH level of the liquid in the reservoir chamber 107. Nutrients that may be used for culturing in the exemplary bioreactor system may include, but are not limited to, glucose, lactate, glutamine, glutamic acid, or combinations thereof. One or more gases that may be used for culturing in the exemplary bioreactor system may include, but are not limited to, oxygen, nitrogen, carbon dioxide, air, or any combination thereof. In some embodiments, the one or more gases are dissolved gases (e.g., dissolved in the medium).

[0020] Bioreactor 103, in some embodiments, can further include at least two sensors (not shown) that measure multiple parameters, both physical and chemical, in the fluid medium and cells contained therein. In some embodiments, bioreactor 103 may further include at least three sensors. In some embodiments, bioreactor 103 may further include at least four sensors. In some embodiments, bioreactor 103 may further include five or more sensors. In some embodiments, reservoir chamber 107 of the exemplary bioreactor system can include at least one sensor that measures both physical and chemical parameters in the fluid medium contained therein. In some embodiments, reservoir chamber 107 may further include at least two sensors. In some embodiments, reservoir chamber 107 may further include at least three sensors. In some embodiments, reservoir chamber 107 may further include at least four sensors. In some embodiments, reservoir chamber 107 may further include five or more sensors.

[0021] In some embodiments, the parameters sensed and measured (e.g., via sensors) in the exemplary bioreactor system can be selected from, but are not limited to, at least the following: cell concentration level, at least one nutrient level, at least one gas level, first culture medium liquid volume, first culture medium liquid pH level, first culture medium liquid temperature, or any combination thereof.

[0022] In some embodiments, the parameters are sensed, detected, measured, controlled, or any combination thereof. In some embodiments of the exemplary bioreactor system, these parameters are selected from, but not limited to, at least the following: a level of cell concentration contained in a bioreactor chamber, a flow rate of a fluid into a reservoir, a flow rate of the same or a different fluid into a bioreactor chamber, a volume of at least one fluid, a pH of at least one fluid, a temperature of at least one fluid, a level of dissolved oxygen in at least one fluid, a level of dissolved CO2 in at least one fluid, a level of HCO3 in at least one fluid, a level of nutrients in at least one fluid, and any combination thereof.

[0023] In some embodiments, the parameters sensed and measured may be, but are not limited to, temperature, pH level, glucose concentration, dissolved oxygen concentration, lactate concentration, glutamine concentration, glutamate concentration, dissolved carbon dioxide concentration, HCO ion concentration, and any combination thereof.

[0024] In some embodiments, at least three of the above parameters are detected by sensors in the bioreactor system. In some embodiments, at least three of the above parameters are measured by the bioreactor system. In some embodiments, at least three of the above parameters are controllable by the configuration of the bioreactor system (e.g., via a controller controlling the fluid circuitry). In some embodiments, the exemplary bioreactor system is capable of controlling the sensed and measured parameters to a predetermined set point or predetermined range of that measured value. In some embodiments, the exemplary bioreactor system is capable of controlling one to five parameters. In some embodiments, the exemplary bioreactor system is capable of controlling five to ten parameters. In some embodiments, the exemplary bioreactor is capable of controlling at least three parameters simultaneously, substantially simultaneously, or the control inputs for multiple parameters are not simultaneous, but activation of the fluid circuitry within the bioreactor system based on the control inputs affects changes to these parameters simultaneously.

[0025] 1A, the fluid circuit may include a fluid circuit 109 in which a first pump 109a extends from a reservoir chamber 107 into a bioreactor 103 and a second pump 109b may extend from at least one bioreactor into at least one reservoir. In some embodiments, an inlet 111 of the reservoir chamber 107 can be used to input materials for bioreactor culture. In some embodiments, an outlet 105 of the reservoir chamber 107 can be used to remove spent waste, medium, or any combination thereof.

[0026] In some embodiments, the configuration of the fluid circuit (e.g., pump system) 109 in the exemplary bioreactor system causes the reservoir chamber 107 to control all inputs to the bioreactor via the controller 106 or a component thereof, e.g., a processor. In some embodiments, the reservoir chamber 107 can use its own pump system in conjunction with the reservoir to control parameters of the biological reaction or cells and first fluid medium within the bioreactor.

[0027] In some embodiments, the exemplary bioreactor system can measure at least one parameter in the bioreactor and use that measurement to control that parameter by altering a parameter in the reservoir. In some embodiments of the exemplary bioreactor system, the measurement of the parameter is made in the bioreactor 103 and controlled by altering the parameter in the reservoir chamber 107. In some embodiments, the exemplary bioreactor system can alter the parameter in the reservoir to affect a change in the parameter in the bioreactor 103 using the pump system 109. In some embodiments of the exemplary bioreactor system, the measurement of the parameter is made in the bioreactor 103 and controlled solely by altering the parameter in the reservoir chamber 107. For example, in some embodiments, the pH level of the first medium in the bioreactor can be controlled to a range of 6.5 pH to 7.5 pH by controlling the reservoir fluid medium range to a range of 5 pH to 8 pH while controlling other set points. In some embodiments, the following parameters introduced by the pump system 109 can also be measured by sensors in either the bioreactor or the reservoir: the flow rate of bioreactor liquid to the reservoir, the flow rate of liquid from the reservoir to the bioreactor, or any combination thereof.

[0028] In some embodiments, the exemplary bioreactor system may require more medium and nutrients and larger culture volumes. In some embodiments, the exemplary bioreactor system may allow for the volume of liquid medium within the bioreactor to be changed, allowing for the addition of additional medium without the need to transfer the cells to a separate vessel.

[0029] In some embodiments, suitable controllers for controlling the flow of gases and / or fluids can include, but are not limited to, one or more valves and / or one or more pumps, for example, as shown herein.

[0030] In some embodiments, the exemplary bioreactor system can use a pump system to regulate the volume of medium contained in the bioreactor.

[0031] In some embodiments, the pump system may remove at least a portion of the liquid from the bioreactor, add at least a portion of the liquid in the reservoir to the liquid in the bioreactor, or any combination thereof, such that the volume of the liquid in the bioreactor is adjustable.

[0032] In some embodiments, the exemplary bioreactor system 100B may alternate between culture modes, as described in more detail below. In some embodiments, alternating between culture modes may facilitate the ability of the bioreactor system 100B to simultaneously control multiple parameters.

[0033] In some embodiments, the system includes a batch culture mode. In some embodiments, the exemplary bioreactor system can operate in a batch culture mode by having the reservoir chamber 107 receive a predetermined amount of medium and pumping the medium into the bioreactor. The bioreactor can then discharge waste products through the outlet 105.

[0034] In some embodiments, the system includes a fed-batch culture mode. In some embodiments, the exemplary bioreactor system can process the fed-batch mode by having the reservoir chamber 107 receive a predetermined amount of medium and pumping the medium into the bioreactor. In some embodiments, the process is then repeated for a predetermined amount of time. In some embodiments, the predetermined amount of time is between 1 day and 2 months. In some embodiments, the predetermined amount of time is between 2 days and 4 months.

[0035] In some embodiments, the system includes a perfusion culture mode. In some embodiments, the exemplary bioreactor system can handle the perfusion culture mode by having the reservoir chamber 107 receive medium through the inlet 111 and pumping this same medium into the bioreactor. Sensors detect parameters such that only a significant amount of waste is removed through the bioreactor outlet 105.

[0036] In some embodiments, the system includes a recirculation mode. In some embodiments, the exemplary bioreactor system can handle a recirculation culture mode with a first pump 109a continuously pumping liquid medium from a reservoir to the bioreactor and a second pump 109b continuously pumping liquid medium from the bioreactor to the reservoir.

[0037] 1C is a block diagram of a controller 106 that controls bioreactor systems 100A and 100B according to one or more embodiments of the present disclosure. Controller 106 may include a processor 200, non-transitory memory 210, input and / or output devices 215, communication circuitry 220, interface circuitry 225, and / or control circuitry 230. Processor 200 may execute a cell culture control machine learning model 205 and an image processing module 204. Processor 200 may receive sensor data from multiple sensors 104a, 104b, 104c via interface circuitry 225 and generate commands to digitally control devices via control circuitry 230.

[0038] 1A (e.g., an imaging camera) of any suitable type, can be positioned anywhere in and / or around the bioreactor chamber and / or reservoir to output image data of an image of any portion of the bioreactor, including generating images of a cell culture growing in the bioreactor for analysis by the controller 106. Images of the cell culture via the interface circuit 225 can be analyzed and processed by the image processing module 204.

[0039] In some embodiments, an automated cell counter (not shown) may automatically microsample the cell culture by any suitable method to determine the number of cells in the cell culture. At least one imaging camera may be attached to the microscope to image the cells in the microsample. The images are analyzed by the image processing module 204 to determine the types and numbers of different cells in the cell culture at time points either set by the operator or by control of the cell culture control machine learning model 205.

[0040] In some embodiments, the cell analyzer can be used to test activity and / or cell phenotype within the cell culture in the bioreactor chamber.

[0041] In some embodiments, the input / output devices 215 of the controller 106 may include any display device known in the art for displaying processed results and values ​​of any sensed parameters to an operator or user of the system 100. The controller 106 may also include one or more user interface devices (e.g., without limitation, a mouse, light pen, pointing device, keyboard, touch-sensitive screen, or any other input device known in the art) used by a user or operator of the bioreactor systems 100A and 100B to input data and / or appropriate commands to the controller 106. For example, a user may control the bioreactor 103 by inputting appropriate commands to the controller 106 via one or more user interface devices, which in turn causes the controller 106 to send appropriate control signals to any of the bioreactor fluid controls via the control circuitry 230. The user may input any appropriate parameters via the one or more user interface devices as inputs to the MLM 205 and to view any outputs generated from the MLM 205 on a display.

[0042] In some embodiments, computer-controlled sensor and / or electronic control components of the bioreactor system that can be monitored and / or controlled via interface circuit 225 and / or via control circuit 230 to sample multiple sensors can include, for example, but are not limited to: (1) An agitator or stirrer that keeps the contents of the bioreactor mixed and ensures proper distribution of nutrients, oxygen, and heat. Different types of impellers (paddles, turbines) can be used depending on the specific needs of the culture. (2) A temperature control system that maintains the optimal temperature for cell growth and activity. Bioreactors can use heating jackets, internal coils, and / or even water baths to achieve this. (3) A pH control system that can use any suitable pH sensor and / or dosing system to adjust the acidity or alkalinity of the culture medium to maintain it within a desired pH range. (4) Aeration and aeration to oxygenate the culture. Some bioreactors can use spargers to introduce gas bubbles, while others rely on agitation or membrane technology. Other gases, such as CO2, can also be controlled. (5) A nutrient inlet-outlet that can provide fresh nutrients to the culture and remove waste materials that can be fed into the bioreactor. This can be done via computer-controlled ports and / or integrated tubing. (6) Sensors and / or analytical instruments that monitor critical parameters such as, for example, but not limited to, oxygen levels, pH, and / or cell density. The bioreactor 103 can include any suitable variety of sensors and / or probes coupled to provide real-time data. (7) A computer-controlled sampling port to take samples of the culture for analysis without interrupting the process. (8) A sterilization system to keep the bioreactor clean and free of contamination. Steam sterilization may be used. Pre-sterilized single-use systems may also be used. (9) A computer-controlled sparger and / or air inlet that introduces gases such as air or oxygen directly into the culture medium via a sparger and / or diffuser. (10) A computer-controlled foaming system to manage excessive foaming that may impede mixing and oxygen transfer. Anti-foam agents and / or mechanical devices may be deployed by the computer-controlled foaming system to manage this.

[0043] The embodiment shown in Figure 1A depicts basic components of a bioreactor system solely for conceptual clarity in describing how machine learning models can monitor and / or control cell growth by processing sensor data and / or controlling a bioreactor system's controller. The bioreactor 103 can include any suitable form factor and any suitable number of additional elements (not shown in Figure 1A) to provide optimal and adaptive culture, such as, for example, but not limited to, the bioreactor system 100A and 100B elements shown in Figures 1A-1C. For example, different embodiments of bioreactors can be described below and in the following references. More detailed embodiments of the bioreactor system can be found, for example, in the following U.S. patents and patent applications, which are incorporated herein in their entireties: U.S. Patent No. 11,549,090, filed August 21, 2017; U.S. Patent No. 11,667,882, filed March 7, 2022; U.S. Patent No. 11,859,163, filed October 24, 2022; and U.S. Patent Application No. 17 / 562,586, filed December 27, 2021.

[0044] In some embodiments, the bioreactor 103 may include a chamber having an enlarged shape, such as a frusto-conical shape, or a portion thereof, that results in a reduction in the velocity of the fluid. Thus, in this case, the bioreactor may be referred to herein as a "cone" or "bioreactor-cone."

[0045] In some embodiments, bioreactor 103 can include two portion chambers divided by a perforated barrier that allows for constant fluid flow, such as, but not limited to, a fluid growth medium, and a plurality of cells can be retained in the second (upper) chamber. Any of a plurality of sensors, shown at 104a and 104b, may be coupled to both the cell growth subchamber (conical) and / or the medium (second) subchamber to sample any of the sensor parameters.

[0046] Those skilled in the art will understand that the term "perforated barrier" can be used interchangeably with the terms "filter" or "membrane" or "perforated plate," all of which have the same qualities and meaning.

[0047] In some embodiments, the perforated barrier can include a plurality of perforations that allow a liquid, such as a growth medium, to flow bidirectionally through the perforations in the perforated barrier, such that the liquid can flow from the first chamber to the second chamber and from the second chamber to the first chamber.

[0048] Those skilled in the art will understand that the term "first chamber" as used herein may, in some embodiments, be used interchangeably with the term "lower chamber," with all of its same meanings and qualities. Those skilled in the art will understand that the term "second chamber" as used herein may, in some embodiments, be used interchangeably with the term "upper chamber," with all of its same meanings and qualities. In some embodiments, cells are cultured in the second chamber of a bioreactor vessel.

[0049] In some embodiments, cell types suitable for growth in the bioreactor 103 disclosed herein may include, but are not limited to, stem cells, acinar cells, adipocytes, alveolar cells, ameloblasts, annulus cells, arachnoid cells, astrocytes, blastocysts, calvarial cells, cancer cells (adenocarcinoma, fibrosarcoma, glioblastoma, hepatoma, melanoma, myeloid leukemia, neuroblastoma, osteosarcoma, sarcoma), cardiomyocytes, chondrocytes, chordoma cells, chromaffin cells, cumulus cells, endothelial cells, endothelial-like cells, ensheathing cells, epithelial cells. , fibroblasts, fibroblast-like cells, germ cells, hepatocytes, hybridomas, insulin-producing cells, stromal cells, pancreatic islet cells, keratinocytes, lymphocytes, macrophages, mast cells, melanocytes, meniscus cells, mesangial cells, mesenchymal progenitor cells, monocytes, mononuclear cells, myeloblasts, myoblasts, myofibroblasts, neuronal cells, odontoblasts, oocytes, osteoblasts, osteoblast-like cells, osteoclasts, osteoclast precursors, oval cells, papillary cells, parenchymal cells, pericytes, and peridontal ligament cells Ligament cells, periosteal cells, platelets, lung cells, preadipocytes, epicardial cells, renal cells, salivary gland stem cells, Schwann cells, secretory cells, smooth muscle cells, sperm cells, astrocytes, stem cells, stem cell-like cells, Stertoli cells, interstitial cells, synovial cells. cells), synoviocytes, T cells, tendon cells, T lymphoblasts, trophoblast cells, natural killer cells, dendritic cells, urothelial cells, vitreous cells, etc.;For example, but not limited to, cells derived from any of the following tissues: adipose tissue, adrenal gland, amniotic fluid, amniotic sac, aorta, arteries (carotid, coronary, lung), bile duct, bladder, blood, bone, bone marrow, brain (including cerebral cortex), breast, bronchus, cartilage, cervix, villi, colon, conjunctiva, connective tissue, cornea, dental pulp, duodenum, dura mater, ear, endometrial cyst, endometrium, esophagus, eyeball, eye, foreskin, gallbladder, ganglion, gums, head / neck, heart, heart valve, hippocampus, ilium, intervertebral disc, joint, jugular vein, kidney, knee, lacrimal gland, ligament, liver, lung, lymph node, mammary gland, mandible, meninges , mesoderm, microvasculature, mucosa, muscle-derived (MD), myeloid leukemia, myeloma, nose, nasopharynx, nerve, nucleus pulposus, oral mucosa, ovary, pancreas, parotid gland, penis, placenta, prostate, kidney, respiratory tract, retina, salivary gland, saphenous vein, sciatic nerve, skeletal muscle, skin, small intestine, sphincter, spine, spleen, stomach, synovium, teeth, tendons, testes, thyroid, tonsils, trachea, umbilical artery, umbilical cord, blood, umbilical cord, umbilical cord, umbilical cord artery, umbilical cord, umbilical cord blood, umbilical vein, umbilical cord (Wharton's jelly), urinary tract, uterus, vasculature, cardiac ventricle, vocal folds, and cells, or any combination thereof. In some embodiments, cells grown in the bioreactors disclosed herein may comprise a combination of different cell types. As used herein, in some embodiments, the terms "cell" and "microorganism" may be used interchangeably, all having the same meaning and quality.

[0050] In some embodiments, bioreactor 103 may include one or more sensors 104a, 104b, and 104c, which may be suitably linked and / or connected to controller 106 via interface circuit 225 to monitor and / or regulate various physical and / or chemical parameters within the growth medium (e.g., temperature, pH, glucose concentration, dissolved oxygen concentration, concentration of dissolved carbon dioxide or HCO ions, concentration of lactate, and ionic strength, etc.) in the bioreactor and / or bioreactor headspace and / or growth medium, which may all be sensed, monitored, and controlled at fluid reservoirs and / or various inlet or outlet ports connectable to the bioreactor. In some embodiments, the sensors may detect products synthesized by cells or microorganisms grown in the bioreactor. In some embodiments, control of some of the above features may require mixing of the growth medium, which may be provided at the fluid reservoirs.

[0051] In some embodiments, the computer-based system of the disclosed bioreactor controls and monitors metabolic and environmental factors such as oxygen, pH, glucose, lactate, glutamine, glutamate, etc. For example, the computer-based system of the disclosed bioreactor is applied to different biological materials, such as cells, that consume or produce O at different rates, depending on their state. Furthermore, the computer-based system of the disclosed bioreactor may be applied to different types of cells that consume or produce O differently.

[0052] In some embodiments, the computer-based system of the disclosed bioreactor may be applied to non-activated T cells, which may consume small amounts of O2 and glucose and produce very small amounts of lactate. When the T cells are subsequently activated, they not only begin to proliferate but also change their metabolism, shifting their energy cycle from O2 to lactate, thereby altering the consumption rates of all of the above, resulting in increased lactate secretion per cell. Such activity depends on the level of activation / stimulation achieved by adding antibodies to the culture medium. Within a few days, depending on the stimulation level, the T cells may slow down, return to their natural state, or become exhausted (reduced Lac production per cell). In some embodiments, the computer-based system of the disclosed bioreactor measures and controls, for example, bacterial contamination, when the consumption rates of O2 and glucose increase dramatically.

[0053] In some embodiments, the computer-based system of the disclosed bioreactor is applied to T cells as they are introduced into a target, which activates the T cells and then alters their consumption and production rates.

[0054] In some embodiments, the computer-based system of the bioreactor of the present disclosure applies online monitoring to identify such changes and predict the state of the cells with respect to at least one of subsequent activation, transduction, contamination in culture, differentiation, cell death, exhaustion and / or even phenotype and killing potential.

[0055] In some embodiments, the computer-based system of the disclosed bioreactor is applied to primary cells, such as, but not limited to, mesenchymal stem cells. When stimulated to proliferate until a surface is covered (confluence) and inhibited by contact inhibition, mesenchymal stem cells change their metabolism. These primary cells then become activated, not only beginning to proliferate, but also changing their metabolism and shifting their energy cycle from O2 to lactate, altering the consumption rates of all of the above, resulting in increased lactate secretion per cell. Such activity depends on the level of activation / stimulation achieved by adding antibodies to the culture medium. Within a few days, depending on the stimulation level, these primary cells slow down and either return to their natural state or become exhausted (reduced Lac production per cell). In some embodiments, the computer-based system of the disclosed bioreactor measures and controls, for example, bacterial contamination, as well as dramatic increases in O2 and glucose consumption rates.

[0056] In some embodiments, the computer-based system of the disclosed bioreactor may be applied to primary cells when they are introduced into a target that activates these primary cells and subsequently alters their consumption and production rates.

[0057] In some embodiments, the computer-based system of the bioreactor of the present disclosure may apply online monitoring to identify such changes and predict the state of the cells with respect to at least one of subsequent activation, transduction, contamination in culture, differentiation, cell death, exhaustion and / or even phenotype and killing potential.

[0058] In some embodiments, the culture chamber (e.g., assay) can include multiple sensors 104a, 104b, and 104c similar to those in bioreactor systems 100A and 100B described above. Multiple cells can be removed from bioreactor 103 and introduced into the culture chamber to measure the state of the cells, which can be monitored by cell culture control machine learning model 205.

[0059] In some embodiments, the computer-based system of the disclosed bioreactor can be applied to cells (e.g., stem cells), where the cells are stimulated to grow until they differentiate, and then identify when the cells differentiate and not only begin to proliferate but also change their metabolism, shifting from the O2 energy cycle to lactate, thus changing the consumption rates of all of the above, meaning more lactate secretion per cell. In some embodiments, the computer-based system of the disclosed bioreactor measures and controls when, for example, bacterial contamination, O2 and glucose consumption rates dramatically increase.

[0060] In some embodiments, the computer-based system of the bioreactor of the present disclosure can be applied as an online QC to ensure sterility. In some embodiments, the computer-based system of the bioreactor of the present disclosure can be applied to predict when cells will be ready to move to different stages of the culture or to intervene during the culture to reactivate them.

[0061] In some embodiments, the computer-based systems of the bioreactors of the present disclosure can be applied to measure and control not only cell metabolic changes but also "time courses" (e.g., parametric changes over time) and / or gradients and / or differences (e.g., deltas) between parameter value points to predict outcomes.

[0062] FIG. 2 illustrates sensor measurement output data from a bioreactor according to one or more embodiments of the present disclosure. The top trace is the O2 level within the cone. The bottom trace is the circulation rate of the pump feeding the cone. The 40% marker is the set point (SP) for activating perfusion. Points A-B are unactivated cells showing stable oxygen consumption. Point C is the time at which activation reagents can be added. Points D-E can be where cells consume significantly more oxygen. Between points E and G is where viruses are introduced for genetic manipulation. Points I-J are where the pump begins to operate. The processor 200 can now calculate the slope. In other embodiments, the pump can be stopped for X minutes and the slope measured again, where X is any suitable positive number.

[0063] Figure 3 is a graph of glucose (Glu) and lactate (Lac) levels obtained from the same data (e.g., the same run) as Figure 2. However, the slope of Glu varies differently than Lac. In some embodiments, the computer-based system of the disclosed bioreactor can be adapted so that results can be correlated to the difference (e.g., delta) between the slopes of one parameter for the same parameter at different time points and / or to correlate changes between the differences (deltas) of different parameters. In this way, a time course concept can be used to examine and compare changes in consumption over an X amount of time compared to the slope of a later stage, where X is any suitable positive number.

[0064] In some embodiments, processor 200 evaluates the slope of A / B where A=GLU and B=LAC is approximately flat, however, once cells in cell culture can be activated, the slope of A / B can become very steep.

[0065] In some embodiments, the computer-based system of the bioreactor of the present disclosure can be applied as shown in Figure 4. Figure 4 shows that increasing the O2 pump rate correlates with increasing dissolved O2 (DO) in the cell culture, so the cells can still be activated and grow.

[0066] In some embodiments, the computer-based system of the disclosed bioreactor can be applied as shown in FIG. 5. FIG. 5 is a graph of both dissolved oxygen (DO) levels and O2 pump speed versus time. The graph also shows the DO setpoint value. Inside the box, the pump is at its first maximum event on day 5, then at its second maximum event again on day 8, when the cells consume more O2, then less, and then switch back on on day 9. Cells change metabolism, which correlates with changes in phenotype or cell population during growth. Therefore, changes in consumption / secretion of factors and metabolic factors are used to correlate state and / or change culture conditions. In other words, this metabolic change correlates with phenotypic changes in cell state or phenotypic protein changes in cells, which are linked to phenotype and activity, and then to predictions of number and state.

[0067] In some embodiments, the computer-based system of the bioreactor of the present disclosure can be applied as shown in Figure 7. Figure 7 shows the change in lactate levels as a function of time (days) in an exemplary run of Lac.

[0068] In some embodiments, the computer-based system of the bioreactor of the present disclosure can be used to correlate multi-parameter changes / gradients (O2, pH, Glu, Lac levels) at different time points to predict the state of the culture and use it in several different applications.

[0069] In some embodiments, the computer-based system of the bioreactor of the present disclosure can apply graphs of bacterially contaminated runs as supporting data and correlate desired results based on this data.

[0070] In some embodiments, the computer-based system of the bioreactor of the present disclosure can apply the assistance data to result in a lower and / or higher activation rate or percentage of activated cells.

[0071] In some embodiments, the computer-based system of the bioreactor of the present disclosure can apply supporting data to indicate the effect of adding an activation reagent after cell growth has slowed.

[0072] In some embodiments, the computer-based system of the bioreactor of the present disclosure can apply supporting data of samples of cells at different stages to determine correlations with phenotypes.

[0073] In some embodiments, the computer-based system of the bioreactor of the present disclosure can apply supporting data to indicate killing activity due to metabolic alterations.

[0074] In some embodiments, a cancer drug resistance / activity assay that uses a metabolic change readout to test anti-cancer drugs can be used to determine whether a targeted drug stops or slows tissue growth by measuring metabolic changes and correlating drug resistance and / or activity assays.

[0075] 6 is a graph showing oxygen consumption levels (DO) versus run time, according to one or more embodiments of the present invention. The graph shows the correlation from activation time (left arrow) to run time with changes in oxygen consumption during the run for multiple samples. As oxygen increases (right arrow), the process slows down due to metabolic changes, not due to cell death. Viability is 96%.

[0076] 7 is a graph showing lactate accumulation rate versus run time, according to one or more embodiments of the present invention. The graph shows the correlation from activation time (arrow) across run time with changes in lactate accumulation rate during running.

[0077] 8 is a graph showing glucose consumption rate versus run time, according to one or more embodiments of the present invention. The graph shows the correlation from activation time (arrow) across run time with changes in glucose consumption rate during run.

[0078] In general, those skilled in the art know that a machine learning model can be trained using a training dataset having specific input data features and specific output data features to match a machine learning model that outputs specific output data features within a desired prediction accuracy in response to the input of specific input data features. In other words, the trained machine learning model maps specific input data features to specific output data features. As a result, without the above-mentioned detailed specificity of (1) a specific machine learning model and (2) a specific training dataset with specific inputs and outputs, any training process cannot achieve convergence that provides prediction accuracy.

[0079] In some embodiments, the exemplary parameter correlations over time shown in Figures 6-8 across thousands of cell culture runs for thousands of subjects (e.g., patients) can be utilized in constructing a dataset capturing multiparametric time-dependent correlations between multiple sensor parameters and multiple cell culture growth parameters. These specific input features in the dataset can include a desired cell growth configuration (e.g., initialization and definition files) and sensor data from each of multiple sensors (e.g., different sensor types, such as pH, DO, and temperature) at different sampling times, as well as image data. The desired cell growth configuration can include at least one cell culture growth parameter from the multiple cell culture growth parameters and at least one desired range for each of the multiple sensor parameters measured by the multiple sensors at predetermined time intervals for each of the at least one cell culture growth parameter during cell culture growth. In other embodiments, the at least one desired range can include a single parametric set point.

[0080] Particular output features in the dataset may include multiple output data features and / or output features related to cell culture parameter predictions, which may include multiple cell culture control actions such as, but not limited to, a display, sending at least one control circuit command (e.g., a digital command to the control circuit 230) to one or more controllers to control gas levels and / or liquid flow in the bioreactor chamber, and / or to remove waste from the liquid medium.

[0081] 9A-9E are tables illustrating different parameter features whose values ​​can be used to construct a dataset for training at least one machine learning model. These tables may relate to, but are not limited to, the above-described bioreactor chamber embodiment of a conical-shaped bioreactor chamber separated by a perforated barrier into two subchambers (a conical subchamber for cell growth and a medium subchamber). Each subchamber may have its own sensors and computer controller that control gas and / or fluid flow within the subchamber.

[0082] FIG. 9A is a table showing sensor data levels measured in the cone and media subchambers at predetermined sampling times during a cell growth cycle, according to one or more embodiments of the present disclosure.

[0083] FIG. 9B illustrates correlations between measured sensor data and cell culture growth parameters, according to one or more embodiments of the present disclosure. Time-dependent multivariate correlations between measured sensor data in the cone and medium at a given sampling time can be used to determine cell culture growth parameters that can be derived from these time-dependent correlations. For example, from FIG. 9B , correlations between measured cone DO, pH, and lactate levels measured by sensors at different sampling times (from the start time of the cell growth process) can be used to monitor cell seeding. Similarly, correlations between cone DO levels, medium lactate levels, medium glucose levels, medium glutamine levels, and medium glutamate levels measured at different sampling times can be used to determine cell phenotype and cell harvest. These correlations can be used to build datasets for training machine learning models across multiple cell samples collected from multiple subjects (e.g., patients) for multiple sampling times from the cell run start time to the cell run end time.

[0084] In some embodiments, correlations between two or more parameters (e.g., oxygen / lactate / glucose consumption) can represent cellular stages after activation, such as when glucose slows, lactate increases, and oxygen also increases, and parameter correlations can be based on measuring the difference in slopes. For example, at day 11, metabolism changes and the cells are no longer activated, as exemplified by changes in the profiles of all three parameters.

[0085] In some embodiments, for example, a data set capturing correlations between various parameters over time detected and monitored in real time by sensors 104a, 104b, and 104c can be used to train cell culture control machine learning model 205 to predict cell states and / or outcomes at different stages of the expansion process. As a result, these correlations between cell states and particular measured parameters can provide future estimates related to cell quantity, cell health, and other factors. Furthermore, if a particular parameter at a particular point in the expansion process is determined to be likely to result in unhealthy cells at a particular future time and not yield good cells for harvest, the MLM may, for example, output a warning to halt the particular cell expansion process and / or output a set of commands via control circuitry that automatically controls bioreactor fluid controls and / or temperature controllers to alter system parameters to place cell growth on a different path toward good cell health so that cells can be harvested in the future.

[0086] In some embodiments, at least one cell culture control MLM205 may be trained using a parametric correlation between at least two and three parameters. In some embodiments, at least one cell culture control MLM205 may be trained using a parametric correlation between at least three and four parameters. In some embodiments, at least one cell culture control MLM205 may be trained using a parametric correlation between at least four and six parameters. In some embodiments, at least one cell culture control MLM205 may be trained using a parametric correlation between at least six and ten parameters. In some embodiments, at least one cell culture control MLM205 may be trained using a parametric correlation between at least ten parameters. In some embodiments, at least one cell culture control MLM205 may be trained using a parametric correlation between at least 50 parameters.

[0087] 9C is a table illustrating desired cell growth run configuration file parameters according to one or more embodiments of the present disclosure. These parameters can be entered into the system when initiating a cell growth run (e.g., an initialization configuration data file). These parameters can include, for example, performing an action regardless of machine learning model output. Furthermore, these parameters can be used in constructing a dataset for training at least one cell culture control MLM 205.

[0088] 9D is a table showing input data features for a conical bioreactor chamber according to one or more embodiments of the present disclosure. The input data features may include cell culture start time, sampling time after cell culture start time, cone and / or medium gas parameters, cone and / or medium parameter levels (DO, pH, CO, O, N, glucose, lactate, glutamine, glutamate (similar to FIG. 9A)), cell count and / or image data from medium and / or cone images.

[0089] In some embodiments, the computer-based system of the bioreactor of the present disclosure can be used to construct multiple training data sets based on correlations between different gradients of different parameters, such as, but not limited to, O2, Glu, Lac, pH, and cellular and system parameters at different times t, where t=0 can be the start of the growth process that predicts the state of cells and their growth process at a future time. The at least one cell culture control machine learning model 205 can be trained to output one or more of the following cell culture parameter predictions based on monitoring the different parameters: 1. Prediction of activation status and the number or percentage of activated cells 2. Prediction of cell number 3. Prediction of cell proliferation or differentiation state 4.Prediction of cell differentiation 5. Phenotype (activation / inactivation) prediction 6. Predict populations and subpopulations within a culture that behave metabolically differently due to stimuli such as activation, heat shock, stress, and hypoxia. 7. Prediction of contamination (bacteria or fungi) 8. Predicting or even testing functionality (will T cells respond to and kill the target) 9. Predicting when cells may change and require intervention such as reactivation or transfer to a different medium. 10. Food contamination prediction: This can be used in other industries such as food to see contamination. 11. Prediction of quality control (QC) tests that can be performed within the devices as they grow, including phenotype, activity, and sterility. The QC concept uses indirect measurements and correlations to test activity and phenotype. 12. Predictions for the identification of cancer cells in culture by metabolic consumption. 13. Prediction of the identified activity of drugs such as antibiotics or anticancer drugs based on changes in consumption. 14. Prediction of drug resistance and activity in cancer cells - for example, metabolic changes due to the addition of anticancer drugs.

[0090] 9E is a table illustrating output data features of a conical bioreactor chamber associated with culture for cell parameter prediction, according to one or more embodiments of the present disclosure. The input data features of FIG. 9D combined with the output data features of FIG. 9E can be used to generate a dataset across multiple cell samples taken from multiple subjects at different sampling times to generate a dataset with millions of data features for training at least one cell culture control MLM 205. The predicted values ​​of the output data features shown in FIG. 9E can be based on at least one cell culture control MLM 205 trained on the measurement data from FIG. 9B.

[0091] In some embodiments, the at least one cell culture control MLM 205 may output predicted values ​​of a particular output data feature, such as that shown in FIG. 9E, with a prediction accuracy of 0.1-1% for measurements in the dataset, depending on the type of prediction parameter selected. In other embodiments, the at least one cell culture control MLM 205 may output predicted values ​​of a particular output data feature, such as that shown in FIG. 9E, with a prediction accuracy of 1-10% for measurements in the dataset, depending on the type of prediction parameter selected. In yet other embodiments, the at least one cell culture control MLM 205 may output predicted values ​​of a particular output data feature, such as that shown in FIG. 9E, with a prediction accuracy of 10-30% for measurements in the dataset, depending on the type of prediction parameter selected.

[0092] In some embodiments, the different predictions or predicted results shown in Figure 9E can be in the form of flags (Yes, Contaminated, or No Contaminated) based on input sensor level readings over multiple sampling times and the correlations between them. In other embodiments, the predictions can include predicted values ​​and / or predicted ranges for each measurement-based value of the output metric at future times based on correlations such as those shown in Figures 2-8 and later figures (Figures 10-16A and 16B).

[0093] 9F is a table of output data characteristics from at least one cell culture control MLM 205 sending output commands to control circuit 230, according to one or more embodiments of the present disclosure. The at least one control circuit command can be used by control circuit 230 to automatically control gas and / or liquid flow rate changes and / or waste removal within the bioreactor chambers.

[0094] In some embodiments, the at least one control circuit command can cause at least one cell culture prediction (eg, any of the predictions in FIG. 9E) to be displayed on a display.

[0095] In some embodiments, the at least one control circuit command can control a gas regulator that varies the gas level in the bioreactor chamber.

[0096] In some embodiments, the at least one control circuit command can control a device that controls liquid flow of the nutrient fluid from the reservoir chamber to the bioreactor chamber.

[0097] In some embodiments, the at least one control circuit command can control, for example, a device coupled to the bioreactor chamber to remove waste products from the liquid medium.

[0098] In some embodiments, the at least one cell culture control MLM 205 may be further trained to output automated actions in the bioreactor system 100A and / or 100B, such as in the following scenarios:

[0099] In some embodiments, stem cells may be grown within the bioreactor on a surface or in suspension. Once the stem cells reach confluence or a desired density, their growth may slow or cease consumption, which may in turn alter the rate of glucose, oxygen, and / or lactate accumulation and alter the ratios between them. At this point, at least one cell culture control MLM205 can cause the system to add cytokines and / or differentiation factors to the cell culture to induce differentiation toward a desired phenotype.

[0100] In some embodiments, cells such as mesenchymal stem cells can secrete extracellular vesicles called exosomes. Seeded cells in a bioreactor can grow until they reach a specific density or activity, defined by the ratio of metabolic parameters. Once a specific density is reached, the medium can be automatically changed by at least one control command output from the at least one cell culture control MLM 205 to the controller, changing the medium from a rich growth support medium to a recovery medium, which may be serum-free, to ensure a high yield of harvested exosomes. The same scenario can occur for vaccine, virus, protein, and / or antibody secretion, and yield can be optimized using at least one control command output from the at least one cell culture control MLM 205.

[0101] In some embodiments, mesenchymal stem cells may be grown to confluence, and then oxygen levels within the system may be automatically altered by at least one control command output from at least one cell culture control MLM 205 to control the device to prime the cells to a hypoxic state that has been shown to result in stronger angiogenic activity.

[0102] In some embodiments, cell contamination can be identified by measurements taken over consecutive time samples that show correlations, such as a sudden change in pH, a sudden drop in DO, glucose, lactate, pressure, and / or a change in a color parameter of the liquid medium (e.g., the liquid medium may become cloudy). Data from thousands of cell samples terminated prematurely due to contamination can be used to train at least one cell culture control MLM205 to identify cell contamination. Thus, when real-time measurement sensor and / or image data at a predetermined sampling time for a cell culture can be input into at least one cell culture control MLM205 trained with these correlations, the at least one cell culture control MLM205 can output a prediction that the cell culture is contaminated and generate a command to display a warning or sound an alarm to the bioreactor system operator.

[0103] In some embodiments, the at least one cell culture control MLM 205 may be further trained to generate control circuit commands that perform automatic system corrections by initiating changes in gas and / or liquid levels within the bioreactor chamber, as shown in FIG. 9E. For example, if a decrease in DO or a change in, for example, lactate formation rate, is observed over successive time samples, indicating that cells may not be responding as expected, the at least one cell culture control MLM 205 may detect this and output a command to the controller to automatically introduce interleukin-2 (e.g., IL-2) into the cell sample, for example, to increase T cell proliferation. The at least one cell culture control MLM 205 may automatically monitor the administration schedule of IL-2 over time to prevent T cell exhaustion and optimize cell stimulation.

[0104] The cell culture control machine learning model 205 may include types of machine learning models that may include, but are not limited to, decision trees, boosting, support vector machines, neural networks, nearest neighbor algorithms, naive Bayes, bagging, random forests, etc. In some embodiments, optionally in combination with any of the above or below embodiments, the exemplary neural network technique may be one of, but is not limited to, a feedforward neural network, a radial basis function network, a recurrent neural network, a convolutional network (e.g., U-net), or other suitable network.

[0105] In some embodiments, optionally in combination with any of the embodiments described above or below, an exemplary implementation of a neural network may be performed as follows. i) Define the neural network architecture / model, ii) forwarding the input data to an exemplary neural network model; iii) incrementally learning example models; iv) determining the accuracy of a certain number of time steps; v) using the example trained model to process newly received input data; vi) Optionally and in parallel, continue training the example trained model at predetermined intervals.

[0106] In some embodiments, optionally in combination with any of the above or below embodiments, the exemplary trained neural network model (e.g., MLM 205) may specify the neural network by at least a neural network topology, a set of activation functions, and connection weights. For example, the topology of the neural network may include the configuration of nodes in the neural network and the connections between such nodes. In some embodiments, optionally in combination with any of the above or below embodiments, the exemplary trained neural network model may also be specified to include other parameters, including, but not limited to, a bias value / function and / or an aggregation function. For example, the activation function of a node may be a step function, a sine function, a continuous or piecewise linear function, a sigmoid function, a hyperbolic tangent function, or any other type of mathematical function that represents a threshold at which the node is activated. In some embodiments, optionally in combination with any of the above or below embodiments, the exemplary aggregation function may be a mathematical function that combines (e.g., sum, product, etc.) input signals to the node. In some embodiments, optionally in combination with any of the above or below embodiments, the output of the exemplary aggregation function may be used as an input to the exemplary activation function. In some embodiments, optionally in combination with any of the embodiments described above or below, the bias may be a constant value or function that may be used by the aggregation function and / or activation function to make a node more or less likely to be activated.

[0107] In some embodiments, the bioreactor system 100 can automatically construct datasets using data collected from cell sample runs and measurement data. These datasets can be used by the controller 106 to automatically retrain at least one cell culture control machine learning model 205. Optionally or alternatively, datasets from multiple bioreactor systems 100 with cell cultures from multiple subjects (e.g., patients) respectively can be transmitted via communications circuitry 220 to a backend cloud server (not shown) to retrain at least one cell culture control machine learning model 205 using datasets from different bioreactor systems.

[0108] In some embodiments, at least one cell culture control MLM 205 may include two machine learning models, where a first machine learning model may be trained to map input data including sensor data from each of a plurality of sensors to output data including predictive cell culture parameters, and a second machine learning model may map the predictive cell culture parameters to a plurality of control circuit commands to automatically control gas and / or liquid flow within a bioreactor chamber.

[0109] In some embodiments, metabolic analysis, such as correlating changes in the ratios of DO, glucose, lactate, glutamine, and / or glutamate over time during cell culture growth, can identify metabolic changes that may be important for the differentiation and functionality of T cells (effector and regulatory cells). For example, effector T cells may increase their glycolysis levels upon activation. Measurement of changes in glucose consumption levels and lactate production rates can be important indicators of proliferation progression. Regulatory T cells may have different metabolic preferences, such as fatty acid oxidation and mitochondrial metabolism, which may be more prevalent in regulatory T cells than in effector T cells. Glutamine metabolism may be involved in regulating the expansion and function of regulatory T cells. Glutamine uptake can be significantly enhanced upon TCR stimulation in T lymphocytes and may be important for their proliferation and cytokine production.

[0110] 10 is a graph showing phenotype prediction using metabolic sensing, according to one or more embodiments of the present disclosure. At day 1 (region A), a mixture of PBMCs (peripheral blood mononuclear cells) is deactivated and shows a steep O2 consumption slope at marker A1. A large subset of cells, such as non-T cells, has died, as indicated by lower O2 consumption at marker A2. When T cells are activated at day 6 (region B), O2 consumption increases as a result of proliferation, and the O2 pump rate increases, maintaining a substantially flat DO level as T cells grow at higher O2 consumption (region C). (The top trace is O2 supply, and the bottom trace is O2 level.)

[0111] 11 is a graph showing lactate formation according to one or more embodiments of the present disclosure. Prior to T cell activation on day 6 (region A), lactate formation is minimal. At day 6 (region B), activated T cells begin to produce lactate and the rate of lactate formation increases. At day 11 (region C), T cells change their phenotype to inactivated and the rate of lactate formation decreases.

[0112] 12 is a graph showing glucose consumption according to one or more embodiments of the present disclosure. In region A, minimal glucose consumption is observed (higher DO levels) as there is no proliferation. In region B, T cells are activated and begin to proliferate, resulting in increased glucose consumption as DO levels decrease. In region C, the T cell phenotype changes from activated to inactivated, resulting in higher glucose consumption as DO levels decrease further.

[0113] 13 is a graph showing dissolved oxygen and O2 pump rate in a cone according to one or more embodiments of the present disclosure. In pre-activation region A, oxygen consumption increases slightly and the O2 pump rate is low and fairly flat. In post-activation region B, medium is added to the cone, DO levels spike at about 60%, and oxygen consumption increases and the O2 pump rate is higher when the medium is changed around day 13.

[0114] 14 is a graph showing lactate formation rate (LFR) and glucose formation rate (GCR) according to one or more embodiments of the present disclosure. In pre-activation region A, there is a slight increase in LFR and GCR. In activation region B, lactate levels increase and glucose levels decrease for each cell, especially as the medium is changed.

[0115] FIG. 15 is a graph showing the LFR / GCR ratio according to one or more embodiments of the present disclosure. As the culture is consumed, the population may change, and the ratio of glucose to lactate may change with more activated cells. Thus, FIGS. 13-15 show that each parameter responds differently during a run. The ratio changes, indicating a change in the state of multiple cells. FIG. 15 shows that the LFR / GCR ratio nearly reaches the theoretical ratio value of 2, indicating that nearly 100% of the cells may be in a proliferative state.

[0116] 16A and 16B show two embodiments of transduction efficiency according to one or more embodiments of the present disclosure. Following cell transduction, perfusion begins 24 hours later, and the dissolved oxygen percentage may increase to a higher value if the transduction efficiency is low, but remains at a lower percentage if the transduction efficiency is high. When the DO falls below the DO set point (SP), the O2 pump may be activated, causing an increase in DO (day 3). Furthermore, the pump speed and DO level may show a higher rate of increase if the transduction efficiency is low compared to if the transduction efficiency is high. In FIG. 16B, there is a small population of activated cells, as evidenced by the drop in DO.

[0117] FIG. 17 is a flowchart of a method 1000 for controlling and monitoring metabolic rate and environmental factors of at least one bioreactor according to one or more embodiments of the present disclosure.

[0118] The method 1000 may include providing 1010 a bioreactor apparatus including a bioreactor chamber for growing a cell culture including a plurality of cells or microorganisms in a liquid medium, a controller, a plurality of sensors coupled to the bioreactor chamber, a plurality of control devices for varying gas flow, fluid flow, or both in the bioreactor chamber, and a control circuit for receiving control circuit commands from the controller to control the plurality of control devices, wherein the plurality of sensors measure a plurality of sensor parameters in the liquid medium including dissolved oxygen (DO) level, glucose level, and lactate level.

[0119] The method 1000 may include receiving 1020 by the controller 106 a desired cell growth configuration, the desired cell growth configuration including at least one desired value range, at least one set value, or any combination thereof, for each of a plurality of sensor parameters measured by a plurality of sensors at predetermined time intervals for each of a plurality of cell culture growth parameters during growth of the cell culture.

[0120] The method 1000 may include receiving 1030 sensor data by the controller 106 at predetermined time intervals from each of the plurality of sensors.

[0121] The method 1000 may include inputting 1040 by the controller 106 the desired cell growth configuration and sensor data from each of the plurality of sensors into at least one cell culture control machine learning model, wherein the at least one cell culture control machine learning model is trained using the data set based at least in part on time-dependent correlations between the plurality of sensor parameters and the plurality of cell culture growth parameters.

[0122] The method 1000 can include performing 1050, by the controller 106, based on output data from the at least one cell culture control machine learning model, at least one of: sending at least one control circuit command for displaying on a display, at least one cell culture parameter prediction from the plurality of cell culture growth parameters, sending at least one control circuit command for controlling a gas control device that varies a gas level in the bioreactor chamber, sending at least one control circuit command to a device that controls liquid flow of a nutrient fluid to the bioreactor chamber, or sending at least one control circuit command to open a device coupled to the bioreactor chamber to remove waste from the liquid medium.

[0123] In some embodiments, exemplary specially programmed computing systems / platforms of the present invention with associated devices operate in a distributed network environment and communicate with each other over one or more suitable data communication networks (e.g., the Internet, satellite, etc.), utilizing one or more suitable data communication protocols / modes such as, but not limited to, IPX / SPX, X.25, AX.25, AppleTalk™, TCP / IP (e.g., HTTP), Near Field Communication (NFC), RFID, Narrowband Internet of Things (NBIOT), 3G, 4G, 5G, GSM, GPRS, WiFi, WiMax, CDMA, satellite, ZigBee, and other suitable communication modes. In some embodiments, NFC can refer to a short-range wireless communication technology in which NFC-enabled devices communicate by "swiping," "bumping," "tapping," or otherwise moving in close proximity. In some embodiments, NFC can include a set of short-range wireless technologies that typically require a distance of 10 cm or less. In some embodiments, NFC can operate over the ISO / IEC 18000-3 air interface at 13.56 MHz at speeds ranging from 106 kbit / s to 424 kbit / s. In some embodiments, NFC can include an initiator and a target. The initiator actively generates an RF field that can power a passive target. In some embodiments, this allows the NFC target to take on a very simple form factor, such as a tag, sticker, key fob, or card, that does not require a battery. In some embodiments, NFC peer-to-peer communication can occur when multiple NFC-enabled devices (e.g., smartphones) are in close proximity to each other.

[0124] The materials disclosed herein may be implemented in software or firmware, or a combination thereof, or as instructions stored on a machine-readable medium that can be read and executed by one or more processors. A machine-readable medium may include any medium and / or mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device). For example, a machine-readable medium may include read-only memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, electrical, optical, acoustical, or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), and the like.

[0125] As used herein, the terms "computer engine" and "engine" identify at least one software component and / or a combination of at least one software component and at least one hardware component that is designed / programmed / configured to manage / control other software and / or hardware components (e.g., libraries, software development kits (SDKs), objects, etc.).

[0126] Examples of hardware elements may include processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, etc.), integrated circuits, application specific integrated circuits (ASICs), programmable logic devices (PLDs), digital signal processors (DSPs), field programmable gate arrays (FPGAs), logic gates, registers, semiconductor devices, chips, microchips, chipsets, etc. In some embodiments, one or more processors may be implemented as complex instruction set computer (CISC) or reduced instruction set computer (RISC) processors; x86 instruction set compatible processors, multi-core, or any other microprocessor or central processing unit (CPU). In various implementations, one or more processors may be dual-core processors, dual-core mobile processors, etc.

[0127] As used herein, computer-related system, computer system, and system include any combination of hardware and software. Examples of software may include software components, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application program interfaces (APIs), instruction sets, computer code, computer code segments, words, values, symbols, or any combination thereof. The decision whether an embodiment is implemented using hardware and / or software elements may vary according to any number of factors, such as desired computational speed, power levels, thermal tolerances, processing cycle budgets, input data rates, output data rates, memory resources, data bus speeds, and other design or performance constraints.

[0128] One or more aspects of at least one embodiment may be embodied by representative instructions stored on a machine-readable medium that represent various logic within a processor, which, when read by a machine, causes the machine to create logic that performs the techniques described herein. Such representations, known as "IP cores," may be stored on tangible machine-readable media and supplied to various customers or manufacturing facilities for loading into manufacturing machines that create the logic or processors. Of note, the various embodiments described herein may, of course, be implemented using any suitable hardware and / or computing software language (e.g., C++, Objective-C, Swift, Java, JavaScript, Python, Perl, QT, etc.).

[0129] In some embodiments, one or more of the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may be partially or fully contained within or incorporated into at least one personal computer (PC), laptop computer, ultra-laptop computer, tablet, touchpad, portable computer, handheld computer, palmtop computer, personal digital assistant (PDA), mobile phone, mobile phone / PDA combination, television, smart device (e.g., smartphone, smart tablet, or smart television), mobile internet device (MID), messaging device, data communication device, and the like.

[0130] As used herein, the term "server" should be understood to refer to a service point that provides processing, database, and communication capabilities. By way of example and not limitation, the term "server" can refer to a single physical processor with associated communication and data storage and database capabilities, or it can refer to a networked or clustered complex of processors and associated network and storage devices, as well as an operating system and one or more database systems and application software that support the services provided by the server. A cloud server is an example.

[0131] In some embodiments, as detailed herein, one or more of the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may acquire, manipulate, transfer, store, convert, generate, and / or output (e.g., from within and / or outside of a particular application) any digital objects and / or data units, which may be in any suitable form, such as, but not limited to, files, contacts, tasks, emails, social media posts, maps, entire applications (e.g., calculators), etc. In some embodiments, as detailed herein, one or more of the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may be implemented across one or more of a variety of computer platforms, including, but not limited to, the following: (1) FreeBSD, NetBSD, OpenBSD; (2) Linux; (3) Microsoft Windows; (4) OS X (MacOS); (5) MacOS 11; (6) Solaris; (7) Android; (8) iOS; (9) Embedded Linux; (10) Tizen; (11) WebOS; (12) IBM i; (13) IBM AIX; (14) Binary Execution Environment for Wireless (BREW); (15) Cocoa (API); (16) Cocoa Touch; (17) Java Platform; (18) JavaFX; (19) JavaFX Mobile; (20) Microsoft DirectX; (21) .NET Framework; (22) Silverlight; (23) Open Web Platform; (24) Oracle Database; (25) Qt; (26) Eclipse Rich Client Platform; (27) SAP NetWeaver; (28) Smartface; and / or (29) Windows Runtime.

[0132] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of this disclosure may utilize hardwired circuitry that may be used in place of or in combination with software instructions to implement features consistent with the principles of this disclosure. Thus, implementations consistent with the principles of this disclosure are not limited to any particular combination of hardware circuitry and software. For example, various embodiments may be embodied in many different ways as a software component, including, but not limited to, a standalone software package, a combination of software packages, or a software package incorporated as a "tool" in a larger software product.

[0133] For example, exemplary software specifically programmed according to one or more principles of the present disclosure may be downloadable from a network, e.g., a website, as a standalone product or as an add-in package for installation into an existing software application. For example, exemplary software specifically programmed according to one or more principles of the present disclosure may also be available as a client-server software application or as a web-enabled software application. For example, exemplary software specifically programmed according to one or more principles of the present disclosure may also be embodied as a software package installed on a hardware device.

[0134] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may handle a large number of concurrent users, including, but not limited to, at least 100 (e.g., but not limited to, 100-999), at least 1,000 (e.g., but not limited to, 1,000-9,999), at least 10,000 (e.g., but not limited to, 10,000-99,999), or at least 10,000 (e.g., but not limited to, 10,000-99,999). 9), at least 100,000 (e.g., but not limited to, 100,000 to 999,999), at least 1 million (e.g., but not limited to, 1,000,000 to 9,999,999), at least 10 million (e.g., but not limited to, 10,000,000 to 99,999,999), at least 100 million (e.g., but not limited to, 100,000,000 to 999,999,999), at least 1 billion (e.g., but not limited to, 1,000,000,000 to 999,999,999,999), etc.

[0135] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may output to a separate, specifically programmed graphical user interface implementation (e.g., desktop, web app, etc.) of the present disclosure. In various implementations of the present disclosure, the final output may be displayed on a display screen, which may be, but is not limited to, a computer screen, a mobile device screen, etc. In various implementations, the display may be a holographic display. In various implementations, the display may be a transparent surface capable of receiving visual projections. Such projections may convey various forms of information, images, and / or objects. For example, such projections may be visual overlays for mobile augmented reality (MAR) applications.

[0136] As used herein, terms such as "mobile electronic device" can refer to any portable electronic device that may or may not be enabled with location tracking capabilities (e.g., MAC address, Internet Protocol (IP) address, etc.). For example, a mobile electronic device can include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a Blackberry™, a Pager, a smart phone, or any other reasonable mobile electronic device.

[0137] As used herein, the terms "proximity detection," "location determination," "location data," "location information," and "location tracking" refer to any form of location tracking technology or location methodology that can be used to provide, for example, the location of a particular computing device / system / platform of the present disclosure and / or any associated computing devices, and that is based at least in part on one or more of the following technologies / devices, without limitation: accelerometer, gyroscope, Global Positioning System (GPS); GPS accessed using Bluetooth™; GPS accessed using any reasonable form of wireless and / or non-wireless communication; WiFi™ server location data; Bluetooth™-based location data; triangulation, for example, without limitation techniques and systems that use geographic coordinate systems, such as, but not limited to, longitude and latitude-based, geodetic height-based, Cartesian coordinate-based, etc.; radio frequency identification, such as, but not limited to, long-range RFID, short-range RFID, etc.; the use of any form of RFID tag, such as, but not limited to, active RFID tags, passive RFID tags, battery-assisted passive RFID tags, etc.; or any other reasonable method of determining location. For simplicity, the above variations may not be listed or may only be partially listed, but this is in no way meant to be limiting.

[0138] As used herein, the terms “cloud,” “Internet cloud,” “cloud computing,” “cloud architecture,” and similar terms correspond to at least one of the following: (1) a large number of computers connected via a real-time communications network (e.g., the Internet); (2) providing the ability to run programs or applications simultaneously on a large number of connected computers (e.g., physical machines, virtual machines (VMs)); (3) network-based services (e.g., allowing them to be moved and scaled up (or down) on the fly without impacting end users) that appear to be provided by real server hardware but are actually provided by virtual hardware (e.g., virtual servers) simulated by software running on one or more real machines.

[0139] In some embodiments, the exemplary inventive computer-based systems / platforms, exemplary inventive computer-based devices, and / or exemplary inventive computer-based components of the present disclosure may store and / or transmit data securely by utilizing one or more of encryption techniques (e.g., private / public key pairs, Triple Data Encryption Standard (3DES), block cipher algorithms (e.g., IDEA, RC2, RC5, CAST, and Skipjack), cryptographic hash algorithms (e.g., MD5, RIPEMD-160, RTR0, SHA-1, SHA-2, Tiger (TTH), WHIRLPOOL, RNG).

[0140] The above examples are, of course, illustrative and not limiting.

[0141] As used herein, the term "user" shall mean at least one user. In some embodiments, the terms "user," "subscriber," "consumer," or "customer" shall be understood to refer to a user of the applications described herein and / or a consumer of data provided by a data provider. By way of example and not limitation, the terms "user" or "subscriber" may refer to a person receiving data over the Internet in a browser session or data provided by a service provider, or may refer to an automated software application that receives data and stores or processes the data.

[0142] In some embodiments, a method includes providing a bioreactor apparatus, the bioreactor apparatus comprising: a bioreactor chamber for growing a cell culture, which may include a plurality of cells or microorganisms in a liquid medium; A controller; a plurality of sensors coupled to the bioreactor chamber; a plurality of controllers for varying gas flow, fluid flow, or both within the bioreactor chamber; a control circuit capable of receiving control circuit commands from the controller for controlling the plurality of control devices; Including, The plurality of sensors Dissolved oxygen (DO) levels and Glucose levels and Lactic acid levels and measuring a plurality of sensor parameters in a liquid medium, which may include The method is: receiving by the controller via an input device a desired cell growth configuration, wherein the desired cell growth configuration may include at least one desired value range, at least one set point, or any combination thereof, for each of a plurality of sensor parameters measured by a plurality of sensors at predetermined time intervals for each of a plurality of cell culture growth parameters during growth of the cell culture; receiving, by a controller, sensor data from each of a plurality of sensors at predetermined time intervals; inputting, by the controller, the desired cell growth configuration and sensor data from each of the plurality of sensors into a cell culture control machine learning model, wherein the at least one cell culture control machine learning model can be trained using a data set based at least in part on a time-dependent correlation between the plurality of sensor parameters and the plurality of cell culture growth parameters; by the controller based on output data from the at least one cell culture control machine learning model. sending at least one control circuit command to display on a display at least one cell culture parameter prediction from the plurality of cell culture growth parameters; sending at least one control circuit command to control a gas control device to vary the gas level in the bioreactor chamber; sending at least one control circuit command to control a device that controls the liquid flow of the nutrient fluid into the bioreactor chamber; or sending at least one control circuit command to open a device coupled to the bioreactor chamber to remove waste from the liquid medium; and performing at least one of the following: may include:

[0143] In some embodiments, the at least one cell culture control machine learning model can be further trained to predict a plurality of cell culture growth parameters of the cell culture based at least in part on at least one correlation between at least one change in at least one sensor parameter value from the plurality of sensor parameters and at least one change in a sensor parameter slope from the plurality of sensor parameters at different time points.

[0144] In some embodiments, the multiple sensors may measure multiple sensor parameters in the liquid medium, which may include pH level, temperature level, and pressure.

[0145] In some embodiments, inputting sensor data into at least one cell culture control machine learning model may include inputting image data of at least one image of a cell culture in liquid medium from an imaging camera.

[0146] In some embodiments, inputting image data into at least one cell culture control machine learning model may include inputting image data of at least one image of a plurality of cells or microorganisms in a liquid medium received from an imaging camera coupled to a microscope that images the cell culture.

[0147] In some embodiments, the method may include determining, by the controller, a cell count of a plurality of cells or microorganisms in a liquid medium using image data of at least one image received from an imaging camera coupled to a microscope that images the cell culture.

[0148] In some embodiments, the at least one cell culture prediction may be selected from the group consisting of: Prediction of activation status by the number or percentage of activated cells; Prediction of cell numbers, Predicting the proliferation or differentiation state of cells; Prediction of cell differentiation, Prediction of activation phenotypes, Prediction of the inactivation phenotype, Prediction of populations, subpopulations, or both within cell cultures that behave metabolically differently due to activation stimuli, heat shock stimuli, stress stimuli, and hypoxia; Prediction of bacterial or fungal contamination, Predicting whether T cells will respond to and kill a target; Predicting when multiple cells change and interventions are made that reactivate or move multiple cells to different media; Predicting food contamination, Prediction of quality control (QC) test results, Prediction of cancer cell identification in cell cultures by metabolic consumption; Predicting the identified activity of drugs by changing cell culture consumption; and Prediction of drug resistance, drug activity, or both in cancer cells based on metabolic changes following the addition of an anticancer drug.

[0149] In some embodiments, the bioreactor chamber can be partitioned into a conical subchamber and a media subchamber by a perforated barrier, and the conical subchamber can contain a plurality of cells. Receiving sensor data from each of the plurality of sensors can include receiving sensor data from a first set of sensors from the plurality of sensors coupled to the conical subchamber and a second set of sensors from the plurality of sensors coupled to the media subchamber.

[0150] In some embodiments, receiving the desired cell growth configuration may include receiving additional parameters including: Definition of a cell, cell type, Cell phenotype at the expected sampling time, conditions that halt cell proliferation performance, differentiation state, and A time period during which at least one behavior is performed independently of output data from at least one cell culture controlled machine learning model.

[0151] In some embodiments, the method may further include generating a new dataset by the controller using data collected from the multiple cell sample runs from each of the multiple subjects, and retraining, by the controller, at least one cell culture control machine learning model using the new dataset.

[0152] The bioreactor system a bioreactor chamber for growing a cell culture comprising a plurality of cells or microorganisms in a liquid medium; A controller; a reservoir chamber for holding a nutrient fluid containing at least one nutrient for a plurality of cells or microorganisms; a plurality of sensors coupled to the bioreactor chamber; a plurality of controllers for varying gas flow, fluid flow, or both within the bioreactor chamber; a control circuit for receiving control circuit commands from the controller for controlling the plurality of control devices; and The plurality of sensors Dissolved oxygen (DO) levels and Glucose levels and Lactic acid levels and and measuring a plurality of sensor parameters in a liquid medium, which may include The controller receiving via an input device a desired cell growth configuration, the desired cell growth configuration may include at least one desired value range, at least one set point, or any combination thereof, for each of a plurality of sensor parameters measured by a plurality of sensors at a predetermined time interval for each of a plurality of cell culture growth parameters during growth of the cell culture; receiving sensor data from each of a plurality of sensors at predetermined time intervals; inputting a desired cell growth configuration and sensor data from each of a plurality of sensors into a cell culture control machine learning model, wherein the at least one cell culture control machine learning model can be trained using a data set based at least in part on a time-dependent correlation between a plurality of sensor parameters and a plurality of cell culture growth parameters; Based on the output data from the cell culture control machine learning model, sending at least one control circuit command to the display to display on the display at least one cell culture parameter prediction from the plurality of cell culture growth parameters; sending at least one control circuit command to control a gas control device to vary the gas level in the bioreactor chamber; sending at least one control circuit command to control a device that controls the liquid flow of the nutrient fluid into the bioreactor chamber; or sending at least one control circuit command to open a device coupled to the bioreactor chamber to remove waste from the liquid medium; and performing at least one of the following: The controller may execute computer code that causes the controller to:

[0153] In some embodiments, the at least one cell culture control machine learning model can be further trained to predict a plurality of cell culture growth parameters of the cell culture based at least in part on at least one correlation between at least one change in at least one sensor parameter value from the plurality of sensor parameters and at least one change in a sensor parameter slope from the plurality of sensor parameters at different time points.

[0154] In some embodiments, the plurality of sensors may measure a plurality of sensor parameters in a liquid medium, which may include: pH level, temperature level, and pressure.

[0155] In some embodiments, the controller may input sensor data into at least one cell culture control machine learning model by inputting image data of at least one image of a cell culture in liquid medium from an imaging camera.

[0156] In some embodiments, the controller may input image data into at least one cell culture control machine learning model by inputting image data of at least one image of a plurality of cells or microorganisms in a liquid medium received from an imaging camera coupled to a microscope that images the cell culture.

[0157] In some embodiments, the controller may determine the cell count of a plurality of cells or microorganisms in a liquid medium using image data of at least one image received from an imaging camera coupled to a microscope that images the cell culture.

[0158] In some embodiments, the at least one cell culture prediction may be selected from the group consisting of: Prediction of activation status by the number or percentage of activated cells; Prediction of cell numbers, Predicting the proliferation or differentiation state of cells; Prediction of cell differentiation, Prediction of activation phenotypes, Prediction of the inactivation phenotype, Prediction of populations, subpopulations, or both within cell cultures that behave metabolically differently due to activation stimuli, heat shock stimuli, stress stimuli, and hypoxia; Prediction of bacterial or fungal contamination, Predicting whether T cells will respond to and kill a target; Predicting when multiple cells change and interventions are made that reactivate or move multiple cells to different media; Predicting food contamination, Prediction of quality control (QC) test results, Prediction of cancer cell identification in cell cultures by metabolic consumption; Predicting the identified activity of drugs by changing cell culture consumption; and Prediction of drug resistance, drug activity, or both in cancer cells based on metabolic changes following the addition of an anticancer drug.

[0159] In some embodiments, the bioreactor chamber may be partitioned into a conical subchamber and a media subchamber by a perforated barrier, and the conical subchamber may contain a plurality of cells. The controller may receive sensor data from each of the plurality of sensors by receiving sensor data from a first set of sensors from the plurality of sensors coupled to the conical subchamber and a second set of sensors from the plurality of sensors coupled to the media subchamber.

[0160] In some embodiments, the controller: Definition of a cell, cell type, Cell phenotype at the expected sampling time, conditions that halt cell proliferation performance, differentiation state, and time to perform at least one action independently of output data from at least one cell culture control machine learning model. The desired cell growth configuration may be received by receiving additional parameters including:

[0161] In some embodiments, the controller further comprises: generating a new dataset using data collected from multiple cell sample runs from each of multiple subjects; At least one cell culture control machine learning model may be retrained using the new dataset.

[0162] Publications cited throughout this document are incorporated herein by reference in their entirety. While one or more embodiments of the present disclosure have been described, it is understood that these embodiments are exemplary only and not limiting, and that many modifications may be apparent to those skilled in the art, including that the various embodiments of the inventive methodologies, inventive systems / platforms, and inventive devices described herein can be utilized in any combination with one another. Furthermore, the various steps may be performed in any desired order (any desired steps may be added and / or any desired steps may be deleted).

Claims

1. 1. A method comprising: A bioreactor apparatus is provided, the bioreactor apparatus comprising: a bioreactor chamber for growing a cell culture comprising a plurality of cells or microorganisms in a liquid medium; A controller; a plurality of sensors coupled to the bioreactor chamber; a plurality of controllers for varying gas flow, fluid flow, or both within the bioreactor chamber; a control circuit that receives control circuit commands from the controller to control the plurality of control devices; Including, The plurality of sensors measure a plurality of sensor parameters in the liquid medium, the plurality of sensor parameters comprising: Dissolved oxygen (DO) levels; and Glucose levels and Lactic acid levels and Including, The method comprises: receiving by the controller via an input device a desired cell growth configuration, the desired cell growth configuration including at least one desired value range, at least one set point, or any combination thereof, for each of a plurality of sensor parameters measured by the plurality of sensors at predetermined time intervals for each of a plurality of cell culture growth parameters during growth of the cell culture; receiving, by the controller, sensor data from each of the plurality of sensors at the predetermined time intervals; inputting, by the controller, the desired cell growth configuration and the sensor data from each of the plurality of sensors into at least one cell culture control machine learning model, the at least one cell culture control machine learning model being trained using a dataset based at least in part on time-dependent correlations between the plurality of sensor parameters and a plurality of cell culture growth parameters; by the controller, based on output data from the at least one cell culture control machine learning model, sending at least one control circuit command to display on a display at least one cell culture parameter prediction from the plurality of cell culture growth parameters; sending at least one control circuit command to control a gas control device to vary the gas level in the bioreactor chamber; sending at least one control circuit command to control a device controlling liquid flow of nutrient fluid into said bioreactor chamber; or sending at least one control circuit command to open a device coupled to the bioreactor chamber to remove waste from the liquid medium; and performing at least one of A method comprising:

2. 10. The method of claim 1, wherein the at least one cell culture control machine learning model is further trained to predict the plurality of cell culture growth parameters of the cell culture based at least in part on at least one correlation between at least one change in at least one sensor parameter value from the plurality of sensor parameters and at least one change in a sensor parameter slope from the plurality of sensor parameters at different times.

3. The plurality of sensors measure a plurality of sensor parameters of the liquid medium, the plurality of sensor parameters comprising: pH level and The temperature level and Pressure and The method of claim 1 , comprising:

4. 10. The method of claim 1, wherein inputting the sensor data into at least one cell culture control machine learning model comprises inputting image data of at least one image of the cell culture in the liquid medium from an imaging camera.

5. 5. The method of claim 4, wherein inputting the image data into at least one cell culture control machine learning model comprises inputting image data of at least one image of the plurality of cells or microorganisms in the liquid medium received from an imaging camera coupled to a microscope that images the cell culture.

6. 6. The method of claim 5, further comprising determining, by the controller, a cell count of the plurality of cells or microorganisms in the liquid medium using the image data of the at least one image received from the imaging camera coupled to a microscope that images the cell culture.

7. the at least one cell culture prediction comprises: Prediction of activation status by number or percentage of activated cells; Prediction of cell numbers, Predicting the proliferation or differentiation state of cells; Prediction of cell differentiation, Prediction of activation phenotypes, Prediction of the inactivation phenotype, Prediction of populations, subpopulations, or both within said cell culture that will behave metabolically differently due to activation stimuli, heat shock stimuli, stress stimuli, and hypoxia; Prediction of bacterial or fungal contamination, predicting whether a T cell will respond to a target and kill said target; a prediction when an intervention will be performed that will change the plurality of cells and reactivate or move the plurality of cells to a different medium; Predicting food contamination, Predicting quality control (QC) test results; predicting the identification of cancer cells in said cell culture by metabolic consumption; Predicting the identified activity of drugs by changing cell culture consumption; and Predicting drug resistance, drug activity, or both in cancer cells based on metabolic changes following the addition of anticancer drugs 2. The method of claim 1, wherein the compound is selected from the group consisting of:

8. the bioreactor chamber is divided into a conical subchamber and a medium subchamber by a perforated barrier; the conical subchamber contains the plurality of cells; 2. The method of claim 1, wherein receiving the sensor data from each of the plurality of sensors comprises receiving sensor data from a first set of sensors from the plurality of sensors coupled to the conical subchamber and a second set of sensors from the plurality of sensors coupled to the media subchamber.

9. receiving the desired cell growth configuration Definition of a cell, cell type, Cell phenotype at the expected sampling time, conditions that halt cell proliferation performance, differentiation state, and and performing at least one action independently of the output data from the at least one cell culture control machine learning model. The method of claim 1 , further comprising receiving additional parameters including:

10. generating, by said controller, a new data set using data collected from a plurality of cell sample runs from each of a plurality of subjects; retraining, by the controller, the at least one cell culture control machine learning model using the new data set; The method of claim 1 further comprising:

11. 1. A bioreactor system comprising: a bioreactor chamber for growing a cell culture comprising a plurality of cells or microorganisms in a liquid medium; A controller; a reservoir chamber for holding a nutrient fluid containing at least one nutrient for the plurality of cells or microorganisms; a plurality of sensors coupled to the bioreactor chamber; a plurality of controllers for varying gas flow, fluid flow, or both within the bioreactor chamber; a control circuit that receives control circuit commands from the controller to control the plurality of control devices; Including, The plurality of sensors include: Dissolved oxygen (DO) levels; and Glucose levels and Lactic acid levels and measuring a plurality of sensor parameters in the liquid medium, The controller receiving via an input device a desired cell growth configuration, the desired cell growth configuration including at least one desired value range, at least one set point, or any combination thereof, for each of a plurality of sensor parameters measured by the plurality of sensors at predetermined time intervals for each of a plurality of cell culture growth parameters during growth of the cell culture; receiving sensor data from each of the plurality of sensors at the predetermined time intervals; inputting the desired cell growth configuration and sensor data from each of the plurality of sensors into a cell culture control machine learning model, wherein the at least one cell culture control machine learning model is trained using a data set based at least in part on a time-dependent correlation between the plurality of sensor parameters and a plurality of cell culture growth parameters; Based on output data from the cell culture control machine learning model, sending at least one control circuit command to a display to display at least one cell culture parameter prediction from the plurality of cell culture growth parameters on the display; sending at least one control circuit command to control a gas control device to vary the gas level in the bioreactor chamber; sending at least one control circuit command to control a device controlling liquid flow of nutrient fluid into said bioreactor chamber; or sending at least one control circuit command to open a device coupled to the bioreactor chamber to remove waste from the liquid medium; and performing at least one of a bioreactor system that executes computer code that causes the controller to perform the steps of:

12. 12. The bioreactor system of claim 11, wherein the at least one cell culture control machine learning model is further trained to predict the plurality of cell culture growth parameters of the cell culture based at least in part on at least one correlation between at least one change in at least one sensor parameter value from the plurality of sensor parameters and at least one change in a sensor parameter slope from the plurality of sensor parameters at different times.

13. The plurality of sensors measure a plurality of sensor parameters of the liquid medium, and the plurality of sensor parameters are: pH level and The temperature level and Pressure and 12. The bioreactor system of claim 11, comprising:

14. 12. The bioreactor system of claim 11, wherein the controller inputs the sensor data into at least one cell culture control machine learning model by inputting image data of at least one image of the cell culture in the liquid medium from an imaging camera.

15. 15. The bioreactor system of claim 14, wherein the controller inputs image data of at least one image of the plurality of cells or microorganisms in the liquid medium received from an imaging camera coupled to a microscope that images the cell culture, thereby inputting the image data into at least one cell culture control machine learning model.

16. 16. The bioreactor system of claim 15, wherein the controller determines a cell count of the plurality of cells or microorganisms in the liquid medium using the image data of the at least one image received from the imaging camera coupled to a microscope that images the cell culture.

17. the at least one cell culture prediction comprises: Prediction of activation status by number or percentage of activated cells; Prediction of cell numbers, Predicting the proliferation or differentiation state of cells; Prediction of cell differentiation, Prediction of activation phenotypes, Prediction of the inactivation phenotype, Prediction of populations, subpopulations, or both within said cell culture that will behave metabolically differently due to activation stimuli, heat shock stimuli, stress stimuli, and hypoxia; Prediction of bacterial or fungal contamination, predicting whether a T cell will respond to a target and kill said target; a prediction when an intervention will be performed that will change the plurality of cells and reactivate or move the plurality of cells to a different medium; Predicting food contamination, Predicting quality control (QC) test results; predicting the identification of cancer cells in said cell culture by metabolic consumption; Predicting the identified activity of drugs by changing cell culture consumption; and Predicting drug resistance, drug activity, or both in cancer cells based on metabolic changes following the addition of anticancer drugs 12. The bioreactor system of claim 11, selected from the group consisting of:

18. the bioreactor chamber is divided into a conical subchamber and a medium subchamber by a perforated barrier; the conical subchamber contains the plurality of cells; 12. The bioreactor system of claim 11, wherein the controller receives the sensor data from each of the plurality of sensors by receiving sensor data from a first set of sensors from the plurality of sensors coupled to the conical subchamber and a second set of sensors from the plurality of sensors coupled to the medium subchamber.

19. The controller Definition of a cell, cell type, Cell phenotype at the expected sampling time, conditions that halt cell proliferation performance, differentiation state, and and performing at least one action independently of the output data from the at least one cell culture control machine learning model.

12. The bioreactor system of claim 11, wherein the desired cell growth configuration is received by receiving additional parameters including:

20. The controller further comprises: generating a new dataset using data collected from multiple cell sample runs from each of multiple subjects; 12. The bioreactor system of claim 11, wherein the new data set is used to retrain the at least one cell culture control machine learning model.

Images