System and methods for generating a hybrid model-based digital simulator (HMBDS) that simulates bioprocesses in a real-world cell culture container

Abstract

A method for generating a hybrid model based digital simulator (HMBDS) that simulates at least one bioprocess that executing in a real-world cell culture container, comprising: receiving a model of a first bioprocess; receiving a plurality of experimental results data of the first bioprocess in the real-world cell culture container; generating a HMBDS based on the received first bioprocess model, the real-world cell culture container, and the received experimental results data; performing a simulation of a bioprocess executing within the real-world cell culture container using the HMBDS; performing optimization of the bioprocess based on the results of the simulation; and causing execution of the optimized bioprocess by the at least a first real-world cell culture container.

Description

SYSTEM AND METHODS FOR GENERATING A HYBRID MODEL-BASED DIGITAL SIMULATOR (HMBDS) THAT SIMULATES BIOPROCESSES IN A REAL-WORLD CELL CULTURE CONTAINERCROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 673,038 filed on July 18, 2024, the contents of which are incorporated herein by reference.TECHNICAL FIELD

[0002] The disclosure generally relates to monitoring, simulating and controlling of bioprocesses, and more specifically to techniques for generating a hybrid model based digital simulator that simulates bioprocesses that execute in a real-world cell culture container.BACKGROUND

[0003] In the ever-evolving landscape of biotechnology, the quest for sustainable and efficient production of bioproducts has become paramount. From antibiotics to industrial enzymes, the demand for high-quality, cost-effective products continues to rise. However, achieving this goal is not without challenges. The intricate dance between biological processes and production facility infrastructure requires integration of biology, engineering, and digitalization.

[0004] Bioprocesses lie at the core of biomanufacturing. These dynamic systems harness living cells — be it bacteria, yeast, or mammalian cells — to produce valuable products. The marriage of biology and engineering in bioprocesses enables the creation of antibiotics, organic acids, pharmaceutical proteins, and enzymes for diverse applications. However, the road to efficient production is fraught with challenges. These stem from the need to move between different bioprocess executing on changing scales of manufacturing, from experimentation in laboratory equipment to full-fledged industrial scale bioreactors.

[0005] Historically, bioprocess development has followed a winding path. Researchers and engineers have grappled with slow, error-prone processes that require multiple experimental stages before reaching full-scale production. The delicate interplaybetween the biological process and the production facility structure demands meticulous optimization. Unfortunately, existing methods fall short in terms of speed, reliability, and scalability. This is because several hurdles need to be addressed, managed and balanced. Traditional bioprocesses involve trial and error, leading to prolonged development timelines. Researchers must navigate complex interactions between cell growth, nutrient availability, and product yield. This is topped by constraints of production facilities, regardless of scale, which are often rigid, inflexible and costly. Scaling up from lab-scale to commercial production requires significant modifications, leading to delays, necessary adjustment, changes, and cost overruns. The need for adaptable, modular designs remains unmet.

[0006] On top of that cells exhibit inherent variability, affecting product quality and consistency. Existing processes struggle to accommodate this biological diversity, resulting in suboptimal yields. It is therefore that the transition from benchtop experiments to large-scale production is fraught with risk. Unforeseen challenges emerge, necessitating costly adjustments.

[0007] Industry yearns for robust, risk-mitigated approaches, given that it is no longer possible to simply move exorbitant research, development and production costs onto consumers. Therefore, it would be advantageous to provide a solution for biological process development under much tighter economic constraints, that effectively bridges biology, engineering, and digitalization to provide speedy and trustworthy predictions of expected results.SUMMARY

[0008] A summary of several example embodiments of the disclosure follows. This summary is provided for the convenience of the reader to provide a basic understanding of such embodiments and does not wholly define the breadth of the disclosure. This summary is not an extensive overview of all contemplated embodiments, and is intended to neither identify key or critical elements of all embodiments nor to delineate the scope of any or all aspects. Its sole purpose is to present some concepts of one or more embodiments in a simplified form as a prelude to the more detailed description that is presented later. For convenience, the term “some embodiments” or “certainembodiments” may be used herein to refer to a single embodiment or multiple embodiments of the disclosure.

[0009] One aspect of the invention may include a system for generating a hybrid model based digital simulator (HMBDS) that simulates at least one bioprocess executing in a real-world cell culture container, comprising: a processing circuitry; a memory communicatively connected to the processing circuitry, the memory containing instructions that, when executed by the processing circuitry, configure the system to: receive a model of a first bioprocess; receive a plurality of experimental results data of the first bioprocess in the real-world cell culture container; generate a HMBDS based on the received first bioprocess model, the real-world cell culture container, and the received experimental results data; perform a simulation of a bioprocess executing within the real- world cell culture container using the HMBDS; perform optimization of the bioprocess based on the results of the simulation; and cause execution of the optimized bioprocess by the at least a first real-world cell culture container.

[0010] Another aspect of the invention may include a method for generating a hybrid model based digital simulator (HMBDS) that simulates at least one bioprocess that executing in a real-world cell culture container, comprising: receiving a model of a first bioprocess; receiving a plurality of experimental results data of the first bioprocess in the real-world cell culture container; generating a HMBDS based on the received first bioprocess model, the real-world cell culture container, and the received experimental results data; performing a simulation of a bioprocess executing within the real-world cell culture container using the HMBDS; performing optimization of the bioprocess based on the results of the simulation; and causing execution of the optimized bioprocess by the at least a first real-world cell culture container.

[0011] Yet another aspect of the invention may include a non-transitory computer readable medium having stored thereon instructions for generating a hybrid model based digital simulator (HMBDS) that simulates at least one bioprocess that executing in a real- world cell culture container, comprising: receiving a model of a first bioprocess; receiving a plurality of experimental results data of the first bioprocess in the real-world cell culture container; generating a HMBDS based on the received first bioprocess model, the real- world cell culture container, and the received experimental results data; performing asimulation of a bioprocess executing within the real-world cell culture container using the HMBDS; performing optimization of the bioprocess based on the results of the simulation; and causing execution of the optimized bioprocess by the at least a first real-world cell culture container.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The subject matter disclosed herein is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other objects, features, and advantages of the disclosed embodiments will be apparent from the following detailed description taken in conjunction with the accompanying drawings.

[0013] FIG. 1 shows an illustrative system for generation of a hybrid model-based digital simulator (HMBDS) for simulation of a bioprocess in a bio reactor according to an embodiment;

[0014] FIG. 2 shows an illustrative server of an HMBDS according to an embodiment;

[0015] FIG. 3 shows an illustrative schematic diagram for the generation of the hybrid model of the HMBDS according to an embodiment.

[0016] FIG. 4 shows a flowchart of an illustrative process for the generation of the HMBDS according to an embodiment;

[0017] FIG. 5 shows a flowchart of an illustrative process for the calibration of the HMBDS according to an embodiment; and

[0018] FIG. 6 shows an illustrative flowchart 600 of a process for simulation of a bioprocess and optimization thereof according to an embodiment.DETAILED DESCRIPTION

[0019] The embodiments disclosed by the disclosure are only examples of the many possible advantageous uses and implementations of the innovative teachings presented herein. In general, statements made in the specification of the present application do not necessarily limit any of the various claimed disclosures. Moreover, some statements may apply to some inventive features but not to others. In general,unless otherwise indicated, singular elements may be in plural and vice versa with no loss of generality. In the drawings, like numerals refer to like parts through several views.

[0020] A system and methods thereof generate a hybrid model based digital simulator (HMBDS) that simulates bioprocesses executing in a cell culture container, for example, a bio reactor, an Erlenmeyer flask, a baffled flask, and an orbital shaker. The system comprises: a processing circuitry; an artificial intelligence (Al) engine communicatively connected to the processing circuitry; a network interface communicatively connected to the processing circuitry; and, a memory communicatively connected to the processing circuitry, the memory containing instructions that, when executed by the processing circuitry, configure the system to: receive at least a first bioprocess model from the storage; receive a plurality of experimental results data of the at least a first bioprocess in the at least a first cell culture container; and, generate a HMBDS based on the received at least a first bioprocess, the at least a first cell culture container, and the received experimental results data.

[0021] In a further embodiment the memory further contains instructions that when executed by the processing circuitry, configure the system to: receive at least a first engineering model of a cell culture container from a storage communicatively connected to the network interface. In yet a further embodiment the generation of the HMBDS is further based on the received at least a first engineering model.

[0022] FIG. 1 shows an illustrative system 100 for generation of a hybrid modelbased digital simulator (HMBDS) for simulation of a bioprocess in a bio reactor according to an embodiment. To a network 110 there are communicatively connected a server 120 and a storage 150. Furthermore, one or more user terminals U1 130-1 through Un 130- n, where n is an integer equal to or greater than 1 are communicatively connected to the network 110. To the network 110 there are also communicatively connected one or more cell culture containers CCC1 140-1 through CCCm 140-m, where n is an integer equal to or greater than 1 .

[0023] The network 110 may comprises a variety of networks such as, but not limited to, local area network (LAN), wide area network (WAN), metro area network (MAN), the Internet, the worldwide web (WWW), and any other applicable network, as well as any permissible combination thereof. Network 110 may be based on a variety ofcommunication protocols, whether standard or proprietary, as well as any permissible combination thereof. Network 110 may further comprises wired, such as, fiber optics, plain old telephone system (POTS), or Ethernet, and / or wireless, such as, cellular networks, Wireless Fidelity (WiFi), Bluetooth®, or any permissible combination thereof.

[0024] User terminal 130 allows a user of the system 100 to provide parameters for one or more bioprocesses, as well as experimental results of bioprocesses from a cell culture container, for example, any one of the cell culture containers 140, or, for that matter, also cell culture containers not communicatively connected to the network 110. The cell culture containers 140 may extend a range of cell culture containers, from laboratory scale units or configurations, semi-industrial units, and full-blown industry scale production units. While all cell culture containers 140 are shown as communicatively connected to network 110, in an embodiment none or a few of the cell culture containers are communicatively connected to network 110. Cell culture containers, or CCCs, may include but not limited to a bioreactor, an Erlenmeyer flask, a baffled flask, orbital shaker, Petri Dishes, T-Flasks, 96-Well Plates, 24-Well Plates, 6-Well Plates, Spinner Flasks, Stirred-Tank Bioreactors, Wave Bioreactors, Hollow Fiber Bioreactors, Microwell Plates, Single-Use Bioreactor Bags, Perfusion Culture Bags, Microcarrier Culture Systems, Perfusion Plates, Bioprocess Bags, Transwell Inserts, and Plate Readers.

[0025] Storage 150 contains various data that may be collected or processed by server 120 and as further described herein. Storage 150 may contain one or more descriptions of a bioprocess description and accompanying parameters. For example, a bioprocess description may include the steps for the bioprocess, consumables used, temperature profiles, profiles of speed of media through a cell culture container, and more. Storage 150 may further contain engineering descriptions of one or more cell culture containers, for example, cell culture containers 140. The engineering description may include physical description as well as control capabilities. For example, this may include the various components and respective characteristics (dimensions, materials, limitations, etc.), as well as the control capabilities.

[0026] Server 120 is configured to generate a HMBDS based on information stored, for example, in storage 150. According to an embodiment, one or more bioprocesses are performed on one or more cell culture containers 140. A limited numberof experimental results are collected and then stored in storage 150. Server 120 then generates the HMBDS using the information regarding the one or more bioprocess, one or more cell culture containers and the limited experimental results. The HMBDS is then used to simulate a bioprocess by providing certain input parameters and selecting a desired cell culture container. The results of the simulations are then compared to actual execution of the bioprocess on the selected actual cell culture container. The actual results are compared to the simulated results and as may be necessary the HMBDS is calibrated to ensure simulated results are within a predetermined tolerance of the actual result. This process may be repeated as necessary. Thereafter, the HMBDS may be used to simulate bioprocesses on identified cell culture containers, thereby saving significantly on time, effort, resource and costly errors or misdirection.

[0027] FIG. 2 shows an illustrative server 200 of an HMBDS according to an embodiment. In an embodiment, server 200 may be used as server 120 described in FIG. 1. The system 200 includes a processing circuitry 210 communicatively connected to a memory 220, an artificial intelligence (Al) engine 230, and a network interface 240. In an embodiment, the components of the system 200 may be communicatively connected via a bus 250.

[0028] The processing circuitry 210 may be realized as one or more hardware logic components and circuits. For example, and without limitation, illustrative types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), Application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), graphics processing units (GPUs), tensor processing units (TPUs), general-purpose microprocessors, microcontrollers, digital signal processors (DSPs), and the like, or any other hardware logic components that can perform calculations or other manipulations of information. Any permissible combinations of these hardware logic components is further envisioned and specifically included.

[0029] Memory 220 may be volatile, e.g., random access memory, etc., nonvolatile, e.g., read only memory, flash memory, etc., or any combination thereof. In an embodiment, memory 220 is an on-chip memory, an off-chip memory, a combination thereof, and the like. In certain embodiments, memory 220 is a scratch-pad memory forthe processing circuitry 210. In yet other embodiments the memory 220 may further provide cache memory functionality.

[0030] In one configuration, software for implementing one or more embodiments disclosed herein may be stored in storage 150, in memory 220, in a combination thereof, and the like. Software shall be construed broadly to mean any type of instructions, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. Instructions may include code, e.g. , in source code format, binary code format, executable code format, or any other suitable format of code. The instructions, when executed by processing circuitry 210, cause the processing circuitry 210 to perform the various processes described in greater detail herein. Memory 220 may further include therein a code memory 225 where instructions are stored. Such instructions may be executed by processing circuitry 210. More specifically, in an embodiment, such instructions may be used to control the operations described in Figs. 3 through 6 and / or the operation of the system 100.

[0031] Al engine 230 is used to train models generated by the system 100 as further described herein. Al engine 230 may use various techniques of training of the models, including supervised and unsupervised training, as may be necessary for a particular application. Model parameters are adjusted until a generated simulator based on a hybrid model of engineering and bioprocess parameters provides sufficiently accurate predictions. In some embodiments the Al engine 230 may be implemented by hardware separate from processing circuitry 210 while in other embodiments Al engine 230 may be implemented at least partly by processing circuitry 210, e.g., in conjunction with memory 220. In some embodiments, the Al engine is pre-trained using supervised learning on labeled datasets comprising historical bioprocess execution data and corresponding outcomes.

[0032] Network interface 240 provides for network interface of system 200. For example, when used as server 120 it provides the communication link to network 110. Accordingly, network interface 240 may provide network connectivity to one or more of the like of local area network (LAN), wide area network (WAN), metro area network (MAN), the Internet, the worldwide web (WWW), and any other applicable network, as well as any permissible combination thereof. Network interface 240 may support a varietyof communication protocols, whether standard or proprietary, as well as any permissible combination thereof. Network interface 240 may further support wired, such as, fiber optics, plain old telephone system (POTS), or Ethernet, and / or wireless, such as, cellular networks, Wireless Fidelity (WiFi), Bluetooth®, or any permissible combination thereof.

[0033] The bus 250, communicatively connecting between the components of system 200, may include serial and / or parallel busses, and permissible combinations thereof. The bus 250 may be a proprietary bus or a standard bus such as, but not limited to, peripheral component interconnect (PCI), small computer system interface (SCSI), universal serial bus (USB), IEEE 1394 (aka FireWire), and the like, as well as any permissible combinations thereof.

[0034] FIG. 3 shows an illustrative schematic diagram 300 for the generation of the hybrid model of the HMBDS according to an embodiment. In order to generate the simulator according to an embodiment, one or more bioprocess models 310 are provided. The bioprocess models 310 describe a bioprocess from various perspectives, including but not limited to, cell culture, fermentation, purification, refinement, genetic modification, feeding methods, aeriation methods, agitation methods, perfusion rates, harvest timing, inoculation methods and more. In addition, minimal experimental data 320 pertaining to bioprocess models 310 are further provided. These may include time-series data on the development of the cell culture at various points in time and end result, media content at various points in time and end result, and other like data. These may include, but are not limited to, measurements from sensors that provide sensory information such as dissolved oxygen, pH, and temperature, as well as offline measurements, analyzed by standard biological lab analyzers. Lastly, one or more models of cell culture container engineering models 330 used for the bioprocess and the resultant experimental data are also provided.

[0035] The models provided and the experimental data are used to generate a hybrid model 340 that is the basis for the hybrid model-based digital simulator (HMBDS) The simulator may be created using an Al engine, for example, Al engine 230, typically configured for supervised learning. In supervised learning, the model is trained on labeled data, meaning that the input data is paired with the correct output. The goal is for the model to learn a mapping from inputs to outputs so as to minimize the difference betweenthe predicted output and the actual output. Example algorithms include, but are not limited to, linear regression, logistic regression, support vector machines, and neural networks. Once a model for an initial model for the simulator is available it can be continuously refined by comparison of simulation results to actual results provided from experimental data.

[0036] Upon determination that the simulator is sufficiently stable, i.e., results of simulations and actual results are within a predefined tolerance, it is possible to simulate bioprocess as they execute within a cell culture container 350. The simulation provides the advantage that it is not necessary to actually have a particular cell culture container in place but rather use an engineering model thereof to simulate the bio process thereon. The simulation can validate with great confidence the predicted results of a bioprocess executing on a specific cell culture container.

[0037] In an embodiment, Al optimization may be performed on the validated process using an Al engine, for example, Al engine 230. The optimization process attempts to optimize the bioprocess, the choice of cell culture container, use thereof, or any permissible combination thereof. That is, a bioprocess that is validated may not necessarily be the most optimal for the particular delivered results. The Al engine may be employed to provide an optimized bioprocess by changing certain elements of the process, for example, providing an enhanced media for the cell culture, deploying a different temperature cycle and so on. In another case, it may determine that a use of another cell culture container having an engineering model would provide better results because of its particular characteristics that improve the desired results of the bioprocess. It may save on costs, materials, energy and more. The optimized bioprocess may then be used in real-life, i.e., not in simulation but using at least one real-world cell culture container. This saves on many costly experiments and even full scale production implications and risks.

[0038] In some embodiments, the optimized bioprocess may be executed by configuring an actual, real-world cell culture container accordingly. To do so may include generating an optmized control protocol that defines a set of operational parameters required for executing the optimized bioprocess, such as media composition, nutrient flow rates, temperature profiles, gas exchange settings, and agitation cycles. In anembodiment, the control protocol may be implemented as a machine-readable control protocol that may be transmitted to a control unit (not shown) associated with the real- world cell culture container, thereby enabling automated implementation of the optimized bioprocess in practice in the real-world. This integration between simulation-based optimization and real-world execution minimizes human intervention, reduces error, and allows for reproducible deployment of the optimized bioprocess under controlled conditions.

[0039] FIG. 4 shows a flowchart 400 of an illustrative process for the generation of the HMBDS according to an embodiment. In an embodiment the generation of the HMBDS is performed on system 100 as described herein, and in particular, at least in part, on server 120.

[0040] At S410 an engineering model of a cell culture container is received. The engineering model describes in detail the cell culture container environment, components and subsystems, and provides valuable insights into scaleup dynamics and optimal operating conditions of the cell culture container.

[0041] At S420 a bioprocess is received, typically in the form of mechanistic models. These models capture the underlying biological and chemical processes and interactions happening at the cells’ population level. The more complex the models provided and the more data-intensive they are, the deeper the insights that can be extracted when using such models.

[0042] At S430 k experimental sets of data, where k is an integer equal to or greater than 1 , are received. The experimental data reflects actual results of experiments made for the bioprocess. These results allow for supervised learning between inputs and outputs.

[0043] At S440 an HMBDS is generated by producing a hybrid model for the simulator. The generation of the HMBDS may be achieved by using an Al engine, for example Al engine 230. The hybrid model combines the strengths of the mechanistic and data-driven approaches. It leverages the deep understanding of the scientific principles from mechanistic models, while further incorporating therein real-world-data and statistical relationship captured by data-driven models. The result is a more flexibleand powerful tool than the solutions provided by the prior art, which can handle complex systems, adapt to changing conditions, and provide more accurate predictions.

[0044] FIG. 5 shows a flowchart 500 of an illustrative process for the calibration of the HMBDS according to an embodiment. Once the HMBDS is initially ready it is necessary to further calibrate it, that is, provide it with bioprocess and a selected bio reactor, exercise the HMBDS, and check the predicted results provided at the end of the simulations to actual results of a bioprocess executing on a real-life cell culture container. In an embodiment the calibration of the HMBDS is performed on system 100 as described herein, and in particular, at least in part, on server 120.

[0045] At S510 the HMBDS simulates a given bioprocess in a given cell culture container. That is, the simulator receives the inputs that characterize a particular definition of a bioprocess targeted for execution on a particular cell culture container, the cell culture container having its identified characteristics. As a result of the simulation a plurality of simulation results are available that are the predicted output of the bioprocess.

[0046] At S520 actual results of the real-world bioprocess executing on the real- world cell culture container are provided.

[0047] As S530 the received real-world (actual) results and the simulated results which were output by the HMBDS are compared.

[0048] At S540 it is checked whether the difference between the real-world results and the simulated results are within a predetermined tolerance, and if so, execution continues with S560; otherwise, execution continues with S550.

[0049] At S550 the HMBDS is calibrated to account for the results of the real-world bioprocess executing in the real-world cell culture container. This calibration ensures that when the HMBDS executes a subsequent similar simulation the simulated results shall not vary from the real-world results by more than the predetermined variance.

[0050] At S560 it is checked whether the process should continue and if so, execution continues with S510; otherwise, execution continues with S510.

[0051] FIG. 6 shows an illustrative flowchart 600 of a process for simulation of a bioprocess and optimization thereof according to an embodiment. In an embodiment the simulation and optimization of a bioprocess is performed on system 100 as described herein, and in particular, at least in part, on server 120, using the HMBDS.

[0052] At S610 a request to simulate a bioprocess on a cell culture container using HMBDS. This is done when it is necessary to predict what would be the outputs of the bioprocess executing in the cell culture container. The expectation is to get close enough results to real-world experimentation while saving on time and cost. In certain cases this further avoid risky bioprocesses that may, for example, have an impact on the environment.

[0053] At S620 the HMBDS model is received, or fetched, from storage, for example storage 150. Specifically, a model that pertains to the bioprocess and to the cell culture container may be fetched. This ensures that the HMBDS operates within the boundaries of the specific needs of the simulation of the bioprocess.

[0054] At S630 input parameters for the bioprocess are received. These may include specific amounts, proportions, timings, temperatures, and so on that are used with respect to the bioprocess execution in a particular cell culture container. In an embodiment the user interface may enable entering one or more components of an objective function of the optimization process alongside constraints that can arise from operational, technical or economic reasons. The objective function sets the goal of a problem, focusing on decision-making within specified constraints. Typically, this is a real-valued function that is either maximized, minimized or set to one or more specific target value as the case may require.

[0055] At S640 the simulation is executed using the received input parameters and the received HMBDS model. The HMBDS model is the one which befits the specific bioprocess and cell culture container. The simulation provides output results of the bioprocess.

[0056] In an embodiment, at S650 an optimization of the input bioprocess may take place. That optimization process may be performed by an Al engine, for example Al engine 230. The resultant optimized process may optimize the bioprocess, the cell culture container or both.

[0057] At S650 the simulation results and / or the optimized bioprocess are stored in storage, for example storage 150.

[0058] It should be understood that the simulation enables a user to go through ‘what-if’ scenarios for a given cell culture container without the need to execute theexperiment in a real-life facility. The simulation allows changes in a variety of parameters, for example, of the quantities of media, carbon source and the like, provided for cell growth, timing of media, carbon source, or like feeding, inoculation concentration of relevant materials, temperature, and other environmental parameters. Furthermore, it can provide comparisons between uses of different engineering models used in the process and identified the most desired combination for a given desired result. Furthermore, it may be used to simulate various cost functions to ensure economical value of a production process and avoiding significant expenditure on real-world experimentation, or at least significantly increasing the chances of successful production when real-world cell culture containers are used in large manufacturing scale.

[0059] In an embodiment an optimization platform of system 100 enables the user to select from a variety of optimizers. Such optimizers may include one or more optimizers. These optimizers may include, protein production optimization, biomass yield optimization, cost reduction optimization, process time minimization, and more. In an embodiment, the user may further input customized optimization methods.

[0060] The user interface of the system, for example system 100, may further allow for the definition of target functions. In an embodiment a primary target may be selected, for example, maximization of yield, and further defining a target value or an acceptable range. In a further embodiment one or more secondary targets may be provided, for example, maximization of productivity, minimization of production cost, minimization of process time, maintaining a desired quality figure of merit, and so on. One or more of the secondary targets may further include a target value or a target range.

[0061] The user interface of the system, for example system 100, may further allow for the setting of constraints. These may include, the likes of biological constraints, engineering constraints, and economic constraints. Biological constraints may include, but are not limited to, cell viability, e.g., greater than 90%, cell density, e.g., greater than 10A6 cells / mL, metabolite levels, e.g., lactate less than 10 g / L, and growth rate greater than 1.5 hA-1. Engineering constraints may include, but are not limited to, dissolved oxygen, e.g., 20-40%, pH level, e.g., 6.5-7.5, and temperature, e.g., 20-37°C. Economic constraints may include, but are not limited to, budget, e.g., less than $0.5M, and timeframe, e.g., less than 6 months.

[0062] The user interface of the system, for example system 100, after processing takes place may provide an optimized protocol. This may include information on various items of the protocol. For example, a description of a feeding strategy to be used may be provided. It can include times of feeding, amounts of feed, type of feed, duration of feed and more pertinent information. It may further provide an expected yield value as well as tolerance thereof. In an embodiment graphs of critical process parameters may be provided. The user interface may further provide predictions of the outcome under different conditions as well as tolerances and uncertainty estimations. A dashboard of the user interface may further provide values for example, for efficiency, cost savings and time reduction when compared to other processes.

[0063] The various embodiments disclosed herein can be implemented as hardware, firmware, software, or any combination thereof. Moreover, the software is preferably implemented as an application program tangibly embodied on a program storage unit or computer readable medium consisting of parts, or of certain devices and / or a combination of devices. The application program may be uploaded to, and executed by, a machine comprising any suitable architecture. Preferably, the machine is implemented on a computer platform having hardware such as one or more central processing units (“CPUs”), a memory, and input / output interfaces. The computer platform may also include an operating system and microinstruction code. The various processes and functions described herein may be either part of the microinstruction code or part of the application program, or any combination thereof, which may be executed by a CPU, whether or not such a computer or processor is explicitly shown. In addition, various other peripheral units may be connected to the computer platform such as an additional data storage unit and a printing unit. Furthermore, a non-transitory computer readable medium is any computer readable medium except for a transitory propagating signal.

[0064] All examples and conditional language recited herein are intended for pedagogical purposes to aid the reader in understanding the principles of the disclosed embodiment and the concepts contributed by the inventor to furthering the art, and are to be construed as being without limitation to such specifically recited examples and conditions. Moreover, all statements herein reciting principles, aspects, and embodiments of the disclosed embodiments, as well as specific examples thereof, areintended to encompass both structural and functional equivalents thereof. Additionally, it is intended that such equivalents include both currently known equivalents as well as equivalents developed in the future, i.e. , any elements developed that perform the same function, regardless of structure.

[0065] It should be understood that any reference to an element herein using a designation such as “first,” “second,” and so forth does not generally limit the quantity or order of those elements. Rather, these designations are generally used herein as a convenient method of distinguishing between two or more elements or instances of an element. Thus, a reference to first and second elements does not mean that only two elements may be employed there or that the first element must precede the second element in some manner. Also, unless stated otherwise, a set of elements comprises one or more elements.

[0066] As used herein, the phrase “at least one of” followed by a listing of items means that any of the listed items can be utilized individually, or any combination of two or more of the listed items can be utilized. For example, if a system is described as including “at least one of A, B, and C,” the system can include A alone; B alone; C alone; 2A; 2B; 2C; 3A; A and B in combination; B and C in combination; A and C in combination; A, B, and C in combination; 2A and C in combination; A, 3B, and 2C in combination; and the like.

Claims

CLAIMSWhat is claimed is:

1. A system for generating a hybrid model based digital simulator (HMBDS) that simulates at least one bioprocess executing in a real-world cell culture container, comprising: a processing circuitry; a memory communicatively connected to the processing circuitry, the memory containing instructions that, when executed by the processing circuitry, configure the system to: receive a model of a first bioprocess; receive a plurality of experimental results data of the first bioprocess in the real- world cell culture container; generate a HMBDS based on the received first bioprocess model, the real-world cell culture container, and the received experimental results data; perform a simulation of a bioprocess executing within the real-world cell culture container using the HMBDS; perform optimization of the bioprocess based on the results of the simulation; and generate an optimized control protocol for configuring at least a first real-world cell culture container to perform the optimized bioprocess.

2. The system of claim 1 , wherein the memory further contains instructions that when executed by the processing circuitry, configure the system to: cause execution of the optimized bioprocess by the at least a first real-world cell culture container.

3. The system of claim 1 , wherein the real-world cell culture container is one of: Petri Dishes, T-Flasks, Erlenmeyer Flasks, 96-Well Plates, 24-Well Plates, 6-Well Plates, Spinner Flasks, Stirred-Tank Bioreactors, Wave Bioreactors, Hollow Fiber Bioreactors, Microwell Plates, Single-Use Bioreactor Bags, Perfusion Culture Bags, MicrocarrierCulture Systems, Perfusion Plates, Bioprocess Bags, Transwell Inserts, and Plate Readers.

4. The system of claim 1 , wherein the memory further contains instructions that when executed by the processing circuitry, configure the system to: receive an engineering model of the real-world cell culture container.

5. The system of claim 3, wherein generation of the HMBDS is further based on the received engineering model.

6. The system of claim 1 , wherein the processing circuitry further comprises an artificial intelligence (Al) engine.

7. The system of claim 6, wherein the Al engine is trained via supervised learning.

8. The system of claim 6, wherein the Al engine is used to generate the HMBDS.

9. The system of claim 1 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to: execute a simulation of a second bioprocess on the real-world cell culture container; receive real-world actual results of the second bioprocess executed on the real- world cell culture container; compare the actual results of the second bioprocess to the simulated results of the second bioprocess to determine differences therebetween; and calibrate the HMBDS upon determination that the differences are above a predetermined threshold.

10. The system of claim 1 , wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to:perform a simulation of a second bioprocess executing within the real-world cell culture container using the HMBDS; and perform optimization of the second bioprocess based on results of the simulation of the second bioprocess.11 . The system of claim 9, wherein the memory contains further instructions which when executed by the processing circuitry further configure the system to: perform at least one of the optimizations using an Al engine.

12. A method for generating a hybrid model based digital simulator (HMBDS) that simulates at least one bioprocess executing in a real-world cell culture container, comprising: receiving a model of a first bioprocess; receiving a plurality of experimental results data of the first bioprocess in the real- world cell culture container; generating a HMBDS based on the received first bioprocess model, the real-world cell culture container, and the received experimental results data; performing a simulation of a bioprocess executing within the real-world cell culture container using the HMBDS; performing optimization of the bioprocess based on the results of the simulation; and generating an optimized control protocol for configuring at least a first real-world cell culture container to perform the optimized bioprocess.

13. The method of claim 12, further comprising: causing execution of the optimized bioprocess by the at least a first real-world cell culture container.

14. The method of claim 12, wherein the real-world cell culture container is one of: Petri Dishes, T-Flasks, Erlenmeyer Flasks, 96-Well Plates, 24-Well Plates, 6-Well Plates, Spinner Flasks, Stirred-Tank Bioreactors, Wave Bioreactors, Hollow Fiber Bioreactors,Microwell Plates, Single-Use Bioreactor Bags, Perfusion Culture Bags, Microcarrier Culture Systems, Perfusion Plates, Bioprocess Bags, Transwell Inserts, and Plate Readers.

15. The method of claim 12, further comprising: receiving a first engineering model of the real-world cell culture container.

16. The method of claim 15, wherein generation of the HMBDS is further based on the received engineering model.

17. The method of claim 12, further comprising: performing generation of the HMBDS by a trained artificial intelligence (Al) engine.

18. The method of claim 12, further comprising: executing a simulation of a second bioprocess on the real-world cell culture container; receiving real-world actual results of the second bioprocess executed on the real- world cell culture container; comparing the actual results of the second bioprocess to the simulated results of the second bioprocess to determine differences therebetween; and calibrating the HMBDS upon determination that the differences are above a predetermined threshold.

19. The method of claim 12, further comprising: performing a simulation of a second bioprocess executing within the real-world cell culture container using the HMBDS; and performing optimization of the second bioprocess based on results of the simulation of the second bioprocess.

20. The method of claim 19, wherein at least one of the optimizations is performed using an Al engine.21 . A non-transitory computer readable medium having stored thereon instructions for generating a hybrid model based digital simulator (HMBDS) that simulates at least one bioprocess executing in a real-world cell culture container, comprising: receiving a model of a first bioprocess; receiving a plurality of experimental results data of the first bioprocess in the real- world cell culture container; generating a HMBDS based on the received first bioprocess model, the real-world cell culture container, and the received experimental results data; performing a simulation of a bioprocess executing within the real-world cell culture container using the HMBDS; performing optimization of the bioprocess based on the results of the simulation; and generating an optimized control protocol for configuring at least a first real-world cell culture container to perform the optimized bioprocess.

Images