System and method for seed train optimization

Abstract

A technique for determining the parameters of a seed train process for growing cell cultures. This technique includes determining the parameters of a seed train process, which includes obtaining specifications of seed train process constraints for multiple stages of the seed train process, and determining the parameters of the seed train process, which include a set of parameters for each specific stage of the multiple stages of the seed train process, determining the likelihood that performing the seed train process using the parameters will satisfy the seed train process success criteria, using historical cell growth data and the seed train process parameters, and outputting the set of parameters for each stage of the multiple stages of the seed train process and the likelihood that performing the seed train process will satisfy the seed train process success criteria.

Description

[Technical Field]

[0001] Related applications This application claims priority to U.S. Patent Application No. 63 / 489,958, filed on 13 March 2023 under 119(e) of the U.S. Patent Act, entitled “SYSTEMS AND METHODS FOR SEED TRAIN OPTIMIZATION,” the entire contents of which U.S. Patent Application are incorporated herein by reference. [Background technology]

[0002] Biological products are used to treat, prevent, and diagnose various medical conditions and diseases. Biological products can be produced by cells specifically engineered for their production. Some biological products include polypeptides (e.g., therapeutic proteins, monoclonal antibodies, vaccines, etc.), nucleic acids (e.g., messenger RNA (mRNA), small interfering RNA (siRNA), microRNA, etc.), or viral vectors (e.g., lentiviral vectors, adenovirus vectors, recombinant adeno-associated virus (rAAV) vectors, etc.).

[0003] Growing cell cultures used to produce biological products helps increase their production. Such cultures are typically grown using a "seed-train process," which refers to a process used to progressively scale the culture from a small number of cells to a larger number of cells. A seed-train process typically involves multiple stages, each corresponding to a culture system used to grow the culture to a volume greater than the volume achieved during the preceding stage. [Overview of the Initiative] [Means for solving the problem]

[0004] Some embodiments provide a method for determining seed train process parameters for a seed train process to grow a cell culture, the seed train process having multiple stages, and the method is performed using at least one software application program including a common interface module, a parameter optimization module, and a simulation module. In some embodiments, the method includes using at least one computer hardware processor to obtain specifications of seed train process constraints for multiple stages of a seed train process using a common interface module, determining seed train process parameters using a parameter optimization module and seed train process constraints, wherein the seed train process parameters include a set of parameters for each specific stage of the multiple stages of the seed train process, determining a corresponding set of parameters for growing a culture during a particular stage, using a parameter optimization module and seed train process constraints for each specific stage of the multiple stages, determining a likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria, and outputting a set of determined seed train process parameters for each stage of the multiple stages of the seed train process and the likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria.

[0005] Some embodiments provide a system comprising at least one computer hardware processor and at least one non-temporary computer-readable storage medium storing processor-executable instructions, wherein the processor-executable instructions, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to execute a method for determining seed-train process parameters for a seed-train process that grows a cell culture, having a plurality of steps, and the method is executed using at least one software application program which includes a common interface module, a parameter optimization module, and a simulation module. In some embodiments, the method includes using at least one computer hardware processor to obtain specifications of seed train process constraints for multiple stages of a seed train process using a common interface module, determining seed train process parameters using a parameter optimization module and seed train process constraints, wherein the seed train process parameters include a set of parameters for each specific stage of the multiple stages of the seed train process, determining a corresponding set of parameters for growing a culture during a particular stage, using a parameter optimization module and seed train process constraints for each specific stage of the multiple stages, determining a likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria, and outputting a set of determined seed train process parameters for each stage of the multiple stages of the seed train process and the likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria.

[0006] Some embodiments provide at least one non-temporary computer-readable storage medium for storing processor-executable instructions that cause at least one computer hardware processor to execute a method for determining seed train process parameters for a seed train process for growing a cell culture, the method being executed using at least one software application program including a common interface module, a parameter optimization module, and a simulation module. In some embodiments, the method includes using at least one computer hardware processor to obtain specifications of seed train process constraints for multiple stages of a seed train process using a common interface module, determining seed train process parameters using a parameter optimization module and seed train process constraints, wherein the seed train process parameters include a set of parameters for each specific stage of the multiple stages of the seed train process, determining a corresponding set of parameters for growing a culture during a particular stage, using a parameter optimization module and seed train process constraints for each specific stage of the multiple stages, determining a likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria, and outputting a set of determined seed train process parameters for each stage of the multiple stages of the seed train process and the likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria.

[0007] In some embodiments, determining each set of parameters for growing the culture during a particular stage for each specific stage of a plurality of stages includes determining at least one seed train process parameter, the at least one seed train process parameter being selected from the group consisting of live cell density, an indication of whether a particular stage is included in the seed train process, a target duration for the seed train process, batch medium volume, working volume per container, and the number of containers.

[0008] In some embodiments, obtaining a seed train process constraint specification involves obtaining a seed train process constraint specification selected from the group consisting of a target live cell density range, a target working volume range, a split ratio culture growth process constraint, and a batch medium volume range.

[0009] In some embodiments, the historical cell proliferation data includes data indicating the doubling time associated with the proliferation of one or more cell cultures.

[0010] In some embodiments, determining seed train process parameters using a parameter optimization module includes determining seed train process parameters using a genetic algorithm.

[0011] In some embodiments, determining the likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria involves performing Monte Carlo simulations using historical cell proliferation data.

[0012] In some embodiments, the seed train process success criteria include, for each of the multiple stages of the seed train process, a first criterion that the expected period required to grow the culture during a particular stage does not exceed a threshold period for growing the culture during that stage, and a second criterion that the expected viable cell density resulting from growing the culture during a particular stage does not exceed a threshold viable cell density resulting from growing the culture during that stage.

[0013] In some embodiments, determining each parameter set at a particular stage of multiple stages includes using each parameter set to determine the expected duration required to grow the cell culture during the particular stage and determining whether the expected duration exceeds each of the threshold durations for the particular stage.

[0014] In some embodiments, determining each parameter set for each specific step of a plurality of steps includes using each parameter set to determine the expected viable cell density obtained from growing the cell culture during the particular step, and determining whether the expected viable cell density exceeds the respective threshold viable cell density for the particular step.

[0015] In some embodiments, outputting a set of seed train process parameters for each stage of multiple stages of the seed train process and a likelihood indicating whether the implementation of the seed train process satisfies the success criteria of the seed train process includes generating a graphical user interface (GUI) using an interface module and displaying the set of seed train process parameters and / or likelihoods through the generated GUI.

[0016] In some embodiments, displaying a set of seed train process parameters through a common interface module includes displaying a visual indication of whether the seed train process parameters of the set of seed train process parameters violate the seed train process constraints of the seed train process constraints.

[0017] In some embodiments, determining the seed train process parameters comprises determining the seed train process parameters based on a set of estimated culture doubling times included in the seed train process constraints, the set of estimated culture doubling times including the estimated culture doubling times for each of a plurality of stages of the seed train process, and determining whether implementing the seed train process using the determined seed train process parameters meets the seed train process success criteria. Some embodiments further include displaying a visual indication of the result of determining whether implementing the seed train process using the seed train process parameters meets the seed train process success criteria via a graphical user interface (GUI) generated by the common interface module.

[0018] Some embodiments further include comparing the determined likelihood with a likelihood threshold, and outputting a set of seed train process parameters for each stage of a plurality of stages of the seed train process, which further includes outputting the determined seed train process parameters when the likelihood is determined to exceed the likelihood threshold.

[0019] In some embodiments, outputting a set of seed train process parameters for each stage of a plurality of stages of a seed train process includes determining whether implementing the seed train process using the determined seed train process parameters meets the seed train process success criteria, and if the likelihood indicating whether it meets the likelihood threshold, outputting a recommendation for implementing the seed train process for each stage of the plurality of stages of the seed train process using the set of seed train process parameters.

[0020] In some embodiments, at least one software application program further includes a seed train process automation module, and outputting a set of seed train process parameters for each stage of a plurality of stages of a seed train process and a likelihood indicating whether implementing the seed train process meets the seed train process success criteria includes sending the set of seed train process parameters and / or likelihood to the seed train process automation module, and using the seed train process automation module to cause a seed train process automation system to execute a specific stage of the plurality of stages of the seed train process according to each set of the seed train process parameters.

[0021] Some embodiments further include using a common interface module to obtain an input indicating the result of growing a cell culture during a first stage of a plurality of stages of a seed train process, using a parameter optimization module, the input, and seed train process constraints to determine updated seed train process parameters for a subsequent stage of the seed train process, and outputting the updated seed train process parameters.

[0022] Some embodiments further include using a common interface module to obtain specifications for the second seed train process constraints for multiple stages of the second seed train process; using a parameter optimization module and the second seed train process constraints to determine the second seed train process parameters of the second seed train process; using a simulation module, historical cell proliferation data and the second seed train process parameters to determine a second likelihood indicating whether performing the second seed train process using the second seed train process parameters satisfies the second seed train process criteria; and outputting the second seed train process parameters and the second likelihood indicating whether performing the second seed train process using the second seed train process parameters satisfies the second seed train process criteria.

[0023] In some embodiments, determining seed train process parameters using a parameter optimization module includes: determining a first score for a first candidate seed train process parameter using an objective function; determining a second score for a second candidate seed train process parameter using an objective function; comparing the first and second scores; and selecting a seed train process parameter from the first and second candidate seed train process parameters based on the comparison results.

[0024] In some embodiments, the seed train process parameters include a first set of seed train process parameters for a first stage of a plurality of stages of the seed train process, and determining the likelihood that performing the seed train process using the seed train process parameters will satisfy the seed train process success criteria includes, for a first stage of the seed train process, determining the first likelihood that growing a culture of cells during the first stage will satisfy the first criterion of the seed train process success criteria, using the first set of seed train parameters for the first stage.

[0025] In some embodiments, determining the likelihood that performing a seed train process using seed train process parameters will satisfy the seed train process success criteria includes simulating a first set of cell growth values ​​using historical cell growth data, wherein the first set of cell growth values ​​includes a first historical cell growth value for each of several stages of the seed train process; predicting a first outcome of performing a seed train process using seed train process parameters and a first set of cell growth values, wherein the first outcome indicates whether performing a seed train process using the determined seed train process parameters will satisfy the seed train process success criteria; simulating a second set of cell growth values ​​using historical cell growth data, wherein the second set of cell growth values ​​includes a second historical cell growth value for each of several stages of the seed train process; predicting a second outcome of performing a seed train process using seed train process parameters and a second set of cell growth values, wherein the second outcome indicates whether performing a seed train process using seed train process parameters will satisfy the seed train process success criteria; and determining the likelihood based on the predicted first and second outcomes.

[0026] In some embodiments, determining the likelihood based on the predicted first and second outcomes includes determining the number of predicted outcomes that would indicate that performing the seed train process would satisfy the seed train process success criteria using seed train process parameters and respective historical cell proliferation data, and determining the ratio of the number of predicted outcomes to the total number of predicted outcomes.

[0027] In some embodiments, the seed train process success criterion includes, for each of the multiple stages of the seed train process, a first criterion that the expected period required to grow the culture during a particular stage does not exceed a threshold period for growing the culture during that stage, and predicting the first outcome includes, for each specific stage of the multiple stages, determining a first expected period required to grow the cell culture during a particular stage of the seed train process using each set of seed train process parameters for that stage and the historical cell growth value from the first set of historical cell growth values, and comparing the first expected period to a threshold period, and predicting the second outcome includes, for each specific stage of the multiple stages, determining a second expected period required to grow the cell culture during a particular stage of the seed train process using each set of seed train process parameters for that stage and the historical cell growth value from the second set of historical cell growth values, and comparing the second expected period to a threshold period.

[0028] In some embodiments, the seed train process success criterion includes, for each of the multiple stages of the seed train process, a second criterion that the expected viable cell density resulting from growing the culture during a particular stage does not exceed a threshold viable cell density resulting from growing the culture during a particular stage, and predicting the second result includes, for each specific stage of the multiple stages, determining a first expected viable cell density resulting from growing the cell culture during a particular stage of the seed train process using the historical cell growth values ​​of a first set of historical cell growth values ​​and comparing the first expected viable cell density to a threshold viable cell density, and predicting the second result includes, for each specific stage of the multiple stages, determining a second expected viable cell density resulting from growing the cell culture during a particular stage of the seed train process using the historical cell growth values ​​of a second set of historical cell growth values ​​and comparing the second expected viable cell density to a threshold viable cell density.

[0029] The attached drawings are not intended to be drawn to scale. In the drawings, identical or nearly identical components shown in various figures are represented by similar numbers. For clarity, it is impossible to mark all components in all drawings. The drawings are as follows: [Brief explanation of the drawing]

[0030] [Figure 1A] This figure shows an exemplary technique 100 for determining seed train process parameters of a seed train process, according to some embodiments of the technique described herein. [Figure 1B] This is a block diagram of an exemplary system 160 for determining seed train process parameters of a seed train process according to some embodiments of the technology described herein. [Figure 2]This is a flowchart of an exemplary process 200 for determining seed train process parameters of a seed train process according to some embodiments of the technology described herein. [Figure 3A] This is a flowchart of an exemplary process 300 for determining seed train process parameters using a parameter optimization module and seed train process constraints, according to some embodiments of the technology described herein. [Figure 3B] The following are exemplary objective functions used to determine seed train process parameters according to some embodiments of the technology described herein. [Figure 4] This is a flowchart of an exemplary process 400 for determining the likelihood that implementing the seed train process using seed train process parameters, according to some embodiments of the technology described herein, will satisfy the seed train process success criteria. [Figure 5A-1] This specification provides exemplary interfaces illustrating seed train process parameters and seed train process constraints according to several embodiments of the technology described herein. [Figure 5A-2] This specification provides exemplary interfaces illustrating seed train process parameters and seed train process constraints according to several embodiments of the technology described herein. [Figure 5B-1] This specification provides exemplary interfaces illustrating seed train process parameters and seed train process constraints according to several embodiments of the technology described herein. [Figure 5B-2] This specification provides exemplary interfaces illustrating seed train process parameters and seed train process constraints according to several embodiments of the technology described herein. [Figure 5C-1] This specification provides exemplary interfaces illustrating seed train process parameters and seed train process constraints according to several embodiments of the technology described herein. [Figure 5C-2]This specification provides exemplary interfaces illustrating seed train process parameters and seed train process constraints according to several embodiments of the technology described herein. [Figure 5D] This specification provides an exemplary interface representing a prediction of whether implementing the seed train process using seed train process parameters will satisfy the seed train process success criteria, based on several embodiments of the technology described herein. [Figure 6] Exemplary historical cell proliferation data regarding doubling time is shown. [Figure 7A] This specification shows exemplary doubling time data from which historical cell proliferation data are derived according to several embodiments of the technology described herein. [Figure 7B] This specification shows exemplary doubling time data from which historical cell proliferation data are derived according to several embodiments of the technology described herein. [Figure 8A] Compared to implementing a manually designed seed train process, the embodiments of the technology described herein demonstrate a higher overall success rate in implementing the seed train process. [Figure 8B] Compared to implementing a manually designed seed train process, the embodiments of the technology described herein demonstrate a higher overall success rate in implementing the seed train process. [Figure 8C] This specification demonstrates that by implementing the 500L seed train process using embodiments of the technology described herein, a success rate of over 80% can be achieved at each stage of the seed train process. [Figure 8D] By implementing a 2kL seed train process using embodiments of the technology described herein, we demonstrate that a success rate of over 70% can be achieved at each stage of the seed train process. [Figure 9] This is a schematic diagram of an exemplary computing device that can implement the embodiments described herein. [Modes for carrying out the invention]

[0031] The inventors have developed a technique for designing and implementing an optimized seed-training process for growing cell cultures. In some embodiments, the technique includes determining seed-training process parameters for the seed-training process. For example, a set of seed-training process parameters may be determined for each of several stages of the seed-training process. In some embodiments, the seed-training process parameters are determined using a parameter optimization module and seed-training process constraints for each of the several stages of the seed-training process. After determining the seed-training process parameters, the technique includes using a simulation module and historical cell growth data to determine the likelihood that implementing the seed-training process using the determined seed-training process parameters will satisfy various seed-training process success criteria, such as, for example, a success criterion that the estimated duration for implementing the stages of the seed-training process does not exceed a threshold duration, and a success criterion that the estimated viable cell density resulting from growing the culture during the stages of the seed-training process does not exceed a threshold viable cell density.

[0032] While it is possible to produce biological products using small vials of cells, this would be highly inefficient for producing such products in industrial-scale quantities. Therefore, cell cultures are grown to a volume that can support industrial-scale production. For example, cell cultures can be grown to a volume that can be used for inoculation into a bioreactor, a large-scale system that supports a biologically active environment for large-scale bioproduction. Growing a cell culture to such a volume involves gradually scaling the culture from its initial volume to the target volume. Depending on the target volume, this process may take up to several days or even weeks.

[0033] The "seed train process" refers to the process used to progressively scale a culture from a small number of cells to a larger number of cells. A seed train process typically involves multiple stages ("multi-stage seed train processes"), each corresponding to a culture system used to grow the culture during a particular stage. For example, the first stage of a seed train process might utilize 250 mL. During the first stage, cells are grown in a 250 mL shaking flask until the culture meets certain criteria, such as achieving a target viable cell density. The culture is then transferred to a different container, such as a 1000 mL shaking flask, for growth in the second stage. As the seed train process progresses, the cell culture continues to expand until it reaches the target volume.

[0034] Various factors influence the quality of a seed train process. Examples of such factors include the containers selected, the volume of culture medium used to fill the selected containers, the ratio of fresh medium to subcultured cells, the culture period, and the apparent growth rate. When designing a seed train process, many of these factors can be adjusted to control culture growth. For example, the designer of the seed train process (e.g., user or automated system) can select the containers at each stage of the seed train process and the amount of culture medium to fill each container. However, other factors cannot be controlled. For example, the cell growth rate varies between different stages and different cultures. Furthermore, the cell growth rate is complex in that it depends on several external factors such as process scale, container selection, seeding density, substrate, and metabolite concentration.

[0035] Because cell growth rate directly affects the time required to complete each stage of the seed-training process, and due to variability between different stages and cultures, predicting the time required to complete the seed-training process or a specific stage within it is difficult. For example, cells growing at an unexpectedly low growth rate will require more time to reach the target volume, leading to delays. Such delays can cause scheduling problems for the manufacturing facility where the seed-training process is being carried out. In contrast, cells growing at an unexpectedly high growth rate will require less time to reach the target volume, but if the culture is not monitored, it can lead to cell overgrowth. Overgrowth of the culture results in cell death, and in many cases, the culture must be discarded. This not only wastes resources but also causes significant delays by requiring the culture to be regrow.

[0036] Conventional techniques for designing seed-training processes are empirical. They involve designing later stages of the seed-training process based on observations made during the earlier stages. For example, such techniques include growing a culture during a specific stage of the seed-training process, recording observations about the culture's growth (e.g., cell growth rate) during that stage, and using those observations to design the next stage of the seed-training process. While such techniques can facilitate the growth of high-quality cell cultures by preventing overgrowth of cells, they do not allow for estimation of the duration of the seed-training process. Firstly, such techniques are still subject to delays caused by unexpected changes in cell growth rates across the various stages of the seed-training process. Secondly, many parameters affecting the duration of the seed-training process, such as the number of stages, the choice of containers, and the split ratio, are selected midway through the process, making it difficult to predict in advance how long it will take for different stages of the seed-training process to complete.

[0037] Accordingly, the inventors have developed a technique to address the aforementioned limitations of conventional seed train process design techniques. In some embodiments, the technique includes (a) obtaining seed train process constraints for multiple stages of the seed train process; (b) determining seed train process parameters using the seed train process constraints and optimization modules; (c) determining the likelihood that performing the seed train process using the seed train process parameters will satisfy the success criteria for the seed train process, using the simulation module and historical cell proliferation data; and (d) outputting the determined seed train process parameters and the determined likelihood.

[0038] The term “seed train process constraints” refers to aspects of the seed train process that cannot be altered. In some embodiments, they are defined by the equipment on which the seed train process is carried out. For example, the duration of the seed train process may be limited by the schedule of the equipment on which the seed train process is carried out. Additionally or alternatively, in some embodiments, seed train process constraints are defined by the equipment available for carrying out the seed train process. For example, the types, number, and / or volumes of available containers may limit the volume of culture medium that can be supplied to the cell culture at each stage. In addition or alternatively, in some embodiments, seed train process constraints are defined by the cell culture itself. For example, different cell lines grow at different rates. Growth rate can be a constraint on the seed train process because it cannot be altered. In some embodiments, the growth rate and / or doubling time of a particular cell line may be estimated based on historical cell growth data. Examples of seed train process constraints are listed in Table 1.

[0039] The term "seed train process parameters" can refer to modifiable aspects of the seed train process. Seed train process parameters can be selected within seed train process constraints. For example, seed train process constraints can define upper and lower limits for specific aspects of the seed train process (e.g., medium volume), and seed train process parameters can be selected within those boundaries. Exemplary seed train process parameters are listed in Table 2.

[0040] The term “success criteria” may refer to one or more criteria that define one or more successful outcomes of the implementation of the seed train process. In some embodiments, success criteria include the criterion that the expected period required to grow the culture during a particular stage of the seed train process does not exceed a threshold period for growing the culture during that particular stage. If the period criterion is met, in some embodiments this may indicate that no more than a threshold amount of additional time is required to grow the cell culture during that particular stage. If the period criterion is not met, this may indicate that implementing the seed train process according to the seed train process constraints and selected parameters could potentially disrupt the scheduling of the facility and / or the timing of downstream processes. In addition or alternatively, in some embodiments, success criteria include the criterion that the expected viable cell density obtained from growing the culture during a particular stage of the seed train process does not exceed a threshold viable cell density. In some embodiments, if the expected viable cell density does not exceed a threshold (e.g., the criterion is met), this may indicate that growing the culture during a particular stage according to the seed train process constraints and selected parameters will not result in overgrowth of the cell culture. In contrast, if the expected viable cell density exceeds the viable cell density threshold, this may indicate that growing the culture during a particular stage according to seed-training process constraints and selected parameters can lead to cell culture overgrowth.

[0041] The technology developed by the inventors improves upon conventional seed train process design techniques by including the determination of seed train process parameters that, when used to implement one or more stages of the seed train process, are estimated to result in the successful completion of the seed train process under mean cell proliferation conditions. Such a technology makes it possible to design the seed train process before initiating it, thereby enabling the manufacturing equipment to accurately estimate the time required to complete the seed train process and create a schedule accordingly. This is far more efficient than conventional techniques, which design the seed train process while it is in progress, thereby hindering accurate estimation of the time required to complete the seed train process.

[0042] Furthermore, the technology developed by the inventors improves upon conventional techniques by predicting the likelihood of successfully completing the seed train process using determined seed train process parameters, taking into account the variability of chronological cell proliferation rates. Therefore, before implementing the seed train process, it is possible to estimate whether the seed train process will be successful if the cell proliferation rate is slower or faster than average. Such information can be used to determine whether to proceed with the seed train process using the determined parameters, determine updated parameters, or completely cancel the seed train process. Thus, such technology helps ensure compliance with equipment scheduling and reduces wasted resources and time.

[0043] The technologies described herein are not limited to any particular method of implementation and can be carried out in a variety of ways. Detailed examples of embodiments are provided for illustrative purposes only. Furthermore, the technologies disclosed herein can be used individually or in any suitable combination, as the embodiments of the technologies described herein are not limited to the use of any particular technology or combination of technologies.

[0044] Figure 1A shows an exemplary technique 100 for designing a seed train process according to several embodiments of the technique described herein. In some embodiments, technique 100 includes (a) determining seed train process parameters based on seed train process constraints 102 in operation 110, (b) determining the likelihood of meeting seed train process success criteria as a result of performing one or more steps of the seed train process according to the determined parameters, based on historical cell proliferation data 104, in operation 120, and (c) determining whether to perform one or more steps of the seed train process based on the likelihood of meeting the success criteria in operation 130. In some embodiments, if it is determined in operation 130 that one or more steps of the seed train process should not be performed, technique 100 terminates. In some embodiments, if it is determined that one or more steps should be performed, technique 100 includes performing one or more steps of the seed train process in operation 140. Based on the results of performing one or more steps of the seed train process, operation 145 includes determining whether the results meet the success criteria. If the result meets the success criteria, action 150 includes determining whether there are additional stages in the seed-training process. If there are additional stages in the seed-training process, one or more actions of technique 100 may be repeated for the next stage. Otherwise, technique 100 terminates.

[0045] As described herein, the seed train process is used to scale a culture from a small number of cells to a larger number of cells. For example, at the start of the seed train process, the cell culture may occupy a container having a volume of 25 mL, 50 mL, 100 mL, 150 mL, 200 mL, 250 mL, 300 mL, 400 mL, 500 mL, 10 mL to 1000 mL, 25 mL to 500 mL, 200 mL to 400 mL, or any other suitable volume, but the embodiments of the technique described herein are not limited thereto. During the seed train process, the cell culture may grow to achieve any suitable volume. For example, by the end of the seed train process, the cell culture may occupy a container that is 2, 5, 10, 25, 50, 75, 100, 150, 200, 300, 500, 1,000, 2,000, 5,000, 10,000, 1.5 to 50,000, 2 to 10,000, 25 to 5,000 times, or any other suitable multiple of the initial container size, but the embodiments of the technology described herein are not limited thereto.

[0046] In some embodiments, the seed train process includes multiple stages. For example, as shown in operation 140 of technique 100, the seed train process includes stages 1 to N-1, where N is any suitable number, but embodiments of the techniques described herein are not limited to any particular number of seed train process stages. As described herein, in some embodiments, the number of stages is a seed train process parameter determined in operation 110 of technique 100.

[0047] In some embodiments, carrying out a seed train process involves growing a cell culture according to determined seed train process parameters. In some embodiments, each stage of the seed train process is associated with a set of seed train process constraints and / or seed train parameters. For example, a first stage of the seed train process may be associated with a first set of constraints, during which the cell culture may be grown using the first set of parameters. A nth stage of the seed train process may be associated with an nth set of constraints, during which the cell culture may be grown using the nth set of parameters. The first set of constraints and the nth set of constraints may be the same (e.g., including all of the same constraints) or different (e.g., including some of the same constraints or none of them). The first set of parameters and the nth set of parameters may be the same (e.g., including all of the same parameters) or different (e.g., including some of the same parameters or none of them).

[0048] In some embodiments, the seed train process constraints 102 are immutable aspects of the seed train process. In some embodiments, they are defined by the equipment on which the seed train process is carried out. For example, the duration of the seed train process may be limited by the schedule of the equipment on which the seed train process is carried out. Additionally or alternatively, in some embodiments, the seed train process constraints 102 are defined by the equipment available for carrying out the seed train process. For example, the types, number, and / or volumes of available containers may limit the volume of culture medium that can be supplied to the cell culture at each stage. In addition or alternatively, in some embodiments, the seed train process constraints 102 are defined by the cell culture itself. For example, different cell lines grow at different rates. The growth rate may be a constraint on the seed train process because it cannot be changed. In some embodiments, the growth rate and / or doubling time of a particular cell line may be estimated based on historical cell growth data obtained from the historical cell growth data store 172.

[0049] Table 1 lists non-limiting examples of seed train process constraints. Since the embodiments of the technology described herein are not limited in this respect, it should be understood that the seed train process may be associated with additional or alternative seed train process constraints. In some embodiments, the exemplary seed train process constraints listed in Table 1 may apply to one, some, or all of the stages of the seed train process. In some embodiments, after one or more stages of the seed train process have been performed, the seed train process constraint 102 may be updated to include real-time culture growth data 142, such as cell doubling time and growth constant during the completed stages of the seed train process. Additional or alternative examples of seed train process constraints are described herein, including at least with reference to Figures 5A-1 to 5C-2.

[0050] [Table 1]

[0051] [Table 2]

[0052] In some embodiments, the seed train process parameters are modifiable aspects of the seed train process. Table 2 lists non-limiting examples of seed train process parameters. However, since the embodiments of the technology described herein are not limited in this respect, it should be understood that the seed train process may be associated with additional or alternative seed train process parameters. In some embodiments, the exemplary seed train process parameters listed in Table 2 may apply to one, some, or all of the stages of the seed train process. In some embodiments, one or more seed train process parameters listed in Table 2 may be calculated based on one or more other seed train process parameters and / or seed train process constraints. For example, Table 3 lists formulas for calculating at least some of the seed train process parameters in Table 2. Additional or alternative examples of seed train process parameters are described herein, including those described with respect to at least Figures 5B-1 to 5C-2.

[0053] [Table 3]

[0054] [Table 4]

[0055] In some embodiments, changing seed train process parameters affects the outcome of performing the seed train process. For example, changing seed train process parameters may affect the time required to complete the stages of the seed train process. In addition, or alternatively, changing seed train process parameters may affect the viable cell density resulting from growing the culture according to the seed train process parameters.

[0056] In some embodiments, designing a seed train process involves estimating the results of carrying out the seed train process according to seed train process parameters and constraints. This may include, for example, estimating the time required to grow the culture during a particular stage of the seed train process. In some embodiments, the duration of a stage in the seed train process may depend on one or more seed train process parameters and / or constraints. For example, the doubling time of a cell line, which can be estimated based on historical cell growth data (e.g., historical cell growth data 104), may affect the duration of a particular stage in the seed train process. Given the variability of doubling times, it may be beneficial to (a) estimate the duration based on the standard doubling time of the cell line (e.g., the average doubling time determined from historical cell growth data 104) and (b) estimate the duration based on the worst-case doubling time of the cell line based on historical cell growth data 104. In some embodiments, the estimated duration may provide guidance on whether the seed train process conforms to the facility schedule and / or whether additional time is required to carry out the seed train process.

[0057] In addition, or instead, estimating the results of performing the seed train process according to seed train process parameters and seed train process constraints may include estimating the final viable cell density resulting from growing the culture during a particular stage. In some embodiments, the estimated final viable cell density provides indication of whether growing the cell culture during a particular stage may result in overgrowth of the cell culture, which may lead to cell death. In some embodiments, the final viable cell density also depends on the doubling time of the cell line. Thus, in some embodiments, the final viable cell density may be estimated based on the normal doubling time for the cell line (e.g., the average doubling time determined from historical cell growth data 104) and / or the shortest doubling time.

[0058] In some embodiments, the estimated results of the seed train process are evaluated to determine whether they meet one or more “success criteria.” In some embodiments, the success criteria include the criterion that the expected period required to grow the culture during a particular stage does not exceed a threshold period for growing the culture during that stage. In some embodiments, the threshold period includes any suitable period, and embodiments of the art are not limited in this respect. For example, the threshold period may be defined by seed train process constraints (e.g., standard culture time). Further or alternatively, in some embodiments, the success criteria include the criterion that the additional time required to grow the culture during a particular stage (e.g., compared to the allocated time) does not exceed a threshold. For example, the threshold may be 0 hours, 2 hours, 4 hours, 8 hours, 12 hours, 20 hours, 40 hours, or any other suitable number of hours, and embodiments of the art are not limited in this respect. If the period criterion is not met, this may indicate that carrying out the seed train process according to the seed train process constraints and selected parameters could potentially disrupt the scheduling of the facility and / or the timing of downstream processes.

[0059] In addition, or alternatively, in some embodiments, the success criterion includes the criterion that the expected viable cell density obtained from growing the culture during a particular stage of the seed-train process does not exceed a threshold viable cell density. In some embodiments, if the expected viable cell density does not exceed a threshold (e.g., the criterion is met), this may indicate that growing the culture during a particular stage according to seed-train process constraints and selected parameters will not result in overgrowth of the cell culture. In contrast, if the expected viable cell density exceeds a viable cell density threshold, this may indicate that growing the culture during a particular stage according to seed-train process constraints and selected parameters may result in overgrowth of the cell culture. In some embodiments, the viable cell density threshold may depend on the container used to grow the culture during a particular stage.

[0060] In some embodiments, Technique 100 includes determining seed train process parameters for performing one or more stages of the seed train process in operation 110. In some embodiments, the seed train process parameters are determined such that the estimated outcome of performing the seed train process according to the determined parameters satisfies one or more success criteria. By determining seed train process parameters that are expected to yield results that satisfy the success criteria, Technique 100 can be used to design a seed train process that avoids overgrowth of cell cultures and adheres to time constraints (e.g., of the facility, whether the seed train process is performed or not). Additionally or alternatively, in some embodiments, the seed train process parameters are determined such that the estimated outcome of performing the seed train process according to the determined parameters is more desirable than the estimated outcome of performing the seed train process according to other seed train process parameters. For example, a more desirable estimated outcome may include a relatively short period of time for performing one or more stages of the seed train process and / or a relatively low viable cell density compared to other expected periods and / or viable cell densities.

[0061] In some embodiments, determining seed train process parameters in operation 110 includes (a) estimating the results of performing the seed train process according to the candidate set of parameters for each of several sets of candidate seed train process parameters, (b) comparing the estimated results, and (c) determining seed train process parameters based on the results of the comparison. Determining seed train process parameters may include selecting candidate parameters that yield estimated results satisfying one or more success criteria, and / or selecting candidate parameters that yield more desirable results than other candidate parameters. In some embodiments, seed train process parameters are determined using a parameter optimization module, such as parameter optimization module 182, described herein, including with respect to at least Figure 1B. In some embodiments, the parameter optimization module determines seed train process parameters using optimization techniques. For example, a genetic algorithm may determine seed train process parameters by testing candidate seed train process parameters against an objective function. Techniques for determining seed train process parameters are described in more detail herein, including with respect to at least Figures 1B, 2, 3A, and 3B.

[0062] In some embodiments, as described above, the estimated results of performing a particular stage of the seed-training process depend on the doubling time of a particular cell line during growth. However, doubling times vary among different cell cultures, with some cultures having relatively long doubling times and others having relatively short ones. Figure 6 shows an exemplary distribution of doubling times for multiple cultures of the same cell line. Therefore, the results of performing the seed-training process using the determined parameters may meet the success criteria if the culture's doubling time is equivalent to the historical mean, but this may not be true if the culture has a doubling time that is longer or shorter than the historical mean. For example, if the true doubling time is shorter than average, performing the seed-training process according to the determined parameters may result in overgrowth. If the true doubling time is longer than average, the duration of the seed-training process may exceed the period allocated for performing the seed-training process. In other words, the results of the seed-training process (e.g., duration, viable cell density) may not conform to the success criteria.

[0063] Accordingly, in some embodiments, technique 100 includes, in operation 120, determining the likelihood of satisfying the seed train process success criteria using the parameters determined in operation 110. In some embodiments, this includes evaluating multiple input scenarios. An input scenario may include the parameters determined in operation 110 and a set of doubling times randomly sampled from a normal distribution calculated from historical cell proliferation data 104. For example, the set of doubling times may include doubling times for each stage of the seed train process. The input scenarios may represent a potential set of conditions under which the seed train process can be performed. In some embodiments, at least 10, at least 25, at least 75, at least 100, at least 150, at least 200, at least 250, at least 300, at least 350, at least 400, at least 450, at least 500, at least 550, at least 600, at least 650, at least 700, at least 800, at least 900, at least 1,000, at least 1,500, at least 2,000, or any other suitable number of input scenarios may be evaluated, and embodiments of the Art are not limited in this respect.

[0064] In some embodiments, the historical cell proliferation data 104 includes cell doubling time data. For example, the cell doubling time data may include cell doubling time data from one or more previous seed-training processes. The cell doubling time data may include cell doubling times for each of one or more stages of the previous seed-training process. In some embodiments, the mean and standard deviation of the doubling time at each stage are calculated from the data. In some embodiments, the normal distribution of the doubling time at each stage is calculated by fitting the mean and standard deviation.

[0065] In some embodiments, determining the likelihood of satisfying the success criteria for a seed train process involves, for each of several input scenarios, (a) estimating the outcome of performing the seed train process according to the input scenario (e.g., duration, final viable cell density, etc.), and (b) determining whether the estimated outcome satisfies the success criteria for the seed train process. For example, one or more outcomes may be estimated for each stage of the seed train process and then compared to the success criteria for the seed train process for that particular stage. In some embodiments, an input scenario may be considered a successful scenario if at least a threshold number of outcomes satisfy their respective success criteria. For example, an input scenario may be considered a successful scenario if all outcomes satisfy their respective success criteria at each stage. In some embodiments, the likelihood of satisfying the seed train process success criteria is the ratio of the number of successful scenarios to the total number of input scenarios evaluated.

[0066] In some embodiments, the simulation module is used to determine the likelihood of satisfying the seed-train process success criteria. For example, the simulation module 184 described herein, including at least with respect to Figure 1B, may be used to determine the likelihood of satisfying the seed-train process success criteria. In some embodiments, the simulation module performs a Monte Carlo simulation to evaluate different input scenarios. The Monte Carlo simulation can be repeated any appropriate number of times for a particular input scenario. For example, the Monte Carlo simulation can be repeated at least 5 times, at least 10 times, at least 25 times, at least 50 times, at least 75 times, at least 100 times, at least 125 times, at least 150 times, at least 175 times, at least 200 times, or any other appropriate number of times, and the embodiments of the technology described herein are not limited in this respect.

[0067] In some embodiments, technique 100 includes determining in operation 130 whether to perform one or more stages of the seed train process. The determination may be based on the likelihood of satisfying the seed train process success criteria. For example, in some embodiments, operation 130 includes determining whether the likelihood of satisfying the seed train process success criteria exceeds a threshold. The threshold may be any suitable threshold, such as at least 40%, at least 50%, at least 60%, at least 70%, at least 80%, at least 85%, at least 90%, at least 95%, at least 98%, or any other suitable threshold, and embodiments of the technique described herein are not limited to any particular threshold. In some embodiments, if the likelihood satisfies the threshold, technique 100 proceeds to operation 140, which performs one or more stages of the seed train process. If the likelihood does not satisfy the threshold, technique 100 terminates or, optionally, returns to operation 110, which determines seed train process parameters, although these are not shown.

[0068] In some embodiments, operation 130 is performed by a processor and / or an individual. When operation 130 is performed by an individual, the likelihood of satisfying the seed train process success criteria may be output to the user. For example, the likelihood may be output via a user interface display. Additionally or alternatively, the processor may output recommendations on whether to perform one or more stages of the seed train process (e.g., via a user interface). In some embodiments, the individual manually determines whether to perform a stage of the seed train process based on the output likelihood of satisfying the success criteria and / or the processor's recommendation. When operation 130 is performed by a processor, the processor can automatically determine whether to perform one or more stages of the seed train process based on the likelihood of satisfying the success criteria.

[0069] In some embodiments, if it is determined that one or more stages of the seed train process are to be performed, the technology 100 proceeds to operation 140, during which the stages are performed. In some embodiments, one or more stages include one, some, or all of the stages of the seed train process. One or more stages may be performed according to the seed train process parameters and seed train process constraints 102 determined in operation 110. For example, a first stage of the seed train process may be performed according to the parameters determined for the first stage and the constraints specified for the first stage. Additionally or alternatively, multiple stages of the seed train process may be performed according to their respective seed train process parameters and constraints.

[0070] In some embodiments, one or more steps of the seed train process are performed automatically or semi-automatically. For example, an automation module such as the seed train process automation module 188 described herein, including at least the one described with respect to Figure 1B, may be used to control an automation system configured to perform one or more steps of the seed train process. Automation may include any suitable components for automating one or more steps of the seed train process. For example, the automation system may include an environment control system configured to control the environment in which the cell culture is growing (e.g., temperature, gas, pressure, pH, etc.), an imaging system, one or more robotic components configured to dispense fluids (e.g., culture medium), and / or any other suitable components for performing one or more steps of the seed train process automatically or semi-automatically.

[0071] In some embodiments, real-time culture growth data 142 is generated during the execution of one or more stages of the seed train process. In some embodiments, the real-time culture growth data 142 includes data that may influence one or more subsequent stages of the seed train process and / or one or more subsequent seed train processes. For example, the data 142 may include data indicating (e.g., by designation or otherwise indicating) the duration of a stage of the seed train process, cell doubling time, final viable cell density, and / or any other appropriate data, and the embodiments of the technique described herein are not limited in this respect. In some embodiments, the real-time culture growth data 142 may be used to update constraints 102 and / or to determine seed train process parameters for subsequent stages of the seed train process.

[0072] In some embodiments, after performing one or more stages of the seed train process in operation 140, technique 100 proceeds to operation 145, which determines whether the results of performing the stages of the seed train process meet one or more success criteria. For example, this may include determining whether the cell proliferation period during a particular stage exceeds a threshold period. If the period exceeds the threshold, this may result in a delay where the overall duration of the seed train process exceeds the time allocated for it. Thus, if the period exceeds the threshold, technique 100 may terminate; otherwise, technique 100 proceeds to operation 150. As another example, determining whether the results of performing the stages of the seed train process meet one or more success criteria includes determining whether the final viable cell density exceeds a viable cell threshold. If the final viable cell density exceeds the threshold, this may indicate cell overgrowth, which can lead to cell death and degrade the quality of the culture. Thus, if the final viable cell density exceeds the threshold, technique 100 may terminate; otherwise, technique 100 proceeds to operation 150.

[0073] Operation 150 includes determining whether there are still stages remaining in the seed train process. If there are no more stages and the seed train process is complete, technique 100 terminates. If the seed train process is incomplete, meaning there are stages of the seed train process that have not yet been implemented, the seed train process may continue.

[0074] In some embodiments, if the seed train process continues, technique 100 returns to operation 110 to determine updated seed train process parameters for subsequent stages of the seed train process. For example, the seed train process parameters may be updated to take real-time culture growth data 142 into account. In some embodiments, after determining the updated seed train process parameters, one or more of operations 120, 130, and 140 of technique 100 may be repeated based on the updated seed train process parameters.

[0075] Figure 1B is a block diagram of an exemplary system 160 for determining seed train process parameters of a seed train process according to some embodiments of the technology described herein. System 160 includes a computing device 170 configured to run software 180 to perform various functions related to the design and / or implementation of one or more stages of the seed train process. In some embodiments, software 180 includes a plurality of modules. Each module may include processor-executable instructions that, when executed by at least one computer hardware processor, cause at least one computer hardware processor to perform the functions of that module. Such modules may be referred to herein as “software modules,” and each of them includes processor-executable instructions configured to perform one or more processes, such as the processes described herein, including the descriptions with respect to at least Figures 2, 3A, and 4.

[0076] The computing device 170 can be one or more computing devices of any suitable type. For example, the computing device 170 may be operated by one or more users 176, such as one or more individuals who design and / or implement the seed train process. Additionally or alternatively, the user 176 may include one or more individuals associated with the facility on which the seed train process is implemented. For example, the user 176 may provide seed train process constraints, initial seed train process parameters, seed train process success criteria, historical cell proliferation data, and / or any other suitable inputs as inputs to the computing device 170 (e.g., by uploading one or more files), and the embodiments of the technology described herein are not limited to any particular type of input. Additionally or alternatively, in some embodiments, the user 176 may provide user inputs specifying processing or other methods to be performed on the seed train process constraints, initial seed train process parameters, seed train process success criteria, historical cell proliferation data, and / or other suitable data.

[0077] As shown in Figure 1B, the software 180 includes several software modules for designing and / or implementing the seed train process, such as a parameter optimization module 182, a simulation module 184, a common interface module 186, and a seed train process automation module 188.

[0078] In some embodiments, the common interface module 186 is configured to generate a graphical user interface (GUI) for displaying to the user 176 seed train process constraints, seed train process parameters, seed train process estimation results, whether the estimation results meet seed train process success criteria, and / or any other appropriate information, and the embodiments of the technology described herein are not limited to the display of any particular type of information. In some embodiments, the common interface module 186 enables multiple different users 176 to consistently view, input, and / or update such information. Examples of displays by the common interface module 186 are shown in Figures 5A-1 to 5D.

[0079] In some embodiments, user 176 can update one or more seed train process constraints and / or seed train process parameters by providing user input via a GUI (e.g., generated by a common interface module 186). For example, user 176 can provide input to update constraints that reflect changes in the equipment schedule, thereby making the duration for implementing one or more stages of the seed train process longer or shorter. Additionally or alternatively, user 176 may provide input indicating initial and / or preferred seed train process parameters (e.g., before or instead of determining the seed train process parameters). In some embodiments, the common interface module 186 automatically updates the display to reflect user changes. For example, the common interface module 186 can automatically generate a GUI for displaying the updated constraints and / or parameters, as well as the updated estimation results resulting from those changes.

[0080] In some embodiments, the parameter optimization module 182 is configured to determine seed train process parameters for performing one or more stages of the seed train process. For example, this may include determining a set of seed train process parameters for each particular stage of the seed train process. Exemplary seed train process parameters are listed in Table 2. In some embodiments, the parameter optimization module 182 is configured to determine seed train process parameters automatically or in response to instructions from the user 176 (for example, by providing input via a GUI generated by the common interface module 186).

[0081] In some embodiments, the parameter optimization module 182 determines the seed train process parameters by performing one or more operations of the process 300 described herein, including operations 110 in Figure 1A, operations 204 in Figure 2, and / or at least the description relating to Figure 3A. For example, in some embodiments, the parameter optimization module 182 determines the seed train process parameters using a genetic algorithm. For example, a genetic algorithm may determine the seed train process parameters by testing candidate seed train process parameters against an objective function such as the objective function in Figure 3B.

[0082] In some embodiments, the parameter optimization module 182 is configured to determine seed train process parameters using seed train process constraints. As described herein, in some embodiments, the seed train process constraints are aspects of the seed train process that cannot be changed. The seed train process constraints may define a range for which seed train process parameters should be selected (e.g., upper and lower limits on initial viable cell density). Additionally or alternatively, seed train process constraints may be used to define success criteria for the seed train process (e.g., the time allocated to carry out the stages of the seed train process). Examples of seed train process constraints are listed in Table 2.

[0083] The parameter optimization module 182 can retrieve (e.g., pull or receive) seed train process constraints from the seed train process constraint data store 174 and / or user 176 (e.g., by a user uploading seed train process constraints). For example, user 176 can upload seed train process constraints using the common interface module 186.

[0084] In some embodiments, the parameter optimization module 182 is configured to additionally or alternatively use historical cell proliferation data to determine seed train process parameters. For example, the historical cell proliferation data may include cell doubling time data from one or more previous seed trains. The cell doubling time data may include cell doubling times at each of one or more stages of the previous seed train process. In some embodiments, the mean and standard deviation of the doubling time at each stage are calculated from the data. In some embodiments, the parameter optimization module 182 may assume an average doubling time at each stage of the seed train process when determining the seed train process parameters.

[0085] The parameter optimization module 182 can obtain (e.g., pull or receive) the average doubling time from the historical cell proliferation data store 172 and / or user 176 (for example, by the user uploading historical cell proliferation data).

[0086] In some embodiments, the common interface module 186 is configured to generate a GUI for displaying parameters determined using the parameter optimization module 182. For example, the common interface module 186 can input the determined parameters into a display, or replace the initial seed train process parameters in an existing display with the determined parameters. The GUI may additionally or alternatively display estimated results (e.g., duration, final viable cell density, etc.) of performing one or more stages of the seed train process using the determined parameters. The GUI may additionally or alternatively display whether the estimated results meet one or more seed train process success criteria. In some embodiments, the user 176 may interact with the GUI to update the seed train process parameters even after they have been determined using the parameter optimization module 182. This may allow the user 176 flexibility in designing the seed train process according to their preferences or expectations.

[0087] In some embodiments, the simulation module 184 is configured to determine the likelihood that performing the seed train process using seed train process parameters determined using the parameter optimization module 182 will satisfy at least one seed train process success criterion. This may include performing one or more operations of the process 400 described herein, including operation 120 in Figure 1A, operation 206 in Figure 2, and / or those described with respect to at least Figure 4. For example, the simulation module 184 may be configured to evaluate multiple input scenarios using Monte Carlo simulation. In some embodiments, as described herein, Monte Carlo simulation is used to predict whether a particular input scenario will result in an outcome that satisfies one or more success criteria. An input scenario may be considered a “successful scenario” if the outcome is predicted to satisfy at least a threshold number of success criteria (e.g., all success criteria for all stages of the seed train process). In some embodiments, the likelihood of satisfying the seed train process success criteria is the ratio of the number of successful scenarios to the total number of input scenarios evaluated.

[0088] In some embodiments, the simulation module 184 is configured to use historical cell proliferation data to determine the likelihood of satisfying the seed train process success criteria. For example, the input scenario evaluated by the simulation module 184 may include a set of doubling times randomly sampled from a normal distribution calculated from historical cell data. For example, the set of doubling times may include the doubling times for each stage of the seed train process.

[0089] The simulation module 184 can retrieve historical cell proliferation data from the historical cell proliferation data store 172 (e.g., by pulling or receiving) and / or from the user 176 (e.g., by the user uploading historical cell proliferation data). For example, user 176 may upload historical cell proliferation data using the common interface module 186.

[0090] In some embodiments, the common interface module 186 is configured to output the likelihood of satisfying the seed train process success criteria determined by the simulation module 184. For example, the common interface module 186 can output likelihood-indicating information such as ratios, percentages, graphics, or any other appropriate information indicating likelihood. Additionally or alternatively, in some embodiments, the common interface module is configured to output the likelihood of satisfying the success criteria for each individual stage of the seed train process.

[0091] In some embodiments, user 176 may determine whether to perform one or more stages of the seed train process based on the output likelihood of satisfying the success criteria. If user 176 decides to perform one or more stages of the seed train process, in some embodiments, the user may instruct the seed train process automation module 188 to perform one or more stages automatically or semi-automatically. Additionally or alternatively, user 176 may perform one or more stages of the seed train process manually.

[0092] In some embodiments, the seed train process automation module 188 receives the likelihood of satisfying the success criteria for the seed train process from the simulation module 184. The seed train process automation module 188 may be configured to determine whether to perform one or more stages of the seed train process based on the received likelihood. For example, if the likelihood is equal to or greater than a threshold (i.e., there is a relatively high likelihood of satisfying the seed train process success criteria using the determined seed train process parameters), the seed train process automation module 188 may decide to perform one or more stages of the seed train process. Conversely, if the likelihood is not greater than or equal to a threshold (i.e., there is a relatively low likelihood of satisfying the seed train process success criteria using the determined seed train process parameters), the seed train process automation module 188 may decide not to perform one or more stages of the seed train process.

[0093] In some embodiments, the seed train process automation module 188 may be further configured to control the seed train process automation system 190. For example, the seed train automation module can control the seed train process automation system 190 to perform one or more stages of the seed train process. In some embodiments, the seed train process automation system 190 includes any suitable components for automating one or more stages of the seed train process. For example, the automation system 190 may include an environment control system configured to control the environment in which the cell culture is growing (e.g., temperature, gas, pressure, pH, etc.), an imaging system, one or more robotic components configured to dispense fluids (e.g., culture medium), and / or any other suitable components for automatically or semi-automatically performing one or more stages of the seed train process.

[0094] The common interface module 186 may be configured to generate a graphical user interface (GUI), a text-based user interface, and / or any other suitable type of interface that allows a user to provide input and display information generated by the software 180. For example, in some embodiments, the common interface may be a web page or web application accessible through an internet browser. In some embodiments, the user interface may be a graphical user interface (GUI) of an application running on a user's mobile device. In some embodiments, the user interface may include a number of selectable elements with which the user can interact. For example, the user interface may include drop-down lists, checkboxes, text fields, or other suitable elements.

[0095] Figure 2 is a flowchart of an exemplary process 200 for determining seed train process parameters for a multi-stage seed train process, according to some embodiments of the technology described herein. One or more operations of process 200 may be performed automatically by any suitable computing device. For example, the operations may be performed by a laptop computer, a desktop computer, one or more servers in a cloud computing environment, the computing device 900 described herein with respect to Figure 9, and / or in other suitable ways. For example, in some embodiments, operation 202 may be performed automatically by any suitable computing device. As another example, operation 204 may be performed automatically by any suitable computing device.

[0096] In operation 202, the processor obtains specifications for seed train process constraints for multiple stages of the seed train process. As described herein, seed train process constraints are immutable aspects of the seed train process. For example, seed train process constraints may include at least some of the seed train process constraints 102 described herein, including the seed train process constraints listed in Table 1 and / or those described with respect to at least Figure 1A.

[0097] In some embodiments, seed train process constraints include one or more constraints for each of multiple stages of the seed train process. For example, a first seed train process constraint may be specified for a first stage of the seed train process, and a second seed train process constraint may be specified for a second stage of the seed train process. In some embodiments, different seed train process constraints are specified for different stages (e.g., first and second stages). For example, some seed train process constraints, such as upper and lower limits of working volume, may depend on the volume of the container used to grow the cell culture during a particular stage. As the container volume increases with each stage, the upper and lower limits of the working volume range also increase. Figures 5A-1 to 5C-2 show examples of seed train process constraints specified for each of stages N-8 to N-0 of an exemplary seed train process.

[0098] In some embodiments, the processor uses a common interface module to obtain specifications for seed train process constraints. For example, the common interface module may include the common interface module 186 described herein, including at least the one described with respect to Figure 1B. In some embodiments, the common interface module includes fields that indicate the relevant seed train process constraints and store the respective values ​​of the seed train process constraints. The user can provide and / or update the values ​​of the seed train process constraints by interacting with a GUI generated by the common interface module (e.g., using text boxes or other selectable elements of the graphical user interface). As an example, if a seed train process is implemented in a facility where several other processes (e.g., other seed train processes) are implemented, the user of the facility can interact with the GUI to update facility-related constraints such as available equipment (e.g., containers), scheduling constraints, and any other appropriate constraints, and embodiments of the art are not limited thereto. Thus, by obtaining seed train process constraints via the common interface module, the processor can obtain the most up-to-date seed train process constraints, which can then be used to design seed train processes that fit the facility scheduling. Additionally or alternatively, the processor may obtain the seed train process constraint specifications from a data store (e.g., seed train process constraint data store 174 in Figure 1B) or use any other suitable method, and the embodiments of the techniques described herein are not limited in this respect.

[0099] In operation 204, the processor uses seed train process constraints to determine seed train process parameters. As described herein, seed train process parameters are modifiable aspects of the seed train process. For example, seed train process parameters may include at least some of the seed train process parameters described herein, including the seed train process parameters listed in Table 2 and / or the descriptions relating to at least Figure 1A.

[0100] In some embodiments, the processor determines seed train process parameters for each specific stage of a plurality of stages in the seed train process, and corresponding sets of seed train process parameters for accelerating the culture during a particular stage. For example, this may include determining a first set of seed train process parameters for a first stage in the seed train process and a second set of seed train process parameters for a second stage in the seed train process. Figures 5B-1 to 5C-2 show exemplary seed train process parameters determined for each of stages N-8 through N-0.

[0101] In some embodiments, the processor determines seed train process parameters using a parameter optimization module, such as the parameter optimization module 182 described herein, including at least the one described with respect to Figure 1B.

[0102] In some embodiments, determining seed-train process parameters involves determining seed-train process parameters using optimization techniques. Any suitable optimization technique may be used, including, for example, a genetic algorithm, random search, or grid search, and embodiments of the techniques described herein are not limited in this respect. In some embodiments, a genetic algorithm may take an objective function and a boundary for each variable in the function as input. For example, the boundary may be defined by seed-train process constraints, and the objective function may include the exemplary objective function shown in Figure 3B. In some embodiments, a genetic algorithm generates a set of values ​​for the variables in the objective function randomly selected from a range defined by a given boundary, and it mutates by iteration until a set of values ​​that gives an overall minimum (or maximum) is found. In some embodiments, the genetic algorithm is a differential evolution algorithm. For example, Storn, R. and Price, K. (Differential Evolution - a simple and efficient adaptive scheme for global optimization over continuous spaces) describes an example of a differential evolution algorithm, which is incorporated herein by reference in whole. Exemplary techniques for determining seed-train process parameters are described herein, including at least those described with respect to Figure 3A.

[0103] In some embodiments, when determining seed train processor parameters, the processor may use a future set of parameters and specified constraints to estimate one or more outcomes of performing one or more stages of the seed train process. For example, this may include estimating the outcome of performing a first stage of the seed train process using a first set of future parameters for that stage and specified constraints for the first stage. In some embodiments, the estimation results may include an estimated period required to grow the cell culture during a particular stage of the seed train process and / or an estimated final viable cell density resulting from growing the cell culture during a particular stage.

[0104] In some embodiments, seed train process parameters are determined in operation 204 such that one or more (e.g., one, several, or all) estimated results of performing one or more stages of the seed train process satisfy the success criteria for the seed train process. As described herein, including at least those described with respect to Figure 1A, the success criteria may include: (a) the expected period required to grow the culture during a particular stage does not exceed a threshold period for growing the culture during that stage, and / or (b) the expected viable cell density resulting from growing the culture during a particular stage of the seed train process does not exceed a threshold viable cell density.

[0105] In some embodiments, if multiple future sets of parameters result in outcomes that satisfy a success criterion, only one set of future parameters may be identified as seed-train process parameters. For example, when testing future seed-train process parameters against an objective function, the processor can select parameters that yield an objective function value that satisfies at least one criterion. For instance, future parameters that yield the maximum or minimum value of the objective function can be selected as seed-train process parameters.

[0106] In operation 206, the processor determines the likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria. In some embodiments, the processor determines the likelihood using a simulation module, historical cell proliferation data, and the determined seed train process parameters. The simulation module may include simulation module 184 in Figure 1B.

[0107] In some embodiments, as described herein, historical cell proliferation data may include data relating to the growth rate of cells from past seed-train experiments. For example, historical cell proliferation data may include culture doubling time data from past seed-train processes. Doubling time data may include the distribution of doubling time values ​​at each of several stages of past seed-train processes.

[0108] In some embodiments, the results of performing the seed train process using determined seed train process parameters are estimated based on only one or a few doubling times (e.g., mean historical doubling time, shortest historical doubling time, and / or longest historical doubling time), and therefore the estimated results do not take into account other potential doubling times (e.g., those included in the distribution of doubling times). Consequently, the estimated results may not accurately reflect the actual results of performing the seed train process. For example, growing a culture during a particular stage of the seed train process may take longer than the estimated period if the estimated period is based on the historical mean doubling time, and the actual doubling time is longer than the historical mean. In this example, the estimated period may meet the success criteria, but the actual period may not.

[0109] Therefore, in some embodiments, it may be beneficial to determine the likelihood of meeting the success criteria before carrying out one or more steps of the seed train process using the determined seed train process parameters. If the likelihood of meeting the success criteria is relatively low, this may indicate that carrying out the seed train process using the determined seed train process parameters is likely to violate the success criteria (for example, it may result in excessive cell proliferation or take longer than the time allocated to carry out a particular step).

[0110] In some embodiments, determining the likelihood of satisfying the seed train process success criteria includes (a) sampling historical cell proliferation data, (b) simulating the results of performing the seed train process using the sampled historical cell proliferation data and seed train process parameters determined in operation 204, and (c) determining whether the simulated results satisfy the success criteria. Techniques for determining the likelihood of satisfying the success criteria are described herein at least with respect to Figure 4.

[0111] In operation 208, the processor outputs (a) a set of seed train process parameters determined for each of the multiple stages of the seed train process, and (b) a likelihood that performing the seed train process using the determined seed train parameters will satisfy the seed train process success criteria.

[0112] In some embodiments, the processor outputs a set of seed train process parameters and / or likelihoods via a common interface module. For example, Figures 5B-1 to 5D show the set of seed train process parameters determined for each of stages N-8 through N-1. In some embodiments, the parameters and / or likelihoods are displayed via a user interface, such as a GUI generated by the common interface module 186 in Figure 1B. Additionally or alternatively, in some embodiments, the parameters and / or likelihoods are output (e.g., transmitted) to a seed train process automation module, such as the seed train process automation system 190 in Figure 1B. Additionally or alternatively, in some embodiments, the parameters and / or likelihoods are output to a data store or output using any other suitable output technique, and the embodiments of the techniques described herein are not limited thereto.

[0113] In some embodiments, the likelihood of performing the seed train process using determined seed train process parameters, which indicates whether the success criteria are met, is used to determine whether to perform one or more stages of the seed train process. For example, this may include deciding to perform one or more stages of the seed train process if the output likelihood exceeds a threshold likelihood. In some embodiments, a user, such as a scientist, manually determines whether to perform one or more stages of the seed train process. In some embodiments, the decision to perform one or more stages is made automatically or semi-automatically using a processor. For example, the seed train process automation module 188 in Figure 1B can automatically determine whether to perform one or more stages of the seed train process.

[0114] Although not shown, in some embodiments, process 200 may include performing one or more stages of the seed train process using determined seed train process parameters. For example, one or more stages of the seed train process may be performed manually (e.g., by a user), automatically, or semi-automatically. For example, a seed train process automation system such as the seed train process automation system 190 in Figure 1B can perform one or more stages of the seed train process automatically or semi-automatically.

[0115] It should be understood that process 200 may include one or more additional or alternative actions not shown in Figure 2A. For example, process 200 may include an action to determine whether to perform one or more stages of the seed train process and / or an action to perform one or more stages of the seed train process.

[0116] Figure 3A is a flowchart of an exemplary process 300 that determines seed train process parameters using a parameter optimization module and seed train process constraints, according to some embodiments of the technology described herein. In some embodiments, process 300 is an exemplary embodiment of operation 204 of process 200 in Figure 2.

[0117] One or more operations of process 300 may be performed automatically by any suitable computing device. For example, the operations may be performed by a laptop computer, a desktop computer, one or more servers in a cloud computing environment, the computing device 900 described herein in the description with respect to Figure 9, and / or in other suitable ways. In some embodiments, a software module, such as the parameter optimization module 182 in Figure 1B, is configured to perform process 300.

[0118] In some embodiments, process 300 includes evaluating multiple future sets of seed train process parameters to identify seed train process parameters that, when used to implement the seed train process, will result in a seed train process that satisfies the success criteria for the seed train process. For example, the multiple future sets of parameters may include any number of parameter future sets, including a first future parameter and a second future parameter. The first future parameter and the second parameter may not include any of the same parameters, or they may include one or more of the same parameters.

[0119] In some embodiments, the future set of parameters includes future seed-train process parameters for each stage of the seed-train process. In some embodiments, each future parameter for a particular stage in the seed-train process is selected to conform to seed-train process constraints for that stage. For example, the future working volume for a first stage of the seed-train process can be selected to be within (or equivalent to) the upper and lower working volumes for the first stage, both of which are seed-train process constraints for the first stage.

[0120] In operation 302, the processor determines a first score for the first future seed train process parameter. For example, determining the first score may involve using the first future seed train process parameter to determine a value relating to an objective function, such as the objective function shown in Figure 3B. In some embodiments, as will be described in more detail herein, the objective function takes into account each of the success criteria. Thus, in some embodiments, the resulting value of the objective function reflects whether using the first future parameter to implement one or more stages of the seed train process results in satisfying the success criteria for each stage. Additionally or alternatively, in some embodiments, the resulting value of the objective function reflects the degree to which the success criteria are satisfied. For example, a relatively large (or relatively small) value of the objective function may indicate that using the first future parameter to implement one or more stages of the seed train process results in a greater satisfaction of the success criteria.

[0121] In some embodiments, determining the extent to which the estimation results satisfy the seed-train process success criteria includes determining the number of estimation results that satisfy the seed-train process success criteria. For example, multiple results may be estimated for each stage of the seed-train process. In some embodiments, the value of the objective function increases (or decreases) as the number of estimation results that satisfy the success criteria at each stage increases. For example, the value of the objective function may be greater when the estimated results satisfy all the criteria for each stage compared to when the estimated results satisfy only some of the success criteria for one or more stages.

[0122] In addition or alternatively, in some embodiments, determining the extent to which the estimated results satisfy the seed-train process criteria includes determining the extent to which each individual estimated result satisfies its respective success criterion. For example, consider an estimated period of 5 hours and a threshold of 10 hours for cell proliferation in the first stage of the seed-train process. In this example, the success criterion is met if the estimated period does not exceed the threshold. Here, the success criterion is met because the estimated period of 5 hours does not exceed 10 hours. The estimated period of 5 hours also satisfies the success criterion to a greater extent than the estimated period of 8 hours, because the estimated period of 8 hours is closer to the threshold period.

[0123] In operation 304, a second score for the second future seed train process parameter is determined. As described with respect to operation 302, in some embodiments, determining the score for the future seed train process parameter includes determining the value of an objective function, such as the objective function shown in Figure 3B.

[0124] In operation 306, the processor compares a first score determined for a first future parameter with a second score determined for a second future parameter. For example, this may include determining the relative value of the first score to the second score.

[0125] In operation 308, based on the comparison results, the processor selects seed-train process parameters from the first and second future parameters. In some embodiments, this includes selecting a set of future parameters with the highest (or lowest) score determined. For example, if in operation 306 the first score is determined to be greater than the second score, the first future parameter may be selected as the seed-train process parameter. In some embodiments, a higher (or lower) score may indicate that performing the seed-train process stages using the future parameter with that score will result in a greater satisfaction of the success criteria.

[0126] It should be understood that one or more additional sets of future parameters may be evaluated during process 300, and that process 300 is not limited to evaluating only the first and second future parameters. Rather, any appropriate number of sets of future parameters may be evaluated and used to determine the seed train process parameters. For example, process 300 may include determining a third score for a third future parameter, comparing the scores of the first, second, and third parameters, and selecting seed train process parameters from among the first, second, and third future parameters. Additionally or alternatively, the processor may search for future seed train process parameters within the seed train process constraint until a combination of future seed train process parameters is found that yields a threshold objective function.

[0127] Figure 3B shows an exemplary objective function used to determine seed train process parameters according to some embodiments of the technology described herein. In some embodiments, the objective function is used to determine seed train process parameters as part of process 300 in Figure 3A. For example, seed train process parameters may be searched to identify a combination of seed train process parameters that maximizes equation 352.

[0128] As shown, an exemplary objective function f obj 352 can be calculated as the sum of functions f1, f2, f3, f4, and f5.

[0129] In some embodiments, the function f1, 354 considers at least one success criterion. For example, the function 354 may consider a success criterion that the additional time required to grow cells during each stage of the seed-train process (e.g., stage n-1) is shorter than the threshold time for that particular stage, where the additional time required to grow cells is based on the standard doubling time of the stage. As described herein, the standard doubling time for a particular stage may be the average doubling time for the stage based on historical cell growth data. n may be equal to the total number of stages in the seed-train process. Additionally or alternatively, n may be less than the total number of stages in the seed-train process. For example, Figures 5A-1 to 5D show that stages N-3 and N-2 use the same container, respectively. In this example, the two stages may be counted only as a single stage, rather than as two different stages.

[0130] Regarding function 354, t normal,1 This refers to the additional time required to grow the culture in stage i of the seed train process, and the additional time is determined based on the standard doubling time.

[0131] As shown in the figure, function 354 is determined by comparing the additional time required for each stage of the seed train process (e.g., stages 1 to n) with a threshold additional time. In this case, the threshold additional time is 0. If the required additional time exceeds the threshold time for a particular stage, the augmented number for that particular stage is t normal,i It is calculated by multiplying by -10. If the required additional time is below the threshold, the adenand for a particular stage is t normal,i That is the case.

[0132] In some embodiments, function 356 takes into account at least one other success criterion. For example, function 356 can take into account the success criterion that the additional time required to grow the cells during each stage (e.g., stages 1 to n) of the seed train process is shorter than the threshold time for that particular stage, and the additional time required to grow the cells is based on the worst doubling time of the stage. As described herein, the worst doubling time for a particular stage can be the longest doubling time included in the historical cell growth data for that stage.

[0133] For function 356, t worst,1 refers to the additional time required to grow the culture at stage i of the seed train process, and the additional time is determined based on the worst doubling time of that stage.

[0134] As shown, function 356 is determined by comparing the normal additional time t normal,i at each stage (e.g., stages 1 to n) of the seed train process with a threshold additional time. In this case, the threshold additional time is -12. If the additional time required exceeds the threshold time for a particular stage, the addend for that particular stage is calculated by multiplying t worst,i by 0.5. If the additional time required is below the threshold, the addend for a particular stage is calculated by multiplying t worst,i by -5.

[0135] In some embodiments, function 358 takes into account at least one other success criterion. For example, function 358 can take into account the success criterion that the final viable cell density resulting from the growth of the cells during each stage (e.g., stages 1 to n) of the seed train process is lower than a threshold final viable cell density.

[0136] For function 358, C vcd,i refers to the final viable cell density resulting from growing the cells during stage i of the seed train process. In some embodiments, the final viable cell density for each stage is calculated based on the best doubling time of the stage. For example, the best doubling time can refer to the shortest doubling time of the stage obtained from the historical cell growth data. Climit,i This refers to a threshold viable cell density at a specific stage. For example, the threshold viable cell density may include an upper limit on the final viable cell density for a particular stage of the seed train process, which is specified as part of obtaining seed train process constraints for the seed train process.

[0137] As shown, function 358 gives the final viable cell density C for each stage of the seed train process (e.g., stages 1 to n). vcd,i threshold live cell density C limit,i It is determined by comparison with C. VCD,i C limit,i If it is smaller, the augmented number at that particular stage is C limit,i and C vcd,i It is calculated by multiplying the difference by 0.5. C vcd,i C limit,i If it exceeds C limit,i and C vcd,i It is calculated by multiplying the difference by -10.

[0138] In some embodiments, function 360 takes into account a safety margin for completing the seed train process within the time constraints for completing the seed train process. For example, if one stage has unexpectedly slow cell growth, the seed train process parameters should allow for a sufficient safety margin to complete the seed train process within the allocated time. Having a sufficient safety margin for the time to grow cells during the next stage can help maintain the duration of the seed train process in accordance with the equipment scheduling and / or the time allocated to complete the seed train process. In some embodiments, this is done by balancing the additional time required to grow cells during each stage.

[0139] In some embodiments, function 360 is f std (t normal,i It is determined by multiplying by -3, where f std (t normal,i) is the additional time (t) required for different stages of the seed train process. normal,i This is a function for determining the standard deviation of ), and the required additional time is based on the standard doubling time for each stage.

[0140] In some embodiments, function 362 takes into account variations in the initial viable cell density. For example, it may be undesirable for the initial viable cell density to deviate from a recommended value.

[0141] In some embodiments, function 362 is the final viable cell density C in the n-1 step prior to the seed train process. vcd,n-1 It is determined based on, where C VCD,n-1 This is determined based on the standard doubling time of stage n-1. For example, function 362 is C VCD,n-1 This can be calculated by multiplying the absolute value of the difference between and 6 by -30.

[0142] Figure 4 is a flowchart of an exemplary process 400 for determining the likelihood that implementing the seed train process using seed train process parameters will satisfy the seed train process success criteria, according to some embodiments of the technology described herein. In some embodiments, process 400 is an exemplary embodiment of operation 206 of process 200 in Figure 2.

[0143] One or more operations of process 400 may be performed automatically by any suitable computing device. For example, the operations may be performed by a laptop computer, a desktop computer, one or more servers in a cloud computing environment, a computing device 900 described herein, including those described with respect to Figure 9, and / or in other suitable ways. In some embodiments, a software module, such as the simulation module 184 in Figure 1B, is configured to perform process 400.

[0144] As described herein, in some embodiments, the outcome of a seed train process depends on seed train process constraints and seed train process parameters used to carry out each stage of the seed train process. Doubling time is one such seed train process constraint. However, doubling time differs in different seed train processes. Therefore, the outcome of a seed train process (e.g., duration of each stage, final viable cell density obtained from each stage, etc.) may depend on a specific doubling time of the culture during growth. Since this value is not known until after one or more stages of the seed train process have been carried out, it can be difficult to predict whether carrying out the seed train process using specific seed train process parameters will result in outcomes that meet the success criteria of the seed train process. As described herein, seed train process parameters may be determined by assuming specific values ​​for the doubling time at each stage, such as the average doubling time for each stage of one or more past seed train processes.

[0145] Therefore, using process 400, it may be beneficial to predict the likelihood that performing the seed train process using the determined seed train process parameters based on historical cell proliferation data (e.g., historical doubling time) will yield results that meet the success criteria.

[0146] In operation 402, the processor uses historical cell proliferation data to simulate a first set of cell proliferation values. In some embodiments, the historical cell proliferation data includes the distribution of historical cell proliferation values ​​for each stage of the seed train process. As described herein, the historical cell proliferation value for a particular stage of the seed train process may include the historical doubling time for that particular stage in the seed train process.

[0147] In some embodiments, simulating a first set of historical cell growth values ​​includes randomly sampling historical cell growth values ​​from historical cell growth data. This may include, for each stage, randomly sampling cell growth values ​​from the distribution of cell growth values ​​for that particular stage. For example, simulating a first set of historical cell growth values ​​may include, for a first stage, randomly sampling doubling times from the distribution of historical doubling times for that stage.

[0148] In operation 404, the processor uses a first set of seed-training process parameters and cell proliferation parameters to predict a first outcome of performing the seed-training process. In some embodiments, this includes predicting the outcome of each stage of the seed-training process based on the sampled historical cell values ​​(e.g., doubling time) for that stage. For example, predicting the outcome of a particular stage of the seed-training process may include predicting the duration for which the culture is grown during that particular stage. The duration of a particular stage may be predicted, for example, using Equation 1.

number

number

[0149] In addition, or alternatively, in some embodiments, predicting the outcome of a particular stage involves predicting the amount of additional time required to grow the culture during that stage compared to a standard culture time (e.g., 72 hours). The required additional time may be predicted, for example, using Equation 3. Additional time required = Estimated period - Standard culture time (Equation 3)

[0150] In addition, or alternatively, in some embodiments, predicting the outcome of a particular stage includes predicting the final viable cell density resulting from growing the culture during that particular stage. The final viable cell density (VCD) resulting from growing the culture during a particular stage can be predicted, for example, using Equation 3. Final VCD = (Initial VCD) * e ((Standard Growth Constant) * (Standard Culture Time)) (Equation 4) In the formula, the standard doubling time is determined using Equation 2.

[0151] In some embodiments, the variables included in Equations 1-4 may correspond to the seed train process parameters and / or seed train process constraints listed in Tables 1-2.

[0152] In operation 406, the processor simulates a second set of cell growth values ​​using historical cell growth data. Techniques for simulating the set of cell growth values ​​are described with respect to operation 402. In some embodiments, the first set of cell growth values ​​and the second set of cell growth values ​​are different. For example, the first and second sets of cell growth values ​​may contain only a subset of the same cell growth values, or none of the same cell growth values.

[0153] In operation 408, the processor predicts a first outcome of performing the seed train process using a first set of seed train process parameters and cell proliferation parameters. In some embodiments, this includes predicting the outcome of each stage of the seed train process based on the sampled historical cell values ​​(e.g., doubling time) of that stage. For example, this may include determining the expected duration of each stage, the additional time required for each stage, and / or the final viable cell density for each stage. Such results may be determined using equations 1-4.

[0154] In operation 410, the processor determines the likelihood that performing the seed train process will satisfy the seed train process success criteria using seed train process parameters. The likelihood is determined using first and second results, each of which may include one or more predicted outcomes for each stage of the seed train process.

[0155] In some embodiments, determining the likelihood involves determining the number of predicted outcomes that indicate that performing the seed train process using each set of seed train process parameters and historical cell proliferation values ​​satisfies the seed train process success criteria. In some embodiments, this involves determining whether a first and second outcome satisfies the seed train process success criteria. Additionally or alternatively, this involves determining that one or more other predicted outcomes satisfy the seed train process success criteria. For example, the process may predict at least 5, at least 10, at least 15, at least 25, at least 50, at least 75, at least 100, at least 150, at least 200, or any other suitable number of outcomes that perform the seed train process using each set of determined seed train process parameters and historical cell proliferation values.

[0156] As described herein, the first result may include one or more predicted results for each of the multiple stages of the seed-training process. Thus, in some embodiments, determining whether the first result meets the success criteria includes determining whether each of the one or more predicted results meets its respective success criteria. For example, the first result may include a predicted period for growing cells during the first stage of the seed-training process. The processor can determine whether the predicted period meets its respective success criteria. For example, the processor may determine whether the predicted period is less than a threshold period, thereby determining whether the first success criterion is met.

[0157] In some embodiments, the first result is determined to satisfy the seed-train process success criteria if the predicted results for at least a threshold percentage (e.g., at least 60%, at least 70%, at least 80%, at least 90%, or 100%) satisfy their respective success criteria. For example, the first result is determined to satisfy the seed-train process success criteria if each of the predicted results for each stage of the seed process satisfies its respective success criteria. In other words, performing the seed-train process using the determined seed-train process parameters is likely to result in a seed-train process success if the culture doubling time falls within the time included in the first set of historical cell proliferation values.

[0158] In some embodiments, this is repeated for each prediction result, including a second result. For example, the processor may determine whether the second result meets the success criteria. The determination of whether the second result meets the success criteria may be carried out in accordance with the techniques described above for determining whether the first result meets the success criteria.

[0159] In operation 410-2, the processor determines the ratio of the number of predicted results that satisfy the success criterion to the total number of predicted results. For example, if the predicted results include a first result and a second result, and only the first result is determined to satisfy the success criterion, the processor determines a ratio of 1 / 2 or 50%. As another example, if 75 out of 100 predicted results are determined to satisfy the success criterion, the processor determines a ratio of 75 / 100 or 75%. In some embodiments, the ratio determined in operation 410-2 is the likelihood that performing the seed-train process using the seed-train process parameters will satisfy the seed-train process success criterion.

[0160] Figures 5A-1 to 5D show exemplary user interfaces for specifying and displaying seed train process information. Figures 5A-1 to 5D further include exemplary seed train process constraints and exemplary seed train process parameters for a 5000 mL seed train process.

[0161] As shown in Figures 5A-1 to 5D, the user interface displays seed train process stage information. Seed train process stage information is indicated by its shading, as shown in Legend 510. In some embodiments, the seed train process information specifies the stage, passage number, and container.

[0162] As shown in Figures 5A-1, 5A-2, 5B-1, 5B-2, 5C-1, and 5C-2, the user interface displays seed train process constraints. Seed train process constraints are indicated by their shading, as shown in legends 510, 520, and 530. In some embodiments, the user can specify values ​​for seed train process constraints by interacting with the user interface. For example, text boxes may be selectable elements of the graphical user interface. Additionally or alternatively, seed train process constraints may be automatically populated based on stored data and / or uploaded data (e.g., uploaded from another device such as another computing device, a seed train process automation module, or by any other appropriate method). Examples of seed train process constraints are shown in Figures 5A-1 to 5C-2, and may include any other seed train process constraints described herein, including those listed in Table 1.

[0163] As shown in Figures 5B-1 and 5B-2, the user interface also displays seed train process parameters. Seed train process parameters are indicated by their shading, as shown in Legend 520. In some embodiments, seed train process parameters are entered based on the results of determining seed train process parameters according to the techniques described herein. For example, seed train process parameters may be determined by performing process 200 in Figure 2, process 300 in Figure 3, and / or process 400 in Figure 4. Additionally or alternatively, the user may specify values ​​for seed train process parameters, obtained by interacting with the user interface or by any other suitable method. Exemplary seed train process parameters are shown in Figures 5A-1, 5A-2, 5B-1, 5B-2, 5C-1, and 5C-2, and may include any other seed train process parameters described herein, including those listed in Table 2.

[0164] As shown in Figures 5A-1, 5A-2, 5B-1, 5B-2, 5C-1, and 5C-2, seed train process parameters and seed train process constraints can be specified and / or determined for each stage of the seed train process. Some variables are considered seed train process constraints in some stages, while others are considered seed train process parameters. For example, the working volume per container is a parameter that can be changed in the first five stages, but is a seed train process constraint in the remaining four stages.

[0165] Figures 5C-1 and 5C-2 also show the calculated seed train process parameters. In some embodiments, the calculated seed train process parameters are calculated based on at least one seed train process parameter (for example, determined according to the seed train process parameter determination techniques described herein). The calculated seed train process parameters are indicated by shading as shown in Legend 530. Exemplary formulas for calculating the calculated seed train process parameters are listed in Table 3.

[0166] Figure 5D shows an exemplary prediction of whether performing the seed train process using seed train process parameters according to several embodiments of the technology described herein will satisfy the seed train process success criteria. At least three columns in Figure 5D correspond to the seed train process parameters and exemplary predictive results of performing the seed train process using the calculated seed train process parameters. For example, the predicted results include, for each stage, “Additional Time Required - Standard,” “Additional Time Required - Worst Case,” and “Final VCD.” In some embodiments, “Additional Time Required - Standard” refers to the additional time required to grow cells during a particular stage of the seed train process, assuming the culture has an average doubling time. “Additional Time Required - Worst Case” may refer to the additional time required to grow cells during a particular stage of the seed train process, assuming the culture has the longest doubling time determined from historical cell proliferation data. “Final VCD - Best Case” may refer to the viable cell density resulting from cell proliferation during a particular stage, assuming the culture has the shortest doubling time determined from historical cell proliferation data. Table 4 lists examples of formulas for determining "Additional Time Required - Standard," "Additional Time Required - Worst-Case," and "Final VCD - Best."

[0167] As described herein, in some embodiments, predicted results are evaluated to determine whether they meet their respective success criteria. In some embodiments, the user interface provides indications as to whether exemplary results meet their respective success criteria. As shown by Legend 540, shading in the user interface indicates whether the success criteria have been met. For example, as shown, the predicted “Additional Time Required – Worst” for stage N-1 and the predicted “Final VCD – Best” for stage 2 do not meet the success criteria for the seed train process.

[0168] In the example, each prediction result is compared to a threshold to determine whether the success criteria are met. For example, the predicted value for "Additional Time - Worst" may be compared to a threshold of 12 hours, the predicted value for "Additional Time - Standard" may be compared to a threshold of 0, the predicted value for "Final VCD - Best" in stages N-1 and N-2 may be compared to a threshold of 100, and the predicted value for "Final VCD - Best" in stages N-8 to N-3 may be compared to a threshold of 50.

[0169] In some embodiments, as constraints and parameters are changed, shading indicating whether the success criteria are met is automatically updated, allowing the user to easily visualize and estimate the results at different stages of the seed train process.

[0170] [Table 5]

[0171] [Table 6]

[0172] [Table 7]

[0173] [Table 8]

[0174] Figure 6 shows an example of historical cell proliferation data from several embodiments of the technology described herein. The historical cell proliferation data includes data from multiple seed-training processes that have already been carried out. For each of the past seed-training processes, the data includes the doubling time of cells that proliferated during a particular stage of the seed-training process.

[0175] As described herein, in some embodiments, the doubling time at a particular stage of the seed train process may be randomly sampled from a distribution of doubling times, such as that shown in Figure 6. For example, the doubling time may be sampled when determining the likelihood that carrying out the seed train process using determined seed train process parameters will satisfy the success criteria for the seed train process, as described herein, including at least with respect to Figure 2.

[0176] Figure 7A shows exemplary doubling time data measured from cultures grown to produce various molecules including monoclonal antibodies (mAbs), bispecific T cell engagers (BiTEs), and bispecific antibodies. The doubling time data includes the mean doubling time and standard deviation for each stage of multiple stages in the seed-training process for each culture type (e.g., mAb, BiTE, bispecific). Figure 7B shows exemplary doubling time data measured from cultures grown in 500L and 2000L containers. The doubling time data includes the mean doubling time and standard deviation for each stage of multiple stages in the seed-training process for each container size (e.g., 500L, 2000L).

[0177] In some embodiments, doubling time data may be stored and / or used as historical cell proliferation data. For example, as described herein, doubling time data may be sampled at each stage and used to predict the likelihood that the culture will meet at least one success criterion if it has the sampled doubling time. Additionally or alternatively, doubling time data may be used to specify seed-train process constraints. For example, the average doubling time for a particular stage may be specified as a standard doubling time constraint for that stage in the seed-train process.

[0178] Figures 8A and 8B show that implementing a seed train process according to embodiments of the technology described herein has a higher overall success rate compared to implementing a manually designed seed train process. Therefore, designing a seed train process using the technology described herein helps reduce equipment scheduling problems caused by seed train processes that are too long or need to be repeated. Furthermore, it helps limit the waste caused by seed train process failures that need to be discarded and repeated.

[0179] Figure 8A is a plot comparing the overall success rate of manually designed seed train processes with the overall success rate of seed train processes designed according to the techniques described herein. In particular, the seed train processes were designed to grow cultures producing three different molecules (e.g., molecule 1, molecule 2, and molecule 3). As shown, for each molecule, the seed train processes designed according to the techniques described herein had a higher overall success rate than those designed manually.

[0180] Figure 8B is a plot comparing the overall success rate of each stage of a manually designed seed train process with the overall success rate of each stage of a seed train process designed according to the techniques described herein. As shown, at least seven of the eight stages of the seed train process designed according to the techniques described herein had an overall success rate equal to or better than that of the manually designed stages.

[0181] Figure 8C shows that by performing the 500L seed train process according to the embodiments of the technique described herein, an average success rate of over 80% can be obtained at each stage of the seed train process. As shown, success in performing the stages means that there were sufficient cells and no overgrowth.

[0182] Figure 8D shows that performing the seed train process with 2 kL using embodiments of the technique described herein results in a success rate of over 70% at each stage of the seed train process. As shown, success in performing the stages means that there were sufficient cells and no overgrowth.

[0183] Figure 9 shows an exemplary embodiment of a computer system 900 that can be used in connection with any embodiment of the technology described herein (e.g., the processes in Figures 2-3A and Figure 4). The computer system 900 includes one or more processors 910 and one or more products including non-temporary computer-readable storage media (e.g., memory 920 and one or more non-volatile storage media 930). The processor 910 can control the reading and writing of data to and from the memory 920 and the non-volatile storage media 930 in any suitable manner, and the embodiments of the technology described herein are not limited to any particular technology of writing or reading data. In order to perform any of the functions described herein, the processor 910 can execute one or more processor-executable instructions stored in one or more non-temporary computer-readable storage media (e.g., memory 920) that function as non-temporary computer-readable storage media storing processor-executable instructions to be executed by the processor 910.

[0184] The computer device 900 may also include a network input / output (I / O) interface 940 that allows the computing device to communicate with other computing devices (e.g., via a network), and may also include one or more user I / O interfaces 950 that allow the computing device to provide output to a user or receive input from a user. The user I / O interface may include devices such as a keyboard, mouse, microphone, display device (e.g., monitor or touchscreen), speaker, camera, and / or various other types of I / O devices.

[0185] The embodiments described above can be implemented in various ways. For example, the embodiments may be implemented using hardware, software, or a combination thereof. If implemented in software, the software code can run on any suitable processor (e.g., a microprocessor) or set of processors, whether it is provided on a single computing device or distributed across multiple computing devices. It should be understood that any component or set of components that performs the above functions can generally be thought of as one or more controllers that control the above functions. One or more controllers can be implemented in various ways, such as dedicated hardware or general-purpose hardware (e.g., one or more processors) programmed to perform the above functions using microcode or software.

[0186] In this regard, it should be understood that one implementation of the embodiments described herein, when executed on one or more processors, includes at least one computer-readable storage medium (e.g., RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device, or other tangible non-temporary computer-readable storage medium) encoded with a computer program (i.e., multiple executable instructions) that performs the functions of one or more embodiments thereof. The computer-readable medium may be transportable so that the program stored therein can be loaded onto any computing device in order to implement the embodiments of the technology described herein. Furthermore, it should be understood that references to computer programs that perform any of the functions described above at runtime are not limited to application programs that run on a host computer. Rather, in this specification, the terms computer program and software are used in a general sense to refer to any type of computer code (e.g., application software, firmware, microcode, or any other form of computer instruction) that can be used to program one or more processors to implement the embodiments of the technology described herein.

[0187] The above-mentioned descriptions of implementations are for illustrative and illustrative purposes only and are not intended to be exhaustive or to limit implementations to the exact form disclosed. Modifications and changes are possible in light of the above teachings and may also be obtained from implementation practice. Other implementations may include fewer operations, different operations, different orders of operations, and / or additional operations in the methods shown in these diagrams. Furthermore, independent blocks may be executed in parallel.

[0188] It will be understood that the exemplary embodiments described above can be implemented in various forms of software, firmware, and hardware in the implementation shown in the figure. Furthermore, specific parts of the implementation may be implemented as “modules” that perform one or more functions. These modules may include hardware such as a processor, an application-specific integrated circuit (ASIC), or a field-programmable gate array (FPGA), or a combination of hardware and software.

[0189] While several aspects and embodiments of the technology described herein have been described, it will be understood that a person skilled in the art will readily conceive of various changes, modifications, and improvements. Such changes, modifications, and improvements are intended to be made within the spirit and scope of the technology described herein. For example, a person skilled in the art will readily imagine various other means and / or structures to perform the functions described herein and / or obtain the results and / or one or more advantages, and each such variation and / or modification will be considered to be within the scope of the embodiments described herein. A person skilled in the art will be able to recognize or confirm many equivalents to the specific embodiments described herein by mere routine experimentation. Thus, it will be understood that the embodiments described herein are presented for illustrative purposes only, and within the scope of the appended claims and their equivalents, embodiments of the present invention can be carried out in ways different from those specifically described. Furthermore, any combination of two or more features, systems, articles, materials, kits, and / or methods described herein is included in the scope of this disclosure, provided that such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent.

[0190] The embodiments described above can be implemented in a variety of ways. One or more aspects and embodiments of the present disclosure, which involve the implementation of a process or method, utilize program instructions executable by a device (e.g., a computer, a processor, or other device) to execute or control the execution of the process or method. In this regard, the concepts of the various inventions can be embodied as computer-readable storage media (or a plurality of computer-readable storage media) (e.g., computer memory, one or more floppy disks, compact disks, optical disks, magnetic tapes, flash memory, field-programmable gate arrays, or circuit configurations of other semiconductor devices, or other tangible computer storage media) encoded by one or more programs that, when executed on one or more computers or other processors, implement one or more of the various embodiments described above. The computer-readable media may be portable, and the programs stored therein can be loaded onto one or more different computers or other processors to implement the various embodiments described above. In some embodiments, the computer-readable media may be non-temporary media.

[0191] In this specification, the terms “program” or “software” are used in a general sense and refer to any type of computer code or set of computer executable instructions that can be used to program a computer or other processor to implement the various embodiments described above. Furthermore, according to one aspect, it will be understood that one or more computer programs that perform the methods of the Disclosure at runtime do not need to reside on a single computer or processor, but may be distributed modularly across multiple different computers or processors to implement the various embodiments of the Disclosure.

[0192] Computer executable instructions can take many forms, such as program modules, that are executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. Typically, the functions of program modules can be combined and distributed as needed in various embodiments.

[0193] Furthermore, data structures can be stored in a computer-readable medium in any suitable format. For simplicity of explanation, a data structure can be described as having fields that are associated by their location within the data structure. Such relationships can also be achieved by allocating storage to the fields, where the location in the computer-readable medium conveys the relationships between the fields. However, any suitable mechanism can be used to establish relationships between the information within the fields of a data structure, including the use of pointers, tags, or other mechanisms for establishing relationships between data elements.

[0194] When implemented in software, the software code can run on any suitable processor or set of processors, whether it is provided on a single computer or distributed across multiple computers.

[0195] Furthermore, a computer may have one or more input and output devices. These devices can, among other things, be used to display a user interface. Examples of output devices that can be used to provide a user interface include printers and display screens for visually displaying output, and speakers and other sound-generating devices for audibly displaying output. Examples of input devices that can be used for a user interface include keyboards and pointing devices such as mice, touchpads, and digital tablets. Another example is that a computer can receive input information in the form of speech recognition or other voice formats.

[0196] Such computers may be interconnected by one or more networks of any suitable form, such as a local area network, a wide area network including an enterprise network, and an intelligent network (IN), or the Internet. Such networks may be based on any suitable technology, operate according to any suitable protocol, and may include wireless networks, wired networks, or fiber optic networks.

[0197] Furthermore, as described, several embodiments may be embodied as one or more methods. The operations performed as part of the method can be ordered in any suitable manner. Thus, embodiments may be constructed in which the operations are performed in an order different from that shown, which may include performing several operations simultaneously, even if they are shown as sequential operations in the exemplary embodiments.

[0198] All definitions defined and used herein should be understood to take precedence over dictionary definitions, definitions incorporated by reference in documents, and / or the ordinary meanings of the defined terms.

[0199] In this specification and in the claims, the indefinite articles "a" and "an" should be understood to mean "at least one" unless explicitly stated otherwise.

[0200] The phrase "and / or" as used herein and in the claims should be understood to mean "either or both" of the elements thus combined, that is, elements that exist sometimes associatively and other times separately. Multiple elements listed in "and / or" should be interpreted similarly, that is, "one or more" of the elements thus combined. In addition to the elements specifically identified in the "and / or" clauses, other elements may be present at their discretion, whether or not they are related to those specifically identified elements. Thus, as a non-restrictive example, a reference to "A and / or B," when used in combination with open-ended language such as "includes," may in one embodiment refer to A only (including elements other than B at their discretion), in another embodiment refer to B only (including elements other than A at their discretion), and in yet another embodiment refer to both A and B (including other elements at their discretion), and so on.

[0201] As used herein and in the claims, the phrase “at least one” in reference to a list of one or more elements should be understood to mean at least one element selected from any one or more elements in the list of elements, but not necessarily including at least one of each element specifically described in the list of elements, nor excluding any combination of elements in the list of elements. This definition also allows for the presence of elements other than those specifically identified in the list of elements to which the phrase “at least one” refers, regardless of whether they are related to the specifically identified elements, at the discretion of the definition. Therefore, as a non-restrictive example, “at least one of A and B” (or equivalently, “at least one of A or B” or equivalently, “at least one of A and / or B”) may, in one embodiment, refer to at least one (or more) A in which B is absent (and optionally includes elements other than B); in another embodiment, refer to at least one (or more) B in which A is absent (and optionally includes elements other than A); and in yet another embodiment, refer to at least one (or more) A and at least one (or more) B (and optionally include other elements), etc.

[0202] In the claims and the above specification, all transitional phrases such as “comprising,” “including,” “carry,” “have,” “contain,” “involve,” “hold,” and “composed of” are understood to be open-ended, meaning they include but are not limited to these. Only the transitional phrases “composed of” and “essentially composed of” are closed or semi-closed transitional phrases, respectively.

[0203] The terms “approximately,” “substantially,” and “about” may be used in some embodiments to mean within ±20% of the target value, within ±10% of the target value, within ±5% of the target value, and within ±2% of the target value. The terms “approximately,” “substantially,” and “about” may include the target value.

Claims

1. A method for determining seed train process parameters for growing a cell culture, wherein the method is performed using at least one software application program including a common interface module, a parameter optimization module, and a simulation module, and the method is Using at least one computer hardware processor, Using the aforementioned common interface module, the specifications of the seed train process constraints for multiple stages of the seed train process are obtained, Determining the seed train process parameters using the parameter optimization module and the seed train process constraints, wherein the seed train process parameters include each set of parameters for each specific stage of the plurality of stages of the seed train process, and the determination is For each specific step of the plurality of steps, the parameter optimization module and the seed train process constraints are used to determine the respective set of parameters for growing the culture during that specific step. This includes making a decision, Using the simulation module, historical cell proliferation data, and the determined seed train process parameters, the likelihood of whether performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria is determined. Outputting a set of seed train process parameters determined for each of the multiple stages of the seed train process, and the likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria, A method that includes performing [something].

2. For each specific step of the plurality of steps, determining the respective set of parameters for growing the culture during that specific step is: The method according to claim 1, comprising determining at least one seed train process parameter, the at least one seed train process parameter being selected from the group consisting of live cell density, an indication of whether a particular stage is included in the seed train process, a target duration of the seed train process, batch medium volume, working volume per container, and the number of containers.

3. Obtaining the aforementioned specifications of the seed train process constraints is, The method according to claim 1 or 2, comprising obtaining specifications for at least one seed train process constraint selected from the group consisting of a target live cell density range, a target working volume range, a split ratio culture growth process constraint, and a batch medium volume range.

4. The method according to any one of claims 1 to 3, wherein the historical cell proliferation data includes data indicating the doubling time related to the proliferation of one or more cell cultures.

5. The method according to any one of claims 1 to 4, wherein determining the seed train process parameters using the parameter optimization module comprises determining the seed train process parameters using a genetic algorithm.

6. The method according to any one of claims 1 to 5, wherein determining the likelihood that performing the seed train process using the determined seed train process parameters will satisfy the seed train process success criteria includes performing a Monte Carlo simulation using the historical cell proliferation data.

7. The seed train process success criteria are defined for each of the multiple stages of the seed train process, A first criterion is that the expected period required to grow the culture during the specific stage does not exceed the threshold period for growing the culture during the specific stage, and A second criterion: the expected live cell density resulting from growing the culture during the specified stage does not exceed the threshold live cell density resulting from growing the culture during the specified stage. The method according to any one of claims 1 to 6, including the method described in any one of claims 1 to 6.

8. Determining each set of parameters for each specific step of the aforementioned plurality of steps is: Using each set of the aforementioned parameters, determine the expected period required to grow the cell culture during the particular stage, Determining whether the expected period exceeds the respective threshold period for the specific stage, The method according to claim 7, including the method described in claim 7.

9. Determining each set of parameters for each specific step of the plurality of steps is: Using each set of the parameters, determine the expected viable cell density obtained from growing the cell culture during the particular step, Determining whether the expected live cell density exceeds the threshold live cell density for each of the specific stages, The method according to claim 7, including the method described in claim 7.

10. Outputting a set of seed train process parameters for each of the multiple stages of the seed train process and the likelihood indicating whether implementing the seed train process satisfies the success criteria of the seed train process is: The common interface module is used to generate a graphical user interface (GUI), The generated GUI is used to display the set of seed train process parameters and / or the likelihood, The method according to any one of claims 1 to 9, including the method described in any one of claims 1 to 9.

11. Displaying the set of seed train process parameters through the aforementioned common interface module is: The method according to claim 10, further comprising displaying a visual indication of whether a seed train process parameter from the set of seed train process parameters violates a seed train process constraint from the seed train process constraints.

12. Determining the seed train process parameters means Determining the seed train process parameters based on a set of estimated culture doubling times included in the seed train process constraints, wherein the set of estimated culture doubling times includes the estimated culture doubling times for each of the plurality of stages of the seed train process. Determining whether performing the seed train process using the determined seed train process parameters satisfies the seed train process success criteria, Includes, The aforementioned method, The graphical user interface (GUI) generated by the common interface module displays a visual indication of the result of determining whether performing the seed train process using the seed train process parameters satisfies the seed train process success criteria. The method according to any one of claims 1 to 11, further comprising:

13. The method according to any one of claims 1 to 12, further comprising comparing the determined likelihood with a likelihood threshold, and outputting a set of seed train process parameters for each of the plurality of stages of the seed train process, wherein if it is determined that the likelihood exceeds the likelihood threshold, the determined seed train process parameters are output.

14. Outputting a set of seed train process parameters for each of the multiple stages of the seed train process is: The method according to any one of claims 1 to 13, wherein the likelihood of performing the seed train process using the determined seed train process parameters satisfies the seed train process success criteria satisfies the likelihood threshold, and the method further comprises outputting a recommendation for performing the seed train process using the set of seed train process parameters for each of the plurality of stages of the seed train process.

15. The at least one software application program further includes a seed train process automation module that outputs a set of seed train process parameters for each of the plurality of stages of the seed train process, and the likelihood that performing the seed train process will satisfy the seed train process success criteria. Transmitting the set of seed train process parameters and / or the likelihood to the seed train process automation module, Using the seed train process automation module, the seed train process automation system is made to execute a specific stage of the multiple stages of the seed train process according to each set of the seed train process parameters. The method according to any one of claims 1 to 14, including the method described in any one of claims 1 to 14.

16. Using the aforementioned common interface module, input is obtained indicating the result of growing the cell culture during the first of the multiple steps of the seed train process, Using the parameter optimization module, the input, and the seed train process constraints, updated seed train process parameters for subsequent stages of the seed train process are determined. Outputting the updated seed train process parameters, The method according to any one of claims 1 to 15, further comprising:

17. Using the aforementioned common interface module, the specifications of the second seed train process constraints for multiple stages of the second seed train process are obtained, Using the parameter optimization module and the second seed train process constraint, the second seed train process parameters for the second seed train process are determined. Using the simulation module, the historical cell proliferation data, and the second seed train process parameters, a second likelihood is determined to indicate whether performing the second seed train process using the second seed train process parameters satisfies the second seed train process criterion. Outputting the second seed train process parameters and the second likelihood indicating whether performing the second seed train process using the second seed train process parameters satisfies the second seed train process criterion, The method according to any one of claims 1 to 16, further comprising:

18. Determining the seed train process parameters using the parameter optimization module is: The objective function is used to determine a first score for the first candidate seed train process parameters, Using the aforementioned objective function, a second score is determined for the second candidate seed train process parameters. Comparing the first score and the second score, Based on the results of the comparison, the seed train process parameter is selected from the first candidate seed train process parameter and the second candidate seed train process parameter. The method according to any one of claims 1 to 17, including the method described in any one of claims 1 to 17.

19. The seed train process parameters include a first set of seed train process parameters for the first stage of the plurality of stages of the seed train process, Determining the likelihood that performing the seed train process using the seed train process parameters will satisfy the seed train process success criteria is: The method according to any one of claims 1 to 18, comprising determining a first likelihood that growing the cell culture during the first stage satisfies a first criterion of the success criteria of the seed train process, using a first set of seed train parameters for the first stage.

20. Determining the likelihood that performing the seed train process using the seed train process parameters will satisfy the seed train process success criteria is: To simulate a first set of cell proliferation values ​​using the aforementioned historical cell proliferation data, wherein the first set of cell proliferation values ​​includes a first historical cell proliferation value for each of the plurality of stages of the seed train process, To predict a first result of performing the seed train process using a first set of seed train process parameters and cell proliferation values, wherein the first result indicates whether performing the seed train process using the determined seed train process parameters satisfies the seed train process success criteria. Using the aforementioned historical cell proliferation data, a second set of cell proliferation values ​​is simulated, including a second historical cell proliferation value for each of the multiple stages of the seed train process. Predicting a second result of performing the seed train process using a second set of seed train process parameters and cell proliferation values, wherein the second result indicates whether performing the seed train process using the seed train process parameters satisfies the seed train process success criteria. The likelihood is determined based on the predicted first and second results, The method according to any one of claims 1 to 19, including the method described in any one of claims 1 to 19.

21. Determining the likelihood based on the predicted first and second results is, Using the seed train process parameters and their respective historical cell proliferation data, determine the number of predicted results that indicate performing the seed train process will satisfy the seed train process success criteria. The ratio of the number of predicted results to the total number of predicted results is determined, The method according to claim 20, including the method described in claim 20.

22. The seed train process success criteria are defined for each of the multiple stages of the seed train process, The first criterion includes that the expected period required to grow the culture during the specific stage does not exceed the threshold period for growing the culture during the specific stage, Predicting the first result means that for each specific step of the plurality of steps, Using each set of seed train process parameters for the specific step and the historical cell growth values ​​from the first set of historical cell growth values, a first expected period required to grow the cell culture during the specific step of the seed train process is determined. Comparing the first forecast period with the threshold period, Includes, Predicting the second result means that for each specific step of the plurality of steps, Using each set of seed train process parameters for the specific step and the historical cell growth values ​​from a second set of historical cell growth values, a second expected period required to grow the cell culture during the specific step of the seed train process is determined. Comparing the second forecast period with the threshold period, The method according to claim 20, including the method described in claim 20.

23. The seed train process success criteria are defined for each of the multiple stages of the seed train process, A second criterion is included, that the expected live cell density resulting from growing the culture during the particular step does not exceed the threshold live cell density resulting from growing the culture during the particular step. Predicting the second result means that for each specific step of the plurality of steps, Using each set of seed train process parameters for the specific step and the historical cell growth values ​​from the first set of historical cell growth values, a first expected viable cell density resulting from growing the cell culture during the specific step of the seed train process is determined. The first expected live cell density is compared with the threshold live cell density, Includes, Predicting the second result means that for each specific step of the plurality of steps, Using each set of seed train process parameters for the aforementioned specific step and the historical cell proliferation values ​​from a second set of historical cell proliferation values, a second expected live cell density resulting from growing the cell culture during the aforementioned specific step of the seed train process is determined. The second expected live cell density is compared with the threshold live cell density, The method according to claim 20, including the method described in claim 20.

24. It is a system, At least one computer hardware processor, At least one non-temporary computer-readable storage medium storing processor-executable instructions, wherein, when executed by the at least one computer hardware processor, the processor-executable instructions cause the at least one computer hardware processor to perform the method according to any one of claims 1 to 23; A system that includes these features.

25. At least one non-temporary computer-readable storage medium storing processor-executable instructions, wherein, when executed by at least one computer hardware processor, the processor-executable instructions cause the at least one computer hardware processor to perform the method according to any one of claims 1 to 23.

Images