Predictive model for evaluating process time impact

Abstract

Systems and methods for assessing effects of processing time of a process, such as a biological process, may include: (a) obtaining a model trained using historical biological process data; (b) determining, by applying an input to the model, a predicted output to be generated when operating the biological process in accordance with the input, where: (i) the input comprises a processing time and the predicted output comprises product quality, or (ii) the input comprises a product quality parameter and the predicted output comprises a processing time; and (c) displaying or storing the value of the predicted output. Additional aspects include receiving the input from a user as a user input. Still further aspects include presenting the predicted output to the user via a graphical user interface.

Description

Technical Field

[0001] The present application generally relates to using predictive models to assess the impact of process time, including process time delays, on product quality. Background Art

[0002] Biomolecules such as proteins, peptides and nucleic acids are widely used to treat a variety of diseases and play an important role in drug discovery. Typically, during the production of products including biomolecules, the products are exposed to steps with adverse chemical conditions, which may impair the stability of the product. These steps may include pool conditioning steps and viral inactivation and clarification steps, which require exposing the product to significant changes in pool pH, conductivity and / or temperature, which are unfavorable to biomolecules (e.g., reducing the stability of biomolecules). Therefore, the product quality of biomolecules produced using these types of steps may be sensitive to the length of time required to perform these steps. In addition, during these steps, any operational delays that increase the processing time will mean that the product is additionally exposed to these adverse chemical conditions, which may be detrimental to product quality.

[0003] A biological process in which processing time may have an impact on the product quality of the corresponding biomolecule is chromatography. Chromatography can be used to purify biomolecules by separating biomolecules from compounds using one or more separation steps based on specific physical, chemical or biological characteristics of the compound and the biomolecule. For example, the size, charge, hydrophobicity, function or content of a given biomolecule can be used to separate a given biomolecule. For commercial manufacturing purification, chromatography is typically performed as column chromatography due to scale considerations. An example of a conventional column chromatography process 200 is shown in FIG2 . As shown in process 200, the load sample is first injected into the column. The mobile phase (eluent) is then pumped through the column so that the molecules of the load sample are separated based on their relative affinity to the stationary phase (stationary resin) and the mobile phase. Compared with the molecules that are more weakly attracted to the stationary phase, the molecules of the load sample that are more strongly attracted to the stationary phase move more slowly through the system. Different molecules will be eluted from the column at different times, and after different volumes of mobile phase have passed through the column, the therapeutic protein is allowed to be separated from other substances eluted from the column at different times.

[0004] Other common types of chromatography include hydrophobic interaction chromatography, affinity chromatography or protein A chromatography. Still other types of chromatography include ion exchange chromatography (IEX), including anion exchange chromatography (AEX) and / or cation exchange chromatography (CEX), hydrophobic interaction chromatography (HIC), mixed mode or multi-mode chromatography (MM), hydroxyapatite chromatography (HA) or reverse phase chromatography. Other chromatographic methods include expanded bed adsorption chromatography, simulated moving bed chromatography, countercurrent chromatography (CCC), hydrodynamic countercurrent chromatography or periodic countercurrent chromatography. Other types of chromatography include gel filtration, planar chromatography (e.g., paper chromatography, thin layer chromatography), displacement chromatography, liquid chromatography, affinity chromatography (e.g., supercritical fluid chromatography), hydrodynamic chromatography, two-dimensional chromatography, pyrolysis gas chromatography, fast protein liquid chromatography, chiral chromatography, centrifugal partition chromatography or aqueous normal phase chromatography.

[0005] Typically, when performing chromatography for purification of biomolecules, the parameters of the chromatography (e.g., elution buffer pH, elution buffer conductivity, elution buffer molarity, gradient slope, linear velocity, load and collection time) and how the purification operation is performed for a specific product / molecule (e.g., with a specific solution, at a specific pH, etc.) are carefully determined. However, conventional chromatography processes (as well as other types of bioprocesses) do not typically account for unexpected variations in processing time due to delays (e.g., due to equipment failure).

[0006] In addition, the optimal processing time may vary from one manufacturing operation to another and, therefore, may be difficult to predict. When producing biomolecules, failure to account for unexpected delays or process-specific variations in the optimal processing time may result in a greater proportion of the produced biomolecules failing to pass the stringent quality control measures that regulatory entities, such as government entities (e.g., the U.S. Food and Drug Administration) may impose on product quality and that the biomolecules must follow. If the biomolecule does not meet the specification limits for product quality, the biomolecule may not be usable. In addition, because the relationship between processing time and product quality is typically specific to a single manufacturing operation, failure to account for variations in processing time may also reduce the transferability of biomolecule production between different bioprocess systems.

[0007] Thus, for conventional processes (e.g., chromatography) used to produce the molecule, the likelihood that the biomolecule will not meet regulatory limits increases. Increased failure or rejection rates, in turn, may correspond to increased costs in terms of time, labor, and other resources. Summary of the invention

[0008] Various aspects of the present disclosure provide a method for evaluating the impact of processing time of a process (e.g., a bioprocess), the method comprising: (a) obtaining a model trained using historical bioprocess data, the historical bioprocess data comprising: (i) historical processing times for multiple instances of the bioprocess and (ii) corresponding historical product qualities of products produced by the multiple instances of the bioprocess; (b) determining a predicted output that will be produced when the bioprocess is operated according to the input by applying an input to the model, wherein: (i) the input includes processing time and the predicted output includes product quality, or (ii) the input includes a product quality parameter and the predicted output includes processing time; and (c) displaying or storing the predicted output.

[0009] In some aspects, the method further includes receiving the input from a user as user input. In some aspects, the method further includes presenting the predicted output to the user via a graphical user interface.

[0010] In some aspects, the treatment time corresponds to one or both of the following: (i) the elapsed time of at least one step of the bioprocess, or (ii) the elapsed time between at least two steps of the bioprocess. In some aspects, the treatment time corresponds to one or both of the following: (i) the delay time of at least one step of the bioprocess, or (ii) the delay time between at least two steps of the bioprocess.

[0011] In some aspects, the model is a linear regression model. In some aspects, the bioprocess is a chromatographic process. In some aspects, the product is one or both of a drug or a therapy and includes one or more of: a protein, a carbohydrate, a lipid, or a nucleic acid.

[0012] In some aspects, the predicted product quality parameter is a measure of one or more of: yield, viable cell density (VCD), titer, concentration, or a measure of how far the parameter of a new instance of a product is from a specification limit. In some aspects, the bioprocess has a negative correlation between a given processing time and a given product quality.

[0013] Another aspect of the present disclosure provides a system comprising (a) one or more processors; and (b) one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the method described in any of the foregoing aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Those skilled in the art will appreciate that the drawings described herein are included for illustrative purposes and are not intended to limit the present disclosure. The drawings are not necessarily drawn to scale, but rather focus on illustrating the principles of the present disclosure. It should be understood that in some cases, various aspects of the described embodiments may be exaggerated or enlarged to aid in understanding the described embodiments. In the drawings, similar reference numerals generally refer to components that are similar in function or structure throughout the drawings.

[0015] Figure 1 is a simplified block diagram of an example system for evaluating the impact of processing time of a process (eg, a biological process).

[0016] Figure 2 depicts an example of a conventional column chromatography process.

[0017] Figure 3 Depicted is an example process of applying the model to a bioprocess manufacturing operation to predict product quality parameters based on observed process delays.

[0018] Figure 4A An example graphical display showing exemplary historical bioprocess data is depicted.

[0019] Figure 4B An example graphical display showing an example input interface is depicted.

[0020] Figure 4C An example graphical display showing exemplary experimental performance data is depicted.

[0021] Figure 5A and Figure 5B is a flow chart depicting an example method for evaluating the impact of processing time of a process (eg, a bioprocess). DETAILED DESCRIPTION

[0022] As the pace of biotechnology accelerates, there is an increasing emphasis on processing additional molecules in bioprocess pipelines, and therefore an increasing need to design and implement steps in manufacturing processes (such as chromatographic purification processes) more quickly. The present disclosure is intended to reduce problems with conventional techniques (e.g., as described in the background section) by providing techniques for evaluating the impact of processing time on a process (e.g., a bioprocess). The techniques of the present invention can apply values ​​of processing time or product quality parameters as inputs to a model to determine values ​​of predicted product quality parameters or predicted processing times, respectively. By determining and then displaying or storing values ​​of predicted processing times or predicted product quality, these techniques are intended to provide insights to operators of bioprocess systems, thereby reducing the amount of biomolecules produced that do not meet quality conditions and improving the transferability of biomolecule production between different bioprocess systems.

[0023] Advantageously, by providing improved insights, the techniques of the present invention can provide insights into the effects of processing time (e.g., delay time) when designing a bioprocess or bioprocess system for producing biomolecules. One advantage of these insights is that fewer resources (e.g., biomolecules) are wasted when calibrating the bioprocess system, and therefore, resource efficiency is improved and the sustainability of the bioprocess system is improved. By making the bioprocess system more sustainable in terms of resource use, the energy efficiency of the bioprocess system can also be improved, and the financial or economic cost of producing each biomolecule can also be reduced. Another advantage of the improved insights is that production can be increased because more biomolecules can be produced with lower calibration times in a given amount of time. In addition, resource, energy and cost efficiency can also be improved when dealing with unexpected delays in bioprocesses because the techniques of the present invention provide insights into the availability of biomolecules produced under delayed conditions (e.g., based on product quality).

[0024] Throughout this disclosure, those of ordinary skill in the art will appreciate the additional advantages of the technology of the present invention relative to the conventional methods of operating biological processes. The various concepts and techniques introduced above and discussed in more detail below can be implemented in any of a variety of ways, and the described concepts are not limited to the embodiments of any particular method. For illustrative purposes, the examples of embodiments are provided below.

[0025] Exemplary Systems

[0026] Figure 1 is a simplified block diagram of an example system 100 for evaluating the impact of processing time of one or more bioprocess systems 150 for producing biomolecules, which may be included in a pharmaceutical product, for example. In some aspects, the system 100 may include a stand-alone device, but in other examples, the system 100 may be incorporated into other devices. At a high level, the system 100 includes components of a computing device 110, a bioprocess system 150, one or more product quality sensors 160, and one or more historical bioprocess data sources 170. Figure 1 In the embodiment, the computing device 110, the bioprocess system 150, and the historical bioprocess data source 170 are communicatively coupled via a network 180, which can be or include a proprietary network, a secure public Internet, a virtual private network, or any other type(s) of suitable wired and / or wireless networks (e.g., dedicated access lines, satellite links, cellular data networks, combinations of these networks, etc.). In embodiments where the network 180 includes the Internet, data communications can be conducted through the network 180 via Internet communication protocols. In some aspects, the system 100 may include more than one network. Figure 1More or fewer instances of the various components of system 100 are shown in (e.g., one instance of computing device 110, ten instances of bioprocess system 150, ten instances of product quality sensor 160, two instances of historical bioprocess data source 170, etc.).

[0027] It is worth noting that although the system 100 is shown as including a bioprocess system 150, one of ordinary skill in the art will appreciate that the techniques and components of the system 100 of the present invention can be applied to assess the impact of processing time (e.g., delay time) on other processes. For example, instead of the bioprocess system 150, the techniques and components of the system 100 of the present invention can be applied to the manufacture of small molecule drug products.

[0028] Bioprocess system 150 may include a single bioprocess system or multiple bioprocess systems that are either co-located or remote from each other and suitable for producing biomolecules. Biomolecules may be any of carbohydrates, lipids, nucleic acids, or proteins produced by cells and living organisms. Biomolecules have a wide range of sizes and structures and perform many functions. The bioprocess that can produce a given biomolecule can separate the biomolecule from the cell that has produced the biomolecule by a process that includes one (and often multiple) of the following: filtration, extraction, crystallization, membranes, and chromatography. Bioprocess system 150 may generally include physical equipment configured to produce (e.g., manufacture) biomolecules.

[0029] In some embodiments, the bioprocess system 150 may be connected to the computing device 110 via the network 180 or directly, thereby allowing at least some functions of the bioprocess system 150 to be controlled by the computing device 110. In some embodiments, the bioprocess system 150 may be able to receive instructions directly from a user (e.g., the bioprocess system 150 may be manually configured). For example, in some embodiments, the bioprocess system 150 may receive instructions directly from a user to control operation (e.g., the processing time of one or more steps of a chromatography process of the bioprocess system 150 may be set to operate based on input from a user).

[0030] The product quality sensor 160 may be included in the bioprocess system 150 (e.g., integrated into the bioprocess system 150), or may be an external sensor connected to the bioprocess system 150. The product quality sensor 160 may be used to collect (e.g., directly or indirectly) product quality parameter data of biomolecules produced by the bioprocess system 150. The product quality parameter may be the purity of the output of the bioprocess system 150, which may be measured as a peak value or peak purity (e.g., a main peak CEX). The product quality sensor 160 may provide the product quality parameter data to, for example, the computing device 110 (e.g., via the network 180). The product quality parameter data may be any suitable data type, such as categorical data, sequenced data, discrete data, or continuous data. The product quality parameter data may be in the form of a suitable data structure, which may be stored in a suitable format, such as one or more of the following formats: JSON, XML, CSV, etc. The product quality parameter data may be collected or provided automatically or in response to a request. For example, a user of the computing device 110 may wish to use the bioprocess system 150 to evaluate the impact of the processing time of a bioprocess. In response, one or more of product quality sensors 160 may collect product quality parameter data and provide it to computing device 110. In some embodiments, one or more of product quality sensors 160 may include a database of data / information related to product quality, or may be configured to receive data / information related to product quality, such as via user input.

[0031] The bioprocess system 150 may include one or more devices (not shown) for chromatography (e.g., one or more of the chromatography methods discussed in the background section). For example, the bioprocess system 150 may include one or more of the following: a chromatography column, a capillary, a plate, a sheet, a frit, a flow cell, a pump, a vacuum device, a detector, a collector, a syringe, etc. for performing the chromatography. In other embodiments, the bioprocess system also includes or alternatively includes other devices, such as a bioreactor, an outlet filter, etc.

[0032] The bioprocess system 150 can be configured to be controllable via manual or automated inputs. In some embodiments, the bioprocess system 150 can be configured to receive these control inputs locally, such as via a user input device local to the bioprocess system 150. In some embodiments, the bioprocess system 150 is configured to receive control inputs remotely, such as from the computing device 110 (e.g., via the network 180). The control inputs can include operating instructions, such as a processing time according to which the bioprocess system 150 should operate.

[0033] The historical bioprocess data source 170 generally includes historical bioprocess data, which may correspond to one or more bioprocesses used to produce one or more biomolecules using the bioprocess system 150. The historical bioprocess data may include: (i) historical processing times for multiple instances of the bioprocess and (ii) corresponding historical product quality of products produced by these instances of the bioprocess. In some embodiments or scenarios, at least a portion of the historical bioprocess data is collected using the bioprocess system 150. However, in some embodiments or scenarios, a different bioprocess system is used to collect all historical bioprocess data. The historical bioprocess data may include data from a bioprocess having similar scales / sizes, settings / parameters, equipment models, etc. as the (multiple) bioprocess systems 150, and / or data from a bioprocess having different scales / sizes, settings / parameters, equipment models, etc. than the (multiple) bioprocess systems 150. In some embodiments, the system 100 may omit the historical bioprocess data source 170, and instead receive data for the historical bioprocess locally, such as via user input at the computing device 110.

[0034] The computing device 110 may include a single computing device, or multiple computing devices located at the same location or remote from each other. The computing device 110 is generally configured to apply inputs to a model 130 trained using historical bioprocess data to determine a predicted output that will be produced when the bioprocess is operated according to the inputs, wherein: (i) the inputs include processing time and the predicted output includes product quality, or (ii) the inputs include product quality parameters and the predicted output includes processing time. The components of the computing device 110 may be interconnected via an address / data bus or other means. The components included in the computing device 110 may include a processing unit 120, a network interface 122, a display 124, a user input device 126, and a memory 128, which will be discussed in further detail below.

[0035] The processing unit 120 includes one or more processors, each of which may be a programmable microprocessor that executes software instructions stored in the memory 128 to perform some or all of the functions of the computing device 110 as described herein. Alternatively, one or more processors in the processing unit 120 may be other types of processors (e.g., an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc.).

[0036] The network interface 122 may include any suitable hardware (e.g., front-end transmitter and receiver hardware), firmware, or software configured to communicate with external devices or systems (e.g., product quality sensors 160, bioprocess systems 150, historical bioprocess data sources 170, etc.) via the network 180 using one or more communication protocols. For example, the network interface 122 may be or include an Ethernet interface.

[0037] The display 124 may use any suitable display technology (e.g., LED, OLED, LCD, etc.) to present information to the user, and the user input device 126 may be a keyboard or other suitable input device. In some aspects, the display 124 and the user input device 126 are integrated into a single device (e.g., a touch screen display). Typically, the display 124 and the user input device 126 may be combined to enable a user to interact with a graphical user interface (GUI) or other (e.g., text) user interface provided by the computing device 110 (e.g., for purposes such as displaying data / information (e.g., product quality parameters or processing time) or notifying a user of a device failure or other defect).

[0038] The memory 128 includes one or more physical memory devices or units including volatile or non-volatile memory, and may or may not include memory located in different computing devices of the computing device 110. Any suitable memory type or types may be used, such as read-only memory (ROM), solid-state drive (SSD), hard disk drive (HDD), etc. The memory 128 may store (i) the model 130, and (ii) instructions of one or more software applications included in a processing time evaluation (PTE) application 140 that may be executed by the processing unit 120. In the example system 100, the PTE application 140 includes a data collection unit 142, a modeling unit 144, a user interface unit 146, and a data storage unit 148. The units 142 to 148 may be different software components or modules of the PTE application 140, or may simply represent functionality of the PTE application 140 that is not necessarily divided between different components / modules. For example, in some embodiments, the data collection unit 142 and the user interface unit 146 are included in a single software module. Furthermore, in some embodiments, units 142 to 148 are distributed among multiple copies of PTE application 140 (e.g., multiple copies executed at different components in computing device 110), or among different types of applications stored and executed at one or more devices of computing device 110.

[0039] Model 130 can be any suitable model for evaluating the impact of the processing time of a process (e.g., a biological process). In some embodiments, and as further discussed below, model 130 can be trained using at least some of system 100, or, in some embodiments, model 130 can be pre-trained (i.e., trained before being obtained by system 100). Model 130 can be trained using historical biological process data, which includes (i) historical processing times for multiple instances of a biological process and (ii) corresponding historical product quality of products produced by the multiple instances of the biological process. In some embodiments, model 130 can include a statistical model that can be parametric, non-parametric, or semi-parametric. A suitable example of a statistical model that can be included in model 130 is a linear regression model. In other embodiments, model 130 includes a machine learning model. For example, model 130 can employ a neural network, such as a convolutional neural network or a deep learning neural network. Other examples of machine learning models in model 130 are models using support vector machine (SVM) analysis, K-nearest neighbor analysis, naive Bayes analysis, clustering, reinforcement learning, or other machine learning algorithms or techniques. The machine learning models included in model 130 can recognize and discern patterns in training data to facilitate making predictions about new data.

[0040] The data collection unit 142 is generally configured to receive data. In some embodiments, the data collection unit 142 receives historical bioprocess data for a bioprocess for producing a biomolecule (e.g., including historical processing times for multiple instances of the bioprocess and corresponding historical product qualities of products produced by the multiple instances of the bioprocess). The data collection unit 142 may receive the historical bioprocess data via, for example, a historical bioprocess data source 170, a user input received via a user interface unit 146 having a user input device 126, or other suitable means. In some embodiments, the data collection unit 142 may receive one or more values ​​of a product quality parameter via, for example, a product quality sensor 160, a user input received via a user interface unit 146 having a user input device 126, or other suitable means. In some embodiments, a processing time sensor (not shown) may provide timing data to the data collection unit 142. In some embodiments, the computing device 110 may receive an indication that the bioprocess has begun, for example, at the data collection unit 142, and one or more components of the computing device 110 may monitor the processing time locally.

[0041] The modeling unit 144 is generally configured to generate, train, or apply the model 130. The modeling unit 144 can train the model 130 using historical bioprocess data received from the historical bioprocess data source 170. The modeling unit 144 can also apply the model 130 when evaluating the impact of the processing time of a process (e.g., a bioprocess). More specifically, the modeling unit 144 can apply inputs to the model 130 to determine a predicted output that will be produced when the bioprocess is operated according to the inputs, wherein: (i) the inputs include processing time and the predicted output includes product quality, or (ii) the inputs include product quality parameters and the predicted output includes processing time. In some embodiments, the model 130 can be trained by a device or system external to the system 100, and the modeling unit 144 only applies the inputs to the model 130 without being involved in training the model 130.

[0042] The user interface unit 146 is generally configured to receive user input. In one example, the user interface unit 146 can generate a user interface for presentation via the display 124, and receive user input for historical bioprocess data to be used by the modeling unit 144 when training the model 130 via the user interface and the user input device 126. In another example, the user interface unit 146 can receive (multiple) inputs (e.g., the processing time of a certain stage of the bioprocess, or one or more desired product quality parameters of a product produced by the bioprocess) to be used by the modeling unit 144 when applying the model 130 via the user interface and the user input device 126. The user interface unit 146 can also be used to display information. For example, the user interface unit 146 can be used to display a predicted output (e.g., the processing time of a bioprocess or one or more product quality parameters of a product produced by the bioprocess).

[0043] The data storage unit 148 is generally configured to store the predicted outputs (e.g., processing time or product quality parameter(s)) determined by the modeling unit 144. The data storage unit 148 can store the predicted outputs in the memory 128, or in a different suitable memory (e.g., in an external database or on a computer system not shown). In some embodiments, the data storage unit 148 also stores other information, such as model inputs corresponding to the predicted model outputs.

[0044] The operation of each of units 142 - 148 is described in more detail below with reference to the operation of system 100 .

[0045] Exemplary Bioprocess Manufacturing Operations

[0046] Figure 3An example process 300 of applying a model to a bioprocess manufacturing operation to predict a product quality parameter based on observed process delays is depicted. As shown, the process 300 includes manufacturing operations at stage 310, process monitoring and technical support at stage 320, and predictive modeling at stage 330. The process 300 can be performed using equipment / apparatus that can be the same or similar to the equipment / apparatus discussed above in connection with the system 100. For example, the computing device 110 can implement at least some of the process 300 (e.g., using data collected from the bioprocess system 150).

[0047] In an exemplary embodiment, the manufacturing operation of stage 310 of process 300 begins at sub-stage 310A, where the bioprocess is in normal process operation. The bioprocess can be operated according to parameters previously determined by experimentation or modeling to produce biomolecules produced according to quality control standards. Assuming that no process delay is observed at sub-stage 310B (e.g., by an operator of the bioprocess, or in an automated manner such as using a computing device 110 with a data collection unit 142), normal process operation can continue at sub-stage 310C until a full amount of biomolecules that meet the quality control standards are produced, while the entire process remains in stage 310 of manufacturing operation. However, if a process delay is observed at sub-stage 310B (e.g., by an operator of the bioprocess, or in an automated manner such as using a computing device 110 with a data collection unit 142) (e.g., due to avoidable or unavoidable reasons), the process 300 can move to stage 320 of process monitoring and technical support.

[0048] Phase 320 may include monitoring and technical support for bioprocesses, such as using computing device 110 to manage solutions to possible problems in bioprocesses. In some embodiments, phase 320 begins with sub-phase 320A of evaluating observed process delays according to the standard operating procedures of bioprocesses. As previously discussed, some process steps of bioprocesses may need to expose biomolecules to chemical conditions that may reduce their stability in the mid-term of production. For example, pool conditioning process steps, virus inactivation and clarification process steps need to expose products to significant changes in pool pH, conductivity or temperature, which are unfavorable to biomolecules. Therefore, for these process steps, there may be a negative correlation between the duration of the process steps and the product quality parameters of the produced biomolecules. At sub-phase 320A, it is possible (for example, by an operator or by computing system 110) to refer to the standard operating procedures to determine whether the observed process delay occurs during the process step that delays the quality of biomolecule products. If not, process 300 returns to phase 310 to continue the normal operation of the bioprocess. However, if the observed process delay does correspond to a process step where delaying is detrimental to biomolecule product quality, then process 300 continues to sub-stage 320C to assess the extent of the product quality impact using a model (e.g., model 130 applied by modeling unit 144). Operation of sub-stage 320C entails advancing the process to stage 330.

[0049] Stage 330 may include operating a trained model (e.g., model 130) to determine a predicted product quality parameter based on an observed process delay. In some embodiments, stage 330 may start with a substage 330A of obtaining a processing time (e.g., total processing time including current or expected delay) of the duration of a processing step. As previously discussed, a process step may be a process step with a negative correlation between the duration of the process step and the product quality parameter of a biomolecule produced by a bioprocess. Therefore, the observed delay in the bioprocess may cause the product quality parameter of the biomolecule to be significantly reduced. At substage 330B, a model (e.g., model 130 used by modeling unit 144) receives the processing time as an input for estimating the product quality parameter of the biomolecule. At substage 330C, the product quality parameter may be displayed (e.g., a graphical user interface presented on display 124 by user interface unit 146). Once the product quality parameter is displayed at substage 330C, process 300 may return to stage 320 of process monitoring and technical support.

[0050] Returning to stage 320, at sub-stage 320D, it is determined whether the product quality parameter displayed at sub-stage 330C corresponds to a "significant" reduction in product quality. In some embodiments, an operator can make a determination at sub-stage 330D. In other embodiments, a computer system (e.g., computing device 110) makes a determination. Determining whether the reduction in product quality parameters is "significant" can be based on certain guidelines or rules. For example, specification limits that can be set by manufacturers or regulatory agencies can be used to determine whether the reduction in product quality parameters is "significant". In another example, a threshold value (e.g., if the product quality parameter is reduced by a certain percentage) can be used to determine whether the reduction in product quality parameters is significant. If the product quality parameter of the biomolecule is not determined to be significant as the reduction in the observed process delay, process 300 returns to stage 310 to continue the normal operation of the bioprocess. However, if the product quality parameter of the biomolecule is determined to be significant as the reduction in the observed process delay, process 300 continues to sub-stage 320E to determine the mitigation measures to be used in subsequent process operations.

[0051] In some embodiments, example mitigation measures used in subsequent process operations of sub-stage 320E may include changing the processing time of one or more steps of the bioprocess. For example, the model (e.g., the model 130 used by the modeling unit 144) may be "run in reverse" with how the model is used in stage 330. Specifically, the model may receive acceptable product quality parameters (e.g., product quality parameters that are just within specification limits) as input so that the model can predict the processing time of one or more steps of the bioprocess to achieve acceptable product quality. In some embodiments, parameters of the bioprocess other than the processing time may be adjusted. For example, when chromatography is a bioprocess, parameters such as elution buffer pH, elution buffer conductivity, elution buffer solution molarity, gradient slope, linear velocity, load, and collection time may be mitigation measures to adjust the bioprocess to meet quality control. In some embodiments, subsequent process steps are adjusted to attempt to correct delayed biomolecules. For example, if the delay causes the variable cell density of the biomolecule to be too low, the amount of nutrients may be increased in subsequent process steps to compensate. In some embodiments, if mitigating the effects of the delay is not possible for the delayed biomolecule, the biomolecule may be discarded entirely. If mitigations exist and can be implemented, process 300 may proceed to sub-stage 320F of continuing process operations of the bioprocess using the mitigations, and then to sub-stage 310D of delivering the biomolecule that meets quality control.

[0052] Example Graphical Display

[0053] FIG. 4A to FIG. 4CDescribes the Figure 1 Example graphical interface(s) 400A to 400C generated by the user interface unit 146 of the embodiment of the present invention. As shown, interface 400A includes an exemplary graphical representation of historical bioprocess data for a bioprocess, the historical bioprocess data including (i) historical processing times for an instance of the bioprocess and (ii) corresponding historical product qualities of a product produced by the instance of the bioprocess. As shown, interface 400B includes an exemplary user interface for estimating output product quality parameters of biomolecules produced by the bioprocess based on input processing times. As shown, interface 400C includes an exemplary graphical representation comparing actual and predicted product qualities of a bioprocess for a plurality of different processing times.

[0054] The user interface unit 146 may present the displays 400A-C in a single screen or multiple screens on the display 124, and may receive input (e.g., input processing time, indication of file location(s) of historical bioprocess data, multiple actual product qualities, etc.) via one or more of the user interfaces 400A-C and the user input device 126. In some embodiments, the historical bioprocess data represented in the interface 400A may be provided by a historical bioprocess data source, such as the historical bioprocess data source 170. The modeling unit 144 may estimate the output product quality parameters represented in the interface 400B using the model 130. The actual product quality parameters represented in the interface 400C may be determined using a product quality sensor, such as the product quality sensor 160 of the bioprocess system 150. The modeling unit 144 may predict the product quality represented in the interface 400C, which may be determined using the model 130.

[0055] The historical bioprocess data of interface 400A can be filtered or modified based on different inputs, outputs, batch numbers and manufacturing dates that can be selected via user input. As shown, the product quality of historical bioprocess data is measured as the pre-peak SE, and the processing time of historical bioprocess data is measured as the number of hours of cystamine use time. In some bioprocesses, biomolecules may be exposed to organic disulfide cystamine. It is known that cystamine is an unstable liquid and has certain toxicity, wherein, in some bioprocesses, the time that biomolecules are exposed to cystamine increases and may be harmful to the product quality parameters of biomolecules. Therefore, it may be useful to assess the impact of cystamine use time on biomolecule pre-peak SE. Pre-peak SE is a measure of product quality and can be used for size exclusion (SE) chromatography. Higher pre-peak SE scores can indicate purer biomolecules, which have higher product quality accordingly.

[0056] The input processing time can be input as a plurality of different processing times via user interface 400B (e.g., by a user). As shown, the input processing time is 2.64 hours of the butyl FF pH adjustment time. Based on the input processing time, the model predicts the output product quality. As shown, the output product quality parameter is 87.544576% main peak CEX. Although the input processing time is in hours of the butyl FF pH adjustment time, and the output product quality parameter is in percentage of the main peak CEX, other possible units of the input processing time can be used, and other possible units of the output product quality parameter can be used. It is also worth noting that in some embodiments, the input can be an input product quality parameter, and the output can be an output processing time. In some embodiments, if an output target (e.g., specification limit, warning limit, etc.) is provided, the interface 400B can indicate to the user whether the output product quality parameter or the output processing time is within the output target. As shown, the interface 400B also includes a time conversion and date difference calculation tool to help the user determine the number of hours of the input processing time as a decimal. In some embodiments, the determined number of hours may be automatically entered as the input processing time for the model, or entered in response to a user selecting a "Set as Input" button, as shown.

[0057] Interface 400C compares the actual and predicted product quality (measured by the main peak CEX) of each batch of historical bioprocess data of interface 400A based on the processing time (measured by cystamine usage time) of each batch. As shown, a generalized linear regression model is used to determine the predicted product quality. The exemplary experimental performance data of interface 400C has an R square value greater than 0.95, a root mean square error of about 0.058, and a mean absolute error of about 0.050. Therefore, the exemplary performance data demonstrates the effectiveness of the technology of the present invention in developing a model for the impact of the processing time of an evaluation process (e.g., a bioprocess) because the predicted product quality parameters closely track the actual product quality.

[0058] Exemplary Flowchart

[0059] Figure 5A and Figure 5BFlowcharts depicting example methods 500A and 500B, respectively, for evaluating the impact of processing time on a process (e.g., a bioprocess). Methods 500A or 500B may be implemented by one or more components of system 100, such as processing unit 120 when implementing PTE application 140, and possibly bioprocess system 150 (which may operate a bioprocess, such as column chromatography process 200). Methods 500A or 500B may be performed as part of a process that is the same as or similar to process 300. Methods 500A or 500B may use historical bioprocess data (e.g., historical bioprocess data represented in interface 400A), and may receive input processing times or input product qualities (e.g., via interface 400B), and display input / output processing times or input / output product qualities using one or more graphical displays that may be displayed in conjunction with process 300. FIG. 4A to FIG. 4C The graphics display is the same or similar.

[0060] Example method 500A may include the following elements: (1) obtaining a model trained using historical bioprocess data of a bioprocess (box 502A), (2) determining a predicted product quality parameter that will be produced when the bioprocess is operated according to a processing time (box 504A), and (3) displaying or storing the predicted product quality parameter (box 506A).

[0061] The trained model obtained at block 502A may have been trained using historical bioprocess data (e.g., as described above), such as historical bioprocess data included in historical bioprocess source 170. In some embodiments, obtaining the model at block 502A includes receiving a pre-trained model (i.e., trained prior to being obtained by, for example, system 100), or generating / training the model (e.g., by system 100). The model may be obtained internally (e.g., by accessing a file / program / data / information stored locally in a computing system such as computing device 110) or externally (e.g., receiving the model from an external source, such as receiving the model at computing device 110 via network 180). The product quality of the historical bioprocess data may be an indicator of the purity of a biomolecule produced by the bioprocess (e.g., measured as a peak or peak purity, such as a main peak CEX), yield, viable cell density (VCD), titer, concentration, etc., or a measure of the difference between a product quality parameter and a specification limit, for example. The processing time of historical bioprocess data can be the duration of one or more steps of a bioprocess (eg, including any delays), or one or more delays in a bioprocess (eg, a time that exceeds an expected amount of time).

[0062] Frame 504A may include determining the predicted product quality parameters that will be generated when the bioprocess is operated according to the processing time by applying the processing time to the model. The processing time can be input by a user via a user interface (e.g., using a user input device 126) or by collecting the processing time as data (e.g., via a data collection unit 146). The predicted product quality parameters can be estimated by the model as a single value or a series of possible values. In some embodiments, the model can determine whether the predicted product quality parameters meet one or more conditions (e.g., thresholds, tolerances, specification limits, warning limits, etc.). In some embodiments, the model can be a linear regression model or some other suitable statistical model. In some embodiments, the model is a machine learning model, such as a linear regressor, a random forest model, a neural network (e.g., a convolutional neural network, a deep learning neural network, etc.), a model using support vector machine (SVM) analysis, K-nearest neighbor analysis, naive Bayes analysis, clustering or reinforcement learning, or another suitable machine learning model.

[0063] Block 506A may include displaying or storing the predicted product quality via a computing device such as computing device 110. In some aspects, the predicted product quality parameter itself may be displayed, while in other aspects, a representation of the predicted product quality parameter may be displayed. Displaying the predicted product quality parameter may specifically use, for example, display 124 and user interface unit 146 of computing device 110. In some embodiments, the predicted product quality parameter itself may be stored, while in other aspects, a representation (e.g., a graphical representation or data visualization technique) of the first value of the predicted product quality parameter may be stored. The predicted product quality parameter is stored in memory 128 of computing device 110, for example, using data storage unit 148.

[0064] Turning to example method 500B, method 500B may include the following elements: (1) obtaining a model trained using historical bioprocess data for a bioprocess (box 502B), (2) determining a predicted processing time that will result when the bioprocess is operated according to a product quality parameter (box 504B), for example, when the bioprocess is operated in a manner that will achieve the desired product quality parameter, and (3) displaying or storing the predicted processing time (box 506B).

[0065] Block 502B may be the same or similar to block 502A, and the model of 502B may be the same or similar to the model of 502A. Block 504B may be the same or similar to block 504A, but instead of processing time being used as an input to the model, product quality parameters are used as inputs to the model, and instead of the model predicting product quality, the model predicts processing time. Finally, block 506B may be the same or similar to block 506A, but instead of displaying or storing predicted product quality, predicted processing time is displayed or stored.

[0066] In some aspects, methods 500A and 500B can be performed entirely by automation, for example, by one or more processors (e.g., a CPU or GPU) executing instructions stored on one or more non-transitory computer-readable storage media (e.g., volatile or non-volatile memory, read-only memory, random access memory, flash memory, electronically erasable program read-only memory, or one or more other types of memory). Methods 500A and 500B can be performed using Figure 1 To any component, process or technique of one or more of Figure 4.

[0067] Additional considerations

[0068] The terms "process operation" or "unit operation" refer to functional steps performed as part of a process for purifying a recombinant protein of interest and are used interchangeably. For example, a process operation may include steps such as, but not limited to, harvesting, chromatography (capture and refinement), filtration, viral inactivation, viral filtration, concentration, and / or formulation of a product of interest.

[0069] The harvesting operation clarifies and / or purifies the product to remove at least one impurity found in the cell culture fluid, such as residual cell culture medium, cells and / or cell debris, undesirable cells or culture medium components, and / or product-related impurities and / or process-related impurities. Methods for harvesting include, but are not limited to, acid precipitation, accelerated sedimentation (such as flocculation), separation using gravity, centrifugation, sonic separation, filtration (including membrane filtration, ultrafilters, microfilters, tangential flow, alternating tangential flow, depth filters, and alluvial filtration filters).

[0070] Chromatographic operations utilize media that capture and / or purify the target product. Chromatographic operations include single column systems, multi-column systems, such as periodic countercurrent culture and expanded bed chromatography systems, etc. Chromatographic media include monoliths, resins and / or membranes containing reagents that will bind and / or interact with at least one desired product, impurity or contaminant in some way. Chromatographic media include those that utilize the following: Staphylococcal proteins, such as protein A, protein G, protein A / G and protein L; substrate binding capture mechanisms; antibody or antibody fragment binding capture mechanisms; aptamer binding capture mechanisms; cofactor binding capture mechanisms; immobilized metal affinity chromatography (IMAC), size exclusion chromatography, ion exchange chromatography (IEX) (such as cation exchange (CEX) and anion exchange (AEX) chromatography), hydrophobic interaction chromatography (HIC), multimode or mixed mode (MMC), hydroxyapatite chromatography (HA), reverse phase chromatography and gel filtration, etc. Such media are known in the art and are commercially available and include, but are not limited to, MABSELECT™ SURE Protein A, Protein A Agarose FAST FLOWTM 、MABSELECT TM PrismA (Cytiva, Marborough, MA), PROSEP-A TM (Merck Millipore, UK), TOYOPEARL TM HC-650F Protein A (TosoHass Co., Philadelphia, PA) and AP Plus (Purolite, King of Prussia, PA), Capto™ Adhere, Capto TM MMCImpress, Capto MMC (Situofan), PPA Hypercel, MEP Hypercell, HEA Hypercell (Pall Corporation, Port Washington, NY), Eshmuno HCX (Merck Millipore), Toyopearl MX-Trp-650M (Tosoh Bioscience), PhenylSephroseTM (Situofan), Tosoh hexyl (Tosoh Bioscience), and CaptoTM phenyl (Situofan), CA++Pure-HA (Tosoh Bioscience), HA (Sartorius) etc.

[0071] The filtration operation is used to reduce and / or remove any generated turbidity, precipitation, impurities and / or contamination associated with the product. Filtration includes the use of depth filters, sterile and / or bioreduction control filters, ultrafilters, microfilters, tangential flow filters, alternating tangential flow filters, alluvial filters, etc. Depth filters suitable for the method are known in the art and are commercially available. Such filters include, but are not limited to, cellulose, pretreated filter matrices, synthetic fiber meshes, or a combination of all. In some embodiments, the filtration step is depth filtration or tangential flow filtration. Such filters are known in the art and are commercially available, and include, but are not limited to Pro Shield, Pro Shield H, D0HC filter, X0HC filter, C0HC filter, C0SP filter, X0SP filter, Clarisolve 20MS filter, Clarisolve 40MS filter, Clarisolve 60HX filter (Millipore Corporation, Burlington, Massachusetts), DL60 filter, DL75 filter (Sartorius, Göttingen, Germany), 3M TM Zeta Plus TM Filter, diatomaceous earth, 3M TM Emphaze TM AEX Hybrid Purifier (EM Corporation, Meriden, Connecticut), etc. Sterile and / or bioreduction control filtration. Such filters are known in the art and commercially available and include, but are not limited to, Millipore SHC hydrophilic polyethersulfone filter (Millipore Corporation) and 2 Polyethersulfone (PES) liquid filter (Sartorius).

[0072] Process operations designed to inactivate, reduce and / or eliminate viral contaminants may include operations to reduce viral risks by manipulating the environment and / or by using filtration. Viruses are classified as enveloped viruses and non-enveloped viruses. For enveloped viruses, the envelope allows the virus to recognize, bind, enter and infect target host cells. Therefore, enveloped viruses are susceptible to inactivation methods. Various methods can be used to inactivate viruses and these methods include heat inactivation / pasteurization, UV and gamma ray irradiation, use of high-intensity broad-spectrum white light, addition of chemical inactivators, surfactants, and solvent / detergent treatment. Surfactants (such as detergents) can dissolve membranes and therefore may be very effective in specifically inactivating enveloped viruses, etc. Non-enveloped viruses are more difficult to inactivate without damaging the purified product and are removed by filtration methods. Virus filtration can be performed using microfilters or nanofilters (such as from (Asahi Kasei, Chicago, IL), (Sartorius AG, Göttingen, Germany), Pro (MilliporeSigma, Burlington, MA), Pegasus™ Prime (those available from Pall Biotech, Port Washington, NY), CUNO ZetaPlus VR (3M Company, St. Paul, MN)).

[0073] The production operation may also include product concentration and formulation. One such operation utilizes ultrafiltration and diafiltration. Suitable materials known and common in the art are commercially available from many sources, including regenerated cellulose Pellicon (Millipore Sigma, Danvers, Mass.), stabilized cellulose, Slice, ECO (Sartorius, Göttingen, Germany), polyethersulfone (PES) membrane, Omega (Pall Corporation, Port Washington, New York), etc.

[0074] Product quality includes physical, chemical, biological and / or microbiological properties or characteristics, and appropriate limits or ranges of these properties or characteristics have been determined to ensure the desired product quality. Such attributes can be key attributes such as specific productivity, pH, osmotic pressure, appearance, color, aggregation, yield percentage and titer, etc. Monitoring and measurement can be performed using known techniques and commercially available equipment.

[0075] The methods described herein can be used in combination with a production process for purifying a target product. The product may have scientific or commercial significance, including protein-based therapeutic agents. The target product includes, but is not limited to, secretory proteins, non-secretory proteins, intracellular proteins, or membrane-bound proteins. The target product can be produced by a recombinant animal cell line using the cell culture method described herein, and can be referred to as a "recombinant protein". The expressed (multiple) proteins can be produced intracellularly or secreted into a culture medium, from which these proteins can be recovered and / or collected. The target product is purified to remove proteins or polypeptides or other pollutants that interfere with the treatment, diagnosis, prevention, research, or other uses of the product. The target product includes, but is not limited to, proteins that play a therapeutic role by binding to one or more targets (e.g., targets listed below, including targets derived therefrom, targets associated therewith, and modifications thereof).

[0076] The protein of interest may include, but is not limited to, an "antigen binding protein". An "antigen binding protein" refers to a protein or polypeptide that includes an antigen binding region or antigen binding portion that has affinity for another molecule (antigen) to which it binds. Antigen binding proteins include, but are not limited to, antibodies, peptibodies, antibody fragments, antibody derivatives, antibody analogs, fusion proteins (including, for example, single-chain variable fragments (scFv), double-chain (bivalent) scFv and IgGscFv (see, for example, Orcutt et al., 2010, Protein Eng Des Sel [Protein Engineering Design and Selection] 23:221-228)), heterologous IgG (see, for example, Liu et al., 2015, J Biol Chem [Journal of Biological Chemistry] 290:7535-7562), bispecific antibodies, multispecific antibodies, mutant proteins, Molecules (Xencor, Inc., Monrovia, CA). Also included are all forms of bispecific T cell engager molecules. In addition, chimeric antigen receptors (CAR, CAR T) and T cell receptors (TCR) are also included.

[0077] In some embodiments, the product of interest may include a colony stimulating factor, such as granulocyte colony stimulating factor (G-CSF). Such G-CSF agents include, but are not limited to (filgrastim) and (Pegfilgrastim). Also included are erythropoiesis stimulating agents (ESAs), such as (Epoetin α), (darbepoetin alfa), (Epoetine δ), (methoxy polyethylene glycol-epoetin beta), MRK-2578, INS-22, (Epoetin ζ), (Epoetin β), (Epoetin ζ), (epoetin alfa), epoetin alfa Hexal, (Epoetin α), (Epoetine θ), (Epoetine θ), (Epoetin θ), Epoetin α, Epoetin β, Epoetin ζ, Epoetin θ and Epoetin δ, Epoetin ω, Epoetin ι; tissue plasminogen activator; and GLP-1 receptor agonist; and variants or analogs thereof and biosimilars of any of the foregoing.

[0078] In some embodiments, the product of interest binds to one or more of the following, alone or in any combination: CD proteins, including but not limited to CD3, CD4, CD5, CD7, CD8, CD19, CD20, CD22, CD25, CD30, CD33, CD34, CD38, CD40, CD70, CD123, CD133, CD138, CD171, and CD174; HER receptor family proteins, including, for example, HER2, HER3, HER4, and EGF receptor, EGFRvIII, cell adhesion molecules (e.g., LFA-1, Mol, p150, 95, VLA-4, ICAM-1, VCAM, and αv / β3 integrin); growth factors, including but not limited to, for example, vascular endothelial growth factor ("VEGF"); VEGFR2, growth hormone, thyroid stimulating hormone, follicle stimulating hormone, luteinizing hormone, growth hormone releasing factor, parathyroid hormone, Müllerian inhibitory substance, Human macrophage inflammatory protein (MIP-1-α), erythropoietin (EPO), nerve growth factor (e.g., NGF-β), platelet-derived growth factor (PDGF), fibroblast growth factor (including, for example, aFGF and bFGF), epidermal growth factor (EGF), Cripto, transforming growth factor (TGF) (especially including TGF-α and TGF-β (including TGF-β1, TGF-β2, TGF-β3, TGF-β4 or TGF-β5)), insulin-like growth factor-I and insulin-like growth factor-II (IGF-I and IGF-II), des (1-3)-IGF-I (brain IGF-I) and osteoinductive factor, insulin and insulin-related proteins (including but not limited to insulin, insulin A chain, insulin B chain, proinsulin and insulin-like growth factor binding protein); (coagulation proteins and coagulation-related proteins, especially such as factor VIII, tissue factor, von Willebond (von Willebond) Willebrand factor, protein C, alpha-1-antitrypsin, plasminogen activators (such as urokinase and tissue plasminogen activator ("t-PA")), bombazine, thrombin, thrombopoietin and thrombopoietin receptors, colony stimulating factors (CSF) (including, inter alia, the following: M-CSF, GM-CSF and G-CSF), other blood and serum proteins (including, but not limited to, albumin, IgE and blood group antigens), receptors and receptor-associated proteins (including, for example, flk2 / flt3 receptors, obesity (OB) receptors, growth hormone receptors and T cell receptors); neurotrophic factors, including, but not limited to, bone-derived neurotrophic factor (BDNF) and neurotrophin-3, neurotrophin-4, neurotrophin-5 or neurotrophin-6 (NT-3, NT-4, NT-5 or NT-6);Relaxin A chain, relaxin B chain and prorelaxin, interferons (including, for example, interferon alpha, interferon beta and interferon gamma), interleukins (ILs) (e.g., IL-1 to IL-10, IL-12, IL-15, IL-17, IL-23, IL-12 / IL-23, IL-2Ra, IL1-R1, IL-6 receptor, IL-4 receptor and / or IL-13 receptor, IL-13RA2 or IL-17 receptor, IL-1RAP); viral antigens, including but not limited to AIDS enveloped virus antigens, lipoproteins, calcitonin, glucagon, atrial natriuretic peptide, lung surfactant , tumor necrosis factor-α and tumor necrosis factor-β, enkephalinase, BCMA, IgKappa, ROR-1, ERBB2, mesothelin, RANTES (normal T cell expressed and secreted factor regulated by activation), mouse gonadotropin-related peptide, DNA enzyme, FR-α, inhibin and activin, integrin, protein A or D, rheumatoid factor, immunotoxin, bone morphogenetic protein (BMP), superoxide dismutase, surface membrane protein, decay accelerating factor (DAF), AIDS envelope, transporter, homing receptor, MIC (MIC-a, MIC-B), ULBP 1-6, EPCAM, addressin, regulatory protein, immunoadhesin, antigen binding protein, growth hormone, CTGF, CTLA4, eotaxin-1, MUC1, CEA, c-MET, claudin-18, GPC-3, EPHA2, FPA, LMP1, MG7, NY-ESO-1, PSCA, ganglioside GD2, ganglioside GM2, BAFF, OPGL (RANKL), myostatin, Dickkopf-1 (DKK-1), Ang 2. NGF, IGF-1 receptor, hepatocyte growth factor (HGF), TRAIL-R2, c-Kit, B7RP-1, PSMA, NKG2D-1, programmed cell death protein 1 and ligand, PD1 and PDL1, mannose receptor / hCGβ, hepatitis C virus, mesothelin dsFv [PE38] conjugate, Legionella pneumophila (lly), IFNγ, interferon gamma inducible protein 10 (IP10), IFNAR, TALL-1, thymic stromal lymphopoietin (TSLP), proprotein convertase subtilisin / Kexin PCSK9, stem cell factor, Flt-3, calcitonin gene-related peptide (CGRP), OX40L, α4β7, platelet-specific (platelet glycoprotein IIb / IIIb (PAC-1), transforming growth factor β (TFGβ), zona pellucida sperm-binding protein 3 (ZP-3), TWEAK, platelet-derived growth factor receptor α (PDGFRα), sclerostin, and biologically active fragments or variants of any of the foregoing.

[0079] In some embodiments, the protein of interest comprises abciximab, adalimumab, adelimumab, aflibercept, alemtuzumab, alirocumab, anakinra, atacicept, basiliximab, belimumab, bevacizumab, biosozumab, blinatumomab, brentuximab, brodalumab, mocantuzumab, canakinumab, cetuximab, certolizumab, canatumumab, daclizumab, denosumab, eculizumab, edrecolomab, efalizumab, epratuzumab, etanercept, evolocumab, galiximab, ganitazumab, gemtuzumab, golimumab, ibritumomab tiuxetan, infliximab, ipilimumab imab, lerdizumab, ruximab, lxdkizumab, mapatumumab, motesanib diphosphate, muromonab-CD3, natalizumab, nesiritide, nimotuzumab, nivolumab, oremuzumab, ofatumumab, omalizumab, oprelleukin, palivizumab, panitumumab, pembrolizumab, pertuzumab, pexelizumab, ranibizumab, rituximab, rituximab, romiplostim, lomosozumab, sargramostim, tocilizumab, tositumomab, trastuzumab, ustekinumab, vedolizumab, visilizumab, volocizumab, zalumab, and zalutumumab, and biosimilars of any of the foregoing.

[0080] Some figures described herein show example block diagrams with one or more functional components. It will be understood that such block diagrams are for illustrative purposes, and the described and illustrated devices may have additional, fewer, or alternative components than those shown. Additionally, in various aspects, components (and the functions provided by the corresponding components) may be associated with or otherwise integrated as a part of any suitable component.

[0081] Some aspects of the present disclosure relate to non-transitory computer-readable storage media having thereon instructions / computer-readable storage media for performing various computer-implemented operations. The term "instructions / computer-readable storage media" is used herein to include any medium capable of storing or encoding a series of instructions or computer code for performing the operations, methods, and techniques described herein. The media and computer code may be media and computer code specifically designed and constructed for the purposes of various aspects of the present disclosure, or the media and computer code may be of a type known and available to those skilled in the art of computer software. Examples of computer-readable storage media include, but are not limited to: magnetic media, such as hard disks, floppy disks, and magnetic tapes; optical media, such as CD-ROMs and holographic devices; magneto-optical media, such as optical disks; and hardware devices specifically configured to store and execute program code, such as ASICs, programmable logic devices ("PLDs"), and ROM and RAM devices.

[0082] The example of computer code includes machine code such as produced by a compiler, and files containing higher-level codes executed by a computer using an interpreter or compiler. For example, Java, C++ or other object-oriented programming languages ​​and development tools can be used to implement aspects of the present disclosure. Additional examples of computer code include encrypted codes and compressed codes. In addition, aspects of the present disclosure can be downloaded as a computer program product, which can be transmitted to a requesting computer (for example, a computer or different server computers) from a remote computer (for example, a server computer) via a transmission channel. Another aspect of the present disclosure can be implemented by replacing machine executable software instructions with hard-wired circuitry or in combination with machine executable software instructions.

[0083] As used herein, unless the context clearly indicates otherwise, the singular terms "a", "an" and "the" may include plural references. Unless otherwise expressly stated or clearly intended, this specification and subsequent claims should be understood to include one or at least one, and the singular also includes the plural. As used herein, the terms "comprise", "include", "have" or any other variation thereof are intended to cover non-exclusive inclusions. For example, a process, method, article or device comprising a series of elements is not necessarily limited to those elements, but may include other elements that are not explicitly listed or inherent to such processes, methods, articles or devices. In addition, unless expressly stated to the contrary, "or" refers to an inclusive or rather than an exclusive or. For example, conditions A or B satisfy any of the following: A is true (or exists) and B is false (or does not exist), A is false (or does not exist) and B is true (or exists), and both A and B are true (or exist).

[0084] As used herein, the terms "approximately," "substantially," "substantially," "roughly," and "about" are used to describe and explain small variations. When used in conjunction with an event or situation, these terms may refer to situations where the event or situation happens to occur as well as situations where the event or situation occurs approximately. For example, when used in conjunction with a numerical value, these terms may refer to a range of variation where the numerical value is less than or equal to ±10%, such as less than or equal to ±5%, less than or equal to ±4%, less than or equal to ±3%, less than or equal to ±2%, less than or equal to ±1%, less than or equal to ±0.5%, less than or equal to ±0.1%, or less than or equal to ±0.05%. For example, if the difference between the values ​​is less than or equal to ±10% of the average value of the values, such as less than or equal to ±5%, less than or equal to ±4%, less than or equal to ±3%, less than or equal to ±2%, less than or equal to ±1%, less than or equal to ±0.5%, less than or equal to ±0.1%, or less than or equal to ±0.05%, then two numerical values ​​may be considered to be "substantially" the same.

[0085] In addition, quantities, ratios, and other numerical values ​​are sometimes presented in a range format herein. It should be understood that this range format is used for convenience and brevity, and should be flexibly interpreted to include the values ​​explicitly specified as the limits of the range, but also include all individual values ​​and subranges contained within the range, just as if each value or subrange was explicitly specified.

[0086] Although the technology disclosed herein has been described primarily with specific operations performed in a specific order, it should be understood that these operations can be combined, subdivided, or reordered to form equivalent technologies without departing from the teachings of the present disclosure. Therefore, unless specifically indicated herein, the order and grouping of operations are not limitations of the present disclosure.

Claims

1. A method for evaluating the impact of processing time of a process, the method comprising: Obtaining, by one or more processors, a model trained using historical process data, the historical process data comprising (i) historical processing times for a plurality of instances of the process and (ii) corresponding historical product qualities of products produced by the plurality of instances of the process; applying, by the one or more processors, an input to the model to determine a predicted output that will be produced when the process is operated according to the input, wherein: (i) the input comprises a processing time and the predicted output comprises a predicted product quality parameter, or (ii) the input comprises a product quality parameter and the predicted output comprises a predicted processing time; as well as The predicted output is displayed or stored by the one or more processors.

2. The method of claim 1, further comprising: The input is received by the one or more processors from a user as user input.

3. The method according to any one of the preceding claims, further comprising: The prediction output is presented to a user by the one or more processors via a graphical user interface.

4. A method as claimed in any one of the preceding claims, wherein One or both of the processing time or the predicted processing time each corresponds to one or both of: (i) the elapsed time of at least one step of the process, or (ii) the elapsed time between at least two steps of the process.

5. A method as claimed in any one of the preceding claims, wherein: One or both of the processing time or the predicted processing time each corresponds to one or both of: (i) a delay time of at least one step of the process, or (ii) a delay time between at least two steps of the process.

6. A method as claimed in any one of the preceding claims, wherein: The model is a linear regression model.

7. A method as claimed in any one of the preceding claims, wherein: The process is a biological process.

8. The method of claim 7, wherein: The bioprocess is a chromatographic process.

9. A method as claimed in any one of the preceding claims, wherein: The product is either or both a drug or a therapeutic and includes one or more of the following: a protein, a carbohydrate, a lipid, or a nucleic acid.

10. A method as claimed in any one of the preceding claims, wherein: One or both of the product quality parameter or the predicted product quality parameter are each a measure of one or more of: yield, viable cell density (VCD), titer, concentration, or a measure of how far a parameter of a new instance of a product is from a specification limit.

11. A method as claimed in any one of the preceding claims, wherein: The process has a negative correlation between a given processing time and a given product quality.

12. A system comprising: one or more processors; as well as One or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to: obtaining a model trained using historical process data, the historical process data comprising (i) historical processing times for a plurality of instances of the process and (ii) corresponding historical product quality parameters of products produced by the plurality of instances of the process; By applying an input to the model, determining the predicted output that will be produced when the process is operated according to the input, wherein: (i) the input comprises a processing time and the predicted output comprises a predicted product quality parameter, or (ii) the input comprises a product quality parameter and the predicted output comprises a predicted processing time; as well as Display or store the predicted output.

13. The system of claim 12, wherein: The instructions further cause the one or more processors to: The input is received from the user as user input.

14. The system of claim 12 or 13, wherein: The instructions further cause the one or more processors to: The prediction output is presented to a user via a graphical user interface.

15. The system of any one of claims 12 to 14, wherein: One or both of the processing time or the predicted processing time each corresponds to one or both of: (i) the elapsed time of at least one step of the process, or (ii) the elapsed time between at least two steps of the process.

16. The system of any one of claims 12 to 15, wherein: One or both of the processing time or the predicted processing time each corresponds to one or both of: (i) a delay time of at least one step of the process, or (ii) a delay time between at least two steps of the process.

17. The system of any one of claims 12 to 16, wherein: The model is a linear regression model.

18. The system of any one of claims 12 to 17, wherein: The process is a chromatographic process.

19. The system of any one of claims 12 to 18, wherein: The product is either or both a drug or a therapeutic and includes one or more of the following: a protein, a carbohydrate, a lipid, or a nucleic acid.

20. The system of any one of claims 12 to 19, wherein: One or both of the product quality parameter or the predicted product quality parameter are each a measure of one or more of: yield, viable cell density (VCD), titer, concentration, or a measure of how far a parameter of a new instance of a product is from a specification limit.

21. A method for determining the availability of a product that has experienced an unexpected delay during purification, the method comprising: purifying the product by one or more process operations; experiencing unexpected delays during process operations; obtain a sample of the product after the unplanned delay; The sample is subjected to a model trained using historical process data, the historical process data comprising: (i) the historical processing times for multiple instances of the process, and (ii) the corresponding historical product quality of the products produced by the plurality of instances of the process; Determine the predicted output that will be produced when the process is operated on the input, where: (i) the input includes a processing time, and the predicted output includes a predicted product quality parameter, or (ii) the input comprises a product quality parameter and the prediction output comprises a predicted processing time; and Use this forecast output to determine the availability of products produced under delay conditions.

22. The method of claim 21, wherein: The process operations include one or more of harvesting, chromatography, filtration, viral inactivation, viral filtration, concentration and / or formulation.

23. The method of claim 21 or 22, wherein: The availability is based on the predicted product quality of the product produced under these delay conditions.

24. The method of claim 23, further comprising reducing the amount of product produced that does not meet product quality parameters.

Images