Predictive models for assessing the impact of processing time

Abstract

Systems and methods for assessing the impact of processing time on a process (such as a bioprocess) may include: (a) obtaining a model trained using historical bioprocess data; (b) applying inputs to the model to determine predicted outputs that would occur when operating the bioprocess according to the inputs, where either (i) the inputs include processing time and the predicted outputs include product quality, or (ii) the inputs include product quality parameters and the predicted outputs include processing time; and (c) displaying or storing the values ​​of the predicted outputs. Further aspects include receiving the inputs as user inputs from a user. Yet further aspects include presenting the predicted outputs to a user via a graphical user interface.

Description

[Technical Field]

[0001] This application relates generally to the use of predictive models to assess the impact of processing time, including processing time delays, on product quality. [Background technology]

[0002] Biomolecules, such as proteins, peptides, and nucleic acids, are widely used as treatments for several diseases and play an important role in drug discovery. Typically, during the manufacturing of products containing biomolecules, the product is exposed to processes with unacceptable chemical conditions that can compromise product stability. These processes can include pool conditioning processes and viral inactivation and clarification processes that require exposing the product to large changes in pool pH, conductivity, and / or temperature that are unfavorable to the biomolecule (e.g., reduce the stability of the biomolecule). Therefore, the product quality of biomolecules produced using these types of processes can be affected by the length of time required to perform these processes. Furthermore, any operational delays that increase processing time during these processes mean that the product is exposed to these unacceptable chemical conditions, which can adversely affect product quality.

[0003] One bioprocess in which processing time can affect the product quality of a corresponding biomolecule is chromatography. Chromatography can be used to purify biomolecules by separating them from compounds using one or more separation steps based on specific physical, chemical, or biological characteristics of the compounds and biomolecules. For example, the size, charge, hydrophobicity, functionality, or content of a given biomolecule can be used to isolate a given biomolecule. For commercial production purification, chromatography is typically performed as column chromatography due to scale considerations. An example of a conventional column chromatography process 200 is shown in FIG. 2. As shown in process 200, a loaded sample is first injected into the column. A mobile phase (eluent) is then pumped through the column, causing the molecules of the loaded sample to separate based on their relative affinity for the stationary phase (immobilized resin) and the mobile phase. Molecules of the loaded sample that are more strongly attracted to the stationary phase will migrate more slowly through the system compared to molecules that are less strongly attracted to the mobile phase. Different molecules elute from the column at different times, allowing the therapeutic protein to be separated from other substances that elute from the column at different times after different volumes of mobile phase have been passed through the column.

[0004] Other common types of chromatography include hydrophobic interaction chromatography, affinity chromatography, or protein A chromatography. Further types of chromatography include ion exchange chromatography (IEX), such as anion exchange chromatography (AEX) and cation exchange chromatography (CEX), hydrophobic interaction chromatography (HIC), mixed-mode or multimodal chromatography (MM), hydroxyapatite chromatography (HA), or reversed-phase chromatography. Other chromatographic methods include expanded adsorption fluidized bed chromatography, simulated moving bed chromatography, countercurrent chromatography (CCC), hydrodynamic countercurrent chromatography, or cyclic 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] Traditionally, when performing chromatography to purify biomolecules, the chromatographic parameters (e.g., elution buffer pH, elution buffer conductivity, elution buffer molarity, gradient, linear velocity, load and collection times) and how the purification operation will be performed for a particular product / molecule (e.g., with a particular solution, at a particular pH, etc.) are carefully determined. However, traditional chromatographic processes (and other types of bioprocesses) traditionally do not account for unexpected changes in processing time due to delays (e.g., due to equipment malfunctions).

[0006] Furthermore, optimal processing times can vary between manufacturing operations and therefore can be difficult to predict. Failure to account for unexpected delays or process-specific variations in optimal processing times when producing biomolecules can result in a high percentage of produced biomolecules failing strict quality control measures regarding product quality that may be imposed by regulatory agencies, such as government agencies (e.g., the Food and Drug Administration), and to which biomolecules must adhere. If a biomolecule does not meet product quality specification limits, the biomolecule may be unusable. Furthermore, because the relationship between processing time and product quality is typically specific to individual manufacturing operations, failure to account for processing time variations can also reduce the transferability of biomolecule production between different bioprocessing systems.

[0007] Thus, traditional processes for producing molecules (e.g., chromatography) increase the likelihood that the biomolecule will not meet regulatory limits. Increased failure or rejection rates can, in turn, correspond to increased costs in terms of time, labor, and other resources. Summary of the Invention [Means for solving the problem]

[0008] An aspect of the present disclosure is a method for assessing the impact of processing time of a process (e.g., a bioprocess), comprising: (a) obtaining a model trained using historical bioprocess data, the historical bioprocess data including (i) historical processing times of multiple instances of the bioprocess and (ii) corresponding historical product qualities of products produced by the multiple instances of the bioprocess; (b) applying inputs to the model to determine predicted outputs that would occur when operating the bioprocess according to the inputs, where either (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; and (c) displaying or storing the predicted outputs.

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

[0010] In some embodiments, the processing time corresponds to one or both of (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 embodiments, the processing time corresponds to one or both of (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 embodiments, the model is a linear regression model. In some embodiments, the bioprocess is a chromatography process. In some embodiments, the product is one or both of a drug or a therapy and comprises one or more of a protein, a carbohydrate, a lipid, or a nucleic acid.

[0012] In some embodiments, the predicted product quality parameter is one or more of the following measures: yield, viable cell density (VCD), titer, concentration, or a measure of distance to a specification limit of a parameter of a new instance of a product. In some embodiments, 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 that includes: (a) one or more processors; and (b) one or more non-transitory computer-readable media that store instructions that, when executed by the one or more processors, cause the one or more processors to perform a method of any one of the preceding aspects.

[0014] Those skilled in the art will understand that the figures described herein are included for illustrative purposes and are not intended to limit the present disclosure. The figures are not necessarily to scale, emphasis instead being placed on illustrating the principles of the present disclosure. It should be understood that in some instances, various aspects of the described implementations may be shown exaggerated or enlarged to facilitate understanding of the described implementations. In the figures, like primary characters generally refer to functionally similar or structurally similar components. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 is a simplified block diagram of an example system for assessing the impact of processing time on a process (e.g., a bioprocess). [Figure 2] An example of a conventional column chromatography process is shown below. [Figure 3] An example process is shown in which a model is applied to a bioprocess manufacturing operation to predict product quality parameters based on observed process delays. [Figure 4A] 1 illustrates an example graphical display showing exemplary historical bioprocess data. [Figure 4B] 1 illustrates an example graphical display showing an exemplary input interface. [Figure 4C] 1 illustrates an example graphical display showing exemplary experimental performance data. [Figure 5A] FIG. 1 is a flow diagram illustrating an example method for evaluating the impact of processing time of a process (e.g., a bioprocess). [Figure 5B] FIG. 1 is a flow diagram illustrating an example method for evaluating the impact of processing time of a process (e.g., a bioprocess). DETAILED DESCRIPTION OF THE INVENTION

[0016] As the pace of biotechnology advances, there is an increasing emphasis on processing additional molecules in bioprocessing pipelines, thus increasing the need to design and implement manufacturing processes, such as chromatography purification processes, more quickly. The present disclosure aims to reduce the problems of conventional techniques (e.g., as described in the Background section) by providing techniques for assessing the impact of processing time of a process (e.g., a bioprocess). The present technique may 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 time, respectively. By determining and then displaying or storing values ​​of predicted processing time or predicted product quality, the present technique aims to provide insight to operators of a bioprocessing system, reduce the amount of biomolecules produced that do not meet quality requirements, and increase the transferability of biomolecule production between different bioprocessing systems.

[0017] Advantageously, by providing improved insight, the present techniques may provide insight into the impact of processing time (e.g., lag time) when designing a bioprocess or bioprocessing system for producing a biomolecule. One benefit of these insights is that fewer resources (e.g., biomolecules) are wasted while calibrating the bioprocessing system, thus increasing resource efficiency and improving the sustainability of the bioprocessing system. Making the bioprocessing system more sustainable in terms of resource use may also improve the energy efficiency of the bioprocessing system, reducing the capital or economic cost of producing each biomolecule. Another benefit of improved insight is that more biomolecules may be produced in a given time with shorter calibration times, thereby increasing production throughput. Furthermore, because the present techniques provide insight into the utility (e.g., based on product quality) of biomolecules produced under lag conditions, resource, energy, and cost efficiencies may also be improved when dealing with unexpected lags in a bioprocess.

[0018] Additional advantages of the present technique over conventional methods of operating a bioprocess will be recognized by those skilled in the art through this disclosure. The various concepts and techniques introduced above and discussed in more detail below may be implemented in any of many ways, and the concepts described above are not limited to any particular implementation method. Example implementations are provided below for illustrative purposes.

[0019] Exemplary System FIG. 1 is a simplified block diagram of an example system 100 for assessing the impact of processing time on one or more bioprocessing systems 150 for producing biomolecules that may be included in a drug product. In some embodiments, the system 100 may comprise a standalone device, while in other examples, the system 100 may be incorporated into other devices. At a high level, the system 100 includes the following components: a computing device 110, a bioprocessing system 150, one or more product quality sensors 160, and one or more historical bioprocessing data sources 170. In FIG. 1, the computing device 110, the bioprocessing system 150, and the historical bioprocessing data sources 170 are communicatively coupled via a network 180, which may be or include a proprietary network, the secure public Internet, a virtual private network, or any other type of suitable wired and / or wireless network (e.g., a dedicated access line, a satellite link, a cellular data network, a combination thereof, etc.). In embodiments in which the network 180 comprises the Internet, data communications may occur over the network 180 using Internet communications protocols. In some embodiments, more or fewer instances of the various components of system 100 may be included in system 100 than are shown in FIG. 1 (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.).

[0020] It is worth noting that while system 100 is shown as including bioprocessing system 150, one skilled in the art would understand that the techniques and components of system 100 may be applied to assessing the impact of processing time (e.g., lag time) in other processes. For example, instead of bioprocessing system 150, the techniques and components of system 100 may be applied to the manufacture of small molecule drug products.

[0021] The bioprocessing system 150 may be a single bioprocessing system or may include multiple bioprocessing systems, co-located or separate, suitable for the production of biomolecules. Biomolecules can be carbohydrates, lipids, nucleic acids, or proteins produced by cells and organisms. Biomolecules come in a wide range of sizes and structures and perform many functions. A bioprocess that can produce a given biomolecule may isolate the biomolecule from the cells that produced it through processes that include one (and often more than one) of filtration, extraction, crystallization, membranes, and chromatography. The bioprocessing system 150 generally may include physical devices configured for use in the production (e.g., manufacturing) of biomolecules.

[0022] The bioprocessing system 150, in some embodiments, may be connected to the computing device 110 via a network 180 or directly, such that at least a portion of the functionality of the bioprocessing system 150 may be controlled by the computing device 110. In some embodiments, the bioprocessing system 150 may be capable of receiving instructions directly from a user (e.g., the bioprocessing system 150 may be manually configurable). For example, in some embodiments, the bioprocessing system 150 may receive instructions directly from a user that control its operation (e.g., one or more steps of a chromatography process of the bioprocessing system 150 may be configured to operate according to input from a user).

[0023] The product quality sensor 160 may be included in the bioprocessing system 150 (e.g., integrated into the bioprocessing system 150) or may be an external sensor connected to the bioprocessing 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 bioprocessing system 150. The product quality parameter may be the purity of the output of the bioprocessing system 150, which may be measured as a peak or peak purity (e.g., a main peak CEX). The product quality sensor 160 may provide the product quality parameter data, for example, to the computing device 110 (e.g., via the network 180). The product quality parameter data may be any suitable type of data, such as nominal data, ordinal data, discrete data, or continuous data. The product quality parameter data may be in the form of a suitable data structure and may be stored in a suitable format, such as one or more of 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 computing device 110 may desire to evaluate the impact of processing time on a bioprocess using bioprocess system 150. In response, one or more of product quality sensors 160 may collect and provide product quality parameter data to computing device 110. In some embodiments, one or more of product quality sensors 160 may include a database of data / information regarding product quality or may be configured to receive data / information regarding product quality, such as via user input.

[0024] The bioprocessing system 150 can include one or more devices (not shown) used in chromatography (e.g., one or more of the types of chromatography discussed in the background section). For example, the bioprocessing system 150 can include one or more of the following: columns, capillary tubes, plates, sheets, frits, flow cells, pumps, vacuums, detectors, harvesters, collectors, injectors, etc. for performing chromatography. In other embodiments, the bioprocessing system also or instead includes other equipment, such as a bioreactor, outlet filters, etc.

[0025] The bioprocessing system 150 may be configured to be controllable by manual or automatic input. In some embodiments, the bioprocessing system 150 may be configured to receive such control input locally, such as via a local user input device of the bioprocessing system 150. In some embodiments, the bioprocessing system 150 is configured to receive control input remotely, such as from the computing device 110 (e.g., via the network 180). The control input may include operating instructions, such as processing times according to which the bioprocessing system 150 should operate.

[0026] The historical bioprocess data source 170 generally includes historical bioprocess data that may correspond to one or more bioprocesses for producing one or more biomolecules using the bioprocess system 150. The historical product information may include (i) historical processing times for multiple instances of the bioprocess and (ii) corresponding historical product qualities for the products produced by those instances of the bioprocess. In some embodiments or scenarios, at least some of the historical bioprocess data is collected using the bioprocess system 150. However, in some embodiments or scenarios, all of the historical bioprocess data is collected using a different bioprocess system. The historical bioprocess data may include data from a bioprocess having a similar scale / size, settings / parameters, equipment model, etc. to the bioprocess system 150 and / or data from a bioprocess having a different scale / size, settings / parameters, equipment model, etc. from the bioprocess system 150. In some embodiments, the system 100 may omit the historical bioprocess data source 170 and instead receive the historical bioprocess data locally, such as via user input at the computing device 110.

[0027] The computing device 110 may include a single computing device or multiple computing devices collocated 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 occur when operating the bioprocess according to the inputs, where either (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 are described in more detail below.

[0028] Processing unit 120 includes one or more processors, each of which may be a programmable microprocessor that executes software instructions stored in memory 128 to perform some or all of the functions of computing device 110 described herein. Alternatively, one or more processors in processing unit 120 may be other types of processors (e.g., application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), etc.).

[0029] The network interface 122 may include any suitable hardware (e.g., front-end transceiver hardware), firmware, or software configured to communicate with external devices or systems (e.g., product quality sensor 160, bioprocess system 150, historical bioprocess data source 170, etc.) over the network 180 using one or more communication protocols. For example, the network interface 122 may be or include an Ethernet interface.

[0030] Display 124 may present information to a user using any suitable display technology (e.g., LED, OLED, LCD, etc.), and user input device 126 may be a keyboard or other suitable input device. In some aspects, display 124 and user input device 126 are integrated into a single device (e.g., a touchscreen display). In general, display 124 and 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 computing device 110 (e.g., for purposes such as displaying data / information such as product quality parameters or processing times, or notifying a user of equipment failures or other malfunctions).

[0031] Memory 128 may include one or more physical memory devices or units, including volatile or non-volatile memory, and may or may not include memory located on different computing devices of computing device 110. One or more suitable memory types, such as read-only memory (ROM), solid-state drive (SSD), or hard disk drive (HDD), may be used. Memory 128 may store instructions for one or more software applications, including (i) model 130 and (ii) processing time evaluation (PTE) application 140, which may be executed by processing unit 120. In the example system 100, PTE application 140 includes a data collection unit 142, a modeling unit 144, a user interface unit 146, and a data storage unit 148. Units 142-148 may be separate software components or modules of PTE application 140, or may simply represent functionality of PTE application 140 that is not necessarily separated into different components / modules. For example, in some embodiments, data collection unit 142 and user interface unit 146 are included in a single software module. Further, in some embodiments, units 142-148 are distributed among multiple copies of PTE application 140 (e.g., running on different components within computing device 110) or among different types of applications stored and running on one or more devices of computing device 110.

[0032] Model 130 may be any suitable model for assessing the impact of processing time on a process (e.g., a bioprocess). In some embodiments, and as described further below, model 130 may be trained using at least some of the system 100, or in some embodiments, model 130 may be pre-trained (i.e., trained before being acquired by system 100). Model 130 may be trained using historical bioprocess data, including (i) historical processing times of multiple instances of the bioprocess and (ii) corresponding historical product qualities of products produced by the multiple instances of the bioprocess. In some embodiments, model 130 may include a statistical model, which may be parametric, non-parametric, or semi-parametric. One suitable example of a statistical model that may be included in model 130 is a linear regression model. In other embodiments, model 130 includes a machine learning model. For example, model 130 may 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 that use 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 may identify and recognize patterns in training data to facilitate making predictions for new data.

[0033] The data collection unit 142 is generally configured to receive data. In some embodiments, the data collection unit 142 receives historical bioprocess data of a bioprocess for producing a biomolecule (e.g., including historical processing times of 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, for example, via historical bioprocess data sources 170, user input received via the user interface unit 146 by the user input device 126, or other suitable means. In some embodiments, the data collection unit 142 may receive one or more values ​​of product quality parameters, for example, via the product quality sensor 160, user input received via the user interface unit 146 by the 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 started, for example, at the data collection unit 142, and one or more components of the computing device 110 may locally monitor the processing time.

[0034] The modeling unit 144 is generally configured to generate, train, or apply the model 130. The modeling unit 144 may train the model 130 using historical bioprocess data, which may be received from the historical bioprocess data source 170. The modeling unit 144 may also apply the model 130 when evaluating the impact of processing time of a process (e.g., a bioprocess). More specifically, the modeling unit 144 may apply inputs to the model 130 to determine predicted outputs that will occur when operating the bioprocess according to the inputs, where either (i) the inputs include processing time and the predicted outputs include product quality, or (ii) the inputs include product quality parameters and the predicted outputs include processing time. In some embodiments, the model 130 may be trained by a device or system external to the system 100, and the modeling unit 144 instead applies only inputs to the model 130 and is not involved in training the model 130.

[0035] The user interface unit 146 is generally configured to receive user input. In one example, the user interface unit 146 generates a user interface for presentation via the display 124 and may receive, via the user interface and user input device 126, user input of historical bioprocess data used by the modeling unit 144 when training the model 130. In another example, the user interface unit 146 may receive, via the user interface and user input device 126, input (e.g., processing times for stages of a bioprocess or one or more desired product quality parameters of a product produced by the bioprocess) used by the modeling unit 144 when applying the model 130. The user interface unit 146 may also be used to display information. For example, the user interface unit 146 may be used to display predicted outputs (e.g., processing times for stages of a bioprocess or one or more desired product quality parameters of a product produced by the bioprocess).

[0036] The data storage unit 148 is generally configured to store the predicted outputs (e.g., processing times or product quality parameters) determined by the modeling unit 144. The data storage unit 148 may store the predicted outputs in memory 128 or a different suitable memory (e.g., an external database or computer system, not shown). In some embodiments, the data storage unit 148 also stores other information, such as model inputs that correspond to the predicted model outputs.

[0037] The operation of each unit 142-148 is described in further detail below with reference to the operation of system 100.

[0038] Exemplary Bioprocess Manufacturing Operating Process 3 illustrates an example process 300 for applying a model to bioprocess manufacturing operations to predict product quality parameters based on observed process delays. As shown, process 300 includes manufacturing operations at stage 310, process monitoring and technical support at stage 320, and predictive modeling at stage 330. Process 300 may be performed using the same or similar equipment / devices as described above in connection with system 100. For example, computing device 110 may perform at least some of process 300 (e.g., using data collected from bioprocessing system 150).

[0039] In one exemplary embodiment, manufacturing operations in stage 310 of process 300 begin at substage 310A, where the bioprocess is in normal process operation. The bioprocess may operate according to parameters previously determined, either empirically or through modeling, to produce biomolecules manufactured in accordance with quality control standards. Assuming no process delays are observed in substage 310B (e.g., by a bioprocess operator or in an automated manner, such as using the computing device 110 with data collection unit 142), normal process operation may continue in substage 310C until the entire amount of biomolecules meeting quality control standards is produced, and the entire process remains in manufacturing operations stage 310. However, if a process delay (e.g., due to either preventable or unavoidable causes) is observed in substage 310B (e.g., by a bioprocess operator or in an automated manner, such as using the computing device 110 with data collection unit 142), process 300 may transition to process monitoring and technical support stage 320.

[0040] Stage 320 may include bioprocess monitoring and technical support, for example, using computing device 110 to manage the resolution of potential problems in the bioprocess. In some embodiments, stage 320 begins with substage 320A, in which an observed process delay is evaluated according to the standard operating procedure for the bioprocess. As previously discussed, certain process steps in a bioprocess may require exposing the biomolecule being produced to chemical conditions that may reduce its stability. For example, pool conditioning process steps, viral inactivation, and clarification process steps require exposing the product to large changes in pool pH, conductivity, or temperature that are unfavorable to the biomolecule. Therefore, for these process steps, a negative correlation may exist between the duration of the process step and product quality parameters of the biomolecule being produced. In substage 320A, the standard operating procedure may be consulted (e.g., by an operator or computing system 110) to determine whether the observed process delay occurs during a process step where the delay is detrimental to biomolecule product quality. If not, process 300 returns to stage 310 to continue normal operation of the bioprocess. However, if the observed process delay corresponds to a process step where the delay is detrimental to biomolecule product quality, process 300 continues to sub-stage 320C to assess the extent of the impact on product quality using a model (e.g., model 130 applied by modeling unit 144). Operation of sub-stage 320C requires the process to proceed to stage 330.

[0041] Stage 330 may include running the trained model (e.g., model 130) to determine predicted product quality parameters based on observed process delays. In some embodiments, stage 330 may begin with substage 330A, which obtains a processing time for the duration of a process step (e.g., a total processing time including a current or expected delay). As previously described, the process step may have a negative correlation between the duration of the process step and a product quality parameter of a biomolecule produced by the bioprocess. Thus, an observed delay in the bioprocess may potentially cause a significant degradation of the product quality parameter of the biomolecule. In substage 330B, the model (e.g., model 130 used by modeling unit 144) receives the processing time as an input and estimates the product quality parameter of the biomolecule. In substage 330C, the product quality parameter may be displayed (e.g., via a graphical user interface presented by user interface unit 146 on display 124). Once the product quality parameters are displayed in sub-stage 330C, process 300 may return to process monitoring and technical support stage 320.

[0042] Returning to stage 320, in sub-stage 320D, it is determined whether the product quality parameter displayed in sub-stage 330C corresponds to a “significant” degradation in product quality. In some embodiments, an operator may make the determination in sub-stage 330D. In other embodiments, a computer system (e.g., computing device 110) makes the determination. The determination of whether the degradation of the product quality parameter is “significant” may be based on specific guidelines or rules. For example, specification limits, which may be set by a manufacturer or regulatory agency, may be used to determine whether the degradation of the product quality parameter is “significant.” In another example, a threshold value (e.g., when the product quality parameter has decreased by a certain percentage) may be used to determine whether the degradation of the product quality parameter is significant. If the degradation of the product quality parameter of the biomolecule with the observed process delay is not determined to be significant, process 300 returns to stage 310 and continues normal operation of the bioprocess. However, if the degradation of the product quality parameter of the biomolecule with the observed process delay is determined to be significant, process 300 continues to sub-stage 320E to determine mitigation strategies to be used in subsequent process operations.

[0043] In some embodiments, an example of a mitigation used in subsequent process operations of sub-stage 320E may include modifying the processing time of one or more steps of the bioprocess. For example, a model (e.g., model 130 used by modeling unit 144) may be "run in reverse" of how the model is used in stage 330. Specifically, the model may receive acceptable product quality parameters (e.g., product quality parameters within specification limits) as inputs so that the processing time of one or more steps of the bioprocess can be predicted to achieve acceptable product quality. In some embodiments, parameters of the bioprocess other than processing time may be adjusted. For example, if chromatography is the bioprocess, parameters such as elution buffer pH, elution buffer conductivity, elution buffer molarity, gradient, linear velocity, load, and harvest time may be mitigations to adjust the bioprocess to meet quality control. In some embodiments, subsequent process steps are adjusted to attempt to correct for the delayed biomolecule. For example, if the viable cell density of the biomolecule is too low as a result of the delay, the amount of nutrients in a later process step may be increased 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 a mitigation strategy exists and is implementable, process 300 can proceed to substage 320F, which uses the mitigation strategy to continue processing operations of the bioprocess, and then to substage 310D, which delivers a biomolecule that meets quality control.

[0044] Example Graphic Display 4A-C illustrate example graphical interfaces 400A-C that may be generated by the user interface unit 146 of FIG. 1. As shown, interface 400A includes an example graphical representation of historical bioprocess data for a bioprocess, including (i) historical processing times for instances of the bioprocess and (ii) corresponding historical product qualities for products produced by the instances of the bioprocess. As shown, interface 400B includes an example user interface for estimating output product quality parameters for biomolecules produced by the bioprocess based on input processing times. As shown, interface 400C includes an example graphical representation comparing actual product quality and predicted product quality for a bioprocess for several different processing times.

[0045] The user interface unit 146 can present the views 400A-C on the display 124 in a single screen or multiple screens and can receive input (e.g., input processing time, indication of file location 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. The historical bioprocess data represented in the interface 400A can, in some embodiments, be provided by a historical bioprocess data source, such as the historical bioprocess data source 170. The modeling unit 144 can use the model 130 to estimate the output product quality parameters represented in the interface 400B. The actual product quality parameters represented in the interface 400C can be determined using a product quality sensor, such as the product quality sensor 160 of the bioprocess system 150. The modeling unit 144 can use the model 130 to predict the product quality represented in the interface 400C.

[0046] The historical bioprocess data in interface 400A can be filtered or modified based on different inputs, outputs, batch numbers, and production dates, which can be selected via user input. As shown, the product quality of the historical bioprocess data is measured as pre-peak SE, and the processing time of the historical bioprocess data is measured as the number of hours of cystamine exposure. In certain bioprocesses, biomolecules may be exposed to the organic disulfide, cystamine. Cystamine is known to be an unstable liquid and has certain toxicity, and in some bioprocesses, increased exposure time of biomolecules to cystamine can be detrimental to the product quality parameters of the biomolecule. Therefore, it can be useful to evaluate the impact of cystamine exposure time on the pre-peak SE of a biomolecule. Pre-peak SE is a measure of product quality that can be used in size exclusion (SE) chromatography. A higher pre-peak SE score may indicate a purer biomolecule and therefore a biomolecule with higher product quality.

[0047] The input processing time may be input (e.g., by a user) as several different processing times via user interface 400B. As shown, the input processing time is a Butyl FF pH adjustment time of 2.64 h. 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. The input processing time is Butyl FF pH adjustment time in hours, and the output product quality parameter is Main Peak CEX in percent, although other possible units of input processing time may be used, and other possible units of output product quality parameter may be used. It is also worth noting that in some embodiments, the input may be the input product quality parameter, and the output may be the output processing time. In some embodiments, if an output target (e.g., specification limits, warning limits, etc.) is provided, interface 400B may indicate to the user whether the output product quality parameter or the output processing time is within the output target. As shown, interface 400B also includes a time conversion and date difference calculation tool to assist the user in determining the number of hours of the input processing time as a decimal. In some embodiments, the determined number of hours may be entered as the input processing time for the model automatically or in response to a user selecting either the "Set as Input" button as shown.

[0048] Interface 400C compares the actual and predicted product quality (measured by the main peak CEX) for each batch of historical bioprocess data from interface 400A based on the processing time (measured by cystamine use time) of each batch. As shown, the predicted product quality is determined using a generalized linear regression model. Exemplary experimental performance data from interface 400C has an R-squared value of greater than 0.95, a root mean square error of about 0.058, and a mean absolute error of about 0.050. Thus, the exemplary performance data demonstrates the effectiveness of the present technique in developing models for assessing the impact of processing time in a process (e.g., a bioprocess) because the predicted product quality parameters closely track the actual product quality.

[0049] Exemplary Flow Diagram 5A and 5B are flow diagrams illustrating example methods 500A and 500B, respectively, for assessing the impact of processing time on a process (e.g., a bioprocess). Method 500A or 500B may be performed by one or more components of system 100, such as processing unit 120, when also implementing PTE application 140 and, optionally, bioprocessing system 150 (which may operate a bioprocess, such as column chromatography process 200). Method 500A or 500B may be performed as part of the same or similar process as process 300. Methods 500A and 500B may use historical bioprocess data (e.g., the historical bioprocess data represented by interface 400A), receive input processing times or input product qualities (e.g., via interface 400B), and display the input / output processing times or input / output product qualities using one or more graphical displays, which may be the same as or similar to the graphical displays of FIGS. 4A-4C.

[0050] An example method 500A may include the following elements: (1) obtaining a trained model using historical bioprocess data for a bioprocess (block 502A), (2) determining predicted product quality parameters that will occur when operating the bioprocess according to a processing time (block 504A), and (3) displaying or storing the predicted product quality parameters (block 506A).

[0051] The trained model obtained in block 502A may be 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 in block 502A includes receiving a pre-trained model (i.e., trained, for example, before being obtained by system 100) or generating / training a model (e.g., by system 100). The model may be obtained internally (e.g., by accessing files / programs / data / information stored locally on a computing system, such as computing device 110) or externally (e.g., by 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, for example, an indicator of purity (e.g., measured as a peak or peak purity, such as main peak CEX), yield, viable cell density (VCD), titer, concentration, etc., of the biomolecule produced by the bioprocess, or a measure of the difference between a product quality parameter and a specification limit. The processing time for past bioprocess data can be the duration of one or more steps of the bioprocess (e.g., including any delays) or one or more delays in the bioprocess (e.g., time that exceeds a desired amount of time).

[0052] Block 504A may include applying the processing time to a model to determine a predicted product quality parameter that will result when operating the bioprocess according to the processing time. The processing time may be input or provided by a user via a user interface (e.g., using user input device 126) or by collecting the processing time as data (e.g., via data collection unit 146). The predicted product quality parameter may be estimated by the model as either a single value or a range of possible values. In some embodiments, the model may determine whether the predicted product quality parameter satisfies one or more conditions (e.g., thresholds, tolerances, specification limits, warning limits, etc.). In some embodiments, the model may 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, a naive Bayesian analysis, clustering, or reinforcement learning, or another suitable machine learning model.

[0053] 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. Display of 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 may be stored in memory 128 of computing device 110, for example, using data storage unit 148.

[0054] Referring to example method 500B, method 500B may include the following elements: (1) obtaining a trained model using historical bioprocess data for the bioprocess (block 502B); (2) determining a predicted processing time that would occur when operating the bioprocess according to the product quality parameter, e.g., when operating the bioprocess to achieve a desired product quality parameter (block 504B); and (3) displaying or storing the predicted processing time (block 506B).

[0055] Block 502B may be the same as or similar to block 502A, and the model in 502B may be the same as or similar to the model in 502A. Block 504B may be the same as or similar to block 504A, except that instead of processing time serving as input to the model, product quality parameters serve as input to the model, and instead of the model predicting product quality, the model predicts processing time. Finally, block 506B may be the same as or similar to block 506A, but instead of displaying or storing predicted product quality, the predicted processing time is displayed or stored.

[0056] In some embodiments, methods 500A and 500B may be performed fully automatically, for example, by one or more processors (e.g., CPUs or GPUs) executing instructions stored in 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 programmable read-only memory) or one or more other types of memory. Methods 500A and 500B may use any one or more components, processes, and / or techniques of FIGS. 1-4.

[0057] Additional considerations The term "process operation" or "unit operation" refers to a functional step performed as part of a process to purify a recombinant protein of interest. For example, a process operation may include, but is not limited to, steps such as recovery of the product of interest, chromatography (capture and polishing), filtration, viral inactivation, viral filtration, concentration, and / or formulation.

[0058] The recovery operation clarifies and / or purifies the product from at least one impurity found therewith, such as residual cell culture medium, cells and / or cell debris, undesirable cell or medium components, and / or product and / or process-related impurities. Methods for recovery include, but are not limited to, acid precipitation, accelerated precipitation such as flocculation, gravity-assisted separation, centrifugation, acoustic wave separation, membrane filtration, filtration including ultrafilters, microfilters, tangential flow filters, alternative tangential flow filters, depth filters, and alluvial filters.

[0059] Chromatography operations utilize media that capture and / or polish the target product. Chromatography operations include single column systems, multi-column systems such as timed countercurrent and expanded bed chromatography systems, etc. Chromatography media include monoliths, resins, and / or membranes containing agents that bind and / or interact in some way with at least one desired product, impurity, or contaminant. Chromatographic media include those utilizing Staphylococcus 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), including cation exchange (CEX) and anion exchange (AEX) chromatography, hydrophobic interaction chromatography (HIC), multimodal or mixed modal (MMC), hydroxyapatite chromatography (HA), reversed-phase chromatography, and gel filtration, among others.Such media are known in the art and commercially available, and include, but are not limited to, MABSELECT™ SURE Protein A, Protein A Sepharose FAST FLOW™, MABSELECT™ Prism A (Cytiva, Marborough, MA), PROSEP-A™ (Merck Millipore, UK), TOYOPEARL™ HC-650F Protein A (TosoHass Co., Philadelphia, PA) and AP Plus (Purolite, King of Prussia, PA), Capto™ Adhere, Capto™ MMC Impress, Capto MMC (Cytiva), PPA Hypercel, MEP Hypercell, HEA Hypercell (Pall Corporation, Port Washington, NY), Eshmuno HCX (Merk Millipore), Toyopearl MX-Trp-650M (Tosoh Bioscience), Phenyl These include Sephrose™ (Cytiva), Tosoh Hexyl (Tosoh Bioscience) and Capto™ Phenyl (Cytiva), CA++Pure-HA, Tosho Bioscience, HA ULTROGEL®, Sartorius, and others.

[0060] Filtration operations are used to reduce and / or remove any resulting turbidity, sediment, impurities, and / or contaminants associated with the product. Filtration can include the use of depth filters, sterilizing and / or bioreducing control filters, ultrafilters, microfilters, tangential flow filters, alternative tangential flow filters, alluvial filters, and the like. Depth filters suitable for use in the present method are known in the art and commercially available. Such filters include, but are not limited to, cellulose, pretreated filtration matrix, synthetic fiber mesh, or combinations. In some embodiments, the filtration step is depth filtration or tangential flow filtration. Such filters are known in the art and commercially available, and include, but are not limited to, VIRESOLVE® Pro Shield, VIRESOLVE® Pro Shield H, MILLISTAK+® DOHC filters, MILLISTAK+® XOHC filters, MILLISTAK+® COHC filters, MILLISTAK+® COSP filters, MILLISTAK+® XOSP filters, Clarisolve 20MS filters, Clarisolve 40MS filters, Clarisolve 60HX filters (Millipore, Burlington, MA), SARTOCLEAR® DL60 filters, SARTOCLEAR® DL75 filters (Sartorius, Goettingen, Germany), 3M™ Zeta Plus™ filters, diatomaceous earth, 3M™ Emphaze™ AEX Hybrid Purifiers (EM, Meriden, CT), etc. Sterile and / or bioreducing control filtration. Such filters are known in the art and commercially available, including, but not limited to, Millipore EXPRESS SHC hydrophilic polyethersulfone filters (Millipore) and SARTOPORE® 2 polyethersulfone (PES) liquid filters (Sartorius).

[0061] Process operations directed at inactivating, reducing, and / or eliminating viral contaminants may include operations that mitigate viral risk by manipulating the environment and / or using filtration. Viruses are classified as enveloped and non-enveloped viruses. For enveloped viruses, the envelope allows the virus to identify, bind, invade, and infect target host cells. Therefore, enveloped viruses are more susceptible to inactivation methods. Various methods can be employed to inactivate viruses, including heat inactivation / pasteurization, UV and gamma irradiation, the use of high-intensity broad-spectrum white light, chemical inactivators, the addition of surfactants, and solvent / detergent treatments. Surfactants, such as detergents, can be very effective at specifically inactivating enveloped viruses because they solubilize membranes. Non-enveloped viruses are more difficult to inactivate without risk to the purified product and are removed by filtration methods. Virus filtration can be performed using microfilters or nanofilters, such as those available from PLAVONA® (Asahi Kasei, Chicago, IL), VIROSART® (Sartorius, Goettingen, Germany), VIRESOLVE® Pro (MilliporeSigma, Burlington, MA), Pegasus™ Prime (Pall Biotech, Port Washington, NY), CUNO Zeta Plus VR, (3M, St. Paul, Mn).

[0062] The production operation may also include concentration and formulation of the product. One such operation utilizes ultrafiltration and diafiltration. Suitable materials are known in the art and are common and commercially available from many sources, including regenerated cellulose Pellicon (MilliporeSigma, Danvers, MA), stabilized cellulose, Sartocon® Slice, Sartocon® ECO Hydrosart® (Sartorius, Goettingen, Germany), polyethersulfone (PES) membranes, Omega (Pall Corporation, Port Washington, NY), and others.

[0063] Product quality includes physical, chemical, biological, and / or microbial properties or characteristics for which appropriate limits or ranges have been determined to ensure the desired product quality. Such attributes may be critical attributes such as specific productivity, pH, osmolality, appearance, color, flocculation, percent yield, and titer, among others. Monitoring and measuring may be performed using known techniques and commercially available equipment.

[0064] The methods described herein can be used in conjunction with a production process used to purify a product of interest. The product can be of scientific or commercial interest, including protein-based therapeutics. Proteins of interest include, but are not limited to, secreted proteins, non-secreted proteins, intracellular proteins, or membrane-bound proteins. The product of interest can be produced by a recombinant animal cell line using the cell culture methods described herein and can be referred to as a "recombinant protein." The expressed protein can be produced intracellularly or secreted into the culture medium, from which it can be recovered and / or harvested. The product of interest is purified from proteins or polypeptides or other contaminants that interfere with the therapeutic, diagnostic, prophylactic, research, or other use of the product. Proteins of interest include, but are not limited to, proteins that exert a therapeutic effect by binding to one or more targets, such as those listed below (including targets derived from, related to, and variants thereof).

[0065] Proteins of interest include, but are not limited to, "antigen-binding proteins." An "antigen-binding protein" refers to a protein or polypeptide that contains an antigen-binding region or 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 (scFvs), two-chain (bivalent) scFvs, and IgGscFvs (see, for example, Orcutt et al., 2010, Protein Eng Des Sel 23:221-228)), hetero-IgGs (see, for example, Liu et al., 2015, J Biol Chem 290:7535-7562), bispecific antibodies, multispecific antibodies, muteins, and XmAb® (Xencorc Inc., Monrovia, CA). All forms of bispecific T cell engager molecules are also included. Additionally, chimeric antigen receptors (CARs, CAR Ts) and T cell receptors (TCRs) are included.

[0066] In some embodiments, the product of interest may include a colony-stimulating factor, such as, for example, granulocyte colony-stimulating factor (G-CSF). Such G-CSF agents include, but are not limited to, Neupogen® (filgrastim) and Neulasta® (pegfilgrastim). Erythropoiesis-stimulating agents (ESAs), such as Epogen® (epoetin alfa), Aranesp® (darbepoetin alfa), Dynepo® (epoetin delta), Mircera® (methyoxypolyethyleneglycol-epoetin beta), Hematide®, MRK-2578, INS-22, Retacrit® (epoetin zeta), Neorecormon® (epoetin beta), Silapo® (epoetin zeta), and Binocrit®. (epoetin alfa), epoetin alfa hexal, Abseamed® (epoetin alfa), Ratioepo® (epoetin theta), Eporatio® (epoetin theta), Biopoin® (epoetin theta), epoetin alfa, epoetin beta, epoetin zeta, epoetin theta and epoetin delta, epoetin omega, epoetin iota, tissue plasminogen activators, GLP-1 receptor antagonists and variants or analogs thereof and biosimilars of any of the above.

[0067] In some embodiments, the product of interest binds to one or more of the following, alone or in any combination: CD proteins, such as, 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, such as HER2, HER3, HER4, and EGF receptor, EGFRvIII; cell adhesion molecules, such as LFA-1, Mol, p150, 95, VLA-4, ICAM-1, VCAM, and αv / β3 integrin; growth factors, such as, but not limited to, vascular endothelial growth factor ("VEGF"); VEGFR2, growth hormone, thyroid-stimulating hormone, follicle-stimulating hormone, luteinizing hormone, growth hormone release hormone (GH), and / or steroid hormone (SHR). growth factors, parathyroid hormone, Murrah inhibitory substance, human macrophage inflammatory protein (MIP-1-alpha), erythropoietin (EPO), nerve growth factors such as NGF-beta, platelet-derived growth factors (PDGF), fibroblast growth factors including, for example, aFGF and bFGF, epidermal growth factor (EGF), Cripto, transforming growth factors (TGF), such as TGF-α and TGF-β, among others, for example, TGF-β1, TGF-β2, TGF-β3, TGF-β4 or TGF-β5, insulin-like growth factors I and II (IGF-I and IGF-II), des(1-3)-IGF-I (brain IGF-I) and bone morphogenetic factors, insulin and insulin-related proteins, such as, but not limited to, insulin, insulin A chain, insulin B chain, proinsulin and insulin-like growth factor binding protein;Coagulation and coagulation-related proteins, such as factor VIII, tissue factor, von Willebrand factor, protein C, alpha-1-antitrypsin, plasminogen activators such as urokinase and tissue plasminogen activator ("t-PA"), among others, bombadin, thrombin, thrombopoietin and thrombopoietin receptors, colony-stimulating factors (CSFs), such as M-CSF, GM-CSF and G-CSF, among others, other blood and serum proteins, such as, but not limited to, albumin, IgE and blood group antigens, receptors and receptor-associated proteins, such as flk2 / flt3 receptor, obesity (OB) receptor, growth hormone receptor, and T cell receptors; neurotrophic factors, such as, but not limited to, bone-derived neurotrophic factor (BDNF) and neurotrophin 3, 4, 5, or 6 (NT-3, NT-4, NT-5, or NT-6); relaxin A chain, relaxin B chain, and prorelaxin, interferons, such as interferon alpha, interferon beta, and interferon gamma, interleukins (IL), such as IL-1 to IL-10, IL-12, IL-15, IL17, IL-23, IL-12 / IL-23, IL-2Ra, IL-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 envelope viral antigens, lipoproteins, calcitonin, glucagon, atrial natriuretic factor, pulmonary surfactant, tumor necrosis factor alpha and beta, enkephalinase, BCMA, Igκ, ROR-1, ERBB2, mesothelin, RANTES (regulated upon activation, expressed and secreted by normal T cells), mouse gonadotropin-related peptide, DNase, FR-alpha, inhibin and activin, integrins, protein A or D, rheumatoid factor, immunotoxins, bone morphogenetic proteins Protein (BMP), superoxide dismutase, surface membrane protein, decay-accelerating factor (DAF), AIDS envelope, transport protein, homing receptor, MIC (MIC-A, MIC-B), ULBP1-6, EPCAM, addressin, regulatory protein, immunoadhesin, antigen-binding protein, somatropin, CTGF, CTLA4, eotaxin-1, MUC1, CEA, c-MET, claudin-18, GPC-3, EPHA2, FPA, LMP1, MG7, NY-ESO-1, PSCA, ganglioside GD2, ganglioside Cytokinin GM2, BAFF, OPGL (RANKL), myostatin, Dickkopf-1 (DKK-1), Ang2, NGF, IGF-1 receptor, hepatocyte growth factor (HGF), TRAIL-R6, c-Kit, B7RP, PSMA, NKG2D-1, programmed cell death protein 1 and ligand, PD1 and PDL1, mannose receptor / hCGβ, hepatitis C virus, mesothelin dsFv[PE38] conjugate, Legionella pneumoniae (lly), IFN-gamma, interferon-gamma-inducible protein 10 (IP10), IFNA R, TALL-1, thymic stromal lymphopoietin (TSLP), proprotein convertase subtilisin / kexin type 9 (PCSK9), stem cell factor, Flt-3, calcitonin gene-related peptide (CGRP), OX40L, α4β7, platelet-specific (platelet glycoprotein Ilb / IIIb (PAC-1)), transforming growth factor β (TFGβ), zona pellucida sperm-binding protein 3 (ZP-3), TWEAK, platelet-derived growth factor receptor alpha (PDGFRα), sclerostin, and biologically active fragments or variants of any of the above;

[0068] In some embodiments, the protein of interest is selected from the group consisting of abciximab, adalimumab, adecatumumab, aflibercept, alemtuzumab, alirocumab, anakinra, atacicept, basiliximab, belimumab, bevacizumab, biosozumab, blinatumomab, brentuximab vedotin, brodalumab, cantuzumab mertansine, canakinumab, cetuximab, certolizumab pegol, conatumumab, daclizumab, denosumab, eculizumab, edrecolomab, efalizumab, epratuzumab, etanercept, evolocumab, galiximab, ganitumab, gemtuzumab, golimumab, ibritumomab tiuxetan, infliximab These include: rilotumumab, rituximab, sargramostimab, trastuzumab, ustekinumab, vedolizumab, visilizumab, volociximab, zanolimumab, zalutumumab, and zalutumumab, as well as biosimilars of any of the foregoing.

[0069] Some of the drawings described herein show example block diagrams having one or more functional components. It will be understood that such block diagrams are for illustrative purposes, and that the devices described and shown may have more, fewer, or alternative components than those shown. Additionally, in various aspects, the components (and the functionality provided by each component) may be associated with or otherwise integrated as part of any suitable component.

[0070] Some aspects of the present disclosure relate to non-transitory computer-readable storage media having instructions / computer-readable storage media for performing various computer-implemented operations. The term “instruction / computer-readable storage medium” is used herein to include any medium capable of storing or encoding a set of instructions or computer code for performing the operations, methods, and techniques described herein. The medium and computer code may be those specially designed and constructed for the purposes of the aspects of the present disclosure or may be of the type known and available to those skilled in the computer software arts. Examples of computer-readable storage media include, but are not limited to, magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CD-ROMs and holographic devices; magneto-optical media such as optical disks; and hardware devices specially configured to store and execute program code, such as ASICs, programmable logic devices (“PLDs”), and ROM and RAM devices.

[0071] Examples of computer code include machine code, such as produced by a compiler, and files containing high-level code executed by a computer using an interpreter or compiler. For example, an aspect of the present disclosure may be implemented using Java, C++, or other object-oriented programming language and development tools. Additional examples of computer code include encryption and compression code. Furthermore, aspects of the present disclosure may be downloaded as a computer program product and transferred from a remote computer (e.g., a server computer) to a requesting computer (e.g., a computer or a different server computer) over a transmission channel. Other aspects of the present disclosure may be implemented in hardwired circuitry in place of or in combination with machine-executable software instructions.

[0072] As used herein, the singular terms "a," "an," and "the" may include plural references unless the context clearly dictates otherwise. This specification and the following claims should be read as including one or at least one, and the singular may also include the plural unless a negative meaning is expressly stated or apparent. As used herein, the terms "comprise," "including," "includes," "including," "has," "having," or any other variation thereof, are intended to cover non-exclusive inclusions. For example, a process, method, article, or device that includes a list of elements is not necessarily limited to those elements and may include other elements not expressly listed or inherent in such process, method, article, or device. Furthermore, unless expressly contrary, "or" refers to an inclusive "or," not an exclusive "or." For example, condition A or B is satisfied by 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).

[0073] As used herein, the terms "nearly," "substantially," "substantial," "roughly," and "about" are used to describe and account for small variations. When used in conjunction with an event or circumstance, these terms can refer to instances in which the event or circumstance occurs exactly, as well as instances in which the event or circumstance occurs approximately. For example, when used in conjunction with a numerical value, the terms can refer to a range of variation of ±10% or less of the numerical value, e.g., ±5% or less, ±4% or less, ±3% or less, ±2% or less, ±1% or less, ±0.5% or less, ±0.1% or less, or ±0.05% or less. For example, two numerical values ​​can be considered "substantially" the same if the difference between the numerical values ​​is ±10% or less of the mean, e.g., ±5% or less, ±4% or less, ±3% or less, ±2% or less, ±1% or less, ±0.5% or less, ±0.1% or less, or ±0.05% or less.

[0074] Additionally, amounts, ratios, and other numerical values ​​are sometimes presented herein in a range format, with the understanding that such range format is used for convenience and brevity and should be understood flexibly to include not only the numerical values ​​expressly stated as the limits of the range, but also to include all individual numerical values ​​or subranges subsumed within that range, as if each numerical value and subrange were expressly stated.

[0075] Although the techniques disclosed herein have been primarily described in terms of particular operations being performed in a particular order, it will be understood that these operations may be combined, further divided, or rearranged to form equivalent techniques without departing from the teachings of the present disclosure. Accordingly, unless specifically indicated herein, the order and grouping of operations is not a limitation of the present disclosure.

Claims

1. 1. A method for assessing the impact of processing time on a process, comprising: obtaining, by one or more processors, a trained model using historical process data including (i) historical processing times of 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 inputs to the model by the one or more processors to determine predicted outputs that will occur when operating the process according to the inputs, wherein either (i) the inputs include processing times and the predicted outputs include predicted product quality parameters, or (ii) the inputs include product quality parameters and the predicted outputs include predicted processing times; displaying or storing, by said one or more processors, said predicted output; A method comprising:

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

3. The method of claim 1 or 2, further comprising presenting, by the one or more processors, the predicted output to a user via a graphical user interface.

4. 4. The method of claim 1, wherein one or both of the processing time or the predicted processing time 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, respectively.

5. 5. The method of claim 1, wherein one or both of the processing time or the predicted processing time 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, respectively.

6. The method according to any one of claims 1 to 5, wherein the model is a linear regression model.

7. The method according to any one of claims 1 to 6, wherein the process is a bioprocess.

8. 8. The method of claim 7, wherein the bioprocess is a chromatography process.

9. 9. The method of any one of claims 1 to 8, wherein the product is a drug or a therapy or both and comprises one or more of a protein, a carbohydrate, a lipid or a nucleic acid.

10. 10. The method of any one of claims 1 to 9, wherein one or both of the product quality parameters or the predicted product quality parameters is a measure of one or more of yield, viable cell density (VCD), titer, concentration or a measure of distance to a specification limit of a parameter of the new instance of the product, respectively.

11. The method of any one of claims 1 to 10, wherein the process has a negative correlation between a given processing time and a given product quality.

12. one or more processors; one or more non-transitory computer-readable media storing instructions; wherein the instructions, when executed by the one or more processors, cause the one or more processors to: Obtaining a trained model using historical process data including (i) historical processing times of a plurality of instances of a process, and (ii) corresponding historical product quality parameters of products produced by the plurality of instances of the process; applying inputs to the model to determine predicted outputs that will occur when operating the process according to the inputs, wherein either (i) the inputs include processing times and the predicted outputs include predicted product quality parameters, or (ii) the inputs include product quality parameters and the predicted outputs include predicted processing times; displaying or storing the predicted output; A system that allows the following to be performed.

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

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

15. 15. The system of claim 12, wherein one or both of the processing time or the predicted processing time 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, respectively.

16. 16. The system of claim 12, wherein one or both of the processing time or the predicted processing time 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, respectively.

17. The system according to 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 chromatography process.

19. The system of any one of claims 12 to 18, wherein the product is a drug or a therapy or both and comprises one or more of a protein, a carbohydrate, a lipid or a nucleic acid.

20. 20. The system of any one of claims 12 to 19, wherein one or both of the product quality parameters or the predicted product quality parameters are measures of one or more of yield, viable cell density (VCD), titer, concentration, or a measure of distance to a specification limit of a parameter of the new instance of the product, respectively.

21. 1. A method for determining the usefulness of a product that has experienced an unexpected delay during purification, comprising: purifying said product by one or more process operations; experiencing unexpected delays during process operation; taking a sample of the product after the unexpected delay; The sample is compared to (i) the past processing times of multiple instances of the process; and (ii) corresponding historical product qualities of products produced by the multiple instances of the process; subjecting the model to training using historical process data including: determining a predicted output that will occur when operating the process according to the input; (i) the input includes processing time and the predicted output includes predicted product quality parameters; or (ii) determining whether the input comprises a product quality parameter and the predicted output comprises a predicted processing time; using the predicted output to determine the utility of the product produced under delay conditions; A method comprising:

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

23. 23. The method of claim 21 or 22, wherein the utility is based on a predicted product quality of the product produced under the delayed conditions.

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

Images