Method and system for determining anomalies in a bioprocess

Abstract

A computer implemented method for determining anomalies in a bioprocess, wherein the bioprocess is performed in a plurality of bioprocess cycles in series, each cycle corresponding to a separate instance of at least a portion of the bioprocess, the plurality of bioprocess cycles comprising a current bioprocess cycle and at least one previous bioprocess cycle, the method comprising: collecting process data for the current bioprocess cycle; providing reference data for the current bioprocess cycle and for the at least one previous bioprocess cycle of the plurality of bioprocess cycles, the reference data corresponding to the process data; communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle, based on the process data and the reference data.

Description

[0001] METHOD AND SYSTEM FOR DETERMINING ANOMALIES IN A BIOPROCESS

[0002] TECHNICAL FIELD

[0003] The present invention relates to a method and a system for determining anomalies in a bioprocess cycle. In particular, to a method and a system for determining anomalies in a bioprocess cycle with a reference trend of a set of reference bioprocess cycles. In a specific example, the bioprocess is a liquid chromatography process and the method allows a user to visually determine when the process deviates from what is expected.

[0004] BACKGROUND ART

[0005] Bioprocessing systems are widely used, e.g. to perform biomolecule / protein separation. An example of a bioprocessing system is a chromatography system. Chromatography is a well-known procedure for purifying protein samples. The sample may typically be provided in a fluid, e.g. deriving from a bioreactor. Other bioprocessing systems include filtration systems and bioreactors.

[0006] A bioprocessing system / device is generally used to provide a particular system functionality, e.g., the bioprocessing system / device may be used to produce and / or separate a desired substance, e.g., protein purification in a bioprocess such as chromatography or filtration or production through cell cultivation or oligo synthesis.

[0007] For many applications of such bioprocessing systems, it is necessary to repeat the same bioprocess or part of the bioprocess in multiple cycles, e.g. in series using the same system / device. However, for many different reasons, anomalies may occur within any given cycle, which result in differences in the bioprocess cycle-to-cycle. In many cases, the output of anomalous cycles is unusable. Therefore, anomalous cycles waste both time and resources. In many case, anomalous cycles are identified only after they are completed, e.g. when the quality of the output is being checked.

[0008] Thus, there is a need for an improved method to identify anomalies as they occur, or soon as possible after they occur, in order to minimise waste. An objective of embodiments of the invention is to provide a solution which mitigates or solves the drawbacks or problems described above

[0009] SUMMARY OF THE INVENTION

[0010] According to an aspect of the disclosure there is provided a computer implemented method for determining anomalies in a bioprocess, wherein the bioprocess is performed in a plurality of bioprocess cycles, each cycle corresponding to a separate instance of at least a portion of the bioprocess, the plurality of bioprocess cycles comprising a current bioprocess cycle and at least one previous bioprocess cycle, the method comprising: collecting process data for the current bioprocess cycle; providing reference data for the current bioprocess cycle and for the at least one previous bioprocess cycle of the plurality of bioprocess cycles, the reference data relating to at least two reference bioprocess cycles and corresponding to the process data; communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle, based on the process data and the reference data. Accordingly, anomalies in a bioprocess can be identified in real-time or soon as possible after they occur by the user of the bioprocess.

[0011] By providing reference data relating to at least two reference bioprocess cycles, a reference trend corresponding to the process data of the current bioprocess cycle and at least one bioprocess cycle can be formed to identify the anomalies in the bioprocess.

[0012] Optionally, the bioprocess is one of: a chromatography process, a bioreactor process, a filtration process, and an oligo synthesis process.

[0013] Optionally, each cycle is performed using the same type of bioprocess system. Optionally, each cycle is performed using the same bioprocess system for each cycle.

[0014] Optionally, each cycle corresponds to a single run of a bioprocess. Alternatively, each cycle corresponds to a repeated portion of a single run of a bioprocess.

[0015] Optionally, communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle comprises communicating to the user deviation and / or conformity between the process data and the reference data.

[0016] Optionally, the process data comprises a plurality of distinct types of data; and communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle comprises communicating deviation to the user deviation and / or conformity between the process data and the reference data separately for at least two distinct types of data of the plurality of distinct types of data.

[0017] Optionally, collecting process data comprises collecting first process data for the current bioprocess cycle and collecting second process data for the at least one previous bioprocess cycle; and communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle, is based on the first and second process data and the reference data.

[0018] Optionally, the process data and the reference data each identify which cycle of the plurality of cycles the process data or the reference data is for.

[0019] Optionally, the process data and reference data each comprises a single parameter corresponding to each bioprocess cycle, optionally for each different type of process data. Optionally, the process data comprises one more of the following types of data: time- integrated time-series sensor data, i.e. an area under a sensor data curve which is sensor signal summed / integrated over time,, , data derived from sensor parameter data.

[0020] Optionally, the process data comprises one more of the following types of data: the peak area (area under peak) may be derived from UV sensor data, as may retention time (Rt), peak height, peak width, peak asymmetry factor, peak resolution (Rs), retention factor (k’), selectivity (a), theoretical plate number (N), height equivalence to a theoretical plate (HETP).

[0021] Optionally, communicating the deviation and / or conformity between the current bioprocess and the reference bioprocess comprises displaying the process data and the reference data together for visual comparison. Optionally, the process data and the reference data are displayed at least for the current cycle and the one or more previous cycles, and the reference data is optionally additionally displayed for one or more future cycles. Optionally, the process data and the reference data are displayed graphically, numerically and / or textually.

[0022] Optionally, the method further comprises comparing the process data and the reference data to determine the deviation and / or conformity.

[0023] Optionally, communicating the deviation and / or conformity between the current bioprocess and the reference bioprocess comprises an alert alerting a user to the determined deviation and / or conformity, such as a visual alert or an audio alert.

[0024] Optionally, the reference data is based on previously collected process data for at least one set of a plurality of reference bioprocess cycles.

[0025] Optionally, the reference data is based on a statistical combination of previously collected process data for least one set of a plurality of reference bioprocess cycles.

[0026] Optionally, the method further comprises generating the reference data. Optionally, the reference data is generated by a mathematical model. Optionally, the mathematical model is trained to generate reference data based on training data comprising collected data for a plurality of previous sets of a plurality of reference bioprocess cycles. Optionally, the mathematical model is a machine learning model.

[0027] Optionally, the method further comprises collecting process data for at least two previous bioprocess cycles; and wherein the reference data is generated based on the previously collected process data for the at least two previous bioprocess cycles.

[0028] According to a second aspect there is provided a computer system for collecting process data for a bioprocess, wherein the bioprocess is performed in a plurality of bioprocess cycles, each cycle corresponding to a separate instance of at least a portion of the bioprocess, the plurality of bioprocess cycles comprising a current bioprocess cycle and at least one previous bioprocess cycle, the computer system comprising: a data interface configured to connect with a bioprocess apparatus for carrying out a bioprocess and collect process data for a current bioprocess cycle; one or more data processors; and a user interface; wherein: the computer system is pre-provided with reference data for the current bioprocess cycle and for the at least one previous bioprocess cycle of the plurality of bioprocess cycles, the reference data relating to at least two reference bioprocess cycles and corresponding to the process data; and the computer system is configured to communicate to a user, via the user interface, deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle, based on the process data and the reference data.

[0029] According to a third aspect there is provided a computer programme product comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method of the first aspect.

[0030] According to a fourth aspect there is provided a data processing device comprising the means for carrying out the method of the first aspect.

[0031] BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Further features of the disclosure will be described below, by way of non-limiting examples and with reference to the accompanying drawings, in which:

[0033] Fig. 1 shows a chromatography system embodied as a chromatography apparatus according to one or more embodiments of the disclosure;

[0034] Fig. 2 is a flow chart showing an example bioprocess;

[0035] Fig. 3 shows an example bioprocess system;

[0036] Fig. 4 shows an example visual display view; and Fig. 5 shows an example computer system.

[0037] DETAILED DESCRIPTION

[0038] An “or” in this description and the corresponding claims is to be understood as a mathematical OR which covers “and” and “or”, and is not to be understand as an XOR (exclusive OR). The indefinite article “a” in this disclosure and claims is not limited to “one” and can also be understood as “one or more”, i.e., plural. The following describes embodiments of the invention based on a chromatography process. It should be understood that the invention is not limited to a chromatography process and the bioprocess may be different in other embodiments. For example, the bioprocess may be a bioreactor process or a filtration process. Each of these processes may use a different apparatus, with different components, and may collect different data.

[0039] Fig. 1 shows a chromatography system 100 embodied as a chromatography apparatus according to one or more embodiments of the disclosure.

[0040] The chromatography system 100 is configured to provide a desired system functionality, typically to receive input substances S input l, Sinput_2, Sinput_3 and produce one or more desired substances SDesiredl, SDesired2, S|)esired3-

[0041] In one example, the chromatography system 100 comprises a chromatography apparatus configured to separate a desired substance or sample Soesired from one or more input substances S input i - Sinput _N, e.g., different mixtures of the sample and other compositions.

[0042] The chromatography system 100 may comprise a selection of bioprocessing units, such as reservoirs 151, 152 ... -N, a column 141, a splitter 170, at least one UV sensor, a pH sensor 131 and a conductivity sensor 132. The chromatography system 100 in the form of a chromatography apparatus is described in further detail below.

[0043] The chromatography apparatus 100 may typically comprise at least one inlet 155. The inlet may optionally be coupled to one or more reservoirs 151, 152 ... -N configured to hold a fluid. It is understood that the chromatography apparatus 100 may comprise any number of reservoirs and corresponding inlets. The inlet 155 may e.g., be implemented as tubular elements such as a tube or hose. The chromatography apparatus 100 may further comprise a valve unit (not shown). The valve unit may be coupled to the reservoir(s) 151, 152 ... -N by the inlet 155 coupled to the fluid inlet 101. The valve unit may be configured to be coupled to a (e.g. a first) column 141 by a first pair of fluid ports 130, 140. The first column 141 may be comprised in the chromatography apparatus 100 or arranged external to the chromatography apparatus 100. The chromatography apparatus 100 may typically comprise one or more pumps (not shown) for providing flow of liquids through the system. In some examples, at least one pump is arranged close to the at least one inlet 155 to draw liquid from the one or more reservoirs 151, 152 ... -N towards the valve unit.

[0044] The chromatography apparatus 100 may further comprise an intelligent packing fluid port or packing fluid port 150 configured to be coupled to a packing port of the column 141. The chromatography apparatus 100 may further comprise a waste fluid port 160 configured to be coupled to a waste reservoir or drain (not shown).

[0045] The chromatography apparatus 100 may further comprise or be operatively coupled to a control unit 110 which comprises circuitry, e.g., a processor and a memory. The memory may contain instructions executable by the processor, whereby said chromatography apparatus 100 is operative to perform any of the steps or methods described herein.

[0046] The chromatography apparatus 100 may optionally comprise a splitter 170 coupled to an optional outlet valve 120. The splitter 170 may be configured to direct fluid to the outlet valve 120 or any other unit. Optionally the splitter 170 may be communicatively coupled to the control unit 110 and perform coupling of fluid in in response to a control signal from the control unit 110.

[0047] The chromatography apparatus 100 may further comprise an outlet valve 120 coupled to the splitter 170. The outlet valve 120 may have one or more outlets or outlet ports 121 -123 and is configured to provide the fluid provided by the splitter 170 to the one or more outlets 121 -123 in response to a control signal, e.g., received from the control unit 110.

[0048] The chromatography apparatus 100 may further comprise a pH sensor 131 and / or a conductivity sensor 132. The pH sensor 131 and a conductivity sensor 132 may be coupled to the splitter 170, as shown.

[0049] The pH sensor 131 may be communicatively coupled to the control unit 110 and configured for measuring the pH of the fluid provided to the splitter 170. One or more UV sensor(s) may also be provided to enable monitoring / detection of target protein products. The chromatography apparatus 100 may further comprise a conductivity sensor 132 communicatively coupled to the control unit 110 and configured for measuring the conductivity of the fluid provided by the splitter 170. The pH sensor 131 and / or the conductivity sensor 132 may further be configured to provide the measured pH and measured conductivity as control signals comprising measurement data to the control unit 110.

[0050] The chromatography apparatus 100 may further comprise one or more pressure sensors (not shown) to monitor fluid pressure in the system. In an example, two of these may be arranged upstream (before the column), to measure system inlet pressure, and downstream (after the column), to measure pressure drop across the column.

[0051] The chromatography apparatus 100 may further comprise one or more flow-rate sensors (not shown) to measure and regulate the flow rate of the mobile phase through the system.

[0052] The chromatography apparatus 100 may further comprise one or more temperature sensors (not shown) to measure the temperature of the mobile phase through the system.

[0053] Mechanical components of the system, including the valve unit, the splitter 170, outlet valve 120, and one or more pumps, may comprise one or more sensors configured to sense an operation mode of the component. Some components may operate bimodally, e.g. on / off, open / closed. Other components may operate multimodally, e.g. where a valve is able to divert flow from two or more inlets and / or to two or more outlets.

[0054] Fig. 2 is a flow chart illustrating a typical chromatography process. In step SI, Method Settings, process steps and system settings for the process are set. In step S2, Equilibration, an equilibration buffer is pumped through the column at a predefined flow rate and the UV absorbance and pressure are monitored to ensure stable baseline conditions. In Step S3, Sample Application, a prepared sample is loaded onto the column using the system's sample pump. In step S4, Column Wash, the column is washed with the equilibration / binding buffer to remove unbound or weakly bound impurities. In step S5, Elution, the concentration of buffer is changed, either gradually or stepwise, to elute the bound molecules based on their binding strength and the eluted fractions are collected using the fraction collector. In step S6, Equilibration, the column is re-equilibrated with equilibration buffer to prepare it for the next cycle. Fig. 3 shows an example chromatography system 300 comprising the chromatography apparatus 100 and a computer system 200. The computer system 200 is configured to receive process data from the chromatography apparatus 100, e.g. via the control unit 110. The computer system may comprise a data interface 201 configured to connect with the chromatography apparatus 100.

[0055] The process data provided to the computer system 200 may include any data provided by the various sensors of the chromatography apparatus 100, e.g. including the pH sensor 131, the conductivity sensor 132, the UV sensor(s), the pressure sensor(s), the flow-rate sensor(s) and the temperature sensor(s). Such process data may be provided in the form of a parameter for a given time, e.g. a continuous parameter which may take any value in a given range. Accordingly, such process data may be referred to as sensor parameter data. This sensor parameter data may be time-series data. The sensor parameter data need not be the raw sensor data, but may be calculated based on the raw data, e.g. as the raw data itself may be an electrical signal for example.

[0056] In some examples, additional data may be derived from sensor parameter data, e.g. calculated based on the sensor parameter data. For example, liquid volume data may be derived from the flow-rate sensor data. For example, peak area (area under peak) may be derived from UV sensor data, as may retention time (Rt), peak height, peak width, peak asymmetry factor, peak resolution (Rs), retention factor (k’), selectivity (a), theoretical plate number (N), height equivalence to a theoretical plate (HETP) and others. Such data may be referred to as data derived from sensor parameter data. Such data may be calculated by the computer system 200 or the control unit 110.

[0057] The process data provided to the computer system may also include time data provided for operations of the mechanical components of the system, e.g. the valve unit, the splitter 170, input valve, outlet valve 120, and the pump(s). Such process data may be provided as the time for different operational modes of a component and the operation modes may comprise one or more of a plurality of discrete modes. For example, the time for turning on the pump(s), the time for turning on the input valve etc.. Accordingly, such data may be referred to as operation mode data. In some examples, the computer system 200 or control unit 110, may detect and optionally provide alerts for the time deviation and / or conformity of occurrence of one of more events between the current bioprocess cycle and the reference cycle. These events may include various sensor parameter data, or data derived from sensor parameter data, reaching or crossing one or more predefined threshold values, e.g. an upper and / or lower threshold. Accordingly, the events may include the occurrence of a parameter reaching a threshold. The events may also include the occurrence of process steps, and / or corresponding instructions, e.g. from the control unit 110 or computer system 200. Accordingly, such data described in this paragraph may be collectively referred to as event data. Accordingly, the time deviation and / or conformity of occurrence of the event data between the current bioprocess cycle and the reference cycle means the time when the event occurs.

[0058] The bioprocess may be performed in a plurality of bioprocess cycles in series. Each cycle may correspond to a separate instance of at least a portion of the bioprocess. For example, a bioprocess may comprise repeating particular steps of the bioprocess a plurality of times, each time corresponding to one cycle. One example for such an application scenario is periodic counter-current chromatography (PCC), in which the loading and eluting steps are repeated for at least two columns in the process. In some examples the term “cycle” may refer to a full run of a bioprocess from start to finish. As run may or may not include subcycles. Each cycle may be performed using at least one bioprocess system common to each cycle. This may also apply for the bioprocess runs. However, more generally runs may be performed using the same type of bioprocess system, provided different bioprocess systems of the same type are comparable. For example, runs may be performed on chromatography systems of different scales, such as lab scale, benchtop scale and large scale.

[0059] In the following description, examples are described for cycles where each cycle is a run, thus the examples are concerned with run-to-run data. However, the examples are equally applicable to comparison between in-run cycles.

[0060] During a bioprocess, one or more different types of process data may be collected for the bioprocess, referred to as a current bioprocess to distinguish from previous bioprocesses for example. The process data may have a temporal relationship to the current bioprocess. For example, for some types of process data, the process data is based on absolute time, e.g. sensor parameter data obtained in a time-series manner, or the time of an occurrence of an event. For example, for some types of process data, the process data is based on relative time between different parts of the reference liquid chromatography process, e.g. the time between the occurrence of two events. Some process data may be obtained in real-time. Other process data may be obtained later, e.g. after completion of a run, such as data derived from sensor parameter data.

[0061] Anomalies in the bioprocess may result in process data for the current bioprocess run diverging from what would typically be expected for the bioprocess run. Some types of process data may be expected to be substantially the same from run-to-run. Some types of process data may be expected to change from run-to-run, following a predictable trend. Some types of process data may be expected to change from run-to-run, but without following a predictable trend, e.g. stochastically. To provide a method for determining anomalies in a bioprocess run, in addition to collecting process data, for a current bioprocess run, reference data is provided, relating to a plurality of reference bioprocess runs. In some embodiments, the reference data may be provided as a reference trend for the current bioprocess run and for at least one previous bioprocess run of the plurality of bioprocess runs in the series. The reference bioprocess run may represent a real or theoretical bioprocess substantially free from anomalies.

[0062] The reference data corresponds to the process data. In other words, the process data and reference data comprise the same types of data such the process data and reference data are comparable to each other.

[0063] Deviation and / or conformity between the current bioprocess run and the reference trend based on the reference bioprocess runs is then communicated to a user of the bioprocess, based on the process data and the reference data. Thus, anomalies in a bioprocess can be determined from run to run.

[0064] In some examples, the reference data may be based on previously collected process data for at least one (real) previous bioprocess run as a reference bioprocess run. For example, the reference data may be process data collected during a previous bioprocess run for the same bioprocess in the same bioprocess system. In some other examples, the reference data may be process data collected during a previous bioprocess run in a different bioprocess system. In some examples, the reference data may be based on a statistical combination of previously collected process data for a plurality of previous bioprocess runs. For example, the reference data may be averaged over the plurality of previous bioprocess runs. In such an example, the reference data may be generated by a mathematical model, based on the process data for a plurality of previous bioprocess runs.

[0065] In some examples, the reference data may be generated by mathematical model trained to generate reference data based on training data comprising collected data for a plurality of previous bioprocess runs. Such a mathematical model may be a machine learning model.

[0066] In some examples, the mathematical model may be trained on data relating to different runs of different bioprocesses of the same type (e.g. chromatography), e.g. bioprocesses following different bioprocess steps with the reference data comparable with the process data in the current bioprocess. The model may receive as input, information about, or identifying, the current bioprocess, e.g. including process steps to be performed, for performing the bioprocess and / or settings for the bioprocess apparatus. Based on this input, the mathematical model may generate process data that models the current bioprocess. In other examples, the mathematical model may be specifically for the current bioprocess, e.g. the same recipe, and be trained on data relating to different runs of essentially the same bioprocess, e.g. with following the same process steps.

[0067] In some examples, reference data may be at least partly based on data that is obtained outside the bioprocess, i.e. not from sensors of the bioprocess system on which the bioprocess was performed. For example, data imported by user input or analysis data from chromatography fractions after the bioprocess is performed and the referenced data may be at least partly based on such data.

[0068] In some examples, the reference data may be modified during the current bioprocess, based on the collected process data. For example, reference data for a future point time may be modified based on the previously collected process data. Thus, the reference data can take into account what has actually happened during the current bioprocess and more accurately predict what should be expected in the future. A mathematical model may be configured to modify the process data in this way. The mathematical model may receive as input at least initial reference data and the process data and output modified reference data. In some examples, the reference data may be stored in a memory of the computer system and retrieved for use prior to the above described method. In some cases, the reference data may be generated, e.g. based on stored data, prior to the above described method, e.g. as a preceding step. In some cases, for reference data based previously collected process data for a previous bioprocess, the method may include performing said previous bioprocesses and collecting said previous process data, which may then be stored in a memory.

[0069] In a preferred embodiment, communicating the deviation and / or conformity between the current bioprocess and the reference bioprocess may comprise displaying the process data and the reference data together for visual comparison, e.g. by a user of the computer system. Figs. 4 to 5 show two different examples of such an embodiment. The computer system 200 may therefore comprise a display for displaying the process data and the reference data.

[0070] In an example, each type of process data may comprise a single parameter for the current bioprocess run. Correspondingly the reference data may comprise a single parameter for each reference bioprocess run. The types of process data may comprise one or more of time-integrated time-series sensor parameter data (e.g. an area under a sensor data curve), or data otherwise derived from sensor parameter data.

[0071] For example, the process data may comprise one more of the following types of data: the peak area (area under peak) may be derived from UV sensor data, as may the time point for reaching the peak, retention time (Rt), peak height, peak width, peak asymmetry factor, peak resolution (Rs), retention factor (k’), selectivity (a), theoretical plate number (N), height equivalence to a theoretical plate (HETP).

[0072] In some examples, the process data and reference data may comprise a plurality of distinct types of data, e.g. of the different types as described above. Deviation and / or conformity between the process data and the reference data may be communicated to a user separately for at least two distinct types of data of the plurality of distinct types of data. In some examples, collecting process data may comprise collecting first process data for the current bioprocess run and collecting second process data for at least one previous bioprocess run. Deviation and / or conformity between the current bioprocess run and a corresponding reference bioprocess run, may be communicated to a user based on the first and second process data and the reference data.

[0073] As shown in Fig. 4, the computer system display view 400 may display process data 401,

[0074] 402 of a plurality of distinct types, for both past runs (402) and the current run (401). The computer system display view 400 may additionally display corresponding reference data

[0075] 403 corresponding to past runs, the current run and future runs based on a plurality of reference bioprocess runs. Such data may be displayed graphically, e.g. as a graph.

[0076] Process and reference data of the different types may be separately displayed, e.g. separate graphs. However, as shown, these may be displayed with the same set of axes. In Fig. 4, data to the left of the dashed line is in the past and data to the right is future reference data.

[0077] As shown in Fig. 4, reference data may be shown as a trend line and actual collected process data as data points. For some types of process data, the reference data may include a zone of tolerance, as shown for the lowermost data in Fig. 4, which indicates where the reference data may take a range of values within the tolerance zone without deviating form expectations. Alternatively, error bars may be shown.

[0078] For some types of process data, such as the topmost type of data in Fig. 4, there may be no single trend. Instead, trends may occur cyclically. Alternatively, trends may follow a deeper trend, as shown. This may be visualised by the reference data.

[0079] Fig. 5 shows an alternative example of a computer system display view 500, in which multiple graphs 501 - 504 corresponding to the different types of process data and reference data may be provided on respective axes, in separate views, but simultaneously.

[0080] Based on the visual display of the process data and the reference data, a user may visually compare the process data and the reference data to determine the deviation and / or conformity between the process data and the reference data. In some examples, the process data and the computer system 200 may be configured to compare the process data and the reference data to determine the deviation and / or conformity between the process data and the reference data. In such an example, communicating the deviation and / or conformity between the current bioprocess and the reference bioprocess may comprise an alert alerting a user to the determined deviation and / or conformity, such as a visual alert or an audio alert. In some examples, the computer system may be configured to automatically pause the bioprocess when a deviation occurs, preferably deviation of a sufficient magnitude or importance. In some examples, the comparison may be performed by a machine learning model trained to determine deviation and or conformity, e.g. deviation of a sufficient magnitude or importance.

[0081] Fig. 6 shows the computer system 200 in further detail according to one or more embodiments of the present disclosure. The computer system 200 may be in the form of e.g., a chromatography system, a computer, a server, an on-board computer, a stationary computing device, a laptop computer, a tablet computer, a handheld computer, a wrist- worn computer, a smart watch, a smartphone, or a smart TV. The computer system 200 may comprise processing circuitry 712 communicatively coupled to a transceiver 704 configured for wired or wireless communication. The computer system 200 may further comprise at least one optional antenna (not shown in figure). The antenna may be coupled to the transceiver 704 and is configured to transmit and / or emit and / or receive wired or wireless signals in a communication network, such as Wi-Fi, Bluetooth, 3G, 4G, 5G etc. In one example, the processing circuitry 712 may be any of a selection of a processor and / or a central processing unit and / or processor modules and / or multiple processors configured to cooperate with each-other. Further, the computer system 200 may further comprise a memory 715. The memory 715 may e.g., comprise a selection of a hard RAM, disk drive, a flash drive or other removable or fixed media drive or any other suitable memory known in the art. The memory 715 may contain instructions executable by the processing circuitry to perform any of the steps or methods described herein. The processing circuitry 712 may be communicatively coupled to a selection of any of the transceiver 704 and the memory 715. The computer system 200 may be configured to send / receive control signals directly to any of the above-mentioned units or to external nodes or to send / receive control signals via a wired and / or wireless communications network. The wired / wireless transceiver 704 and / or a wired / wireless communications network adapter may be configured to send and / or receive data values or parameters as a signal to or from the processing circuitry 712 to or from other external nodes.

[0082] In an embodiment, the transceiver 704 communicates directly to external nodes or via a wireless communications network.

[0083] In one or more embodiments the computer system 200 may further comprise an input device 717, configured to receive input or indications from a user and send a user input signal indicative of the user input or indications to the processing circuitry 712.

[0084] In one or more embodiments the computer system 200 may further comprise a display 718 configured to receive a display signal indicative of rendered objects, such as text or graphical user input objects, from the processing circuitry 712 and to display the received signal as objects, such as text or graphical user input objects.

[0085] In one embodiment the display 718 is integrated with the user input device 717 and is configured to receive a display signal indicative of rendered objects, such as text or graphical user input objects, from the processing circuitry 712 and to display the received signal as objects, such as text or graphical user input objects, and / or configured to receive input or indications from a user and send a user-input signal indicative of the user input or indications to the processing circuitry 712.

[0086] In a further embodiment, the computer system 200 may further comprise and / or be coupled to one or more additional sensors (not shown in the figure) configured to receive and / or obtain and / or measure physical properties pertaining to the computer and / or chromatography system and send one or more sensor signals indicative of the physical properties to the processing circuitry 712. In one or more embodiments, the processing circuitry 712 is further communicatively coupled to the input device 717 and / or the display 718 and / or the additional sensors.

[0087] In embodiments, the communications network communicate using wired or wireless communication techniques that may include at least one of a Local Area Network (LAN), Metropolitan Area Network (MAN), Global System for Mobile Network (GSM), Enhanced Data GSM Environment (EDGE), Universal Mobile Telecommunications System, Long term evolution, High Speed Downlink Packet Access (HSDPA), Wideband Code Division Multiple Access (W-CDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth®, Zigbee®, Wi-Fi, Voice over Internet Protocol (VoIP), LTE Advanced, IEEE802.16m, WirelessMAN-Advanced, Evolved High-Speed Packet Access (HSPA+), 3GPP Long Term Evolution (LTE), Mobile WiMAX (IEEE 802.16e), Ultra Mobile Broadband (UMB) (formerly Evolution- Data Optimized (EV-DO) Rev. C), Fast Low-latency Access with Seamless Handoff Orthogonal Frequency Division Multiplexing (Flash-OFDM), High Capacity Spatial Division Multiple Access (iBurst®) and Mobile Broadband Wireless Access (MBWA) (IEEE 802.20) systems, High Performance Radio Metropolitan Area Network (HIPERMAN), Beam- Division Multiple Access (BDMA), World Interoperability for Microwave Access (WiMAX) and ultrasonic communication, etc., but is not limited thereto.

[0088] Moreover, it is realized by the skilled person that the computer system 200 may comprise the necessary communication capabilities in the form of e.g., functions, means, units, elements, etc., for performing the present solution. Examples of other such means, units, elements and functions are: processors, memory, buffers, control logic, encoders, decoders, rate matchers, de-rate matchers, mapping units, multipliers, decision units, selecting units, switches, interleavers, de-interleavers, modulators, demodulators, inputs, outputs, antennas, amplifiers, receiver units, transmitter units, DSPs, MSDs, TCM encoder, TCM decoder, power supply units, power feeders, communication interfaces, communication protocols, etc. which are suitably arranged together for performing the present solution.

[0089] Especially, the processing circuitry of the present disclosure may comprise one or more instances of a processor, processor modules and multiple processors configured to cooperate with each-other, Central Processing Unit (CPU), a processing unit, a processing circuit, a processor, an Application Specific Integrated Circuit (ASIC), a microprocessor, a Field-Programmable Gate Array (FPGA) or other processing logic that may interpret and execute instructions. The expression “processing circuitry” and / or “processing means” may thus represent a processing circuitry comprising a plurality of processing circuits, such as, e.g., any, some or all of the ones mentioned above. The processing means may further perform data processing functions for inputting, outputting, and processing of data comprising data buffering and device control functions, such as processing control, user interface control, or the like.

[0090] In one embodiment, a computer is provided, wherein the computer is configured to perform any or all of the method steps of the method described herein.

[0091] In one embodiment, a chromatography apparatus and / or system is provided, the chromatography apparatus and / or system comprising all or a selection of the features of the computer described in relation to Fig. 6. The chromatography apparatus or system is configured to perform any or all of the method steps of the method described herein.

[0092] In one embodiment, a computer program is provided comprising computer-executable instructions for causing a computer, when the computer-executable instructions are executed on a processing unit comprised in the computer, to perform any of the method steps of the method described herein.

[0093] In one embodiment, a computer program product is provided comprising a computer- readable storage medium, the computer-readable storage medium having the computer program above embodied therein.

[0094] In one embodiment, a carrier containing the computer program above is provided, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium.

[0095] Various embodiments of the present invention can thus provide a method, computer or program wherein source data, target data and / or raw data is generated by or provided to a bioprocessing device / system that comprises one or more of: a chromatography device, a cell culture device, a filtration device and / or an oligo synthesis device.

[0096] Finally, it should be understood that the invention is not limited to the embodiments described above, but also relates to and incorporates all embodiments within the scope of the appended independent claims.

Claims

CLAIMS1. A computer implemented method for determining anomalies in a bioprocess, wherein the bioprocess is performed in a plurality of bioprocess cycles, each cycle corresponding to a separate instance of at least a portion of the bioprocess, the plurality of bioprocess cycles comprising a current bioprocess cycle and at least one previous bioprocess cycle, the method comprising: collecting process data for the current bioprocess cycle; providing reference data for the current bioprocess cycle and for the at least one previous bioprocess cycle of the plurality of bioprocess cycles, the reference data relating to at least two reference bioprocess cycles and corresponding to the process data; communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle, based on the process data and the reference data.

2. The method of claim 1, wherein the bioprocess is one of: a chromatography process, a bioreactor process, a filtration process, and an oligo synthesis process.

3. The method of any preceding claim, wherein each cycle is performed using the same type of bioprocess system.

4. The method of any preceding claim, wherein each cycle is performed using the same bioprocess system.

5. The method of any preceding claim, wherein each cycle corresponds to a single run of a bioprocess.

6. The method of any one of claims 1 to 4, wherein each cycle corresponds to a repeated portion of a single run of a bioprocess.

7. The method of any preceding claim, wherein communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle comprises communicating to the user deviation and / or conformity between the process data and the reference data.

8. The method of any preceding claim, wherein the process data comprises a plurality of distinct types of data; and communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle comprises communicating deviation to the user deviation and / or conformity between the process data and the reference data separately for at least two distinct types of data of the plurality of distinct types of data.

9. The method of any preceding claim, wherein collecting process data comprises collecting first process data for the current bioprocess cycle and collecting second process data for the at least one previous bioprocess cycle; and communicating to a user deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle, is based on the first and second process data and the reference data.

10. The method of any preceding claim, wherein the process data and the reference data each identify which cycle of the plurality of cycles the process data or the reference data is for.

11. The method of any preceding claim, wherein process data and reference data comprises a single parameter corresponding to each bioprocess cycle, optionally for each different type of process data.

12. The method of claim 11, wherein the process data comprises one or more of the following types of data: time-integrated time-series sensor data, data derived from sensor parameter data.

13. The method of claim 12, wherein the process data comprises one more of the following types of data: a peak area derived from UV sensor data, the time point reaching the peak, retention time (Rt), peak height, peak width, peak asymmetry factor, peak resolution (Rs), retention factor (k’), selectivity (a), theoretical plate number (N), height equivalence to a theoretical plate (HETP).

14. The method of any preceding claim, wherein communicating the deviation and / or conformity between the current bioprocess and the reference bioprocess comprises displaying the process data and the reference data together for visual comparison.

15. The method of claim 14, wherein the process data and the reference data are displayed at least for the current cycle and the one or more previous cycles, and the reference data is optionally additionally displayed for one or more future cycles.

16. The method of claim 14 or 15, wherein the process data and the reference data are displayed graphically, numerically and / or textually.

17. The method of any preceding claim, wherein the method further comprises comparing the process data and the reference data to determine the deviation and / or conformity.

18. The method of any preceding claim, wherein communicating the deviation and / or conformity between the current bioprocess and the reference bioprocess comprises an alert alerting a user to the determined deviation and / or conformity, such as a visual alert or an audio alert.

19. The method of any previous claim, wherein the reference data is based on previously collected process data for at least one set of a plurality of reference bioprocess cycles.

20. The method of any previous claim, wherein the reference data is based on a statistical combination of previously collected process data for least one set of a plurality of reference bioprocess cycles.

21. The method of any previous claim, further comprising generating the reference data.

22. The method of claim 21, wherein the reference data is generated by a mathematical model.

23. The method of claim 22, wherein the mathematical model is trained to generate reference data based on training data comprising collected data for a plurality of previous sets of a plurality of reference bioprocess cycles.

24. The method of claim 22 or 23, wherein the mathematical model is a machine learning model.

25. The method of any preceding claim, further comprising collecting process data for at least two previous bioprocess cycles; and wherein the reference data is generated based on the collected process data for the at least two previous bioprocess cycles.

26. A computer system for collecting process data for a bioprocess, wherein the bioprocess is performed in a plurality of bioprocess cycles , each cycle corresponding to a separate instance of at least a portion of the bioprocess, the plurality of bioprocess cycles comprising a current bioprocess cycle and at least one previous bioprocess cycle, the computer system comprising: a data interface configured to connect with a bioprocess apparatus for carrying out a bioprocess and collect process data for a current bioprocess cycle; one or more data processors; and a user interface; wherein: the computer system is pre-provided with reference data for the current bioprocess cycle and for the at least one previous bioprocess cycle of the plurality of bioprocess cycles, the reference data relating to at least two reference bioprocess cycles and corresponding to the process data; and the computer system is configured to communicate to a user, via the user interface, deviation and / or conformity between the current bioprocess cycle and a corresponding reference bioprocess cycle, based on the process data and the reference data.

27. A computer programme product comprising instructions which, when executed by a computer, cause the computer to carry out the method of any of claims 1-25.

28. A data processing device comprising the means for carrying out the method of any of claims 1-25.22

Images