Patent Application
20220199195
The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.
JP2009-44974A discloses a method for constructing an estimation model for estimating a quality of cells. In the method, for two or more samples in which cells of the same species are cultured, images are acquired by capturing images of cells of each sample are captured at two or more time points with different culture times, and each acquired image is analyzed, thereby generating numerical data for two or more indicators of morphology of the cells. In the method, actual measurement data of the estimation target is provided for each sample, the generated numerical data is used as an input value, and the provided actual measurement data is used as a teacher value for fuzzy neural network analysis, thereby building an estimation model that indicates a combination of indicators effective for estimation that calculate an output value on the basis of the fuzzy rule.
Perfusion culture is a culture method of cells used in the production of biopharmaceutical drugs using antibodies produced from cells. Perfusion culture is a culture method in which a culture liquid containing cells is continuously filtered and discharged, while a fresh culture medium containing nutritional components is continuously supplied to a culture tank. Perfusion culture is also referred to as continuous culture.
In perfusion culture, parameters, which affect the quality of the antibody, such as process conditions, culture medium components, and the number of cells in cell culture, can be changed even during the cell culture process. Therefore, in perfusion culture, on the basis of the information on the cell culture at a certain time point, it is preferable to be able to estimate the quality of the antibody after elapse of a predetermined period from the certain time point. Specifically, for example, on the basis of the information at a certain time point, in a case where the quality of the antibody after elapse of the predetermined period is within an allowable range, the perfusion culture can be continued as it is, and in a case where the quality is out of the allowable range, the above-mentioned parameters can be adjusted. In such a case, it is possible to effectively support perfusion culture.
In the technique described in JP2009-44974A, the quality of cells is estimated from images obtained by capturing cells at two different time points using an estimation model. That is, the technique described in JP2009-44974A estimates the quality of cells from the degree of change in the image of cells at two different time points. Therefore, the technique described in JP2009-44974A cannot estimate the quality of the antibody from the information at a certain time point, and is therefore unable to effectively support the perfusion culture.
The present disclosure has been made in view of the above-mentioned circumstances, and provides an information processing apparatus, an information processing method, and an information processing program capable of effectively supporting perfusion culture.
The information processing apparatus of the present disclosure includes: an acquisition unit that acquires input information including at least one of a process condition, a culture medium component, or the number and diameters of cells in cell culture; and an estimation unit that estimates a quality of an antibody produced from the cells and a quality of the cells after elapse of a predetermined period from a time point at which the acquisition unit acquires the input information, on the basis of the input information and a trained model which is trained in advance using the input information, the quality of the antibody, and the quality of the cells.
The information processing apparatus of the present disclosure may further include an output unit that outputs a warning in a case where the quality of the antibody and the quality of the cells estimated by the estimation unit are out of an allowable range.
Further, in the information processing apparatus of the present disclosure, the output unit may further output at least one information included in the input information in which the quality of the antibody and the quality of the cells are within the allowable range.
Furthermore, in the information processing apparatus of the present disclosure, an input of the trained model may be a plurality of pieces of the input information acquired at a plurality of time points until the predetermined period as a period for cell proliferation has elapsed from start of the cell culture.
Moreover, the information processing method of the present disclosure causes a computer to execute: acquiring input information including at least one of a process condition, a culture medium component, or the number and diameters of cells in cell culture; and estimating a quality of an antibody produced from the cells and a quality of the cells after elapse of a predetermined period from a time point at which the input information is acquired, on the basis of the input information and a trained model which is trained in advance using the input information, the quality of the antibody, and the quality of the cells.
In addition, the information processing program of the present disclosure causes a computer to execute: acquiring input information including at least one of a process condition, a culture medium component, or the number and diameters of cells in cell culture; and estimating a quality of an antibody produced from the cells and a quality of the cells after elapse of a predetermined period from a time point at which the input information is acquired, on the basis of the input information and a trained model which is trained in advance using the input information, the quality of the antibody, and the quality of the cells.
According to the present disclosure, it is possible to effectively support perfusion culture.
Examples of embodiments for carrying out the technique of the present disclosure will be hereinafter described in detail with reference to the drawings.
A configuration of a cell culture device 100 according to the present embodiment will be described with reference to
The cells used in expressing the antibody are not particularly limited, and examples thereof include animal cells, plant cells, eukaryotic cells such as yeast, prokaryotic cells such as grass bacillus, Escherichia coli, and the like. Animal cells such as CHO cells, BHK-21 cells, and SP2/0-Ag14 cells are preferable, and CHO cells are more preferable.
The antibody expressed in animal cells is not particularly limited, and includes, for example, anti-IL-6 receptor antibody, anti-IL-6 antibody, anti-glypican-3 antibody, anti-CD3 antibody, anti-CD20 antibody, anti-GPIIb/IIIa antibody, anti-TNF antibody, anti-CD25 antibody, anti-EGFR antibody, anti-Her2/neu antibody, anti-RSV antibody, anti-CD33 antibody, anti-CD52 antibody, anti-IgE antibody, anti-CD11a antibody, anti-VEGF antibody, anti-VLA4 antibody, and the like. The antibody includes not only monoclonal antibodies derived from animals such as humans, mice, rats, hamsters, rabbits, and monkeys, but also artificially modified antibodies such as chimeric antibodies, humanized antibodies, and bispecific antibodies.
The obtained antibody or fragment thereof can be purified to be uniform. For the separation and purification of the antibody or a fragment thereof, the separation and purification method used in a conventional polypeptide may be used. For example, an antibody can be separated and purified by appropriately selecting and combining a chromatography column such as affinity chromatography, a filter, ultrafiltration, salting out, dialysis, SDS polyacrylamide gel electrophoresis, and isoelectric point electrophoresis. However, the present invention is not limited thereto. The obtained concentration of the antibody can be measured by measurement of the absorbance or by an enzyme-linked immunosorbent assay (ELISA) or the like.
As shown in
The culture container 10 is a container for containing a cell suspension including cells and a culture medium used in expressing an antibody. Inside the culture container 10, a stirring device 11 having a stirring blade is provided. By rotating the stirring blade of the stirring device 11, the culture medium contained together with the cells in the culture container 10 is stirred, and the homogeneity of the culture medium is maintained.
In the cell culture device 100, in order to prevent the concentration of cells in the culture container 10 from becoming excessively high, a cell bleeding treatment is performed, which is for bleeding off a part of the cells in the culture container 10 (for example, about 10%) at an appropriate timing during the culture period. In the cell bleeding treatment, the cells in the culture container 10 are discharged to the outside of the culture container 10 through the flow passage 39.
One end of the flow passage 31 is connected to the bottom of the culture container 10, and the other end is connected to an inlet 20a of the filter unit 20. In the middle of the flow passage 31, a pump P1, which extracts the cell suspension contained in the culture container 10 and sends the cell suspension to the filter unit 20, is provided.
The filter unit 20 comprises a container 21 and a filter membrane 24 that separates the space inside the container 21 into a supply side 22 and a permeation side 23 and performs a membrane separation treatment on the cell suspension extracted from the culture container 10. Further, the filter unit 20 has the inlet 20a through which the cell suspension flows in and an outlet 20b through which the cell suspension flows out on the supply side 22. The cell suspension extracted from the culture container 10 passes through the filter membrane 24 while flowing into the inside of the container 21 from the inlet 20a and flowing out to the outside of the container 21 from the outlet 20b. The filter unit 20 performs the membrane separation treatment by a tangential flow (cross flow) method of sending permeation components to the permeation side 23 while flowing a liquid subjected to the membrane separation treatment along the membrane surface of the filter membrane 24 subjected to the membrane separation treatment (that is, in a direction parallel to the membrane surface). The tangential flow method, which is a method for membrane separation treatment using the filter membrane 24, may be a method of forming a flow in which the cell suspension extracted from the culture container 10 circulates in one direction in parallel along the membrane surface of the filter membrane 24, or may be a method of forming a flow in which the cell suspension extracted from the culture container 10 reciprocates alternately in parallel along the membrane surface of the filter membrane 24. In a case of forming a circulating flow, for example, a KrosFlo perfusion culture flow path device (KML-100, KPS-200, and KPS-600) manufactured by Spectrum Laboratories Corp. can be suitably used. Further, in a case of forming a flow that reciprocates alternately, the ATF system manufactured by REPLIGEN Corp. can be suitably used.
The relatively large-sized components included in the cell suspension do not permeate through the filter membrane 24, flow out to the outside of the container 21 from the outlet 20b, and are returned to the inside of the culture container 10 through the flow passage 32. That is, in the cell suspension extracted from the culture container 10, the components blocked by the filter membrane 24 are returned to the inside of the culture container 10 through the flow passage 32. On the other hand, the relatively small-sized components included in the cell suspension permeate through the filter membrane 24 and are discharged to the outside of the container 21 from a discharge port 20c provided on the permeation side 23. A flow passage 33 provided with a pump P2 is connected to the discharge port 20c of the filter unit 20, and the components discharged to the permeation side 23 are discharged from the discharge port 20c to the outside of the container 21 through the flow passage 33.
In the cell culture device 100 according to the present embodiment, the filter membrane 24 is used for the purpose of separating cells and components unnecessary for cell culture. Examples of components unnecessary for cell culture include cell carcasses, cell crushed products, DNA, HCP, antibodies, waste products, and the like. That is, the filter membrane 24 has a separation performance suitable for blocking the permeation of cells while allowing components unnecessary for cell culture to permeate.
The components unnecessary for cell culture discharged from the culture container 10 as described above are sent to the next process, which is an antibody purification process.
Next, referring to
The storage unit 43 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. A learning program 50 and an information processing program 52 are stored in the storage unit 43 as a storage medium. The CPU 41 reads the learning program 50 from the storage unit 43, expands the program into the memory 42, and executes the expanded learning program 50. Further, the CPU 41 reads the information processing program 52 from the storage unit 43, expands the program into the memory 42, and executes the expanded information processing program 52. Further, the learning data 54 and the trained model 56 are stored in the storage unit 43.
The measurement unit 48 includes various measurement devices each measuring the process conditions, the culture medium components, and the number and diameters of cells in cell culture using the cell culture device 100. Examples of process conditions include a rotation speed of the stirring device 11 per unit time (hereinafter referred to as “stirring rotation speed”), an aeration amount per unit volume of the culture medium contained in the culture container 10, and a temperature of the culture medium contained in the culture container 10. Further, examples of the culture medium components include an amount of nutritional component, an amount of metabolic component, an amount of dissolved gas (for example, an amount of dissolved oxygen), and the like of the culture medium contained in the culture container 10.
The details of the learning data 54 according to the present embodiment will be described with reference to
As shown in
The trained model 56 is a model which is trained in advance using the learning data 54. An example of the trained model 56 is a neural network model. The trained model 56 is generated by the information processing apparatus 40 in the learning phase described later.
Next, referring to
The acquisition unit 60 acquires the learning data 54 from the storage unit 43. The learning unit 62 generates the trained model 56 by training the model using the learning data 54 acquired by the acquisition unit 60 as training data. Then, the learning unit 62 stores the generated trained model 56 in the storage unit 43.
As an example, as shown in
Next, referring to
In step S10 of
Next, referring to
The acquisition unit 70 acquires the process conditions, the culture medium components, and the number and diameters of cells in the cell culture using the cell culture device 100 measured by the measurement unit 48 at a predetermined periodic timing (for example, once a day). The process condition, the culture medium component, and the number and diameters of cells are examples of input information input to the trained model 56.
The estimation unit 72 estimates the quality of the antibody and the quality of the cells after elapse of a predetermined period (for example, 2 days) from the time point at which the acquisition unit 70 acquires the input information, on the basis of the input information acquired by the acquisition unit 70 and the trained model 56. Specifically, the estimation unit 72 inputs the input information, which is acquired by the acquisition unit 70, to the trained model 56. As described above, the trained model 56 is a model that is trained in a case of inputting the process conditions, the culture medium components, the number and diameters of cells and outputting the quality of the antibody and the quality of the cells after elapse of the predetermined period. Therefore, the output from the trained model 56 is estimated values of the quality of the antibody and the quality of the cells after the predetermined period has elapsed from the time point at which the acquisition unit 70 acquires the input information. As described above, the estimation unit 72 estimates the quality of the antibody and the quality of the cells after the predetermined period has elapsed from the time point at which the acquisition unit 70 acquires the input information.
The determination unit 74 determines whether the quality of the antibody and the quality of the cells estimated by the estimation unit 72 are within the allowable range or out of the allowable range. The allowable range is experimentally determined in advance in accordance with, for example, the cell type and the index value used as the quality of the antibody. For example, in a case where the aggregate amount of the antibody is used as the quality of the antibody, the determination unit 74 determines that the quality of the antibody is out of the allowable range in a case where the aggregate amount of the antibody is equal to or greater than a threshold value, and determines that the quality of the antibody is within the allowable range in a case where the aggregate amount of the antibody is less than the threshold value.
In a case where the determination unit 74 determines that the quality of the antibody and the quality of the cells are out of the allowable range, the derivation unit 76 derives one information piece of the information pieces included in the input information in which the quality of the antibody and the quality of the cells are within the allowable range. Specifically, the derivation unit 76 derives the level of contribution of each explanatory variable (that is, each input) of the trained model 56 to the objective variable (that is, the output), and derives the explanatory variable having the highest level of contribution, as one information piece in which the quality of the antibody and the quality of the cells are within the allowable range.
Referring to
The derivation unit 76 derives the inner product of the weights as the level of contribution for each input node. In the example of
Level of contribution of node 1=W1A×WAO+W1B×WBO (1)
Further, the derivation unit 76 also derives change information indicating how the derived explanatory variable having the highest level of contribution is changed in accordance with whether the sign of the level of contribution is positive or negative. As a specific example, description will be given of a case where the explanatory variable having the highest level of contribution is a stirring rotation speed of the stirring device 11 included in the process conditions and the quality of the antibody is an aggregate amount of the antibody. In such a case, in a case where the sign of the level of contribution is a positive sign, the derivation unit 76 derives the information indicating that the stirring rotation speed is reduced as the above-mentioned change information. On the other hand, in a case where the sign of the level of contribution is a negative sign, the derivation unit 76 derives the information indicating that the stirring rotation speed is increased as the above-mentioned change information.
The derivation unit 76 may derive, for example, a plurality of explanatory variables in descending order of the level of contribution, instead of one explanatory variable having the highest level of contribution, as information that the quality of the antibody and the quality of the cells are within the allowable range, and may derive one or more explanatory variables of which the level of contribution is equal to or greater than the threshold value.
In a case where the determination unit 74 determines that the quality of the antibody and the quality of the cells are out of the allowable range, the output unit 78 outputs a warning to the display unit 44. Further, in such a case, the output unit 78 further outputs the information derived by the derivation unit 76 to the display unit 44. With the outputs, the warning screen shown in
In a case where the explanatory variable derived by the derivation unit 76 is a parameter that can be controlled by the information processing apparatus 40, the output unit 78 may change the parameter by outputting the change information derived by the derivation unit 76 to the control target. Specifically, for example, in a case where the derivation unit 76 derives information indicating that the stirring rotation speed is reduced as change information, the output unit 78 outputs the change information to a motor that controls the stirring rotation speed. As a result, the stirring rotation speed is reduced by a predetermined rotation speed.
Next, referring to
In step S20 of
In step S24, the determination unit 74 determines whether the quality of the antibody and the quality of the cells estimated in step S22 are out of the allowable range. In a case where the determination is affirmative, the processing proceeds to step S26. In step S26, as described above, the derivation unit 76 derives the explanatory variable having the highest level of contribution as the information included in the input information in which the quality of the antibody and the quality of the cells are within the allowable range. Further, as described above, the derivation unit 76 also derives change information indicating how the derived explanatory variable having the highest level of contribution is changed in accordance with whether the sign of the level of contribution is positive or negative. The trained model 56 may be retrained in accordance with the number of batches. In such a case, the weights between the nodes of the trained model 56 are also updated. Therefore, in the present embodiment, the processing of step S26 is executed every time the quality estimation processing is executed.
In step S28, the output unit 78 outputs the warning to the display unit 44 and outputs the information derived in step S26 to the display unit 44, as described above. Through the processing of step S28, the warning screen shown in
As described above, according to the present embodiment, the quality of the antibody and the quality of the cells are estimated after the predetermined period has elapsed from the time point at which the acquisition unit 70 acquires the input information. Therefore, the user is able to grasp the quality of the antibody and the quality of the cells after a predetermined period, and is able to adjust the parameters that affect the quality of the antibody and the quality of the cells in the perfusion culture. Therefore, it is possible to effectively support perfusion culture.
A second embodiment of the disclosed technique will be described. Since the configuration of the cell culture device 100 according to the present embodiment is similar to that of the first embodiment, the description thereof will not be repeated. The hardware configuration of the information processing apparatus 40 according to the present embodiment is similar to that of the first embodiment except for the learning data 54 and the trained model 56 stored in the storage unit 43. Therefore, the learning data 54 and the trained model 56 will be described.
In the contract development of antibody drugs, cells are contracted from customers and antibodies are produced by culturing the contracted cells. In the contract development, as shown in
The small-quantity test is performed, for example, for 30 days. In order to effectively support the perfusion culture, it is preferable that the period of the small-quantity test can be shortened.
As an example, as shown in
Referring to
As shown in
Next, referring to
The acquisition unit 80 acquires the learning data 54 from the storage unit 43. The learning unit 82 generates the trained model 56 by training the model using the learning data 54 acquired by the acquisition unit 80 as training data. Then, the learning unit 82 stores the generated trained model 56 in the storage unit 43.
As an example, as shown in
Next, referring to
In step S40 of
Next, referring to
The acquisition unit 90 acquires a plurality of sets of the process conditions, the culture medium components, and the number and diameters of cells in the cell culture using the cell culture device 100 measured by the measurement unit 48 at a plurality of time points until the predetermined period n as the period for cell proliferation has elapsed from the start of cell culture. The process condition, the culture medium component, and the number and diameters of cells are examples of input information input to the trained model 56.
The estimation unit 92 estimates the quality of the antibody and the quality of the cells after the predetermined period m has elapsed from the time point at which the acquisition unit 90 acquires the input information for the last time, on the basis of the plurality of sets of the input information acquired by the acquisition unit 90 at a plurality of time points and the trained model 56. Specifically, the estimation unit 92 inputs the plurality of sets of the input information acquired by the acquisition unit 90 to the trained model 56. As described above, the trained model 56 is a model that is trained in a case of inputting the plurality of sets of the process conditions, the culture medium components, the number and diameters of cells and outputting the quality of the antibody and the quality of the cells after elapse of the predetermined period m. Therefore, the output from the trained model 56 is estimated values of the quality of the antibody and the quality of the cells after the predetermined period m has elapsed from the time point at which the acquisition unit 90 acquires the input information for the last time. As described above, the estimation unit 92 estimates the quality of the antibody and the quality of the cells after the predetermined period m has elapsed from the time point at which the acquisition unit 90 acquires the input information for the last time.
The output unit 94 displays the quality of the antibody and the quality of the cells estimated by the estimation unit 92 by outputting the qualities to the display unit 44. Thereby, a user is able to know the final quality of the antibody and the final quality of the cells at a time point of the end of the cell proliferation phase. Therefore, the user is able to select a condition in which the quality of the antibody and the quality of the cells are expected to be the highest among the various conditions in the small-quantity test at an early stage, and perform the culture medium-quantity trial production.
Next, referring to
In step S50 of
In step S54, as described above, the estimation unit 92 estimates the quality of the antibody and the quality of the cells after the predetermined period m has elapsed from the time point at which the acquisition unit 90 acquires the input information for the last time, on the basis of the plurality of sets of the input information acquired in step S50 at a plurality of time points and the trained model 56. In step S56, the output unit 94 displays the quality of the antibody and the quality of the cells estimated in step S54 by outputting to the display unit 44. In a case where the processing of step S56 is completed, the quality estimation processing is completed. In the second embodiment, the information processing apparatus 40 may monitor whether or not the quality of the antibody and the quality of the cells are within allowable range or adjust parameters, by using the trained model 56 according to the first embodiment, in a similar manner to the first embodiment, in the period after the cell proliferation phase (for example, the stable phase of
As described above, according to the present embodiment, the quality of the antibody and the quality of the cells are estimated after the predetermined period m has elapsed from the time point at which the input information was acquired for the last time, on the basis of the plurality of input information pieces acquired at the plurality of time points until the predetermined period n as the period for cell proliferation has elapsed from the start of cell culture. Therefore, as a result of shortening the period of the small-quantity test, it is possible to effectively support perfusion culture.
As the hardware structure of the processing unit that executes various processes such as each functional unit of the information processing apparatus 40 in each of the above-mentioned embodiments, it is possible to use various processors to be described below. As described above, various processors include not only a CPU as a general-purpose processor which functions as various processing units by executing software (programs) but also a programmable logic device (PLD) as a processor capable of changing a circuit configuration after manufacturing a field programmable gate array (FPGA); and a dedicated electrical circuit as a processor, which has a circuit configuration specifically designed to execute specific processing, such as an application specific integrated circuit (ASIC).
One processing unit may be configured as one of the various processors, or may be configured as a combination of two or more of the same or different kinds of processors (for example, a combination of a plurality of FPGAs or a combination of a CPU and an FPGA). Further, the plurality of processing units may be composed of one processor.
As an example of the plurality of processing units composed of one processor, first, as represented by computers such as a client and a server, there is a form in which one processor is composed of a combination of one or more CPUs and software and this processor functions as a plurality of processing units. Second, as represented by a system on chip (SoC), there is a form in which a processor that realizes the functions of the whole system including a plurality of processing units with a single integrated circuit (IC) chip is used. As described above, the various processing units are configured by using one or more of the various processors as a hardware structure.
Furthermore, as the hardware structure of these various processors, more specifically, it is possible to use an electric circuit (circuitry) in which circuit elements such as semiconductor elements are combined.
Further, in each of the above-mentioned embodiments, the configuration in which the learning program 50 and the information processing program 52 are stored (installed) in the storage unit 43 in advance has been described, but the present invention is not limited thereto. The learning program 50 and the information processing program 52 may be provided in a form in which the programs are stored in a storage medium such as a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), and a universal serial bus (USB) memory. Further, the learning program 50 and the information processing program 52 may be downloaded from an external device through a network.
From the above-mentioned description, the technology relating to the following supplementary items can be found.
An information processing apparatus comprising:
a processor; and
a memory that is built into or connected to the processor,
in which the processor is configured to
The present disclosure of JP2019-173364 filed on Sep. 24, 2019 is incorporated herein by reference in its entirety. Further, all documents, patent applications, and technical standards described in the present specification are incorporated into the present specification by reference to the same extent as in a case where the individual documents, patent applications, and technical standards were specifically and individually stated to be incorporated by reference.
| Number | Date | Country | Kind |
|---|---|---|---|
| 2019-173364 | Sep 2019 | JP | national |
This application is a continuation application of International Application No. PCT/JP2020/018808 filed May 11, 2020, the disclosure of which is incorporated herein by reference in its entirety. Further, this application claims priority from Japanese Patent Application No. 2019-173364 filed on Sep. 24, 2019, the disclosures of which is incorporated herein by reference in its entirety.
| Number | Date | Country | |
|---|---|---|---|
| Parent | PCT/JP2020/018808 | May 2020 | US |
| Child | 17690389 | US |
