Pharmaceutical support device, method of operating the pharmaceutical support device, and operating program for the pharmaceutical support device.

Abstract

A pharmaceutical assistance device comprising a processor, wherein the processor: acquires protein information relating to a protein included in a preservation target biopharmaceutical product, prescription information relating to a prescription of a candidate preservation solution, which is a candidate for a preservation solution for the preservation target biopharmaceutical product, and measurement data representing the preservation stability of the candidate preservation solution measured in actual testing; derives a feature quantity related to the preservation stability of the candidate preservation solution on the basis of the protein information and the prescription information; and inputs the measurement data and the feature quantity into a machine learning model, and causes a score representing the preservation stability of the candidate preservation solution to be output from the machine learning model.

Description

Technical Field

[0001] The technology of the present disclosure relates to a pharmaceutical support device, a method of operating the pharmaceutical support device, and an operating program for the pharmaceutical support device.

Background Art

[0002] Recently, biopharmaceuticals have attracted attention due to their high drug efficacy and few side effects. Biopharmaceuticals contain proteins such as interferon and antibodies as active ingredients. Biopharmaceuticals are stored in a storage solution. In order to stably maintain the quality of biopharmaceuticals, it is important to make the formulation of the storage solution (also referred to as the formulation recipe) suitable for the biopharmaceuticals.

[0003] The storage solution contains a buffer, an additive, and a surfactant. The formulation of the storage solution is, for example, the type and concentration of each of these buffer, additive, and surfactant, and the hydrogen ion index (pH (Potential Of Hydrogen) value) of the storage solution itself.

[0004] Traditionally, determining the formulation of a preservation solution involved preparing multiple solutions by changing combinations of buffers, additives, and surfactants, and then verifying the preservation stability of each solution through actual testing. However, this process is extremely time-consuming. Therefore, techniques have been proposed, such as WO2021 / 041384 and "Theresa K. Cloutier, et al., Machine Learning Models of Antibody-Excipient Preferential Interactions for Use in Computational Formulation Design, Mol. Pharmaceutics, 17, 9, 3589-3599, 2020." (hereinafter referred to as Reference 1), that predict the preservation stability of a preservation solution without testing, using molecular dynamics (MD) methods or machine learning models based on information about the biopharmaceutical protein or the additives in the preservation solution. [Overview of the Initiative] [Problems that the invention aims to solve]

[0005] The techniques described in WO2021 / 041384 and Reference 1 do not verify the storage stability of the preservation solution through actual testing. Therefore, there was a risk of obtaining predictive results that were far removed from the actual storage stability.

[0006] One embodiment of the technology of this disclosure provides a pharmaceutical support device, a method for operating the pharmaceutical support device, and an operating program for the pharmaceutical support device that can improve the accuracy of predicting the storage stability of a storage solution. [Means for solving the problem]

[0007] The pharmaceutical support device of this disclosure includes a processor which acquires protein information regarding proteins contained in the biopharmaceutical to be preserved, formulation information regarding the formulation of candidate preservation solutions which are candidates for preservation solutions of the biopharmaceutical to be preserved, and measurement data indicating the preservation stability of the candidate preservation solutions measured by actual tests. Based on the protein information and formulation information, the processor derives feature quantities related to the preservation stability of the candidate preservation solutions, inputs the measurement data and feature quantities into a machine learning model, and outputs a score indicating the preservation stability of the candidate preservation solutions from the machine learning model.

[0008] Protein information preferably includes at least one of the following: the amino acid sequence of the protein and the three-dimensional structure of the protein.

[0009] The formulation information preferably includes the type and concentration of each buffer, additive, and surfactant contained in the candidate preservation solution, as well as the hydrogen ion concentration of the candidate preservation solution itself.

[0010] The processor preferably derives features using molecular dynamics methods.

[0011] The feature quantities preferably include at least one of the following: the solvent-exposed surface area of ​​the protein, the spatial aggregation tendency, and the spatial charge map.

[0012] The feature quantities preferably include indicators that show the compatibility between the protein and the additives contained in the candidate preservation solution.

[0013] The measurement data preferably includes at least one of the following: aggregation analysis data of subvisible protein particles in the candidate preservation solution; dynamic light scattering analysis data of the protein in the candidate preservation solution; size exclusion chromatography analysis data of the protein in the candidate preservation solution; and differential scanning calorometry analysis data of the protein in the candidate preservation solution.

[0014] The processor preferably presents auxiliary information based on the score, which helps in determining whether or not to adopt a candidate preservation solution.

[0015] Preferably, the processor determines whether the score meets the pre-set selection criteria and presents the determination result as supplementary information.

[0016] Preferably, the processor outputs multiple scores for each of the multiple candidate preservation solutions, determines the ranking of the candidate preservation solutions based on these scores, and presents the ranking results as supplementary information.

[0017] The processor preferably inputs prescription information, in addition to measurement data and features, into the machine learning model.

[0018] The protein is preferably an antibody.

[0019] The method of operating the pharmaceutical support device of this disclosure includes obtaining protein information regarding proteins contained in the biopharmaceutical to be preserved, formulation information regarding the formulation of candidate preservation solutions which are candidates for preservation solutions of the biopharmaceutical to be preserved, and measurement data indicating the preservation stability of the candidate preservation solutions measured by actual tests, deriving feature quantities related to the preservation stability of the candidate preservation solutions based on the protein information and formulation information, and inputting the measurement data and feature quantities into a machine learning model to output a score indicating the preservation stability of the candidate preservation solutions from the machine learning model.

[0020] The operation program of the pharmaceutical support device of the present disclosure causes a computer to execute a process including: acquiring protein information regarding a protein included in a biopharmaceutical to be stored, formulation information regarding a formulation of a candidate storage solution that is a candidate for a storage solution of the biopharmaceutical to be stored, and measurement data indicating the storage stability of the candidate storage solution measured by an actual test; deriving a feature quantity regarding the storage stability of the candidate storage solution based on the protein information and the formulation information; and inputting the measurement data and the feature quantity into a machine learning model to cause the machine learning model to output a score indicating the storage stability of the candidate storage solution.

Advantages of the Invention

[0021] According to the technology of the present disclosure, it is possible to provide a pharmaceutical support device, a method for operating a pharmaceutical support device, and an operation program for a pharmaceutical support device that can improve the prediction accuracy of the storage stability of a storage solution.

Brief Description of the Drawings

[0022] [Figure 1] It is a diagram showing a pharmaceutical support server and an operator terminal. [Figure 2] It is a diagram showing antibody information. [Figure 3] It is a diagram showing a series of processes of preparation of a candidate storage solution, addition of an antibody, a stress test, and measurement of measurement data, as well as formulation information and measurement data. [Figure 4] It is a block diagram showing a computer constituting a pharmaceutical support server. [Figure 5] It is a block diagram showing a processing unit of a CPU of a pharmaceutical support server. [Figure 6] It is a diagram showing the processing of a feature quantity derivation unit. [Figure 7] It is a diagram showing the processing of a prediction unit. [Figure 8] It is a diagram showing the processing of a prediction unit and a distribution control unit. [Figure 9] It is a diagram showing an information input screen. [Figure 10] It is a diagram showing an auxiliary information display screen. [Figure 11] This is a flowchart showing the processing procedure of the pharmaceutical support server. [Figure 12] This diagram shows the conventional procedure for selecting a preservation solution suitable for the biopharmaceutical to be preserved from among several candidate preservation solutions. [Figure 13] This diagram illustrates the procedure for selecting a suitable preservation solution from among several candidate preservation solutions for the biopharmaceutical to be preserved. [Figure 14] This figure shows the processing of the prediction unit in the second embodiment. [Figure 15] This figure shows the processing of the prediction unit and the distribution control unit in the third embodiment. [Figure 16] This figure shows the auxiliary information display screen of the third embodiment. [Figure 17] This figure shows another example of selection criteria. [Modes for carrying out the invention]

[0023] [First Embodiment] As an example, as shown in Figure 1, the pharmaceutical support server 10 is connected to the operator terminal 11 via a network 12. The pharmaceutical support server 10 is an example of a "pharmaceutical support device" related to the technology disclosed herein. The operator terminal 11 is installed, for example, in a pharmaceutical facility and operated by operators such as pharmacists involved in the manufacture of biopharmaceuticals at the pharmaceutical facility. The operator terminal 11 has a display 13 and input devices 14 such as a keyboard and mouse. The network 12 is, for example, a WAN (Wide Area Network) such as the Internet or a public communication network. Although only one operator terminal 11 is connected to the pharmaceutical support server 10 in Figure 1, in reality, multiple operator terminals 11 from multiple pharmaceutical facilities are connected to the pharmaceutical support server 10.

[0024] The operator terminal 11 sends a prediction request 15 to the pharmaceutical support server 10. The prediction request 15 is a request to the pharmaceutical support server 10 to predict the storage stability of candidate storage solutions 35 (see Figure 3), which are candidates for storage solutions of biopharmaceuticals. The prediction request 15 includes antibody information 16 and a prescription information / measurement dataset group 17. The antibody information 16 is information about the antibody 37 (see Figure 3), which is the active ingredient of the biopharmaceutical. The antibody information 16 is input by the operator operating the input device 14. The antibody 37 is an example of a "protein" related to the technology of this disclosure, and the antibody information 16 is an example of "protein information" related to the technology of this disclosure.

[0025] The prescription information / measurement dataset group 17 includes multiple sets of prescription information 18 and measurement data 19. A set of prescription information 18 and measurement data 19 is registered for each of several types of candidate preservation solutions 35, for example, several to several dozen types. The prescription information 18 is information regarding the formulation of the candidate preservation solution 35. The measurement data 19 is data indicating the preservation stability of the candidate preservation solution 35 as measured by actual tests. These prescription information 18 and measurement data 19 are also input by the operator operating the input device 14. Although not shown in the diagram, the prediction request 15 also includes terminal ID (Identification Data) to uniquely identify the operator terminal 11 that sent the prediction request 15.

[0026] When the pharmaceutical support server 10 receives a prediction request 15, it derives auxiliary information 20 to assist in determining whether or not to adopt the candidate storage solution 35. The pharmaceutical support server 10 distributes the auxiliary information 20 to the operator terminal 11 that sent the prediction request 15. Upon receiving the auxiliary information 20, the operator terminal 11 displays the auxiliary information 20 on the display 13 and makes the auxiliary information 20 available for the operator to view.

[0027] As an example, as shown in Figure 2, antibody information 16 includes the amino acid sequence 25 of antibody 37 and the three-dimensional structure 26 of antibody 37. Antibody information 16 is obtained by analyzing antibody 37 using well-known techniques such as mass spectrometry, X-ray crystallography, and electron microscopy. The amino acid sequence 25 describes the order of peptide bonds of the amino acids constituting antibody 37, such as asparagine (abbreviation ASn), glutamine (abbreviation Glu), and arginine (abbreviation Arg), from the amino terminus to the carboxyl terminus. The amino acid sequence 25 is also called the primary structure. The three-dimensional structure 26 shows the secondary, tertiary, and quaternary structures of the amino acids constituting antibody 37. Secondary structures include the α-helix as exemplified, as well as β-sheets, β-turns, etc. Tertiary structures include the dimeric coiled-coil structure as exemplified. Quaternary structures are dimers, trimers, and tetramers. Some antibodies 37 do not have a quaternary structure (i.e., they are monomers). In that case, the quaternary structure will not be registered, as shown in the example. The three-dimensional structure 26 can also be obtained by inputting the amino acid sequence 25 into "AlphaFold2," a protein three-dimensional structure prediction program developed by DeepMind.

[0028] As an example, as shown in Figure 3, the formulation information 18 includes the type and concentration 30 of the buffer, the type and concentration 31 of the additive, and the type and concentration 32 of the surfactant contained in the candidate preservation solution 35. The formulation information 18 is created by the operator based on the antibody information 16 and their own experience. Multiple types of buffers, additives, and surfactants may be used, as can be seen from the example additives L-arginine hydrochloride and purified sucrose. In that case, the type and concentration are registered for each of the multiple types. The formulation information 18 also includes the hydrogen ion index 33 of the candidate preservation solution 35 itself. The molecular formulas of the buffer, additive, and surfactant may also be added to the formulation information 18.

[0029] The operator prepares the candidate preservation solution 35 in a test tube 36 according to the prescription information 18. Then, the antibody 37 is added to the prepared candidate preservation solution 35. Subsequently, a stress test involving repeated freezing, thawing, and agitation is performed for two weeks. During this two-week stress test, measurement data 19 is actually measured using the measuring instrument 38. Figure 3 shows an example in which measurement data 19_1 and 19_2 are measured in the first and second weeks of the stress test, respectively. The measuring instrument 38 transmits the measurement data 19 to the operator terminal 11.

[0030] Measurement data 19, as shown in measurement data 19_1 for week 1, includes agglutination analysis data 40 of sub-visible particles (SVP) of antibody 37 in candidate storage solution 35 (hereinafter referred to as SVP agglutination analysis data), and dynamic light scattering (DLS) analysis data 41 of antibody 37 in candidate storage solution 35 (hereinafter referred to as DLS analysis data). The SVP agglutination analysis data 40 represents the amount of SVP of antibody 37 in candidate storage solution 35 that causes a decrease in the efficacy of the biopharmaceutical. Similarly, the DLS analysis data 41 represents the amount of nanoparticles of antibody 37 in candidate storage solution 35 that causes a decrease in the efficacy of the biopharmaceutical.

[0031] Furthermore, the measurement data 19 includes size exclusion chromatography (SEC) analysis data (hereinafter referred to as SEC analysis data) 42 of the antibody 37 in the candidate storage solution 35, and differential scanning calorimetry (DSC) analysis data (hereinafter referred to as DSC analysis data) 43 of the antibody 37 in the candidate storage solution 35. The SEC analysis data 42 represents the molecular weight distribution of the antibody 37 in the candidate storage solution 35. The DSC analysis data 43 represents values ​​related to thermophysical properties such as the glass transition temperature and crystallization temperature of the antibody 37 in the candidate storage solution 35. Although only one measuring instrument 38 is depicted in Figure 3 for convenience, in reality, various measuring instruments 38 are available to measure these analysis data 40-43.

[0032] A common candidate preservation solution ID is assigned to the formulation information 18 and measurement data 19 of one candidate preservation solution 35. This candidate preservation solution ID links the formulation information 18 and the measurement data 19. Although Figure 3 only illustrates the preparation, addition of antibody 37, stress test, and measurement of measurement data 19 for one candidate preservation solution 35, in reality, these preparations, additions, stress tests, and measurement of measurement data 19 are performed for each of multiple candidate preservation solutions 35.

[0033] As an example, as shown in Figure 4, the computer comprising the pharmaceutical support server 10 includes storage 50, memory 51, CPU (Central Processing Unit) 52, communication unit 53, display 54, and input device 55. These are interconnected via a bus line 56.

[0034] Storage 50 is a hard disk drive built into the computer constituting the pharmaceutical support server 10, or connected via cable or network. Alternatively, storage 50 is a disk array consisting of multiple hard disk drives installed in series. Storage 50 stores control programs such as the operating system, various application programs, and various data associated with these programs. A solid-state drive may be used instead of a hard disk drive.

[0035] Memory 51 is work memory for the CPU 52 to execute processing. The CPU 52 loads the program stored in storage 50 into memory 51 and executes processing according to the program. In this way, the CPU 52 comprehensively controls each part of the computer. CPU 52 is an example of a "processor" related to the technology of this disclosure. Note that memory 51 may be built into the CPU 52.

[0036] The communication unit 53 controls the transmission of various information to external devices such as the operator terminal 11. The display 54 displays various screens. These screens are equipped with GUI (Graphical User Interface) operation functions. The computer constituting the pharmaceutical support server 10 accepts operation instructions from input devices 55 through the various screens. The input devices 55 include keyboards, mice, touch panels, and microphones for voice input.

[0037] As an example, as shown in Figure 5, the storage 50 of the pharmaceutical support server 10 stores an operating program 60. The operating program 60 is an application program that causes the computer to function as the pharmaceutical support server 10. In other words, the operating program 60 is an example of an "operating program for a pharmaceutical support device" related to the technology of this disclosure. The storage 50 also stores antibody information 16 and prescription information / measurement dataset group 17. The storage 50 also stores a storage stability prediction model 61. The storage stability prediction model 61 is an example of a "machine learning model" related to the technology of this disclosure.

[0038] When the operating program 60 is started, the CPU 52 of the computer constituting the pharmaceutical support server 10 works in cooperation with the memory 51 and the like to function as a reception unit 65, a read / write (hereinafter abbreviated as RW (Read Write)) control unit 66, a feature quantity derivation unit 67, a prediction unit 68, and a distribution control unit 69.

[0039] The reception unit 65 receives a prediction request 15 from the operator terminal 11. As described above, the prediction request 15 includes antibody information 16 and prescription information / measurement dataset group 17, and the prescription information / measurement dataset group 17 includes prescription information 18 and measurement data 19. Therefore, by receiving the prediction request 15, the reception unit 65 acquires the antibody information 16, prescription information 18, and measurement data 19. The reception unit 65 outputs the antibody information 16 and prescription information / measurement dataset group 17 to the RW control unit 66. The reception unit 65 also outputs the terminal ID of the operator terminal 11 (not shown) to the distribution control unit 69.

[0040] The RW control unit 66 controls the storage of various data to the storage 50 and the reading of various data from the storage 50. For example, the RW control unit 66 stores antibody information 16 and prescription information / measurement dataset group 17 from the reception unit 65 in the storage 50. The RW control unit 66 also reads the antibody information 16 and prescription information / measurement dataset group 17 from the storage 50, outputs the antibody information 16 and prescription information 18 to the feature extraction unit 67, and outputs the measurement data 19 to the prediction unit 68. Furthermore, the RW control unit 66 reads the storage stability prediction model 61 from the storage 50 and outputs the storage stability prediction model 61 to the prediction unit 68.

[0041] The feature extraction unit 67 extracts feature quantities 75 related to the storage stability of the candidate storage solution 35 based on the antibody information 16 and the formulation information 18. The feature extraction unit 67 outputs the extracted feature quantities 75 to the prediction unit 68.

[0042] The prediction unit 68 uses a storage stability prediction model 61 to derive a score 76 indicating the storage stability of the candidate storage solution 35 from the measurement data 19 and feature quantities 75. The prediction unit 68 outputs the derived score 76 to the distribution control unit 69.

[0043] The distribution control unit 69 generates auxiliary information 20 based on the score 76. The distribution control unit 69 controls the distribution of the auxiliary information 20 to the operator terminal 11 that sent the prediction request 15. At this time, the distribution control unit 69 identifies the operator terminal 11 that sent the prediction request 15 based on the terminal ID from the reception unit 65.

[0044] As an example, as shown in Figure 6, the feature quantity derivation unit 67 derives feature quantities 75 using molecular dynamics. Feature quantities 75 include the hydrophobic solvent-exposed surface area (hereinafter abbreviated as SASA (Solvent Accessible Surface Area)) 80 of the antibody 37, the spatial aggregation tendency (hereinafter abbreviated as SAP (Spatial Aggregation Propensity)) 81, and the spatial charge map (hereinafter abbreviated as SCM (Spatial Charge Map)) 82. The larger the SASA 80 and the larger the SAP 81, the lower the stability of the antibody 37. SCM 82 represents the degree of charge of the antibody 37 for each region of the antibody 37. These SASA 80, SAP 81, and SCM 82 are derived based solely on the antibody information 16 without referring to the formulation information 18. Therefore, SASA 80, SAP 81, and SCM 82 are common to each candidate storage solution 35.

[0045] Furthermore, feature quantity 75 also includes the Preferred Interaction Coefficient (PIC) 83 described in Reference 1. PIC 83 represents the ease of binding between the antibody 37 and the additive, more specifically, the degree to which the additive covers the surface of the antibody 37, for each region of the antibody 37, and is an indicator of the compatibility between the antibody 37 and the additive. According to PIC 83, it is possible that aggregation of antibody 37, which causes a decrease in the efficacy of biopharmaceuticals, may occur. Unlike SASA 80, SAP 81, and SCM 82 mentioned above, PIC 83 is derived based on both antibody information 16 and formulation information 18. Therefore, PIC 83 differs for each candidate storage solution 35. Consequently, the multiple feature quantities 75 for each candidate storage solution 35 are common to SASA 80, SAP 81, and SCM 82, but differ in PIC 83. PIC 83 may also be derived using machine learning models such as Support Vector Machines (SVM) instead of molecular dynamics. Furthermore, feature quantity 75 is assigned a candidate storage solution ID, similar to the prescription information 18 and measurement data 19.

[0046] As an example, as shown in Figure 7, the prediction unit 68 inputs the measurement data 19 and feature quantities 75 into the storage stability prediction model 61. The storage stability prediction model 61 then outputs a score 76. The score 76 is represented as a continuous numerical value, for example, from 0 to 100. The storage stability prediction model 61 is a machine learning model that predicts a continuous numerical score 76, for example, using a support vector regression (SVR) algorithm. The score 76 is also assigned a candidate storage solution ID, similar to the feature quantities 75.

[0047] The training of the storage stability prediction model 61 may be performed on the pharmaceutical support server 10, or on a device other than the pharmaceutical support server 10. Furthermore, the training of the storage stability prediction model 61 may be continued even after deployment.

[0048] As an example, as shown in Figure 8, the prediction unit 68 causes the storage stability prediction model 61 to output multiple scores 76 for each of the multiple candidate storage solutions 35. The distribution control unit 69 determines the ranking of the multiple candidate storage solutions 35 based on the multiple scores 76, as shown in Table 90. The distribution control unit 69 distributes the ranking determination results shown in Table 90 as auxiliary information 20 to the operator terminal 11.

[0049] Figure 8 shows an example of how candidate preservation solution IDs PS0001 to PS0005 determine the ranking of 35 candidate preservation solutions. The scores are 75 for PS0001, 62 for PS0002, 89 for PS0003, 47 for PS0004, and 82 for PS0005. The rankings are as follows: PS0003 with the highest score of 89 is 1st, PS0005 with the next highest score of 82 is 2nd, PS0001 with 75 is 3rd, PS0002 with 62 is 4th, and PS0004 with the lowest score of 47 is 5th.

[0050] Figure 9 shows an example of an information input screen 100 displayed on the display 13 of the operator terminal 11. The information input screen 100 has an input area 101 for antibody information 16 and an input area 102 for candidate storage solution information 35. The input area 102 has an input area 103 for prescription information 18, an input area 104_1 for measurement data for week 1 1 1 1 1 1 1 1 1 1 1 1 2 1

[0051] The input area 101 of the antibody information 16 is provided with an input box 110 for the amino acid sequence 25 and an input box 111 for the three-dimensional structure 26.

[0052] The input area 103 of the prescription information 18 is provided with a pull-down menu 112 for selecting the type of buffer, an input box 113 for the buffer concentration, a pull-down menu 114 for selecting the type of additive, an input box 115 for the additive concentration, a pull-down menu 116 for selecting the type of surfactant, and an input box 117 for the surfactant concentration.

[0053] Below the buffer pull-down menu 112 and input box 113, there is an add buffer button 118. If the add button 118 is selected, the buffer pull-down menu 112 and input box 113 are added. Below the additive pull-down menu 114 and input box 115, there is an add additive button 119. If the add button 119 is selected, the additive pull-down menu 114 and input box 115 are added. Below the surfactant pull-down menu 116 and input box 117, there is an add surfactant button 120. If the add button 120 is selected, the surfactant pull-down menu 116 and input box 117 are added. In addition, below the input area 103, there is an input box 121 for the hydrogen ion concentration.

[0054] The input area 104 of the measurement data 19 is provided with a file selection button 125 for selecting the SVP agglutination analysis data 40 file, and a file selection button 126 for selecting the DLS analysis data 41 file. Additionally, the input area 104 of the measurement data 19 is provided with a file selection button 127 for selecting the SEC analysis data 42 file, and a file selection button 128 for selecting the DSC analysis data 43 file.

[0055] When files 40-43 of each analysis data are selected, file icons 129, 130, 131, and 132 will appear next to file selection buttons 125-128. File icons 129-132 will not be displayed if no files are selected.

[0056] Below the input area 102 for the candidate preservation solution 35, there is an add button 135 for the candidate preservation solution 35. When the add button 135 is selected, an additional input area 102 for the candidate preservation solution 35 is added.

[0057] Below the add button 135 for candidate storage solution 35, a prediction button 136 is provided. When the prediction button 136 is selected, a prediction request 15, including antibody information 16 and prescription information / measurement dataset group 17, is sent from the operator terminal 11 to the pharmaceutical support server 10. The antibody information 16 includes the contents entered in input boxes 110 and 111. The prescription information / measurement dataset group 17 consists of the contents selected in pull-down menus 112, 114, and 116, the contents entered in input boxes 113, 115, 117, and 121, and each analysis data 40 to 43 selected by file selection buttons 125 to 128.

[0058] Figure 10 shows an example of an auxiliary information display screen 140 that is displayed on the display 13 of the operator terminal 11 when auxiliary information 20 is received from the pharmaceutical support server 10. The auxiliary information display screen 140 has a display area 141 for antibody information 16 and a display area 142 for auxiliary information 20. The display area 141 for antibody information 16 displays the amino acid sequence 25 and the three-dimensional structure 26. The display area 142 for auxiliary information 20 displays a table 143 showing the rank and score 76 of each candidate preservation solution 35. The table 143 is provided with a display button 144 for prescription information 18. When the display button 144 is selected, the display screen for the prescription information 18 of the candidate preservation solution 35 pops up on the auxiliary information display screen 140. The auxiliary information display screen 140 disappears when the confirmation button 145 is selected.

[0059] Next, the operation of the above configuration will be explained with reference to the flowchart in Figure 11. First, when the operating program 60 is started in the pharmaceutical support server 10, as shown in Figure 5, the CPU 52 of the pharmaceutical support server 10 functions as the reception unit 65, RW control unit 66, feature quantity derivation unit 67, prediction unit 68, and distribution control unit 69.

[0060] The information input screen 100 shown in Figure 9 is displayed on the display 13 of the operator terminal 11. The operator enters the desired antibody information 16, prescription information 18, and measurement data 19 into the information input screen 100, and then selects the prediction button 136. This sends a prediction request 15 from the operator terminal 11 to the pharmaceutical support server 10.

[0061] In the pharmaceutical support server 10, the prediction request 15 is received by the reception unit 65. As a result, antibody information 16 and prescription information / measurement dataset group 17 (prescription information 18 and measurement data 19) are acquired (step ST100). The antibody information 16 and prescription information / measurement dataset group 17 are output from the reception unit 65 to the RW control unit 66 and stored in the storage 50 under the control of the RW control unit 66 (step ST110).

[0062] The RW control unit 66 reads out antibody information 16 and prescription information / measurement data set group 17 from the storage 50 (step ST120). The antibody information 16 and prescription information 18 are output from the RW control unit 66 to the feature extraction unit 67. The measurement data 19 is output from the RW control unit 66 to the prediction unit 68.

[0063] As shown in Figure 6, in the feature derivation unit 67, feature quantities 75 are derived using molecular dynamics based on antibody information 16 and formulation information 18 (step ST130). Feature quantities 75 are output from the feature derivation unit 67 to the prediction unit 68.

[0064] Next, as shown in Figure 7, the measurement data 19 and feature quantities 75 are input to the storage stability prediction model 61 in the prediction unit 68, and a score 76 is output from the storage stability prediction model 61 (step ST140). The score 76 is output from the prediction unit 68 to the distribution control unit 69. The processing in steps ST130 and ST140 is repeated until scores 76 for all of the multiple candidate storage solutions 35 are output (NO in step ST150).

[0065] If all scores 76 for multiple candidate preservation solutions 35 are output (YES in step ST150), the distribution control unit 69 determines the ranking of the candidate preservation solutions 35 based on the multiple scores 76 for each candidate preservation solution 35, as shown in Figure 8 (step ST160). This ranking determination result is distributed as auxiliary information 20 to the operator terminal 11 that sent the prediction request 15, under the control of the distribution control unit 69 (step ST170).

[0066] The auxiliary information display screen 140 shown in Figure 10 is displayed on the display 13 of the operator terminal 11. The operator views the auxiliary information display screen 140 and selects one candidate preservation solution 35 to be used as the preservation solution for the biopharmaceutical.

[0067] As described above, the CPU 52 of the pharmaceutical support server 10 includes a reception unit 65, a feature extraction unit 67, and a prediction unit 68. The reception unit 65 receives a prediction request 15 and obtains antibody information 16 regarding the antibody 37 contained in the biopharmaceutical to be preserved, prescription information 18 regarding the prescription of candidate preservation solutions 35 which are candidates for preservation solutions for the biopharmaceutical to be preserved, and measurement data 19 indicating the preservation stability of the candidate preservation solution 35 measured by actual tests. The feature extraction unit 67 derives feature quantities 75 related to the preservation stability of the candidate preservation solution 35 based on the antibody information 16 and prescription information 18. The prediction unit 68 inputs the measurement data 19 and feature quantities 75 into the preservation stability prediction model 61 and outputs a score 76 indicating the preservation stability of the candidate preservation solution 35 from the preservation stability prediction model 61. The score 76 is output based on the measurement data 19 measured by actual tests. Therefore, it is possible to improve the prediction accuracy of the preservation stability of the candidate preservation solution 35 compared to when the measurement data 19 is not used.

[0068] Furthermore, as shown in Figures 12 and 13 as an example, it is possible to reduce the cumbersome process of preparing multiple candidate preservation solutions 35 and verifying the storage stability of each candidate preservation solution 35 through actual testing.

[0069] Figures 12 and 13 show an example of selecting one candidate preservation solution 35 to be used as a preservation solution for a biopharmaceutical from 6 × 5 = 30 candidate preservation solutions 35, each with a hydrogen ion concentration of 5.0, 5.5, 6.0, 6.5, 7.0, and 7.5 in 0.5 increments, and using one of five additives: sorbitol, sucrose, trehalose, proline, and L-arginine hydrochloride.

[0070] Figure 12 shows a conventional procedure as a comparative example. Conventionally, stress tests were performed for 4 weeks on each of the 30 candidate preservation solutions 35, and measurement data 19_1 was recorded in the first week, 19_2 in the second week, 19_3 in the third week, and 19_4 in the fourth week. Based on this measurement data 19, the operator analyzed the storage stability of each candidate preservation solution 35 and selected one candidate preservation solution 35 from among the 30 candidate preservation solutions 35 to be used as a preservation solution for biopharmaceuticals.

[0071] In contrast, in the procedure of this example, as shown in Figure 13, the operator cuts the stress test short at two weeks, half of the four-week period. From the measurement data 19_1 from week 1 and measurement data 19_2 from week 2, measured during this two-week stress test, and the feature quantities 75 derived from antibody information 16 and prescription information 18, a score 76 indicating the storage stability of the candidate preservation solution 35 is derived. Then, supplementary information 20 corresponding to the score 76 is presented to the operator. The measurement data 19_1 from week 1 and measurement data 19_2 from week 2 are interim results from the four-week stress test. Based on the supplementary information 20, the operator analyzes the storage stability of each candidate preservation solution 35 and selects one candidate preservation solution 35 from among the 30 candidate preservation solutions 35 to be adopted as a preservation solution for the biopharmaceutical.

[0072] Thus, while conventional procedures require a four-week stress test, the procedure in this example can be completed with a two-week stress test. Therefore, the cumbersome process of preparing multiple candidate preservation solutions 35 and verifying the storage stability of each candidate preservation solution 35 through actual testing can be reduced.

[0073] Another conventional procedure involves narrowing down the type and concentration of the buffer solution in the first stage, the type and concentration of the additive in the second stage, and so on, until the Nth stage, the range of the hydrogen ion concentration is narrowed down, thus determining the formulation of the preservation solution step by step. The procedure in this example reduces the workload at each stage. Furthermore, in some cases, stages can be omitted, for example, by skipping the first stage and starting from the second stage.

[0074] As shown in Figure 2, the antibody information 16 includes the amino acid sequence 25 of antibody 37 and the three-dimensional structure 26 of antibody 37. Therefore, a feature quantity 75 that more accurately represents the storage stability of the candidate storage solution 35 can be derived. Note that the antibody information 16 only needs to include at least one of the amino acid sequence 25 of antibody 37 and the three-dimensional structure 26 of antibody 37.

[0075] As shown in Figure 3, the formulation information 18 includes the types and concentrations 30-32 of the buffer, additives, and surfactants contained in the candidate preservation solution 35, as well as the hydrogen ion index 33 of the candidate preservation solution 35 itself. Therefore, a characteristic quantity 75 that more accurately represents the storage stability of the candidate preservation solution 35 can be derived.

[0076] As shown in Figure 6, the feature derivation unit 67 derives the feature vectors 75 using molecular dynamics. Molecular dynamics is a popular computer simulation method in the bio-field and can be introduced without any particular obstacles. Therefore, the feature vectors 75 can be easily derived without much effort.

[0077] As shown in Figure 6, feature vector 75 includes SASA80, SAP81, and SCM82 of antibody 37. Feature vector 75 also includes PIC83, an index indicating the compatibility between antibody 37 and the additives contained in candidate preservation solution 35. Therefore, the preservation stability prediction model 61 can output a score 76 that more accurately represents the preservation stability of candidate preservation solution 35 (the stability of antibody 37). Note that feature vector 75 only needs to include at least one of SASA80, SAP81, and SCM82 of antibody 37.

[0078] As shown in Figure 3, the measurement data 19 includes SVP agglutination analysis data 40, DLS analysis data 41, SEC analysis data 42, and DSC analysis data 43 of the antibody 37 in the candidate storage solution 35. Therefore, a score 76 that more accurately represents the storage stability of the candidate storage solution 35 (stability of the antibody 37) can be output from the storage stability prediction model 61. Note that the measurement data 19 only needs to include at least one of the SVP agglutination analysis data 40, DLS analysis data 41, SEC analysis data 42, and DSC analysis data 43.

[0079] As shown in Figure 8, the prediction unit 68 outputs multiple scores 76 for each of the multiple candidate preservation solutions 35. The distribution control unit 69 determines the ranking of the candidate preservation solutions 35 based on the multiple scores 76 and presents the ranking determination result as auxiliary information 20 to the operator terminal 11. This makes it easier for the operator to select candidate preservation solutions 35 to be adopted as preservation solutions for biopharmaceuticals.

[0080] Biopharmaceuticals containing antibody 37 as a protein are called antibody drugs and are widely used to treat chronic diseases such as cancer, diabetes, and rheumatoid arthritis, as well as rare diseases such as hemophilia and Crohn's disease. Therefore, this example, in which antibody 37 is used as the protein, can further accelerate the development of antibody drugs that are widely used to treat various diseases.

[0081] [Second Embodiment] As an example, in the second embodiment shown in Figure 14, in addition to the measurement data 19 and feature quantities 75, formulation information 18 is input to the storage stability prediction model 150. The concentrations of the buffer, additives, and surfactants are entered as numerical values. On the other hand, the types of buffer, additives, and surfactants are entered as pre-set values ​​for each type. Since the formulation information 18 is added to the input data of the storage stability prediction model 150, the prediction accuracy of the score 76 can be further improved. Furthermore, antibody information 16 may also be input. In this case as well, the amino acid sequence 25 and three-dimensional structure 26 are entered as pre-set values.

[0082] [Third Embodiment] As an example, as shown in Figure 15, in the third embodiment, in addition to the result of determining the ranking of candidate preservation solutions 35 based on multiple scores 76, auxiliary information 20 is provided indicating whether or not the scores 76 satisfy the pre-set selection conditions 155.

[0083] The selection criteria 155 are stored in the storage 50. The RW control unit 66 reads the selection criteria 155 from the storage 50 and outputs the selection criteria 155 to the distribution control unit 69. As shown in Table 156, the distribution control unit 69 determines whether the score 76 satisfies the selection criteria 155. In addition to the score 76 and the ranking determination result based on the score 76, the distribution control unit 69 distributes the determination result of whether the score 76 satisfies the selection criteria 155 as auxiliary information 20 to the operator terminal 11.

[0084] Figure 15 shows an example of generating auxiliary information 20 for five candidate preservation solutions 35 with candidate preservation solution IDs PS0001 to PS0005, similar to the case shown in Figure 8. The scores 76 are the same as in Figure 8: PS0001 is 75 points, PS0002 is 62 points, PS0003 is 89 points, PS0004 is 47 points, and PS0005 is 82 points. The selection condition 155 is "score of 75 points or higher". Therefore, the judgment result for PS0003, PS0005, and PS0001, whose score 76 is 75 points or higher, is "met", while the judgment result for PS0002 and PS0004, whose score 76 is less than 75 points, is "not met".

[0085] Figure 16 shows an example of the auxiliary information display screen 140 in the case of the example in Figure 15. The display area 142 displays a table 160 showing the rank of each candidate preservation solution 35, its score 76, and the result of determining whether the score 76 satisfies the selection criteria 155. In table 160, if the score 76 satisfies the selection criteria 155, "OK" is displayed as the result of the determination; conversely, if it does not, "NG" is displayed as the result of the determination.

[0086] Thus, in the third embodiment, the distribution control unit 69 presents the result of determining whether the score 76 satisfies the selection criteria 155 as auxiliary information 20. This facilitates the operator in selecting candidate preservation solutions 35 to be adopted as preservation solutions for biopharmaceuticals.

[0087] The selection criteria are not limited to those that set a threshold of 76, such as selection criterion 155, "score of 75 or higher," as exemplified in Figure 15. For example, they may also be related to the ranking of the score 76, as shown in selection criterion 165 in Figure 17.

[0088] Selection criterion 165 is "1st place, 2nd place". Therefore, PS0003, which is ranked 1st, and PS0005, which is ranked 2nd, will be judged as "met", while PS0001, PS0002, and PS0004, which are ranked 3rd to 5th (not 1st or 2nd), will be judged as "not met". Note that selection criteria related to rank could also be something like "top 20%".

[0089] In the embodiments described above, it was assumed that there were multiple candidate preservation solutions 35, but the invention is not limited to this, and there may be only one candidate preservation solution 35.

[0090] Proteins are not limited to the example antibody 37. They may also include cytokines (interferon, interleukin, etc.), hormones (insulin, glucagon, follicle-stimulating hormone, erythropoietin, etc.), growth factors (IGF (Insulin-Like Growth Factor)-1, bFGF (Basic Fibroblast Growth Factor), etc.), blood coagulation factors (factor VII, factor VIII, factor IX, etc.), enzymes (lysosomal enzymes, DNA (deoxyribonucleic acid) degrading enzymes, etc.), Fc (Fragment Crystallizable) fusion proteins, receptors, albumin, and protein vaccines. Furthermore, antibodies may also include bispecific antibodies, antibody-drug conjugates, small molecule antibodies, and glycosylated antibodies.

[0091] Instead of distributing the auxiliary information 20 from the pharmaceutical support server 10 to the operator terminal 11, the screen data of the auxiliary information display screen 140 shown in Figure 10 may be distributed from the pharmaceutical support server 10 to the operator terminal 11.

[0092] The method of making the auxiliary information 20 available for the operator to view is not limited to the auxiliary information display screen 140. The auxiliary information 20 may be provided to the operator as a printed copy, or an email with the auxiliary information 20 attached may be sent to the operator's mobile terminal.

[0093] The pharmaceutical support server 10 may be installed at each pharmaceutical facility, or it may be installed in a data center independent of the pharmaceutical facilities. Furthermore, the operator terminal 11 may perform some or all of the functions of the processing units 65-68 of the pharmaceutical support server 10.

[0094] The hardware configuration of the computer constituting the pharmaceutical support server 10 according to the technology disclosed herein can be modified in various ways. For example, the pharmaceutical support server 10 can be configured with multiple computers separated as hardware, in order to improve processing power and reliability. For example, the functions of the reception unit 65 and the RW control unit 66, and the functions of the feature quantity derivation unit 67, the prediction unit 68, and the distribution control unit 69 can be distributed among two computers. In this case, the pharmaceutical support server 10 is configured with two computers.

[0095] Thus, the hardware configuration of the pharmaceutical support server 10 can be appropriately changed according to the required performance, such as processing power, safety, and reliability. Furthermore, not only the hardware, but also application programs such as the operating program 60 can, of course, be duplicated or distributed and stored on multiple storage devices for the purpose of ensuring safety and reliability.

[0096] In each of the above embodiments, the hardware structure of the Processing Unit that performs various processes, such as the reception unit 65, the RW control unit 66, the feature quantity derivation unit 67, the prediction unit 68, and the distribution control unit 69, can be the various processors shown below. As mentioned above, the various processors include a CPU 52, which is a general-purpose processor that executes software (operation program 60) and functions as various processing units, as well as programmable logic devices (PLDs), such as FPGAs (Field Programmable Gate Arrays), which are processors whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits, such as ASICs (Application Specific Integrated Circuits), which are processors with circuit configurations specifically designed to perform specific processes.

[0097] A single processing unit may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, and / or a combination of a CPU and an FPGA). Alternatively, multiple processing units may be composed of a single processor.

[0098] Examples of configuring multiple processing units with a single processor include, firstly, a configuration where one or more CPUs and software combine to form a single processor, which then functions as multiple processing units, as exemplified by client and server computers. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple processing units, on a single IC (Integrated Circuit) chip, as exemplified by System-on-a-Chip (SoC). Thus, various processing units are configured, in terms of hardware structure, using one or more of the above-mentioned processors.

[0099] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits, which are combinations of circuit elements such as semiconductor devices.

[0100] From the above description, the technology described in the following supplementary information can be understood.

[0101] [Additional note 1] Equipped with a processor, The aforementioned processor, We obtain protein information regarding the proteins contained in the biopharmaceutical to be preserved, formulation information regarding the formulation of candidate preservation solutions that are candidates for preservation solutions for the biopharmaceutical to be preserved, and measurement data indicating the preservation stability of the candidate preservation solutions measured by actual tests. Based on the protein information and the formulation information, characteristic quantities relating to the storage stability of the candidate storage solution are derived. The measurement data and the features are input into a machine learning model, and the machine learning model outputs a score indicating the storage stability of the candidate storage solution. Pharmaceutical manufacturing support device. [Additional note 2] The pharmaceutical support device according to Appendix 1, wherein the protein information includes at least one of the amino acid sequence of the protein and the three-dimensional structure of the protein. [Additional note 3] The formulation information includes the types and concentrations of buffers, additives, and surfactants contained in the candidate preservation solution, as well as the hydrogen ion concentration of the candidate preservation solution itself, as described in Appendix 1 or Appendix 2 of the pharmaceutical support device. [Additional note 4] The processor is a pharmaceutical support device according to any one of Appendix 1 to Appendix 3, which derives the feature quantities using molecular dynamics. [Additional note 5] The pharmaceutical support device according to Appendix 4, wherein the feature quantities include at least one of the solvent-exposed surface area, spatial aggregation tendency, and spatial charge map of the protein. [Additional note 6] The pharmaceutical support device according to any one of Appendix 1 to Appendix 5, which includes an index indicating the compatibility between the protein and the additive contained in the candidate preservation solution. [Additional note 7] The pharmaceutical support device according to any one of Appendix 1 to Appendix 6, wherein the measurement data includes at least one of the following: aggregation analysis data of subvisible particles of the protein in the candidate preservation solution; dynamic light scattering analysis data of the protein in the candidate preservation solution; size exclusion chromatography analysis data of the protein in the candidate preservation solution; and differential scanning calorometry analysis data of the protein in the candidate preservation solution. [Additional note 8] The aforementioned processor, A pharmaceutical support device according to any one of the appendix items 1 to 7, which provides auxiliary information based on the score, which is useful in determining whether or not to adopt the candidate preservation solution. [Additional note 9] The aforementioned processor, Determine whether the aforementioned score meets the pre-set selection criteria. A pharmaceutical support device as described in Appendix 8, which presents the judgment result as supplementary information. [Additional Note 10] The aforementioned processor, Multiple scores are output for each of the multiple candidate preservation solutions. The ranking of the candidate preservation solutions is determined based on the multiple scores. A pharmaceutical support device according to Appendix 8 or Appendix 9, which presents the results of the ranking determination as the auxiliary information. [Additional Note 11] The pharmaceutical support device according to any one of the appendix 1 to 10, wherein the processor inputs the prescription information in addition to the measurement data and the feature quantities into the machine learning model. [Additional Note 12] The pharmaceutical support device according to any one of the appendices 1 to 11, wherein the protein is an antibody.

[0102] The technology of this disclosure can be appropriately combined with the various embodiments and / or variations described above. Furthermore, it is understood that various configurations can be adopted without departing from the spirit of the invention, and the invention is not limited to the embodiments described above. Moreover, the technology of this disclosure extends not only to programs but also to storage media for storing programs non-temporarily.

[0103] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0104] In this specification, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0105] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

Claims

1. Equipped with a processor, The aforementioned processor, We obtain protein information regarding the proteins contained in the biopharmaceutical to be preserved, formulation information regarding the formulation of candidate preservation solutions that are candidates for preservation solutions for the biopharmaceutical to be preserved, and measurement data indicating the preservation stability of the candidate preservation solutions measured by actual tests. Based on the protein information and the formulation information, characteristic quantities relating to the storage stability of the candidate storage solution are derived. The measurement data and the features are input into a machine learning model, and the machine learning model outputs a score indicating the storage stability of the candidate storage solution. Pharmaceutical manufacturing support device.

2. The pharmaceutical support device according to claim 1, wherein the protein information comprises at least one of the amino acid sequence of the protein and the three-dimensional structure of the protein.

3. The pharmaceutical support device according to claim 1, wherein the formulation information includes the types and concentrations of the buffer, additives, and surfactants contained in the candidate preservation solution, as well as the hydrogen ion concentration of the candidate preservation solution itself.

4. The pharmaceutical support device according to claim 1, wherein the processor derives the feature quantities using molecular dynamics.

5. The pharmaceutical support device according to claim 4, wherein the feature quantity includes at least one of the solvent-exposed surface area of ​​the protein, spatial aggregation tendency, and spatial charge map.

6. The pharmaceutical support device according to claim 1, which includes an index indicating the compatibility between the protein and the additive contained in the candidate preservation solution.

7. The pharmaceutical support apparatus according to claim 1, wherein the measurement data includes at least one of the following: aggregation analysis data of subvisible particles of the protein in the candidate preservation solution; dynamic light scattering analysis data of the protein in the candidate preservation solution; size exclusion chromatography analysis data of the protein in the candidate preservation solution; and differential scanning calorometry analysis data of the protein in the candidate preservation solution.

8. The aforementioned processor, The pharmaceutical support device according to claim 1, which provides auxiliary information based on the score, which is useful in determining whether or not to adopt the candidate preservation solution.

9. The aforementioned processor, Determine whether the aforementioned score meets the pre-set selection criteria. The pharmaceutical support device according to claim 8, which presents the judgment result as the auxiliary information.

10. The aforementioned processor, Multiple scores are output for each of the multiple candidate preservation solutions. The ranking of the candidate preservation solutions is determined based on the multiple scores. The pharmaceutical support device according to claim 8, which presents the result of determining the ranking as the auxiliary information.

11. The pharmaceutical support device according to claim 1, wherein the processor inputs the prescription information in addition to the measurement data and the feature quantities into the machine learning model.

12. The pharmaceutical support device according to claim 1, wherein the protein is an antibody.

13. To obtain protein information regarding proteins contained in the biopharmaceutical to be preserved, formulation information regarding the formulation of candidate preservation solutions that are candidates for preservation solutions of the biopharmaceutical to be preserved, and measurement data indicating the preservation stability of the candidate preservation solutions measured by actual tests. Based on the protein information and the formulation information, the characteristic quantities relating to the storage stability of the candidate storage solution are derived, and The measurement data and the features are input into a machine learning model, and the machine learning model outputs a score indicating the storage stability of the candidate storage solution. A method for operating a pharmaceutical support device, including one.

14. To obtain protein information regarding proteins contained in the biopharmaceutical to be preserved, formulation information regarding the formulation of candidate preservation solutions that are candidates for preservation solutions of the biopharmaceutical to be preserved, and measurement data indicating the preservation stability of the candidate preservation solutions measured by actual tests. Based on the protein information and the formulation information, the characteristic quantities relating to the storage stability of the candidate storage solution are derived, and The measurement data and the features are input into a machine learning model, and the machine learning model outputs a score indicating the storage stability of the candidate storage solution. An operating program for a pharmaceutical support device that causes a computer to perform a process including [specific details].

Images