Information processing system and information processing apparatus

Abstract

An object of the present application is to provide an information processing system and an information processing apparatus with which the amount of data transmitted from a local environment to a cloud environment can be reduced. An information processing system according to an embodiment of the present application includes a first information processing apparatus (100) and a second information processing apparatus (200), wherein: the first information processing apparatus is provided with a first processing unit (103) that irradiates a measurement target that has been dyed with a plurality of fluorescent dyes with light and generates compressed data by performing compression processing on measurement data measured by means of the irradiation with light using reference data for each fluorescent dye used to dye the measurement target, and a transmission unit (104) that transmits the compressed data to the second information processing apparatus; and the second information processing apparatus is provided with a second processing unit (203) that performs reconstruction processing using the reference data and the compressed data received from the first information processing apparatus to generate reconstruction data.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to an information processing system and an information processing apparatus. BACKGROUND

[0002] In the fields of medicine, biochemistry, and the like, a flow cytometer is sometimes used to rapidly measure characteristics of a large number of particles. The flow cytometer, which is a measuring device using an analysis method called flow cytometry, irradiates a particle such as a cell flowing through a flow cell with light and detects fluorescence emitted from the particle.

[0003] The following Patent Literature 1 discloses, in the fluorescence detection of a flow cytometer (a particle measuring device), detecting intensities of light in a continuous wavelength region as a fluorescence spectrum. In the particle measuring device disclosed in Patent Literature 1, by using a light splitting element such as a prism or a grating, fluorescence emitted from a particle such as a cell stained with a plurality of fluorescent dyes is dispersed, and the dispersed fluorescence is detected by a light receiving element array in which a plurality of light receiving elements having different detection wavelength regions are arranged. By collecting detection values of each light receiving element constituting the light receiving element array, a fluorescence spectrum of a measurement target such as a cell can be measured.

[0004] Such a flow cytometer is called a spectral flow cytometer. The spectral flow cytometer has the following advantage compared to a filter method in which fluorescence of each wavelength region is separated and detected using a filter: information on fluorescence can be used as analysis information completely.

[0005] Further, for example, the following Patent Literatures 2 to 5 disclose a method in which a fluorescence spectrum (a measurement spectrum) obtained by a spectral flow cytometer is approximated by a linear sum of reference data (a single stain spectrum) representing a standard fluorescence wavelength distribution of each fluorescent dye to obtain measurement data representing a measurement result of each fluorescent dye. Such a method is called spectral unmixing (hereinafter, simply referred to as “unmixing”).

[0006] LIST OF CITATIONS

[0007] PATENT LITERATURE

[0008] Patent Literature 1: JP 5772425 B2

[0009] Patent Literature 2: JP 5985140 B2

[0010] Patent Literature 3: JP 5540952 B2

[0011] Patent Literature 4: JP 5601098 B2

[0012] Patent Literature 5: JP 5834584 B2 SUMMARY

[0013] Technical Problem

[0014] It is advantageous to use a spectral flow cytometer because a measurement spectrum in which a plurality of fluorescent dyes are mixed and measurement data representing a measurement result of each fluorescent dye can be acquired, and thus, both can be used to finely perform analysis of a measurement object. However, in order to perform such analysis in a local environment, it is necessary to secure sufficient computing resources in the local environment.

[0015] Therefore, it is considered to transfer data acquired in the local environment to a cloud environment and analyze a measurement object in the cloud environment. Using an analysis application in the cloud environment makes it possible to easily perform detailed analysis of a measurement object by utilizing sufficient computing resources of the cloud environment, and makes it possible to easily perform data sharing and the like, which improves user friendliness. However, in this case, if the amount of data to be sent from the local environment to the cloud environment is large, the data transmission period and the communication band for data transmission increase, and the storage cost required to store data in the cloud environment also increases. Therefore, it is desirable to reduce the amount of data to be sent from the local environment to the cloud environment.

[0016] Solution to Problem

[0017] According to the present disclosure, an information processing system includes: a first information processing device; and a second information processing device, the first information processing device including: a first processing unit configured to irradiate a measurement object dyed with a plurality of fluorescent dyes with light, generate compressed data by performing compression processing on measurement data measured by the irradiation using reference data for each fluorescent dye used to dye the measurement object; and a transmission unit configured to transmit the compressed data to the second information processing device, the second information processing device including: a second processing unit configured to generate restoration data by performing restoration processing using the reference data and the compressed data received from the first information processing device.

[0018] Further, according to the present disclosure, an information processing device includes: a first processing unit configured to generate compressed data by performing compression processing on measurement data using reference data for each fluorescent dye used to dye a measurement object, the measurement data being measured by irradiating the measurement object dyed with a plurality of fluorescent dyes with light; and a second processing unit configured to generate restoration data by performing restoration processing using the reference data and the compressed data. BRIEF DESCRIPTION OF DRAWINGS

[0019] [ Figure 1 ] is a view showing a general data flow in a case where an analysis application is used in a cloud environment.

[0020] [ Figure 2FIG. 1 is a view showing an example of a data flow in a case where de-mixing is executed in a local environment.

[0021] [ Figure 3 FIG. 2 is a view showing an example of a data flow according to the present disclosure.

[0022] [ Figure 4A FIG. 3 is a view for explaining data reproducibility by inverse conversion of de-mixing.

[0023] [ Figure 4B FIG. 4 is a view for explaining data reproducibility by inverse conversion of de-mixing.

[0024] [ Figure 5 FIG. 5 is a block diagram showing a configuration example of an information processing system according to a first embodiment.

[0025] [ Figure 6 FIG. 6 is a view showing a schematic configuration example of a flow cytometer.

[0026] [ Figure 7 FIG. 7 is a view showing an outline of de-mixing.

[0027] [ Figure 8 FIG. 8 is a flowchart showing a flow of a series of processes executed in the information processing system according to the first embodiment.

[0028] [ Figure 9 FIG. 9 is a view showing an example of a data flow according to a second embodiment.

[0029] [ Figure 10 FIG. 10 is a block diagram showing a configuration example of an information processing system according to the second embodiment.

[0030] [ Figure 11 FIG. 11 is a flowchart showing a flow of a series of processes executed in the information processing system according to the second embodiment.

[0031] [ Figure 12 FIG. 12 is a view showing an example of a data flow according to a third embodiment.

[0032] [ Figure 13 FIG. 13 is a block diagram showing a configuration example of an information processing system according to the third embodiment.

[0033] [ Figure 14 FIG. 14 is a flowchart showing a flow of a series of processes executed in the information processing system according to the third embodiment.

[0034] [ Figure 15 FIG. 15 is a block diagram showing a configuration example of an information processing system according to a fourth embodiment.

[0035] [Figure 16 FIG. 9 is a flowchart illustrating a feature process executed in the information processing system according to the fourth embodiment.

[0036] [ Figure 17 FIG. 10 is a block diagram illustrating a modification example.

[0037] [ Figure 18 FIG. 11 is a view showing a schematic configuration example of a fluorescence imaging apparatus.

[0038] [ Figure 19 FIG. 12 is a diagram showing an example of a hardware configuration of an information processing apparatus. DETAILED DESCRIPTION

[0039] Advantageous embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same function are denoted with the same reference numerals, and redundant description is omitted.

[0040] Note that the description will be given in the following order.

[0041] 1. SUMMARY OF THE DISCLOSURE

[0042] 2. FIRST EMBODIMENT

[0043] 3. SECOND EMBODIMENT

[0044] 4. THIRD EMBODIMENT

[0045] 5. FOURTH EMBODIMENT

[0046] 6. FIFTH EMBODIMENT

[0047] 7. EXAMPLE OF HARDWARE CONFIGURATION

[0048] 8. SUPPLEMENTARY EXPLANATION

[0049] <1. SUMMARY OF THE DISCLOSURE>

[0050] For example, in order to improve user-friendliness of a user who measures an object using a spectral flow cytometer analysis, an analysis application has been studied to be used in a cloud environment. Although user-friendliness is improved by using an analysis application in a cloud environment, data required for analysis processing needs to be transmitted from a local environment to a cloud environment and stored in the cloud environment. Here, if the amount of data to be transmitted from a local environment to a cloud environment can be reduced, the data transmission period and the data communication band can be reduced. Further, the storage cost in a cloud environment can be reduced.

[0051] In Figure 1A general data flow in a case where an analysis application is used in a cloud environment is shown in FIG. 1. In analysis of a measurement object using a spectral flow cytometer, a measurement data (hereinafter, referred to as "fluorescence spectrum") FS measured by irradiating a measurement object dyed with a plurality of fluorescent dyes with light and a compressed data (hereinafter, referred to as "fluorescent dye amount") FC obtained by performing a data compression process on the fluorescence spectrum FS using reference data (hereinafter, referred to as "spectral reference") SR indicating a standard fluorescence wavelength distribution of each fluorescent dye used for dyeing the measurement object are used.

[0052] The data compression process for generating the fluorescent dye amount FC can be lossy compression, linear processing, or nonlinear processing. The nonlinear processing can include, for example, dimension compression processing, clustering processing, grouping processing, and the like. Further, the linear processing can include, for example, a process of generating fluorescence information of each fluorescent dye from spectral information of light of a biological source particle by performing fluorescence separation. In this specification, such a data compression process is referred to as demixing.

[0053] In a case where the analysis application is used in a cloud environment, it is generally conceivable to perform such demixing in the cloud environment. Therefore, in this case, as shown in FIG. 1, the fluorescence spectrum FS acquired from the spectral flow cytometer and the spectral reference SR used for demixing need to be transferred from a local environment to the cloud environment and stored in the cloud environment. Figure 1

[0054] A problem here is that the data size of the fluorescence spectrum FS is very large. Due to this, the data transmission period from the local environment to the cloud environment becomes long, and there are problems such as a large amount of bandwidth being used for data transmission and a storage cost for storing data in the cloud environment becoming high.

[0055] For such a problem, several methods are conceivable. For example, there is a method of transferring the fluorescence spectrum FS after reducing the data amount by lossless compression (or deleting unused bits) before transferring the fluorescence spectrum FS to the cloud environment. However, it is desired to recover the same data as that before compression by lossless compression, which limits the compression rate and reduces the efficiency.

[0056] ​Further, there can be a method in which the fluorescent spectrum FS is lossy compressed to reduce the amount of data before being transmitted to the cloud environment, and then transmitted. In this method, a high compression rate of data can be expected compared to lossless compression. However, if the lossy compressed fluorescent spectrum FS is restored in the cloud environment, an error occurs. The error occurring here increases due to the back mixing to be performed in the cloud environment, which causes a problem in which the error of the fluorescent dye amount FC generated in the cloud environment becomes very large. This is because a repeated product-sum operation is performed on the fluorescent spectrum FS when the fluorescent dye amount FC is generated by back mixing. Through this product-sum operation, the error of the fluorescent spectrum FS increases and propagates to the fluorescent dye amount FC.

[0057] Further, there can also be a method in which the back mixing is performed in the local environment to generate the fluorescent dye amount FC for each fluorescent dye, the fluorescent dye amount FC is transmitted from the local environment to the cloud environment, and the fluorescent spectrum FS is transmitted from the local environment to the cloud environment in the background. The data flow in this case is shown in Figure 2

[0058] The fluorescent dye amount FC is lower in size than the fluorescent spectrum FS, and has a characteristic that the data size is sufficiently smaller than the data size of the fluorescent spectrum FS. Further, the period required for the back mixing is sufficiently shorter than the period required for the data transfer of the fluorescent spectrum FS. Therefore, by generating the fluorescent dye amount FC in the local environment and transmitting the generated fluorescent dye amount FC to the cloud environment, the fluorescent dye amount FC can be used for analysis earlier than the case where the back mixing is performed in the cloud environment. However, not only the fluorescent dye amount FC but also the fluorescent spectrum FS is used in the analysis process as described above, and therefore, the user needs to wait for the fluorescent spectrum FS to be transmitted to the cloud environment in the background. Further, in this method, both the fluorescent spectrum FS and the fluorescent dye amount FC having a large data size need to be stored in the cloud environment, which cannot solve the problem of an increase in the storage cost of storing data in the cloud environment.

[0059] Therefore, the present disclosure uses a method of restoring the fluorescent spectrum FS from the fluorescent dye amount FC and the spectral reference SR in the cloud environment using inverse conversion of the back mixing. This eliminates the need to transmit the fluorescent spectrum FS from the local environment to the cloud environment and store the fluorescent spectrum FS in the cloud environment, which leads to a reduction in the data transmission period, the communication band, and the storage cost.

[0060] Figure 3 An example of the data flow of the present disclosure is shown in FIG. 1. In the present disclosure, as in Figure 3 ​As illustrated in FIG. 6, the fluorescent dye amount FC is generated from the fluorescence spectrum FS obtained by the spectral flow cytometer by unmixing in the local environment. Then, the fluorescent dye amount FC and the spectral reference SR used for the unmixing are transferred from the local environment to the cloud environment. Thereafter, in the cloud environment, inverse conversion of the unmixing performed in the local environment is performed using the fluorescent dye amount FC and the spectral reference SR transferred from the local environment to restore the fluorescence spectrum FS. The restored fluorescence spectrum FS' is referred to as a restored fluorescence spectrum FS'.

[0061] The restored fluorescence spectrum FS' obtained by the inverse conversion of the unmixing does not exactly reproduce the original fluorescence spectrum FS, but is data close enough to the original fluorescence spectrum FS. Therefore, by using the restored fluorescence spectrum FS' and the fluorescent dye amount FC for analysis processing, the measurement target object can be finely analyzed as in the case where the original fluorescence spectrum FS and the fluorescent dye amount FC are used.

[0062] Here, the reproducibility of data by the inverse conversion of the unmixing will be considered. The expression of the unmixing is indicated below. Here, S denotes the spectral reference SR, X i (where i is 1 to n) denotes the value of the fluorescent dye amount FC of each fluorescent dye, n denotes the number of fluorescent dyes, y i (where i is 1 to m) denotes the value of the fluorescence spectrum FS of each detection channel set for each frequency region, and m denotes the number of detection channels. Here, an example in which the unmixing is performed by the weighted least squares method will be described, but the unmixing can be performed using other methods such as the least squares method.

[0063]

[0064] Here, a case where the number of fluorescent dyes is two and the number of detection channels is three will be described as a simple example. In this case, the relationship between the fluorescent dye amount FC and the fluorescence spectrum FS can be expressed using three expressions: S 11 • x1 + S 12 • x2 = y1, S 21 • x1 + S 22 • x2 = y2, and S 31 • x1 + S 32 • x2 = y3. These equations have three solutions (x1, x2). A process of obtaining one most probable solution from these solutions is the unmixing process. In other words, the unmixing means obtaining x1 and x2 that are closest to the following expressions.

[0065]

[0066] For example, as Figure 4AAs shown, by replacing S and y with appropriate numerical values and replacing the above three expressions with the three expressions 2x1+3x2=5, 3x1-x2=2, and -x1+x2=1, three solutions of (2 / 5, 7 / 5), (1, 1), and (3 / 2, 5 / 2) are obtained. In this case, due to backmixing, one solution (137 / 153, 83 / 75) is obtained.

[0067] If (137 / 153, 83 / 75) is obtained by backmixing, values close to y can be obtained from S and x. In other words, if x1=137 / 153 and x2=83 / 75 are substituted into the three expressions 2x1+3x2=5, 3x1-x2=2, and -x1+x2=1, respectively, y1=5.14667, y2=1.633333, and y3=0.1933333 are obtained, which are close to the values of y in the original three expressions. This process corresponds to the inverse conversion of backmixing.

[0068] The three expressions (2x1+3x2=5.14667, 3x1-x2=1.633333, -x1+x2=0.1933333) recovered by the inverse conversion of backmixing are shown in FIG. 6 together with the original three equations (2x1+3x2=5, 3x1-x2=2, -x1+x2=1). Figure 4B In FIG. 6, the solid lines indicate the expressions recovered by the inverse conversion of backmixing, and the dashed lines indicate the original expressions. As can be seen from FIG. 6, the original data cannot be completely reproduced by the inverse conversion of backmixing, but data with close values can be recovered. Figure 4B

[0069] As described above, according to the method of the present disclosure, by using the inverse conversion of backmixing of the fluorescent dye amount FC and the spectral reference SR transmitted from the local environment to the cloud environment, the fluorescent spectrum FS is recovered in the cloud environment, so that it is not necessary to transmit the fluorescent spectrum FS having a large data size from the local environment to the cloud environment. Therefore, the amount of data to be transmitted from the local environment to the cloud environment can be reduced. Furthermore, the fluorescent spectrum FS can be recovered by performing the inverse conversion of backmixing at the time of performing the analysis processing, so that it is not necessary to always store the fluorescent spectrum FS in the cloud environment. Therefore, the amount of data to be stored in the cloud environment can be reduced, so that the storage cost can be reduced.

[0070] <2. First Embodiment>

[0071] Figure 5 is a block diagram showing a configuration example of an information processing system according to the first embodiment. As shown in FIG. 1, the information processing system 1 according to the first embodiment includes a local environment 10 and a cloud environment 20. Figure 5 ​As shown, the information processing system according to the present embodiment includes a flow cytometer 10 and a first information processing apparatus 100 provided in a local environment, and a second information processing apparatus 200 provided in a cloud environment. The first information processing apparatus 100 provided in the local environment and the second information processing apparatus 200 provided in the cloud environment are connected via a network 20. The network 20 can include, for example, a public network such as the Internet, a telephone network, or a satellite communication network, various local area networks (LANs) including Ethernet (registered trademark), a wide area network (WAN), or the like.

[0072] The flow cytometer 10 measures a fluorescence spectrum FS (measurement data) by irradiating a measurement target object dyed with a plurality of fluorescent dyes with light. The measurement target object can be a biogenic particle such as a cell, a tissue, a microorganism, and a biorelated particle. For example, the cell can be an animal cell (e.g., a blood cell), a plant cell, or the like. For example, the tissue can be a tissue collected from a human body or the like, or can be a part of a tissue (including a tissue cell) rather than an entire tissue. For example, the microorganism can be a bacterium such as Escherichia coli, a virus such as tobacco mosaic virus, a fungus such as yeast, or the like. The biorelated particle can be a particle constituting a cell such as a chromosome, a liposome, a mitochondrion, or various organelles (cell organelles). Note that the biorelated particle can include a biorelated polymer such as a nucleic acid, a protein, a lipid, and a sugar chain, and a combination thereof. These biogenic particles can have a spherical shape or a non-spherical shape, and are not particularly limited in terms of size and mass.

[0073] The measurement target object can be an industrial synthetic particle such as a latex particle, a gel particle, and an industrial particle. For example, the industrially synthesized particle can be a particle synthesized with an organic resin material such as polystyrene and polymethyl methacrylate, an inorganic material such as glass, silica, and a magnet, or a metal such as colloidal gold and aluminum. The industrially synthesized particle can also have a spherical shape or a non-spherical shape, and is not particularly limited in terms of size and mass in a similar manner.

[0074] The measurement target object is dyed (labeled) with a plurality of fluorescent dyes before the fluorescence spectrum FS is measured. The measurement target object can be labeled with a fluorescent dye using a known method. Specifically, in the case where the measurement target object is a cell, the measurement target cell can be labeled with a fluorescent dye by mixing a fluorescently labeled antibody selectively binding to an antigen present on the cell surface with the measurement target cell and binding the fluorescently labeled antibody to the antigen on the cell surface. Alternatively, the measurement target cell can also be labeled with a fluorescent dye by mixing a fluorescent dye selectively taken up by a specific cell with the measurement target cell.

[0075] The fluorescently labeled antibody is an antibody to which a fluorescent dye is bound as a label. The fluorescently labeled antibody can be an antibody to which a fluorescent dye is directly bound. Alternatively, the fluorescently labeled antibody can be an antibody to which a fluorescent dye bound to avidin is bound by an avidin-biotin reaction to a biotin-labeled antibody. Note that, as the antibody, a polyclonal antibody or a monoclonal antibody can be used.

[0076] The fluorescent dye used for labeling the cells is not particularly limited, and a known dye or the like used for staining cells can be used. For example, as the fluorescent dye, phycoerythrin (PE), fluorescein isothiocyanate (FITC), PE-Cy5, PE-Cy7, PE-Texas Red (registered trademark), allophycocyanin (APC), APC-Cy7, ethidium bromide, propidium iodide, Hoechst (registered trademark) 33258, Hoechst (registered trademark) 33342, DAPI (4', 6-diamidino-2-phenylindole), acridine orange, chromomycin, mithramycin, olivomycin, pyranine Y, thiazole orange, rhodamine 101, isothiocyanate, BCECF, BCECF-AM, C.SNARF-1, C.SNARF-1 AMA, aequorin, Indo-1, Indo-1-AM, Fluo-3, Fluo-3-AM, Fura-2, Fura-2-AM, oxanol, Texas Red (registered trademark), rhodamine 123, 10-N-nonyl-acridine orange, fluorescein, fluorescein diacetate, carboxyfluorescein, carboxyfluorescein diacetate, carboxy-dichlorofluorescein, carboxy-dichlorofluorescein diacetate, or the like can be used. In addition, a derivative of the above fluorescent dye or the like can also be used.

[0077] Figure 6 A schematic configuration example of the flow cytometer 10 is shown in FIG. 1. As shown in FIG. 1, the flow cytometer 10 includes a laser light source 11, a flow cell 12, a light-splitting element 13, and a photodetector 14. Figure 6

[0078] The laser light source 11 emits laser light having a wavelength capable of exciting a fluorescent dye used for staining a measurement target (sample) S. Although only one laser light source 11 is shown in FIG. 1, a plurality of laser light sources 11 can be provided. As the laser light source 11, for example, a semiconductor laser light source that emits laser light having a predetermined wavelength can be used. The laser light emitted from the laser light source 11 can be pulsed light or continuous light. Figure 6

[0079] ​​Flow cytometer 12 is a flow path that allows a measurement object S, such as a cell, to flow while being aligned in one direction. Specifically, flow cytometer 12 causes the sheath fluid surrounding the measurement object S, such as a cell, to flow at high speed as a laminar flow to align and flow the measurement object S, such as a cell, in one direction.

[0080] The spectroscopic element 13 is an optical element that disperses the fluorescence emitted by the object being measured, S, into a spectrum of continuous wavelengths by means of laser irradiation from the laser source 11. For example, a prism, a grating, or the like can be used as the spectroscopic element 13.

[0081] The photodetector 14 includes an array of light-receiving elements that detect fluorescence generated from a measurement object S irradiated by a laser and dispersed by a beam splitter 13. For example, the light-receiving element array has a configuration in which multiple independent detection channels are arranged, each having a different wavelength region of the light to be detected. Specifically, the light-receiving element array is composed of, for example, arranged light-receiving elements such as multiple photomultiplier tubes (PMTs) or photodiodes, which have different wavelength regions to be detected in one dimension along the spectral direction of the beam splitter 13. The number of light-receiving elements constituting the light-receiving element array, i.e., the number of detection channels, is set to be greater than the number of fluorescent dyes used to stain the measurement object S.

[0082] In the flow cytometer 10 configured as described above, the analyte S flowing through the flow cytometer 12 is irradiated by a laser from the laser source 11, causing the analyte S to emit fluorescence. The fluorescence emitted from the analyte S is dispersed into a continuous spectrum by the spectrophotometer 13 and received (detected) by a plurality of light-receiving elements forming the light-receiving element array of the photodetector 14. This allows for the measurement of the fluorescence spectrum FS of the analyte S stained with various fluorescent dyes.

[0083] like Figure 5 As shown, a first information processing device 100, located in a local environment and connected to a flow cytometer 10, includes a fluorescence spectroscopy acquisition unit 101, a spectral reference storage unit 102, a fluorescence dye quantity generation unit 103 (an example of a "first processing unit"), and a transmission unit 104. It should be noted that some or all of the functions of the first information processing device 100 can be implemented within the flow cytometer 10. In other words, at least a portion of the first information processing device 100 can be integrated with the flow cytometer 10.

[0084] The fluorescence spectroscopy acquisition unit 101 acquires the fluorescence spectrum FS (measurement data) as measurement data obtained by the flow cytometer 10.

[0085] The spectral reference storage unit 102 stores spectral references SR (reference data) representing standard fluorescence wavelength distributions of each fluorescent dye. The spectral reference storage unit 102 stores spectral references SR of various fluorescent dyes that can be used for fluorescence detection by the flow cytometer 10 in, for example, a library format. Note that the spectral reference storage unit 102 can be provided in a server device or the like outside the first information processing device 100.

[0086] The fluorescent dye amount generation unit 103 deconvolves the fluorescence spectrum FS acquired by the fluorescence spectrum acquisition unit 101 using the spectral reference SR corresponding to each fluorescent dye used to dye the measurement object S among the spectral references SR stored in the spectral reference storage unit 102, to generate a fluorescent dye amount FC representing a measurement result of each fluorescent dye used to dye the measurement object S.

[0087] Figure 7 is a diagram illustrating an outline of deconvolution to be performed by the fluorescent dye amount generation unit 103. As shown in Figure 7 the fluorescence spectrum FS of the measurement object S measured by the flow cytometer 10 is a mixture of spectra of a plurality of fluorescent dyes used to dye the measurement object S. Deconvolution is a process of separating the fluorescence spectrum FS in which spectra of a plurality of fluorescent dyes used to dye the measurement object S are mixed into a spectrum of each fluorescent dye using the spectral reference SR corresponding to each fluorescent dye, and obtaining a fluorescent dye amount FC representing a measurement result of each fluorescent dye in this way.

[0088] Specifically, it is assumed that the fluorescence spectrum FS of the measurement object S dyed with a plurality of fluorescent dyes is represented by a linear sum of spectral references SR corresponding to each fluorescent dye used to dye the measurement object S, and the fluorescent dye amount FC as a measurement result of each fluorescent dye can be derived by superimposing the spectral references SR corresponding to each fluorescent dye and fitting the spectral references SR to the fluorescence spectrum FS to obtain a coupling coefficient of each fluorescent dye linearly coupled. A calculation method such as a weighted least squares method or a least squares method can be used for fitting. Note that specific examples of such a calculation method are described in detail in Patent Documents 2 to 5 and the like, and thus detailed description thereof will be omitted here.

[0089] The transmission unit 104 transmits the fluorescent dye amounts FC (i.e., the fluorescent dye amounts FC representing the measurement results of each fluorescent dye used for staining the measurement object S) generated by the fluorescent dye amount generation unit 103 and the spectral references SR (i.e., the spectral references SR corresponding to each fluorescent dye used for staining the measurement object S) used for the de-mixing at the fluorescent dye amount generation unit 103 to the second information processing apparatus 200 via the network 20. Here, it should be noted that the transmission unit 104 does not transmit the fluorescence spectrum FS as the measurement data by the flow cytometer 10 to the second information processing apparatus 200. In other words, in the information processing system according to the present embodiment, the fluorescence spectrum FS having a large data size is not transmitted from the first information processing apparatus 100 to the second information processing apparatus 200, and only the fluorescent dye amounts FC and the spectral references SR having a small data size are transmitted from the first information processing apparatus 100 to the second information processing apparatus 200.

[0090] On the other hand, as shown in FIG. 2, the second information processing apparatus 200 provided in the cloud environment includes a reception unit 201, a storage unit 202, a fluorescence spectrum restoration unit 203 (“second processing unit”), and an analysis processing unit 204. Figure 5

[0091] The reception unit 201 receives the fluorescent dye amounts FC and the spectral references SR transmitted from the first information processing apparatus 100 via the network 20.

[0092] The storage unit 202 stores the fluorescent dye amounts FC and the spectral references SR received by the reception unit 201 from the first information processing apparatus 100.

[0093] The fluorescence spectrum restoration unit 203 restores the fluorescence spectrum FS as the measurement data by the flow cytometer 10 by performing the inverse conversion of the de-mixing performed when the fluorescent dye amount generation unit 103 of the first information processing apparatus 100 generates the fluorescent dye amounts FC using the fluorescent dye amounts FC and the spectral references SR stored in the storage unit 202, and generates a restored fluorescence spectrum FS’. As described above, the restored fluorescence spectrum FS’ does not exactly reproduce the original fluorescence spectrum FS, but is data close enough to the original fluorescence spectrum FS. It is preferable that the restored fluorescence spectrum FS’ (preferably the restored fluorescence spectrum FS) be generated by the fluorescence spectrum restoration unit 203 before the analysis processing by the analysis processing unit 204. Therefore, the generated restored fluorescence spectrum FS’ can be used as it is in the analysis processing by the analysis processing unit 204 without being permanently stored.

[0094] ​The analysis processing unit 204 analyzes the measurement target object S using the fluorescent dye amounts FC stored in the storage unit 202 and the recovered fluorescent spectrum FS' generated by the fluorescent spectrum recovery unit 203. This analysis processing can include, for example, a clustering process on the measurement target object S. By the clustering process, the measurement target objects S such as cells can be classified into a plurality of groups obtained by external isolation and internal binding. The algorithm of the clustering process is not particularly limited, and a known clustering algorithm can be used. For example, the analysis processing unit 204 can perform the clustering process using an algorithm capable of specifying the number of clusters such as k-means, or can perform the clustering process using an algorithm that automatically determines the number of clusters such as flowsom.

[0095] Further, the analysis processing unit 204 can present the result of the analysis processing such as the clustering process to the user. In a case where the result of the clustering process is presented to the user, the analysis processing unit 204 can display the result of the clustering process in, for example, a table format or a minimum spanning tree format. In addition to the clustering process, the analysis processing unit 204 can perform various analysis processes using the fluorescent dye amounts FC and the recovered fluorescent spectrum FS' according to the operation of the user and can present the result to the user.

[0096] Figure 8 is a flowchart showing a flow of a series of processes performed in the information processing system according to the first embodiment. Hereinafter, an outline of the operation of the information processing system according to the present embodiment will be described along with Figure 8 the flowchart.

[0097] First, if a fluorescent spectrum FS of a measurement target object S stained with a plurality of fluorescent dyes is measured by the flow cytometer 10, the fluorescent spectrum acquisition unit 101 of the first information processing apparatus 100 acquires the fluorescent spectrum FS (step S101).

[0098] Next, the fluorescent dye amount generation unit 103 of the first information processing apparatus 100 deconvolves the fluorescent spectrum FS acquired by the fluorescent spectrum acquisition unit 101 in step S101 using the spectral reference SR corresponding to each fluorescent dye used for staining the measurement target object S among the spectral references SR stored in the spectral reference storage unit 102, to generate the fluorescent dye amount FC representing the measurement result of each fluorescent dye (step S102).

[0099] Next, the transmission unit 104 of the first information processing apparatus 100 transmits the fluorescent dye amount FC generated by the fluorescent dye amount generation unit 103 in step S102 and the spectral reference SR used for deconvolution to the second information processing apparatus 200 via the network 20 (step S103).

[0100] Next, the receiving unit 201 of the second information processing device 200 receives the amount of fluorescent dye FC and the spectral reference SR sent from the first information processing device 100 via the network 20 and stores them in the storage unit 202 (step S104).

[0101] Subsequently, the fluorescence spectrum recovery unit 203 of the second information processing device 200 performs an inverse conversion of antimixing in step S102 using the amount of fluorescent dye FC and the spectral reference SR stored in the storage unit 202 to recover the fluorescence spectrum FS, thereby generating the recovered fluorescence spectrum FS' (step S105).

[0102] Then, in step S105, the analysis and processing unit 204 of the second information processing device 200 uses the amount of fluorescent dye FC stored in the storage unit 202 and the restored fluorescence spectrum FS' generated by the fluorescence spectrum recovery unit 203 to perform analysis and processing on the measurement object S (step S106), and a series of processes are completed.

[0103] As described above, in the information processing system according to this embodiment, since the amount of fluorescent dye FC and the spectral reference SR are transmitted from the first information processing device 100 in the local environment to the second information processing device 200 in the cloud environment, and an inverse conversion of antimixing is performed using the amount of fluorescent dye FC and the spectral reference SR in the second information processing device 200 in the cloud environment, a recovered fluorescence spectrum FS' is generated by recovering the fluorescence spectrum FS. This enables analysis and processing using the amount of fluorescent dye FC and the recovered fluorescence spectrum FS' at the second information processing device 200 in the cloud environment without sending the fluorescence spectrum FS, which has a large data size, from the first information processing device 100 in the local environment to the second information processing device 200 in the cloud environment. This reduces the amount of data sent from the local environment to the cloud environment and reduces the amount of data stored in the cloud environment, thereby reducing storage costs.

[0104] <3. Second Implementation Method>

[0105] As described above, the recovered fluorescence spectrum FS' generated by the inverse conversion of the antimixing fluorescence spectrum FS is data that is sufficiently close to the original fluorescence spectrum FS, but does not completely reproduce the original fluorescence spectrum FS. This is because the antimixing performed on the original fluorescence spectrum FS has the property of removing information other than the spectral information of the spectral reference SR used for antimixing.

[0106] In this embodiment, an example of a method for increasing the reproducibility of fluorescence spectra (FS) will be described. Figure 9 An example of the data flow in this embodiment is shown. In this embodiment, as... Figure 9As shown, when performing the unmixing on the fluorescence spectrum FS in the local environment, in addition to the spectral reference SR corresponding to the fluorescent dye used to dye the measurement object S, a virtual spectral reference SR' is used, which is virtual data independent of the fluorescent dye used to dye the measurement object S. The virtual spectral reference SR' includes spectral information not included in the spectral reference SR corresponding to the fluorescent dye used to dye the measurement object S, and thus, by adding the virtual spectral reference SR', it is possible to retain spectral information that was originally deleted by the unmixing, so that it is possible to improve the reproducibility of the recovered fluorescence spectrum FS' generated by the inverse conversion of the unmixing.

[0107] If the unmixing is performed on the fluorescence spectrum FS using the virtual spectral reference SR' in addition to the spectral reference SR, a virtual fluorescent dye amount FC' is generated in which virtual data is added to the original fluorescent dye amount FC. In the present embodiment, the virtual fluorescent dye amount FC', the spectral reference SR, and the virtual spectral reference SR' are transferred from the local environment to the cloud environment. Then, by performing the inverse conversion of the unmixing in the cloud environment using the virtual fluorescent dye amount FC', the spectral reference SR, and the virtual spectral reference SR', a recovered fluorescence spectrum FS' with high reproducibility is generated.

[0108] Further, in the present embodiment, the virtual fluorescent dye amount FC' is transferred from the local environment to the cloud environment instead of the fluorescent dye amount FC, and thus, it is necessary to generate the fluorescent dye amount FC in the cloud environment. Therefore, in the cloud environment, the unmixing is performed on the recovered fluorescence spectrum FS' using the spectral reference SR to generate the fluorescent dye amount FC. Then, the measurement object S is subjected to the analysis process using the fluorescent dye amount FC and the recovered fluorescence spectrum FS'.

[0109] According to the method of the present embodiment, as the data amount of the virtual spectral reference SR' increases, the data amount of the virtual fluorescent dye amount FC' increases, and the reproducibility of the recovered fluorescence spectrum FS' generated by the inverse conversion of the unmixing increases. In other words, the reproducibility rate of the recovered fluorescence spectrum FS' can be controlled by adjusting the data amount of the virtual spectral reference SR'. Therefore, for example, it is possible to control the increase in the amount of data sent from the local environment to the cloud environment by adjusting the data amount of the virtual spectral reference SR' according to the reproducibility rate of the recovered fluorescence spectrum FS' required for the analysis.

[0110] Note that, as the virtual spectral reference SR', spectral information not included in the spectral references SR used for the unmixing can be generated and used. Further, for example, a spectral reference SR corresponding to a fluorescent dye different from the fluorescent dye used for staining the measurement target object S can be used as the virtual spectral reference SR'. Still further, the virtual spectral reference SR' can be any data that can supplement spectral information not included in the spectral references SR used for the unmixing, and, for example, a random number or the like can also be used as the virtual spectral reference SR'.

[0111] Figure 10 is a block diagram showing a configuration example of an information processing system according to a second embodiment. As shown in Figure 10 In the present embodiment, the first information processing device 100' provided in the local environment includes a virtual fluorescent dye amount generation unit 105 ("example of the first processing unit") instead of the fluorescent dye amount generation unit 103 described above. Further, in the present embodiment, the second information processing device 200' provided in the cloud environment further includes a fluorescent dye amount generation unit 205 (part of the function corresponding to the "second processing unit").

[0112] The virtual fluorescent dye amount generation unit 105 unmixes the fluorescent spectrum FS acquired by the fluorescent spectrum acquisition unit 101 using the virtual spectral reference SR' among the spectral references SR stored in the spectral reference storage unit 102 and the spectral references SR corresponding to each of the fluorescent dyes used for staining the measurement target object S, to generate a virtual fluorescent dye amount FC'. As the virtual spectral reference SR', spectral information not included in the spectral references SR corresponding to each of the fluorescent dyes used for staining the measurement target object S can be generated and used individually, or a spectral reference SR other than the spectral references SR corresponding to each of the fluorescent dyes used for staining the measurement target object S among the spectral references SR stored in the spectral reference storage unit 102 can be used, or a random number can be used.

[0113] In the present embodiment, the transmission unit 104 of the first information processing device 100' transmits the virtual fluorescent dye amount FC' generated by the virtual fluorescent dye amount generation unit 105, and the spectral references SR and the virtual spectral reference SR' used for the unmixing at the virtual fluorescent dye amount generation unit 105, to the second information processing device 200' via the network 20.

[0114] The reception unit 201 of the second information processing device 200' receives the virtual fluorescent dye amount FC', the spectral references SR, and the virtual spectral reference SR' transmitted from the first information processing device 100' via the network 20.

[0115] The storage unit 202 stores the virtual fluorescent dye amount FC', the spectral reference SR, and the virtual spectral reference SR' received by the reception unit 201 from the first information processing apparatus 100'.

[0116] The fluorescence spectrum restoration unit 203 uses the virtual fluorescent dye amount FC', the spectral reference SR, and the virtual spectral reference SR' stored in the storage unit 202 to generate a restored fluorescence spectrum FS' by performing inverse conversion of the unmixing performed when the virtual fluorescent dye amount FC' is generated by the virtual fluorescent dye amount generation unit 105 of the first information processing apparatus 100'. In the present embodiment, as described above, the unmixing and the inverse conversion of the unmixing are performed using the virtual spectral reference SR, so that the restored fluorescence spectrum FS' having high reproducibility can be generated compared to the above-described first embodiment.

[0117] The fluorescence dye amount generation unit 205 unmixes the restored fluorescence spectrum FS' generated by the fluorescence spectrum restoration unit 203 using the spectral reference SR stored in the storage unit 202 to generate the fluorescence dye amount FC. The restored fluorescence spectrum FS' generated by the fluorescence spectrum restoration unit 203 is obtained by restoring the original fluorescence spectrum FS having high reproducibility, and thus the fluorescence dye amount generation unit 205 can accurately generate the fluorescence dye amount FC by unmixing the restored fluorescence spectrum FS'.

[0118] The analysis processing unit 204 uses the fluorescence dye amount FC generated by the fluorescence dye amount generation unit 205 and the restored fluorescence spectrum FS' generated by the fluorescence spectrum restoration unit 203 to analyze the measurement target object S in a similar manner to the above-described first embodiment.

[0119] Figure 11 is a flowchart showing a flow of a series of processes performed in the information processing system according to the second embodiment. Hereinafter, an outline of the operation of the information processing system according to the present embodiment will be described along with Figure 11 the flowchart.

[0120] First, if the fluorescence spectrum FS of the measurement target object S stained with a plurality of fluorescent dyes is measured by the flow cytometer 10, the fluorescence spectrum acquisition unit 101 of the first information processing apparatus 100' acquires the fluorescence spectrum FS (step S201).

[0121] Next, the virtual fluorescent dye amount generation unit 105 of the first information processing apparatus 100' unmixes the fluorescence spectrum FS acquired by the fluorescence spectrum acquisition unit 101 in step S201 using the spectral reference SR corresponding to each fluorescent dye used to stain the measurement target object S and the virtual spectral reference SR' in the spectral reference SR stored in the spectral reference storage unit 102 to generate the virtual fluorescent dye amount FC' (step S202).

[0122] Next, the transmission unit 104 of the first information processing apparatus 100' transmits the virtual fluorescent dye amount FC' generated by the virtual fluorescent dye amount generation unit 105 in step S202, and the spectral reference SR and the virtual spectral reference SR' for the reverse mixing to the second information processing apparatus 200' via the network 20 (step S203).

[0123] Next, the reception unit 201 of the second information processing apparatus 200' receives the virtual fluorescent dye amount FC', the spectral reference SR, and the virtual spectral reference SR' transmitted from the first information processing apparatus 100' via the network 20, and stores them in the storage unit 202 (step S204).

[0124] Thereafter, the fluorescent spectrum restoration unit 203 of the second information processing apparatus 200' restores the fluorescent spectrum FS by performing the inverse conversion of the reverse mixing performed by the virtual fluorescent dye amount generation unit 105 of the first information processing apparatus 100' in step S202 using the virtual fluorescent dye amount FC', the spectral reference SR, and the virtual spectral reference SR' stored in the storage unit 202, to generate a restored fluorescent spectrum FS' (step S205).

[0125] Further, the fluorescent dye amount generation unit 205 of the second information processing apparatus 200' reverse-mixes the restored fluorescent spectrum FS' generated by the fluorescent spectrum restoration unit 203 in step S205 using the spectral reference SR stored in the storage unit 202, to generate a fluorescent dye amount FC (step S206).

[0126] Then, the analysis processing unit 204 of the second information processing apparatus 200' performs analysis processing on the measurement target object S using the fluorescent dye amount FC generated by the fluorescent dye amount generation unit 205 in step S206 and the restored fluorescent spectrum FS' generated by the fluorescent spectrum restoration unit 203 in step S205 (step S207), and the series of processing ends.

[0127] As described above, according to the present embodiment, the reverse mixing of the fluorescent spectrum FS and the inverse conversion of the reverse mixing are performed using the virtual spectral reference SR' having spectral information not included in the spectral reference SR, so that the reproducibility of the restored fluorescent spectrum FS' generated in the cloud environment can be improved. Further, the reproducibility of the restored fluorescent spectrum FS' generated in the cloud environment can be controlled by adjusting the data amount of the virtual spectral reference SR', so that an increase in the data amount transferred from the local environment to the cloud environment can be minimized.

[0128] <4. Third Embodiment>

[0129] In the present embodiment, another method for increasing the reproducibility of the fluorescent spectrum FS will be described. In the present embodiment, the virtual spectral reference SR' is generated by the virtual spectral reference generation unit 105 of the first information processing apparatus 100' using the spectral reference SR stored in the storage unit 202.Figure 12 An example of the data flow of this embodiment is shown. In this embodiment, as... Figure 12 As shown, in addition to generating a fluorescent dye amount FC by inverse mixing of the fluorescence spectrum FS using a spectral reference SR in a local environment, a recovered fluorescence spectrum FS' is generated by performing an inverse conversion of the inverse mixing using the generated fluorescent dye amount FC and the spectral reference SR. Then, difference information DF representing the difference between the recovered fluorescence spectrum FS' generated by the inverse conversion of inverse mixing and the original fluorescence spectrum FS is generated.

[0130] Compared to fluorescence spectroscopy (FS), differential information (DF) has a smaller data dynamic range, reduces more bits, and achieves a higher compression ratio in compression algorithms. Therefore, the compressed differential information DF' obtained by compressing the differential information DF, along with the fluorescence dye amount FC and spectral reference SR, is transferred from the local environment to the cloud environment and stored there.

[0131] In a cloud environment, after generating a recovered fluorescence spectrum FS' by performing an inverse conversion of antimixing using the amount of fluorescent dye FC and a spectral reference SR, and then correcting the recovered fluorescence spectrum FS' to approximate the original fluorescence spectrum FS using the difference information DF obtained by decompressing the compressed difference information DF', a corrected recovered fluorescence spectrum FS" with higher reproducibility than the recovered fluorescence spectrum FS' is generated. Then, analytical processing of the measured object is performed using the amount of fluorescent dye FC and the corrected recovered fluorescence spectrum FS".

[0132] According to the method of this embodiment, as the amount of difference information DF increases, the reproducibility of the corrected fluorescence spectrum FS generated by the correction process increases. In other words, the reproducibility rate of the corrected recovery fluorescence spectrum FS can be controlled by adjusting the amount of difference information DF. Therefore, for example, by adjusting the amount of difference information DF according to the reproducibility rate of the corrected recovery fluorescence spectrum FS required in the analysis, an increase in the amount of data sent from the local environment to the cloud environment can be prevented.

[0133] Figure 13 This is a block diagram illustrating a configuration example of an information processing system according to a third embodiment. For example... Figure 13 As shown, in this embodiment, the first information processing device 100” located in the local environment further includes a fluorescence spectral recovery unit 106 (corresponding to part of the functions of the “first processing unit”), a difference information generation unit 107 (corresponding to part of the functions of the “first processing unit”), and a compression processing unit 108. Furthermore, in this embodiment, the second information processing device 200” located in the cloud environment further includes a decompression processing unit 206 and a correction processing unit 207 (corresponding to part of the functions of the “second processing unit”).

[0134] The fluorescence spectrum recovery unit 106 generates a recovered fluorescence spectrum FS' by performing an inverse conversion of the unmixing using the fluorescence dye amount FC generated by the fluorescence dye amount generation unit 103 and the spectral reference SR used for the unmixing at the fluorescence dye amount generation unit 103.

[0135] The difference information generation unit 107 generates difference information DF representing a difference between the fluorescence spectrum FS acquired by the fluorescence spectrum acquisition unit 101 and the recovered fluorescence spectrum FS' generated by the fluorescence spectrum recovery unit 106, based on the fluorescence spectrum FS and the recovered fluorescence spectrum FS'.

[0136] The compression processing unit 108 compresses the difference information DF generated by the difference information generation unit 107 using a predetermined compression algorithm to generate compressed difference information DF'.

[0137] In the present embodiment, the transmission unit 104 of the first information processing apparatus 100" transmits the compressed difference information DF' generated by the compression processing unit 108 to the second information processing apparatus 200" via the network 20, in addition to the fluorescence dye amount FC generated by the fluorescence dye amount generation unit 103 and the spectral reference SR used for the unmixing at the fluorescence dye amount generation unit 103.

[0138] The reception unit 201 of the second information processing apparatus 200" receives the fluorescence dye amount FC, the spectral reference SR, and the compressed difference information DF' transmitted from the first information processing apparatus 100" via the network 20.

[0139] The storage unit 202 stores the fluorescence dye amount FC, the spectral reference SR, and the compressed difference information DF' received from the first information processing apparatus 100" by the reception unit 201.

[0140] The decompression processing unit 206 decompresses the compressed difference information DF' stored in the storage unit 202 to recover the difference information DF.

[0141] The correction processing unit 207 corrects the recovered fluorescence spectrum FS' generated by the fluorescence spectrum recovery unit 203 using the difference information DF recovered by the decompression processing unit 206 to approximate the original fluorescence spectrum FS, thereby generating a corrected recovered fluorescence spectrum FS" having higher reproducibility than the recovered fluorescence spectrum FS'.

[0142] The analysis processing unit 204 analyzes the measurement target object S using the fluorescence dye amount FC stored in the storage unit 202 and the corrected recovered fluorescence spectrum FS" generated by the correction processing unit 207, in a similar manner to the first embodiment described above.

[0143] Figure 14is a flowchart showing a flow of a series of processes executed in the information processing system according to the third embodiment. Hereinafter, an outline of the operation of the information processing system according to the present embodiment will be described along the flowchart of Figure 14

[0144] First, if the fluorescence spectrum FS of the measurement object S stained with a plurality of fluorescent dyes is measured by the flow cytometer 10, the fluorescence spectrum acquisition unit 101 of the first information processing apparatus 100" acquires the fluorescence spectrum FS (step S301).

[0145] Next, the fluorescent dye amount generation unit 103 of the first information processing apparatus 100" unmixes the fluorescence spectrum FS acquired by the fluorescence spectrum acquisition unit 101 in step S301 using the spectral reference SR corresponding to each fluorescent dye used to stain the measurement object S in the spectral references SR stored in the spectral reference storage unit 102, to generate the fluorescent dye amount FC (step S302).

[0146] Then, the fluorescence spectrum restoration unit 106 of the first information processing apparatus 100" performs inverse conversion of the unmixing using the fluorescent dye amount FC generated by the fluorescent dye amount generation unit 103 in step S302 and the spectral reference SR used for the unmixing when generating the fluorescent dye amount FC to generate the restored fluorescence spectrum FS' (step S303).

[0147] Next, the difference information generation unit 107 of the first information processing apparatus 100" generates difference information DF indicating a difference between the fluorescence spectrum FS acquired by the fluorescence spectrum acquisition unit 101 in step S301 and the restored fluorescence spectrum FS' generated by the fluorescence spectrum restoration unit 106 in step S303, based on the fluorescence spectrum FS and the restored fluorescence spectrum FS' (step S304).

[0148] Then, the compression processing unit 108 of the first information processing apparatus 100" compresses the difference information DF generated by the difference information generation unit 107 in step S304 using a predetermined compression algorithm to generate compressed difference information DF' (step S305). By compressing the difference information DF, it is possible to reduce the amount of data to be transmitted to the second information processing apparatus 200" in step S306 to be described later. However, the difference information DF can be transmitted to the second information processing apparatus 200" without being compressed. In this case, the processing in step S305 can be omitted.

[0149] ​Then, the transmission unit 104 of the first information processing apparatus 100" transmits the fluorescent dye amount FC generated by the fluorescent dye amount generation unit 103 in step S302, the spectral reference SR for the inverse mixing, and the compressed difference information DF' generated by the compression processing unit 108 in step S305 to the second information processing apparatus 200" via the network 20 (step S306).

[0150] Next, the reception unit 201 of the second information processing apparatus 200" receives the fluorescent dye amount FC, the spectral reference SR, and the compressed difference information DF' transmitted from the first information processing apparatus 100" via the network 20, and stores them in the storage unit 202 (step S307).

[0151] Thereafter, the fluorescent spectrum restoration unit 203 of the second information processing apparatus 200" performs inverse conversion of the inverse mixing performed by the fluorescent dye amount generation unit 103 of the first information processing apparatus 100" in step S302 using the fluorescent dye amount FC and the spectral reference SR stored in the storage unit 202 to generate a restored fluorescent spectrum FS' (step S308).

[0152] Then, the decompression processing unit 206 of the second information processing apparatus 200" decompresses the compressed difference information DF' stored in the storage unit 202 to restore the difference information DF (step S309).

[0153] Then, the correction processing unit 207 of the second information processing apparatus 200" corrects the restored fluorescent spectrum FS' generated by the fluorescent spectrum restoration unit 203 in step S308 using the difference information DF restored by the decompression processing unit 206 in step S309 to approximate the original fluorescent spectrum FS to generate a corrected restored fluorescent spectrum FS" (step S310).

[0154] Then, in step S310, the analysis processing unit 204 of the second information processing apparatus 200" performs an analysis process on the measurement target object S using the fluorescent dye amount FC stored in the storage unit 202 and the corrected restored fluorescent spectrum FS" generated by the correction processing unit 207 (step S311), and the series of processes ends.

[0155] As described above, according to the present embodiment, the difference information DF representing a difference between the original fluorescence spectrum FS and the recovered fluorescence spectrum FS' generated by the inverse conversion of the backmixing is generated in advance in the local environment and transferred to the cloud environment, and the recovered fluorescence spectrum FS' generated by the inverse conversion of the backmixing in the cloud environment is corrected using the difference information DF, so that the analysis processing can be performed using the corrected recovered fluorescence spectrum FS" having higher reproducibility than the recovered fluorescence spectrum FS'. Further, the reproducibility of the corrected recovered fluorescence spectrum FS" generated in the cloud environment can be controlled by adjusting the data amount of the difference information DF, so that an increase in the data amount transmitted from the local environment to the cloud environment can be minimized.

[0156] <5. Fourth Embodiment>

[0157] Although the flow cytometer 10 described in each of the above embodiments measures the fluorescence spectrum FS for analysis of the measurement object S, there is also a device having a function of classifying a cell that emits a specific fluorescence from the measurement object S by controlling a moving target of the measurement object S such as a cell passing through the flow cell 12 based on the measured fluorescence spectrum FS. The flow cytometer 10' having such a sorting function is called a sorter (cell sorter).

[0158] In the present embodiment, an application example of an information processing system using the flow cytometer 10' having such a classification function will be described. In the flow cytometer 10' having the sorting function, it is necessary to determine whether or not the measurement object S is a sorting target based on the fluorescence spectrum FS measured by irradiating the measurement object S passing through the flow cell 12 with light, and to control a moving destination of the measurement object S. Here, by constructing a learning model using machine learning with the fluorescence spectrum FS measured from the measurement object S as learning data and making a determination using the learning model, it is possible to make a determination based on the fluorescence spectrum FS instantaneously. In the present embodiment, it is considered that such a learning model is constructed in the cloud environment.

[0159] In the present embodiment, first, the fluorescence spectrum FS for constructing a learning model is measured by the flow cytometer 10'. The measured fluorescence spectrum FS is not transferred from the local environment to the cloud environment, but is recovered by being subjected to the inverse conversion of the backmixing in the cloud environment in a similar manner to the above embodiments. Then, in a similar manner to each of the above embodiments, the analysis processing such as the clustering processing is performed on the measurement object S in the cloud environment, and the result of the analysis processing is presented to the user.

[0160] Here, if a user who refers to the analysis processing result specifies a measurement target object S as a sorting target, machine learning is performed by the learning unit 208 of the second information processing apparatus 200' using the recovered fluorescence spectrum FS' corresponding to the specified measurement target object S as a sorting target as learning data, thereby constructing a learning model. Then, the learning model constructed in the cloud environment is transferred to the local environment.

[0161] Thereafter, in the local environment, the sorting target is determined using the learning model transferred from the cloud environment. In other words, if a fluorescence spectrum FS is measured by the flow cytometer 10', it is determined based on the learning model whether a measurement target object S having the fluorescence spectrum is a sorting target. Then, the movement destination of the sorting target S is controlled based on the determination result, and the measurement target object S specified as a sorting target is classified.

[0162] Figure 15 is a block diagram illustrating a configuration example of an information processing system according to a fourth embodiment. As Figure 15 indicated, in the present embodiment, the second information processing apparatus 200'" provided in the cloud environment further includes a learning unit 208 and a transmission unit 209 (corresponding to a "learning model transmission unit"). In addition, in the present embodiment, the first information processing apparatus 100'" provided in the local environment further includes a reception unit 109 (corresponding to a "learning model reception unit"), a learning model storage unit 110, and a determination unit 111. Note that, although Figure 15 a configuration example in which a configuration peculiar to the present embodiment is added to the information processing system according to the above-described first embodiment is illustrated, the basic information processing system can be the information processing system according to the above-described second embodiment or the information processing system according to the above-described third embodiment.

[0163] If a user who refers to the analysis result of the analysis processing unit 204 specifies a particular measurement target object S as a sorting target, the learning unit 208 of the second information processing apparatus 200'" performs machine learning using the recovered fluorescence spectrum FS' corresponding to the measurement target object S specified as a sorting target as learning data, thereby constructing a learning model for determining whether a measurement target object S is a sorting target from a fluorescence spectrum FS.

[0164] The algorithm of machine learning performed by the learning unit 208 is supervised using the recovered fluorescence spectrum FS' corresponding to the measurement target object S specified as a sorting target as learning data. For example, the learning unit 208 can construct a learning model using a machine learning algorithm such as a random forest, a support vector machine, or deep learning.

[0165] Note that the learning unit 208 can determine whether a learning model capable of sufficiently determining the sorting target has been constructed, and can notify the user of the determination result. For example, in a case where the number of learned restored fluorescence spectra FS' of the measurement target object S or the ratio of the learned restored fluorescence spectra FS' to the whole exceeds a threshold value, the learning unit 208 can notify the user that a learning model capable of sufficiently determining the sorting target has been constructed.

[0166] Alternatively, in a case where the correct answer rate of the learning model exceeds a threshold value, the learning unit 208 can notify the user that a learning model capable of sufficiently determining the sorting target has been constructed. The correct answer rate of the learning model can be determined by, for example, N-fold cross-validation. Specifically, by dividing the entire learning data into N, performing learning to construct a learning model using learning data included in N-1 divided parts, and then performing determination using learning data included in the remaining one divided part, the correct answer rate of the constructed learning model can be determined.

[0167] The transmission unit 209 of the second information processing apparatus 200"' transmits the learning model constructed by the learning unit 208 to the first information processing apparatus 100"' via the network 20.

[0168] The reception unit 109 of the first information processing apparatus 100"' receives the learning model transmitted from the second information processing apparatus 200"' via the network 20.

[0169] The learning model storage unit 110 stores the learning model received by the reception unit 109 from the second information processing apparatus 200"'.

[0170] If the fluorescence spectrum FS of the measurement target object S is measured by the flow cytometer 10' after the learning model storage unit 110 stores the learning model, the determination unit 111 determines whether the measurement target object S having the fluorescence spectrum FS is the sorting target based on the learning model stored in the learning model storage unit 110. Then, in a case where the measurement target object S is determined to be the sorting target, the determination unit 111 outputs an instruction to the flow cytometer 10' to sort the measurement target object S. Further, in a case where the flow cytometer 10' is capable of classifying a plurality of groups of measurement target objects S respectively, the determination unit 111 can not only instruct the flow cytometer 10' whether the measurement target object S is the sorting target, but also instruct to which collection unit the measurement target object S is to be collected.

[0171] Note that the learning model storage unit 110 and the determination unit 111 can be provided at the flow cytometer 10'. Further, the constructed learning model can be implemented in a logic circuit, such as an FPGA circuit, provided at the flow cytometer 10'. For example, the determination unit 111 can be provided at the flow cytometer 10" and the logic that executes the learning model designed and constructed based on the type of the determination unit 111 can be implemented at the FPGA circuit provided at the flow cytometer 10'.

[0172] Figure 16 is a flowchart illustrating a process of property processing executed in the information processing system according to the fourth embodiment, and illustrates a process flow executed after the analysis processing in step S106 illustrated in the flowchart of Figure 8 Note that in the analysis processing, it is assumed that the processing result such as the clustering processing is presented to the user, and the sorting target is specified by the user who refers to the presented analysis processing result.

[0173] If the user specifies the sorting target, the learning unit 208 of the second information processing apparatus 200"' machine-learns the restoration fluorescence spectrum FS' corresponding to the measurement object S specified as the sorting target using as the learning data, and constructs a learning model for determining the sorting target (step S401).

[0174] Next, the transmission unit 209 of the second information processing apparatus 200"' transmits the learning model constructed by the learning unit 208 in step S401 to the first information processing apparatus 100"' via the network 20 (step S402).

[0175] Next, the reception unit 109 of the first information processing apparatus 100"' receives the learning model transmitted from the second information processing apparatus 200"' via the network 20 and stores the learning model in the learning model storage unit 110 (step S403).

[0176] Thereafter, if the fluorescence spectrum FS of the measurement object S is measured by the flow cytometer 10', the determination unit 111 of the first information processing apparatus 100' determines whether the measurement object S is the sorting target based on the learning model stored in the learning model storage unit 110 (step S404), and issues an instruction to the flow cytometer 10'. Thus, the measurement object S specified as the sorting target by the user can be properly sorted by the flow cytometer 10'.

[0177] As described above, according to the present embodiment, the construction of the learning model requiring a large processing load is executed in the cloud environment, and the sorting target is determined using the learning model constructed in the cloud environment to cause the flow cytometer 10' to appropriately perform the operation, thereby improving the user friendliness. Further, the fluorescence spectrum FS having a large data size does not need to be transmitted from the first information processing apparatus 100'" in the local environment to the second information processing apparatus 200'" in the cloud environment to construct the learning model in the cloud environment, so that it is possible to reduce the amount of data transmitted from the local environment to the cloud environment and reduce the amount of data stored in the cloud environment, so that it is possible to reduce the storage cost.

[0178] <6. Fifth Embodiment>

[0179] Note that, although the fluorescence spectrum FS of the measurement target S is measured by the flow cytometer 10 (10') in each of the above-described embodiments, the mechanism of the present disclosure can also be effectively applied to, for example, a case where a fluorescence imaging apparatus that measures the fluorescence spectrum FS using an imaging element (two-dimensional image sensor) is used. In the present embodiment, an example of application to an information processing system using such a fluorescence imaging apparatus will be described.

[0180] Figure 17 is a block diagram showing a configuration example of an information processing system according to the fifth embodiment. As shown in Figure 17 , in the present embodiment, a fluorescence imaging apparatus 30 is provided in a local environment instead of the flow cytometer 10 (10'). Note that the basic configuration of the information processing system is similar to that in the first embodiment shown in Figure 5 .

[0181] Figure 18 A schematic configuration example of the fluorescence imaging apparatus 30 is shown. For example, as shown in Figure 18 , the fluorescence imaging apparatus 30 includes a laser light source 31, a movable stage 32, a light splitting element 34, and an imaging element 35.

[0182] The laser light source 31 emits laser light having a wavelength capable of exciting a fluorescent dye used to color the measurement target object S. As the laser light source 31, for example, a semiconductor laser light source that emits laser light having a predetermined wavelength can be used.

[0183] The fluorescent dye sample 33 is placed on the movable stage 32. The movable stage 32 moves in the horizontal direction so that the laser light emitted from the laser light source 31 scans the fluorescent dye sample 33 in two dimensions.

[0184] For example, the fluorescent dye sample 33 is a sample collected from a human body or a sample prepared from a tissue sample for pathological diagnosis or the like, and is stained using a plurality of fluorescent dyes. The fluorescent dye sample 33 includes a large number of measurement targets S such as cells constituting the collected tissue. By moving the moving stage 32, the laser light emitted from the laser light source 31 is scanned in two-dimensional directions with respect to the fluorescent dye sample 33, so that the plurality of measurement targets S included in the fluorescent dye sample 33 can be sequentially irradiated with the laser light.

[0185] The light-splitting element 34 is an optical element that disperses the fluorescence emitted by irradiating the measurement targets S included in the fluorescent dye sample 33 with the laser light into a continuous wavelength spectrum. For example, a prism, a grating, or the like can be used as the light-splitting element 34.

[0186] The imaging element 35 is a two-dimensional image sensor in which light-receiving elements (for example, charge-coupled device (CCD) sensors and complementary metal-oxide semiconductor (CMOS) sensors) are arranged in two dimensions. The imaging element 35 receives the fluorescence emitted by irradiating the measurement targets S included in the fluorescent dye sample 33 with the laser light and dispersed by the light-splitting element 34 with the respective light-receiving elements arranged in two dimensions and outputs an image signal. The fluorescence emitted from the measurement targets S by irradiation with the laser light is dispersed into a continuous spectrum by the light-splitting element 13, and thus the imaging element 35 outputs an image signal corresponding to the fluorescence intensity in each region of the wavelength region.

[0187] In the fluorescence imaging apparatus 30 configured as described above, the fluorescence emitted by irradiating the measurement targets S included in the fluorescent dye sample 33 with the laser light is dispersed into a continuous spectrum by the light-splitting element 34 and detected by the respective light-receiving elements of the imaging element 35. Thus, the image signal output from the imaging element 35 can be used to measure the fluorescence spectrum FS of the measurement targets S in a similar manner to the flow cytometer 10 (10').

[0188] In the information processing system according to the present embodiment, the fluorescence spectrum acquisition unit 101 of the first information processing apparatus 100 provided in the local environment acquires the fluorescence spectrum FS of the measurement targets S measured by the fluorescence imaging apparatus 30. The subsequent processing is the same as that of the first embodiment described above, and thus the description thereof will be omitted. Note that, although Figure 17 An example in which the flow cytometer 10 in the information processing system according to the first embodiment described above is replaced with the fluorescence imaging apparatus 30 is shown, but the underlying information processing system can be the information processing system according to the second embodiment described above or the information processing system according to the third embodiment described above.

[0189] As described above, even in a case where the fluorescence spectrum FS of the measurement target object S is measured by the fluorescence imaging device 30, by applying the mechanism of the present disclosure, the amount of data transmitted from the local environment to the cloud environment and the amount of data stored in the cloud environment can be reduced, so that the storage cost can be reduced.

[0190] <7. Hardware configuration example>

[0191] Subsequently, an example of a hardware configuration of the first information processing device 100 and the second information processing device 200 (hereinafter, these will be collectively referred to as "information processing device 300") will be described with reference to Figure 19 FIG. 8. Figure 19 is a block diagram illustrating an example of a hardware configuration of the information processing device 300.

[0192] As Figure 19 indicated, the information processing device 300 includes a central processing unit (CPU) 301, a read only memory (ROM) 302, a random access memory (RAM) 303, a host bus 305, a bridge 307, an external bus 306, an interface 308, an input device 311, an output device 312, a storage device 313, a drive 314, a connection port 315, and a communication device 316. The information processing device 300 can include a processing circuit such as a circuit, a DSP, or an ASIC instead of or in addition to the CPU 301.

[0193] The CPU 301 functions as an arithmetic processing unit and a control unit, and controls the overall operation in the information processing device 300 according to various programs. Further, the CPU 301 can be a microprocessor. The ROM 302 stores programs, operation parameters, and the like used by the CPU 301. The RAM 303 temporarily stores programs used when the CPU 301 is executed and parameters appropriately changed in the execution, and the like. For example, the CPU 301 can realize the functions of the fluorescence spectrum acquisition unit 101 and the fluorescent dye amount generation unit 103 in the above-described first information processing device 100. Further, for example, the CPU 301 can realize the functions of the fluorescence spectrum restoration unit 203 and the analysis processing unit in the above-described second information processing device 200.

[0194] The CPU 301, the ROM 302, and the RAM 303 are connected to each other through the host bus 305 including a CPU bus or the like. The host bus 305 is connected to the external bus 306, such as a peripheral component interconnect / interface (PCI) bus, via the bridge 307. Note that the host bus 305, the bridge 307, and the external bus 306 are not necessarily separated, and these functions can be realized in one bus.

[0195] The input device 311 is a device such as a mouse, a keyboard, a touch panel, a button, a microphone, a switch, and a lever by which a user inputs information. Alternatively, for example, the input device 311 can be a remote control device using infrared rays or other radio waves, or can be an external connection device such as a mobile phone or a PDA corresponding to the operation of the information processing device 300. Furthermore, the input device 311 can include, for example, an input control circuit that generates an input signal based on information input by a user using the above-described input device.

[0196] The output device 312 is a device capable of notifying a user of information visually or audibly. The output device 312 can be, for example, a display device such as a cathode ray tube (CRT) display device, a liquid crystal display device, a plasma display device, an electroluminescence (EL) display device, a laser projector, a light emitting diode (LED) projector, or a lamp, or can be an audio output device such as a speaker or a headphone.

[0197] The output device 312 can output, for example, a result obtained by various processing of the information processing device 300. Specifically, the output device 312 can visually display a result obtained by various processing of the information processing device 300 in various formats such as text, an image, a table, or a graph. Alternatively, the output device 312 can convert an audio signal such as audio data or acoustic data into an analog signal, and output the analog signal from the sense of hearing. The input device 311 and the output device 312 can perform the function of the interface unit 309, for example.

[0198] The storage device 313 is a device for data storage formed as an example of a storage unit of the information processing device 300. The storage device 313 can be realized by, for example, a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device such as a solid state drive (SSD), an optical storage device, a magneto-optical storage device, or the like. The storage device 313 can include, for example, a storage medium, a recording device that records data in the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded in the storage medium, and the like. The storage device 313 can store a program executed by the CPU 301, various data, various data acquired from the outside, and the like. The storage device 313 can realize, for example, the function of the spectral reference storage unit 102 in the above-described first information processing device 100.

[0199] The drive 314 as a reader / writer for the storage medium is built in or externally attached to the information processing device 300. The drive 314 reads out information recorded in a removable storage medium such as a mounted magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and outputs the information to the RAM 303. Further, the drive 314 can also write information to the removable storage medium.

[0200] The connection port 315 is an interface that connects to an external device. The connection port 315 is a connection port that can transmit data to an external device, and can be, for example, a universal serial bus (USB).

[0201] The communication device 316 is an interface formed of, for example, a communication device or the like, for connecting to the network 20. The communication device 316 can be, for example, a communication card for a wired or wireless local area network (LAN), long term evolution (LTE), Bluetooth (registered trademark), wireless USB (WUSB), or the like. Furthermore, the communication device 316 can be a router for optical communication, a router for asymmetric digital subscriber line (ADSL), a modem for various communications, or the like. The communication device 316 can transmit and receive signals and the like to and from the Internet or other communication devices, for example, in accordance with a predetermined protocol such as TCP / IP. The communication device 316 can realize the function of the transmission unit 104 in the above-described first information processing device 100, for example. Furthermore, the communication device 316 can realize the function of the reception unit 201 in the above-described second information processing device 200, for example.

[0202] Note that a computer program can also be created that causes hardware built into the information processing device 300, such as the CPU 301, the ROM 302, and the RAM 303, to function as functions equivalent to the functions of the components of the above-described first information processing device 100 and second information processing device 200. Furthermore, a storage medium in which the computer program is stored can also be provided.

[0203] <8. Supplementary notes>

[0204] As described above, the preferred embodiments of the present disclosure have been described in detail with reference to the accompanying drawings, but the technical scope of the present disclosure is not limited to such examples. It is clear that those having ordinary knowledge in the technical field to which the present disclosure pertains can further make changes and modifications without departing from the technical concept of the present disclosure, and such changes and modifications should also be construed as falling within the protective scope of the present disclosure.

[0205] Furthermore, the effects described in the present specification are merely illustrative or exemplary, and are not limited. That is, in addition to or in place of the above effects, the technology according to the present disclosure can exhibit other effects apparent to those skilled in the art from the description of the present specification.

[0206] Note that the following configurations also fall within the technical scope of the present disclosure. (1)

[0208] An information processing system including: a first information processing device; and a second information processing device,

[0209] The first information processing apparatus includes:

[0210] a first processing unit configured to irradiate a measurement target object dyed with a plurality of fluorescent dyes with light, generate compressed data by performing a compression process on measurement data measured by the irradiation using reference data for each fluorescent dye used to dye the measurement target object, and

[0211] a transmission unit configured to transmit the compressed data to the second information processing apparatus,

[0212] The second information processing apparatus includes a second processing unit configured to generate restoration data by performing a restoration process using the reference data and the compressed data received from the first information processing apparatus. (2)

[0214] The information processing system according to (1), in which the measurement target is a biological source particle including at least one of a cell, a tissue, a microorganism, and a biological-related particle. (3)

[0216] The information processing system according to (1) or (2), in which the first information processing apparatus and the second information processing apparatus are connected so as to be able to communicate with each other via a predetermined network. (4)

[0218] The information processing system according to any one of (1) to (3), in which the compression process includes at least one of a linear process and a nonlinear process. (5)

[0220] The information processing system according to any one of (1) to (4), in which the compression process includes at least one of a dimension compression process, a clustering process, and a grouping process. (6)

[0222] The information processing system according to any one of (1) to (5), in which the compressed data is a fluorescent dye amount representing a measurement result for each fluorescent dye used to dye the measurement target object. (7)

[0224] The information processing system according to any one of (1) to (6), in which the restoration process is an inverse conversion process of the compressed data. (8)

[0226] The information processing system according to any one of (1) to (7),

[0227] wherein the first processing unit performs the compression processing on the measurement data using the reference data and virtual reference data to generate virtual compressed data in which virtual data is added to the compressed data,

[0228] the transmission unit transmits the virtual compressed data and the virtual reference data to the second information processing apparatus, and

[0229] the second processing unit generates the restored data by performing the restoration processing using the reference data, the virtual compressed data, and the virtual reference data. (9)

[0231] The information processing system according to any one of (1) to (8),

[0232] wherein the first processing unit further restores the measurement data by performing inverse conversion of the demixing using the compressed data and the reference data, and generates difference information indicating a difference between the restored measurement data and the measurement data,

[0233] the transmission unit further transmits the difference information to the second information processing apparatus,

[0234] the second information processing apparatus further receives the difference information from the first information processing apparatus, and

[0235] the second processing unit further corrects the restored measurement data based on the difference information. (10)

[0237] The information processing system according to any one of (1) to (9),

[0238] wherein the second information processing apparatus further includes:

[0239] an analysis processing unit configured to analyze the measurement target object using the compressed data and restored measurement data that is the measurement data obtained by restoring the compressed data. (11)

[0241] The information processing system according to (10),

[0242] wherein the second information processing apparatus further includes:

[0243] a learning unit configured to construct a learning model for determining a sorting target by performing machine learning using the measurement data corresponding to the sorting target specified based on an analysis result of the analysis processing unit, and

[0244] a learning model transmission unit configured to transmit the learning model to the first information processing apparatus, and

[0245] the first information processing apparatus further includes:

[0246] a learning model reception unit configured to receive the learning model from the second information processing apparatus; and

[0247] a determination unit configured to determine the sorting target based on the learning model. (12)

[0249] the information processing system according to any one of (1) to (11),

[0250] wherein the measurement data is a fluorescence signal obtained by measuring fluorescence emitted from the measurement target. (13)

[0252] the information processing system according to any one of (1) to (11),

[0253] wherein the measurement data is image data obtained by imaging the measurement target. (14)

[0255] an information processing apparatus including:

[0256] a first processing unit configured to generate compressed data by performing compression processing on measurement data using reference data for each fluorescent dye used to dye a measurement target, the measurement data being measured by irradiating the measurement target dyed with a plurality of fluorescent dyes with light; and

[0257] a second processing unit configured to generate restoration data by performing restoration processing using the reference data and the compressed data.

[0258] List of Reference Signs

[0259] 10, 10' flow cytometer

[0260] 20 network

[0261] 30 fluorescence imaging apparatus

[0262] 100, 100', 100", 100"' first information processing apparatus

[0263] 101 fluorescence spectrum acquisition unit

[0264] 102 spectral reference storage unit

[0265] 103 fluorescence dye amount generating unit (first processing unit)

[0266] 104 transmitting unit

[0267] 105 bifluorescence dye amount generating unit (first processing unit)

[0268] 106 fluorescence spectrum restoring unit (first processing unit)

[0269] 107 difference information generating unit (first processing unit)

[0270] 108 compression processing unit

[0271] 109 receiving unit

[0272] 110 learning model storage unit

[0273] 111 determining unit

[0274] 200, 200', 200", 200"' second information processing apparatus

[0275] 201 receiving unit

[0276] 202 storage unit

[0277] 203 fluorescence spectrum restoring unit (second processing unit)

[0278] 204 analysis processing unit

[0279] 205 fluorescence dye amount generating unit (second processing unit)

[0280] 206 decompression processing unit

[0281] 207 correction processing unit (second processing unit)

[0282] 208 learning unit

[0283] 209 transmitting unit

[0284] FS fluorescence spectrum (measurement data)

[0285] FS' restored fluorescence spectrum (restored measurement data)

[0286] FS" corrected restored fluorescence spectrum

[0287] SR spectral reference (reference data)

[0288] SR' virtual spectral reference (complex reference data)

[0289] FC fluorescence DYE amount (compressed data)

[0290] FC' virtual fluorescent dye amount (repeated measurement data)

[0291] DF difference information

[0292] DF' compressed difference information.

Claims

1. An information processing system, comprising: First information processing device; And a second information processing device, wherein the first information processing device includes: A first processing unit is configured to irradiate a measurement object stained with multiple fluorescent dyes with light, and to compress the measurement data measured by irradiation using reference data of the standard fluorescence wavelength distribution for each fluorescent dye used to stain the measurement object, thereby generating compressed data. In addition to using the reference data, the first processing unit also performs the compression process on the measurement data using virtual reference data to generate virtual compressed data to which virtual data is added. The virtual reference data is used to retain spectral information lost during the recovery process to improve the accuracy of the recovered data, and the virtual reference data includes: spectral information or random numbers not included in the reference data corresponding to the fluorescent dyes used to stain the measurement object, and... The sending unit is configured to send the compressed data, the virtual compressed data, and the virtual reference data to the second information processing device. The second information processing device includes a second processing unit configured to generate recovery data by performing the recovery processing using the reference data, the compressed data received from the first information processing device, the virtual compressed data, and the virtual reference data.

2. The information processing system according to claim 1, wherein, The measurement object includes at least one of cells, microorganisms, and bio-related polymers.

3. The information processing system according to claim 1, wherein, The first information processing device and the second information processing device are connected so that they can communicate with each other via a predetermined network.

4. The information processing system according to claim 1, wherein, The compression process includes at least one of linear processing and nonlinear processing.

5. The information processing system according to claim 1, wherein, The compression process includes at least one of dimensionality compression, clustering, and grouping.

6. The information processing system according to claim 1, wherein, The compressed data is the amount of fluorescent dye, which represents the measurement result for each fluorescent dye used to stain the measured object.

7. The information processing system according to claim 1, wherein, The recovery process is the reverse transformation process of the compressed data.

8. The information processing system according to claim 1, in, The first processing unit further recovers the measurement data by performing an inverse transformation of the compressed data and the reference data to remove the mixing, and generates difference information representing the difference between the recovered measurement data and the original measurement data. The sending unit further sends the difference information to the second information processing device. The second information processing device further receives the difference information from the first information processing device, and The second processing unit further corrects the recovered measurement data based on the difference information.

9. The information processing system according to claim 1, in, The second information processing device further includes: An analysis and processing unit is configured to analyze the object being measured using the compressed data and the recovered measurement data, wherein the recovered measurement data is the measurement data obtained by recovering the compressed data.

10. The information processing system according to claim 9, in, The second information processing device further includes: A learning unit configured to construct a learning model by performing machine learning on measurement data corresponding to a sorting target specified based on the analysis results of the analysis processing unit, the learning model being used to determine the sorting target; and A learning model sending unit is configured to send the learning model to the first information processing device, and The first information processing device further includes: A learning model receiving unit is configured to receive the learning model from the second information processing device; and The determining unit is configured to determine the sorting target based on the learning model.

11. The information processing system according to claim 1, in, The measurement data is obtained by measuring the fluorescence signal emitted from the object being measured.

12. The information processing system according to claim 1, in, The measurement data is image data obtained by imaging the object being measured.

13. An information processing apparatus, comprising: A first processing unit is configured to generate compressed data by performing compression processing on measurement data using reference data of a standard fluorescence wavelength distribution for each fluorescent dye used to stain the object being measured. The measurement data is obtained by irradiating the object being measured with light after staining it with multiple fluorescent dyes. In addition to using the reference data, the first processing unit also performs the compression processing on the measurement data using virtual reference data to generate virtual compressed data, which is then added to the compressed data. This virtual reference data is used to retain spectral information lost during the recovery process to improve the accuracy of the recovered data. The virtual reference data includes spectral information or random numbers not included in the reference data corresponding to the fluorescent dyes used to stain the object being measured. The sending unit is configured to send compressed data, the virtual compressed data, and the virtual reference data to a second information processing device, the second information processing device including: a second processing unit configured to generate recovery data by performing the recovery processing using the reference data, the compressed data, the virtual compressed data, and the virtual reference data.

Images