WO2026004349A1 - Information processing method, information processing device, and information processing system - Google Patents

Abstract

[Problem] To identify autofluorescence of various biological particles. [Solution] Provided is an information processing method involving: acquiring optical data by irradiating a plurality of biological particles with light; identifying autofluorescence data of the plurality of biological particles by clustering the optical data; and outputting the autofluorescence data.

Description

Information processing method, information processing device, and information processing system

This disclosure relates to an information processing method, an information processing device, and an information processing system.

In recent years, in the fields of medicine and biochemistry, it has become common to use a flow cytometer to rapidly analyze the characteristics of large numbers of bioparticles labeled with at least one fluorescent dye. A flow cytometer irradiates light onto bioparticles flowing in a roughly single file, allowing it to rapidly measure the scattered light and fluorescence of each bioparticle.

However, the fluorescence emitted from bioparticles includes not only the fluorescence from the labeled fluorescent dye, but also autofluorescence emitted from the bioparticles themselves. Therefore, in order to accurately detect the fluorescence of the fluorescent dye labeled to the bioparticles, it is important to identify the autofluorescence of the bioparticles.

For example, Patent Document 1 listed below discloses separating an autofluorescence image containing an autofluorescence component from an image of a specimen labeled with at least one or more fluorescent dyes, and further correcting the separated autofluorescence image using a reference spectrum of the autofluorescent substance.

International Publication No. 2022/004500

However, the technology disclosed in Patent Document 1 separates autofluorescence images using the reference spectrum of the autofluorescent substance contained in the bioparticles, making it difficult to identify the autofluorescence of unknown bioparticles whose autofluorescent substance is unknown.

Therefore, this disclosure proposes a new and improved information processing method, information processing device, and information processing system that are capable of identifying the autofluorescence of a wider variety of biological particles.

According to the present disclosure, an information processing method is provided that includes acquiring light data by irradiating light onto a plurality of biological particles, identifying autofluorescence data of the plurality of biological particles by clustering the light data, and outputting the autofluorescence data.

The present disclosure also provides an information processing device comprising an acquisition unit that acquires light data by irradiating light onto a plurality of biological particles, an autofluorescence identification unit that identifies autofluorescence data of the plurality of biological particles by clustering the light data, and an output unit that outputs the autofluorescence data.

The present disclosure also provides an information processing system including an information processing device that includes: a detection device that acquires light data by irradiating light onto multiple biological particles; an autofluorescence identification unit that identifies autofluorescence data of the multiple biological particles by clustering the light data; and an output unit that outputs the autofluorescence data.

FIG. 1 is a diagram showing a schematic view of the overall configuration of a biological sample analyzer. FIG. 1 is a schematic diagram showing the configuration of an analysis system including a biological sample analyzer. FIG. 10 is a flowchart showing the flow of an analytical experiment using the biological sample analyzer. FIG. 2 is a block diagram showing the functional configuration of an information processing unit. FIG. 2 is a graph showing an example of optical data detected by a detection unit of the spectral flow cytometer. 6 is a graph showing an example of optical data of each cluster obtained by clustering the optical data shown in FIG. 5 with the number of clusters k=2. FIG. 6 is a graph showing an example of optical data of each cluster obtained by clustering the optical data shown in FIG. 5 with the number of clusters k=2. FIG. FIG. 10 is a flowchart showing the flow of operations related to the information processing unit. FIG. 10 is a flowchart showing the flow of a first method for determining the number of clusters. FIG. 10 is a scatter plot of optical data of bioparticles that have been fluorescence-corrected using autofluorescence data identified based on optical data of clusters clustered with a cluster number of 1. FIG. 10 is a scatter plot of optical data of bioparticles, fluorescence-corrected using autofluorescence data identified based on optical data of clusters clustered with a cluster count of 2. FIG. 10 is a scatter plot of optical data of bioparticles, fluorescence-corrected using autofluorescence data identified based on optical data of clusters clustered with a cluster count of 3. FIG. 10 is a flowchart showing the flow of a second method for determining the number of clusters. FIG. 10 is a graph showing the spectrum of each cluster identified based on the optical data of the clusters clustered with a cluster number of 1. FIG. 10 is a graph showing the spectrum of each cluster identified based on the optical data of the clusters clustered with the number of clusters being 2. FIG. 10 is a graph showing the spectrum of each cluster identified based on the optical data of the clusters clustered with the number of clusters being 3. FIG. 10 is a block diagram showing a functional configuration of an information processing unit according to a first modified example. FIG. 10 is a graph showing an example of identifying the spectrum of each cluster obtained by clustering optical data of bioparticles preprocessed with a linear transformation function. FIG. 10 is a graph showing an example of identifying the spectrum of each cluster obtained by clustering optical data of bioparticles preprocessed with a Bi-exponential conversion function. FIG. 10 is a schematic diagram illustrating an example of a clustering target of an information processing unit according to a second modified example. FIG. 11 is a flowchart showing the flow of operations related to an information processing unit according to a third modified example. FIG. 2 is a block diagram illustrating an example of a hardware configuration of an information processing device that realizes an information processing unit according to the present embodiment.

Preferred embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Note that in this specification and drawings, components having substantially the same functional configuration will be assigned the same reference numerals, and redundant explanations will be omitted.

The explanation will be given in the following order.
1. Biological Sample Analyzer 1.1. Configuration of Biological Sample Analyzer 1.2. Configuration of Analysis System 1.3. Analysis Flow 2. Information Processing Unit 2.1. Configuration of Information Processing Unit 2.2. Operation of Information Processing Unit 2.3. Method of Determining the Number of Clusters 2.4. Modified Examples 3. Hardware Configuration

<1. Biological sample analyzer>
(1.1. Configuration of Biological Sample Analyzer)
An example configuration of a biological sample analyzer according to the present disclosure is shown in Figure 1. The biological sample analyzer 100 shown in Figure 1 includes a light irradiation unit 101 that irradiates light onto a biological sample S flowing through a flow path C, a detection unit 102 that detects light generated by irradiating the biological sample S with light, and an information processing unit 103 that processes information related to the light detected by the detection unit 102. Examples of the biological sample analyzer 100 include a flow cytometer and an imaging cytometer. The biological sample analyzer 100 may also include a fractionation unit 104 that separates specific biological particles P from within the biological sample S. An example of a biological sample analyzer 100 that includes a fractionation unit 104 is a cell sorter.

(Biological sample S)
The biological sample S may be a liquid sample containing biological particles P. The biological particles P may be, for example, cells or non-cellular biological particles. The cells may be living cells, and more specific examples include blood cells such as red blood cells and white blood cells, and reproductive cells such as sperm and fertilized eggs. The cells may also be directly collected from a specimen such as whole blood, or may be cultured cells obtained after culturing. Examples of non-cellular biological particles include extracellular vesicles (especially exosomes and microvesicles). The biological particles P may be labeled with one or more labeling substances (e.g., dyes (especially fluorescent dyes) and antibodies labeled with fluorescent dyes). The biological sample analyzer 100 may also analyze particles other than biological particles P, such as beads for calibration purposes.

(Flow path C)
The flow channel C is configured to allow the biological sample S to flow. In particular, the flow channel C can be configured to form a flow in which biological particles P contained in the biological sample S are aligned in a substantially straight line. The flow channel structure including the flow channel C may be designed to form a laminar flow. In particular, the flow channel structure is designed to form a laminar flow in which the flow of the biological sample S (sample flow) is surrounded by the flow of sheath liquid. The design of the flow channel structure may be appropriately selected by those skilled in the art, or a known design may be adopted. The flow channel C may be formed in a flow channel structure such as a microchip (a chip having flow channels on the order of micrometers) or a flow cell. The width of the flow channel C may be 1 mm or less, particularly 10 μm or more and 1 mm or less. The flow channel C and the flow channel structure including the flow channel C may be formed from a material such as plastic or glass.

The biological sample analysis device 100 is configured so that light from a light irradiation unit 101 is irradiated onto the biological sample S flowing within the flow path C, and in particular onto biological particles P within the biological sample S. The biological sample analysis device 100 may be configured so that the interrogation point of light on the biological sample S is within the flow path structure, or so that the interrogation point of light is outside the flow path structure. An example of the former is a cuvette flow cell system in which light is irradiated onto a flow path C within a microchip or flow cell. An example of the latter is a jet-in-air system in which light is irradiated onto biological particles P after they have left the flow path structure (in particular its nozzle section).

(Light irradiation unit 101)
The light irradiation unit 101 includes a light source unit that emits light and a light-guiding optical system that guides the light to an irradiation point. The light source unit includes one or more light sources. The type of light source may be, for example, a laser light source or an LED (Light Emitting Diode) light source. The wavelength of the light emitted from each light source may be any of ultraviolet light, visible light, and infrared light. The light-guiding optical system includes optical components such as a beam splitter group, a mirror group, or an optical fiber. The light-guiding optical system may also include a lens group for focusing light, such as an objective lens. There may be one or more irradiation points where the biological sample S and the light intersect. The light irradiation unit 101 may be configured to focus light emitted from one or more light sources to one irradiation point.

(Detection unit 102)
The detection unit 102 includes at least one photodetector that detects light generated by irradiating the bioparticles P with light. The light detected by the detection unit 102 is, for example, fluorescence or scattered light (e.g., one or more of forward scattered light, backscattered light, and side scattered light). Each photodetector includes one or more light-receiving elements, e.g., a photodetector array. Each photodetector may include one or more photomultiplier tubes (PMTs) as light-receiving elements, or may include photodiodes such as APDs (Avalanche PhotoDiodes) or MPPCs (Multi-Pixel Photon Counters). For example, the photodetector may be a PMT array in which multiple PMTs are arranged in a one-dimensional direction. The detection unit 102 may also include an imaging element such as a CCD image sensor or a CMOS image sensor. The detection unit 102 can acquire images of the bioparticles P (e.g., bright-field images, dark-field images, and fluorescence images) using these imaging elements.

The detection unit 102 includes a detection optical system that allows light of a predetermined detection wavelength to reach a corresponding photodetector. The detection optical system includes a spectroscopic unit such as a prism or diffraction grating, or a wavelength separation unit such as a dichroic mirror or optical filter. The detection optical system is configured, for example, to disperse light generated by irradiating light onto bioparticles P and detect the dispersed light using multiple photodetectors, the number of which is greater than the number of fluorescent dyes with which the bioparticles P are labeled. A flow cytometer that includes such a detection optical system is called a spectral flow cytometer. The detection optical system may also be configured, for example, to separate light corresponding to the fluorescent wavelength range of a specific fluorescent dye from the light generated by irradiating light onto bioparticles P, and detect the separated light using the corresponding photodetector.

The detection unit 102 may also include a signal processing unit that converts the electrical signal obtained by the photodetector into a digital signal. The signal processing unit may include an A/D converter as the device that performs this conversion. The digital signal obtained by conversion by the signal processing unit may be transmitted to the information processing unit 103. The digital signal may be handled by the information processing unit 103 as data related to light (hereinafter also referred to as "light data"). The light data may be, for example, light data including fluorescence data, or more specifically, light intensity data. The light intensity may be light intensity data of light including fluorescence (which may include feature quantities such as area, height, and width).

(Information processing unit 103)
The information processing unit 103 includes, for example, a processing unit that processes various data (e.g., optical data) and a memory unit that stores various data. When the processing unit acquires optical data corresponding to a fluorescent dye from the detection unit 102, the processing unit may perform fluorescence leakage correction (compensation processing) on the light intensity data. Furthermore, in the case of a spectral flow cytometer, the processing unit may perform fluorescence separation processing on the optical data to acquire light intensity data corresponding to the fluorescent dye. The fluorescence separation processing may be performed, for example, according to the unmixing method described in Japanese Patent Application Laid-Open No. 2011-232259. When the detection unit 102 includes an image sensor, the processing unit may acquire morphological information of the bioparticles P based on images acquired by the image sensor. The memory unit may be configured to store the acquired optical data and may further be configured to store spectral reference data used in the unmixing processing.

If the biological sample analyzer 100 includes a fractionation unit 104 (described below), the information processing unit 103 can determine whether or not to fractionate the biological particles P based on the optical data and/or morphological information of the biological particles P. The information processing unit 103 controls the fractionation unit 104 based on the results of this determination, allowing the fractionation unit 104 to fractionate the biological particles P.

The information processing unit 103 may be configured to be able to output various types of data (e.g., optical data or images). For example, the information processing unit 103 may output various types of data (e.g., two-dimensional plots or spectral plots) generated based on optical data. The information processing unit 103 may also be configured to be able to accept input of various types of data. For example, the information processing unit 103 may accept gating processing on a plot by a user. The information processing unit 103 may include an output unit (e.g., a display) or an input unit (e.g., a keyboard) for executing output or input.

The information processing unit 103 may be configured as a general-purpose computer, for example, as an information processing device equipped with a CPU (Central Processing Unit), RAM (Random Access Memory), and ROM (Read Only Memory). The information processing unit 103 may be provided inside the housing in which the light irradiation unit 101 and the detection unit 102 are provided, or may be provided outside the housing. Furthermore, the various processes or functions performed by the information processing unit 103 may be realized by a server computer or cloud connected via a network.

(Preparative separation section 104)
The sorting unit 104 sorts the bioparticles P based on the determination result by the information processing unit 103. For example, sorting of the bioparticles P may be performed by a sorting method in which droplets containing the bioparticles P are generated by vibration and the direction of travel of the charged droplets to be sorted is controlled by electrodes. Sorting of the bioparticles P may also be performed by a sorting method in which the direction of travel of the bioparticles P is controlled within the flow channel structure. In such cases, the flow channel structure is provided with a control mechanism that uses, for example, pressure (spray or suction) or electric charge. An example of a flow channel structure is a chip (e.g., the chip described in JP 2020-76736 A) that has a flow channel structure in which a flow channel C branches downstream into a recovery flow channel and a waste flow channel, and that can recover specific bioparticles P into the recovery flow channel.

(1.2. Configuration of the analysis system)
Figure 2 is a schematic diagram showing the configuration of an analysis system 10 including a biological sample analyzer 100. As shown in Figure 2, the analysis system 10 includes multiple biological sample analyzers 100 and a server 200 connected to the multiple biological sample analyzers 100. Note that while Figure 2 shows four biological sample analyzers 100, the number of biological sample analyzers 100 connected to the server 200 is not particularly limited and may be three or less, or five or more.

The biological sample analyzer 100 is an analyzer that analyzes a biological sample S containing the above-mentioned biological particles P. The biological sample analyzer 100 may be, for example, a flow cytometer, an imaging cytometer, or a cell sorter.

Server 200 is an information processing server that stores various information used in each analysis by biological sample analyzer 100. Server 200 may store, for example, reference data for biological sample analyzer 100, information related to the fluorescence emitted by the fluorescent dye that labels biological particles P (such as fluorescence spectral data), or machine learning models used to analyze biological particles P.

Furthermore, the server 200 may accumulate the analysis results of each biological sample analyzer 100. The analysis results of each biological sample analyzer 100 accumulated in the server 200 can be used, for example, as training data for a machine learning model used in analyzing biological particles P. Furthermore, by accumulating the analysis results of each biological sample analyzer 100 in the server 200, they can be shared with other biological sample analyzers 100.

However, if sending information outside organization Cm is prohibited from the standpoint of protecting privacy or preventing information leaks, the analysis results of each biological sample analyzer 100 may be accumulated on an in-organization server 300 located within organization Cm. Organization Cm is, for example, a research institute such as a university, a medical institution such as a hospital, or a company. The in-organization server 300 can accumulate the analysis results of each biological sample analyzer 100 within organization Cm. The in-organization server 300 may also obtain various types of information used in each analysis by the biological sample analyzer 100 from server 200 and store this information.

(1.3. Analysis flow)
FIG. 3 is a flow chart showing the flow of an analytical experiment using the biological sample analyzer 100.

As shown in FIG. 3, first, a hypothesis to be verified is set as the purpose of the analytical experiment (S11). Next, a protocol for verifying the set hypothesis is created (S12). The created protocol determines, for example, details of the biological sample S sample used to verify the hypothesis (such as details of the fluorescent dye that labels the biological particles P), details of various controls, settings for the biological sample analyzer 100, and the procedures for the analytical experiment. Next, the light irradiation unit 101 and detection unit 102 of the biological sample analyzer 100 are set based on the created protocol (S13).

Thereafter, reference data to be used for calibrating the biological sample analyzer 100 is acquired using the biological sample analyzer 100 (S14). After calibration, a sample of the biological sample S is measured using the biological sample analyzer 100, and optical data of the biological particles P contained in the biological sample S is acquired (S15). The measurement results of the sample of the biological sample S are then analyzed by the information processing unit 103 of the biological sample analyzer 100 (S16). Specifically, in analyzing the measurement results, fluorescence spillover correction or fluorescence separation processing is performed on the optical data of the biological particles P, and light intensity data corresponding to the fluorescent dye that labels the biological particles P is acquired from the optical data of the biological particles P.

Furthermore, experimental data for verifying the set hypothesis is compiled based on the acquired light intensity data corresponding to the fluorescent dye (S17). The compiled experimental data is shared with other users of the biological sample analyzer 100, for example, by being sent to the server 200 (S18).

An analytical experiment using the biological sample analyzer 100 is performed according to the above flow. In analytical experiments using the biological sample analyzer 100, the analysis of the measurement results in step S16 is important. In particular, in multicolor analysis experiments in which biological particles P are labeled with multiple fluorescent dyes, it is important to identify the autofluorescence of the biological particles P from the optical data that is the measurement result, and to exclude the identified autofluorescence of the biological particles P from the optical data. By excluding the autofluorescence from the optical data, the information processing unit 103 is able to analyze only the fluorescence emitted from the multiple fluorescent dyes labeled on the biological particles P. The information processing related to the identification of the autofluorescence of the biological particles P, performed by the information processing unit 103, will be explained in more detail below.

<2. Information Processing Section>
(2.1. Configuration of Information Processing Unit)
Fig. 4 is a block diagram showing the functional configuration of the information processing unit 103. As shown in Fig. 4, the information processing unit 103 includes an acquisition unit 110, an autofluorescence identification unit 120, an output unit 140, and a storage unit 130. The information processing unit 103 may be part of the biological sample analyzer 100, or may be an information processing device separate from the biological sample analyzer 100.

The acquisition unit 110 acquires optical data of the bioparticles P from the detection unit 102. Specifically, the acquisition unit 110 may acquire optical data of light generated by irradiating light onto bioparticles P that are not labeled with a fluorescent dye from the detection unit 102. In this way, the autofluorescence identification unit 120 at the subsequent stage can identify the autofluorescence of the bioparticles P by analyzing the optical data of the bioparticles P that are not labeled with a fluorescent dye.

For example, the acquisition unit 110 may acquire the optical data shown in Figure 5 from the detection unit 102. Figure 5 is a graph showing an example of optical data detected by the detection unit 102 of a spectral flow cytometer.

In the detection unit 102 of the spectral flow cytometer, the fluorescence or scattered light of bioparticles P irradiated with laser light of multiple wavelengths is dispersed and detected as a spectrum by the detection unit 102. The detection unit 102 integrates the spectrum of the light intensity of the fluorescence or scattered light emitted from each bioparticle P, and expresses the number of occurrences of the light intensity of the fluorescence or scattered light as a heat map. For example, in the optical data shown in Figure 5, the vertical axis represents the light intensity of the detected fluorescence or scattered light, and the horizontal axis represents the channel number of the photodetector arrayed in wavelength order, and the number of occurrences of the light intensity of the fluorescence or scattered light from the bioparticles P is expressed as a heat map.

The autofluorescence identification unit 120 identifies the autofluorescence data of the bioparticle P from the optical data of the bioparticle P acquired by the acquisition unit 110, and stores the identified autofluorescence data in the storage unit 130. Specifically, the autofluorescence identification unit 120 includes a clustering unit 121 and an evaluation unit 122. Note that the functions of the autofluorescence identification unit 120 may be executed by the information processing unit 103, or may be executed by a cloud server or the like connected to the information processing unit 103 via a network.

The clustering unit 121 clusters the optical data of the bioparticles P acquired by the acquisition unit 110, thereby dividing the optical data of the bioparticles P into at least one or more independent spectral groups. Specifically, the clustering unit 121 may cluster the optical data of the bioparticles P using a known clustering method such as k-means, DBSCAN (Density-Based Spatial Clustering of Applications with Noise), or hierarchical clustering.

For example, if the optical data of bioparticle P is the optical data shown in Figure 5, the clustering unit 121 can cluster the optical data of bioparticle P into spectrum groups as shown in Figures 6 and 7 with the number of clusters k = 2. Figures 6 and 7 are graphs showing examples of optical data for each cluster obtained by clustering the optical data shown in Figure 5 with the number of clusters k = 2.

The number of clusters used by the clustering unit 121 for clustering may be a predetermined number, or may be a number set appropriately by the user. Furthermore, the number of clusters used by the clustering unit 121 for clustering may be a number optimized using the method described below.

Note that while the above example shows clustering of spectral optical data acquired by a spectral flow cytometer, the technology disclosed herein is not limited to the above example. The clustering unit 121 can also cluster non-spectral optical data obtained by detecting light from bioparticles P separated into specific wavelength ranges. Even in such cases, the clustering unit 121 can extract various trends contained in the optical data of bioparticles P as clusters by clustering groups of light intensity data for each specific wavelength range acquired from each bioparticle P.

The evaluation unit 122 identifies the autofluorescence data of the bioparticles P based on the optical data of each cluster clustered by the clustering unit 121.

Clustering is a machine learning technique that divides data into groups based on the similarity between the data. Therefore, each cluster is considered to be a data group that extracts some tendency contained in the data before clustering. In other words, each cluster of optical data of bioparticles P clustered by the clustering unit 121 is a cluster that extracts various tendencies contained in the optical data of bioparticles P. The autofluorescence of bioparticles P occurs based on the internal structure and substances contained in the bioparticles P, and therefore each type of bioparticle P has a specific tendency. Therefore, any of the optical data of a cluster obtained by clustering optical data of bioparticles P that are not labeled with a fluorescent dye is considered to be optical data that corresponds to the autofluorescence of the bioparticles P.

Specifically, the evaluation unit 122 may identify the autofluorescence data of the bioparticle P based on a statistical representative value of the optical data of a cluster selected from each of the clustered clusters. The statistical representative value is, for example, the mean value, median value, or mode value of the optical data of the cluster.

For example, the evaluation unit 122 may identify the autofluorescence data of the bioparticle P based on the optical data of a cluster arbitrarily selected by the user, or may identify the autofluorescence data of the bioparticle P based on the optical data of a cluster with the largest number of cluster data. Also, the evaluation unit 122 may identify the autofluorescence data of the bioparticle P based on the optical data of a cluster with the number of cluster data equal to or greater than a threshold value.

The evaluation unit 122 may also identify the autofluorescence data of the bioparticle P based on the optical data of multiple clusters. In such cases, the evaluation unit 122 will identify multiple spectra as the autofluorescence data of the bioparticle P. For example, if the bioparticle P includes multiple particle groups with different autofluorescence, or if the bioparticle P has autofluorescence that varies depending on the state, etc., the evaluation unit 122 can generate autofluorescence data from each of the multiple clusters, thereby taking multiple autofluorescences into account when performing fluorescence correction, etc.

The memory unit 130 stores the autofluorescence data identified by the evaluation unit 122. The autofluorescence data stored in the memory unit 130 can be used, for example, to remove autofluorescence from the optical data of biological particles P labeled with fluorescent dyes. The autofluorescence data stored in the memory unit 130 can also be used, for example, to perform fluorescence correction to extract the fluorescence of each fluorescent dye from the optical data of biological particles P labeled with fluorescent dyes.

The output unit 140 outputs the autofluorescence data stored in the memory unit 130. For example, the output unit 140 may present the autofluorescence data of the bioparticle P to a user by outputting the autofluorescence data stored in the memory unit 130 to a display unit external to the information processing unit 103. The output unit 140 may also output the autofluorescence data stored in the memory unit 130 to a calculation unit external to the information processing unit 103, so that the autofluorescence data of the bioparticle P can be used in the analysis of other bioparticles P.

(2.2. Operation of Information Processing Unit)
FIG. 8 is a flowchart showing the flow of operations related to the information processing unit 103.

As shown in FIG. 8, first, optical data of the biological particle P is acquired by the acquisition unit 110 (S101). For example, the acquisition unit 110 may acquire optical data of the biological particle P that is not labeled with a fluorescent dye from the detection unit 102.

Next, the clustering unit 121 determines the number of clusters to be used when clustering the optical data of the biological particles P (S102). The number of clusters may be determined based on input from the user, may be determined based on predetermined parameters of the optical data of the biological particles P, or may be determined using a determination method described below.

Next, the clustering unit 121 clusters the optical data of the bioparticles P using the number of clusters determined in step S102 (S103). For example, the clustering unit 121 may cluster the optical data of the bioparticles P using a known clustering method such as k-means, DBSCAN, or hierarchical clustering.

Furthermore, the evaluation unit 122 identifies the autofluorescence data of the bioparticle P based on the optical data of each cluster clustered by the clustering unit 121 (S104). For example, the evaluation unit 122 may identify the spectrum corresponding to the autofluorescence data of the bioparticle P by extracting, for each channel number, the mean, median, or mode of the optical data of a cluster selected from each cluster. The autofluorescence data of the bioparticle P identified by the evaluation unit 122 is stored, for example, in the storage unit 130.

Then, the information processing unit 103 performs fluorescence correction on the optical data of the bioparticles P labeled with fluorescent dyes (S105). Fluorescence correction refers to, for example, a process of separating the optical data acquired as a spectrum into the fluorescence of each fluorescent dye using an unmixing method, or a process of acquiring the fluorescence of each fluorescent dye by correcting the leakage of the fluorescence of each fluorescent dye from the optical data acquired for each wavelength band. When performing fluorescence correction on the optical data of the bioparticles P, the information processing unit 103 takes into account the autofluorescence of the bioparticles P, thereby being able to separate or correct the fluorescence of the fluorescent dyes with higher accuracy.

For example, the information processing unit 103 may perform fluorescence correction on the optical data of the bioparticle P using the following first or second method.

The first method is to perform fluorescence correction on the optical data of a bioparticle P using one piece of autofluorescence data. Specifically, the information processing unit 103 can perform fluorescence correction on the optical data of a bioparticle P by performing the matrix operation expressed by (2) or (3) below using a fluorescence correction matrix A expressed by (1) below.

The a included in the fluorescence correction matrix A is a fluorescence correction parameter. Furthermore, n is the number of the fluorescent dye, and m is the channel number of the photodetector. The optical data x before fluorescence correction has the autofluorescence data u subtracted from it, and then the inverse matrix of the fluorescence correction matrix A is applied to produce fluorescence data y after fluorescence correction. Note that A ^T is a matrix that adjusts for mismatches where m ≠ n to enable matrix calculations.

According to the first method, the information processing unit 103 can perform fluorescence correction on the optical data of bioparticles P obtained by dividing the autofluorescence data.

In addition, the information processing unit 103 can also perform fluorescence correction on the optical data of the bioparticle P by performing the following calculation (4) instead of the calculation (3) above. This allows the information processing unit 103 to match the scale of the signal intensity of the fluorescence data y after fluorescence correction with the scale of the signal intensity of the optical data x before fluorescence correction.

The second method is to perform fluorescence correction on the optical data of bioparticles P using multiple pieces of autofluorescence data. Specifically, the information processing unit 103 can perform fluorescence correction on the optical data of bioparticles P by performing the calculations expressed in (6) or (7) below using a fluorescence correction matrix A expressed in (5) below.

In the fluorescence correction matrix A, a is a fluorescence correction parameter and u is the autofluorescence data. Furthermore, n is the fluorescent dye number, m is the photodetector channel number, and l is the autofluorescence data identification number. The optical data x before fluorescence correction is subjected to the inverse matrix of the fluorescence correction matrix A to become fluorescence data y after fluorescence correction and autofluorescence data af after fluorescence correction. Note that A ^T is a matrix that adjusts for mismatches where m ≠ n to enable matrix calculations.

According to the second method, the information processing unit 103 can perform fluorescence correction on the optical data of the bioparticle P by taking into account one piece of autofluorescence data.

(2.3. Method for determining the number of clusters)
(First determination method)
A first method for determining the number of clusters by the clustering unit 121 will be described with reference to Figures 9 to 12. The first method for determining the number of clusters is a method for determining the number of clusters based on the degree of variability in optical data after fluorescence correction of optical data of bioparticles P not labeled with a fluorescent dye. Figure 9 is a flowchart showing the flow of the first method for determining the number of clusters. Figures 10 to 12 are scatter plots showing the degree of variability in optical data after fluorescence correction using identified autofluorescence data after clustering with different numbers of clusters.

As shown in FIG. 9, first, the acquisition unit 110 acquires optical data of the bioparticle P (S211). For example, the acquisition unit 110 may acquire optical data of the bioparticle P that is not labeled with a fluorescent dye from the detection unit 102.

Next, the clustering unit 121 determines the search range for the number of clusters when clustering the optical data of the biological particles P (S212). The determined search range for the number of clusters may be, for example, 1 to 10. Next, the clustering unit 121 clusters the optical data of the biological particles P using any number of clusters within the search range determined in step S212 (S213).

Furthermore, the evaluation unit 122 identifies the autofluorescence data of the bioparticle P based on the optical data of each cluster clustered by the clustering unit 121 (S214). For example, the evaluation unit 122 may identify the spectrum corresponding to the autofluorescence data of the bioparticle P based on a statistical representative value of the optical data of a cluster selected from each of the clusters clustered.

Next, the information processing unit 103 uses the autofluorescence data of the bioparticles P identified in step S214 to perform fluorescence correction on the optical data of the bioparticles P that are not labeled with a fluorescent dye (S215). Next, the information processing unit 103 calculates the degree of variability in the fluorescence-corrected optical data of the bioparticles P (S216). Specifically, the information processing unit 103 calculates the degree of variability in the optical data of the bioparticles P by plotting the light intensity of the fluorescence-corrected optical data of the bioparticles P for each wavelength corresponding to the color of the fluorescent dye that labels the bioparticles P during the actual analytical experiment.

For example, Figure 10 is a scatter plot of optical data of a bioparticle P after fluorescence correction using the autofluorescence data of the bioparticle P identified based on the optical data of a cluster clustered with a cluster number of 1. Figure 11 is a scatter plot of optical data of a bioparticle P after fluorescence correction using the autofluorescence data of the bioparticle P identified based on the optical data of a cluster clustered with a cluster number of 2. Figure 12 is a scatter plot of optical data of a bioparticle P after fluorescence correction using the autofluorescence data of the bioparticle P identified based on the optical data of a cluster clustered with a cluster number of 3.

For example, the information processing unit 103 first plots the fluorescence-corrected optical data of the bioparticles P on a scatter plot using the light intensities of wavelengths corresponding to the colors of all the fluorescent dyes used in the analytical experiment (FITC_A and BV785_A in Figures 10 to 12). Next, the information processing unit 103 can calculate the degree of variability in the optical data of the bioparticles P for each cluster number by averaging the degrees of variability in the plots of the bioparticles P calculated at wavelengths corresponding to the colors of all the fluorescent dyes used in the analytical experiment. Examples of the degree of variability in the optical data of the bioparticles P include variance and standard deviation.

Then, the information processing unit 103 determines whether the degree of variation has been calculated for all cluster numbers in the search range determined in step S212 (S217). If the degree of variation has not been calculated for all cluster numbers in the search range (S217/NO), the process returns to step S213, where clustering and autofluorescence data identification are performed using a different number of clusters.

On the other hand, if the degree of variation has been calculated for all cluster numbers in the search range (S217/YES), the information processing unit 103 adopts the cluster number with the lowest calculated degree of variation as the number of clusters to be used for actual clustering (S218). For example, in the data shown in Figures 10 to 12, the cluster number of 3 shown in Figure 12, which has the smallest variation in the optical data of bioparticles P, is adopted as the number of clusters to be used for actual clustering.

According to the first method for determining the number of clusters described above, the information processing unit 103 can adopt, as the number of clusters for clustering, the number of clusters that minimizes the variance in the optical data after fluorescence correction at wavelengths corresponding to the colors of the fluorescent dyes used in the analytical experiment.

(Second determination method)
A second method for determining the number of clusters by the clustering unit 121 will be described with reference to Figs. 13 to 16. The second method for determining the number of clusters is a method for determining the number of clusters based on the similarity of spectra identified from each clustered cluster. Fig. 13 is a flowchart showing the flow of the second method for determining the number of clusters. Figs. 14 to 16 are graphs comparing the similarity of spectra identified from each clustered cluster after clustering with different numbers of clusters.

As shown in FIG. 13, first, the acquisition unit 110 acquires optical data of the bioparticle P (S221). For example, the acquisition unit 110 may acquire optical data of the bioparticle P that is not labeled with a fluorescent dye from the detection unit 102.

Next, the clustering unit 121 determines the search range for the number of clusters when clustering the optical data of the biological particles P (S222). The determined search range for the number of clusters may be, for example, 1 to 10. Next, the clustering unit 121 clusters the optical data of the biological particles P using any number of clusters within the search range determined in step S222 (S223).

Furthermore, the evaluation unit 122 calculates the similarity of the optical data of each cluster clustered by the clustering unit 121 (S226). Specifically, the evaluation unit 122 identifies the spectrum of each cluster based on the optical data of each cluster clustered, and calculates the similarity of the spectra of each cluster.

For example, Figure 14 shows the spectra of each cluster identified based on the optical data of clusters clustered with one cluster. Figure 15 shows the spectra of each cluster identified based on the optical data of clusters clustered with two clusters. Figure 16 shows the spectra of each cluster identified based on the optical data of clusters clustered with three clusters.

For example, the information processing unit 103 can calculate the similarity for each number of clusters by calculating the similarity between the spectra of each cluster. The information processing unit 103 may use the average value of the similarities between the spectra of each cluster as the similarity for the number of clusters, or the maximum value of the similarities between the spectra of each cluster as the similarity for the number of clusters. For example, cosine similarity or spectral similarity index can be used as the similarity between the spectra of each cluster.

When multiple spectra with similar shapes are used in fluorescence correction, the fluorescence correction may not be performed correctly. This is because when multiple spectra with similar shapes are used, some of the simultaneous equations used to perform fluorescence correction may not be independent of each other and may have multiple solutions. Furthermore, when the spectra of each cluster are similar to each other, there is a possibility that groups that should not be divided into different clusters may be divided into multiple clusters. Therefore, the information processing unit 103 can perform more appropriate fluorescence correction by selecting a number of clusters that results in a lower similarity between each cluster.

Then, the information processing unit 103 determines whether similarities have been calculated for all cluster counts in the search range determined in step S222 (S227). If similarities have not been calculated for all cluster counts in the search range (S227/NO), the process returns to step S223, where clustering and similarity calculation are performed for a different number of clusters.

On the other hand, if similarities have been calculated for all cluster numbers in the search range (S227/YES), the information processing unit 103 adopts the cluster number with the lowest calculated similarity as the number of clusters to be used for actual clustering (S228). For example, for the data shown in Figures 14 to 16, the number of clusters shown in Figure 15, 2, which has the lowest spectral similarity between each cluster, is adopted as the number of clusters to be used for actual clustering.

According to the second method for determining the number of clusters described above, the information processing unit 103 can adopt, as the number of clusters for clustering, the number of clusters that results in each cluster tending to be independent of one another.

(2.4. Modifications)
(First Modification)
17 is a block diagram showing the functional configuration of an information processing unit 103A according to a first modified example of this embodiment. The information processing unit 103A according to the first modified example differs from the information processing unit 103 shown in FIG. 4 in that the information processing unit 103A preprocesses the optical data of the bioparticles P before clustering.

Specifically, as shown in FIG. 17, the autofluorescence identification unit 120A includes a preprocessing unit 123, a clustering unit 121, and an evaluation unit 122. Note that the functions and operations of the clustering unit 121 and the evaluation unit 122 are as described with reference to FIG. 4, and therefore will not be described here.

The preprocessing unit 123 performs preprocessing by applying a conversion function to the optical data of the bioparticles P acquired by the acquisition unit 110. Specifically, the preprocessing unit 123 performs preprocessing by applying a conversion function that performs scale conversion on the optical data of the bioparticles P. The conversion function that performs scale conversion is, for example, a linear, log, hyperlog, or bi-exponential conversion function, and can convert the scale of the light intensity data of the optical data of the bioparticles P.

The conversion function used in the preprocessing by the preprocessing unit 123 is selected appropriately depending on the characteristics of the optical data of the bioparticles P. For example, the conversion function used in the preprocessing by the preprocessing unit 123 may be a HyperLog or Bi-exponential conversion function. This allows the preprocessing unit 123 to further emphasize the differences in the optical data of the bioparticles P, for example, between bioparticles P labeled with a fluorescent dye and bioparticles P not labeled with a fluorescent dye.

FIGS. 18 and 19 are graphs showing an example in which identical optical data of bioparticles P is clustered with a cluster count of 3, and the spectrum of each cluster is identified. FIG. 18 shows clustering of optical data of bioparticles P preprocessed with a linear conversion function, and FIG. 19 shows clustering of optical data of bioparticles P preprocessed with a bi-exponential conversion function. As shown in FIGS. 18 and 19, by preprocessing with a bi-exponential conversion function, the clustering unit 121 can cluster the optical data of bioparticles P into clusters that are more independent of each other, compared to when preprocessing is performed with a linear conversion function.

Therefore, the information processing unit 103A according to the first modified example performs preprocessing of scale conversion on the optical data of the biological particles P, making it possible to cluster the optical data of the biological particles P into clusters that are more independent from each other.

(Second Modification)
20 is a schematic diagram showing an example of a clustering target of the information processing unit 103 according to the second modified example of this embodiment. The clustering target by the information processing unit 103 according to the second modified example is not limited to the optical data of bioparticles P measured by a flow cytometer, and may be other image data groups including autofluorescence.

Specifically, as shown in FIG. 20, the clustering target by the information processing unit 103 may be a group of biological images G captured by an imaging flow cytometer or a fluorescence microscope. The group of biological images G is, for example, an image capturing fluorescence or scattered light including autofluorescence of biological particles P, or a group of multiple images capturing fluorescence including autofluorescence from cells or tissues.

The information processing unit 103 can identify the autofluorescence of bioparticles P, cells, or tissues contained in the bioimage group G by similarly performing clustering using the bioimage group G as an explanatory variable. For example, when the information processing unit 103 obtains images G1, G2, ... for each cluster by clustering the bioimage group G, it can identify the autofluorescence images of bioparticles P, cells, or tissues contained in the bioimage group G from the images G1, G2, ... for each cluster.

Therefore, the information processing unit 103 according to the second modified example is able to identify autofluorescence images by clustering even from a group of fluorescence image data that includes autofluorescence.

(Third Modification)
21 is a flowchart showing the flow of operations related to the information processing unit 103 according to the third modified example of this embodiment. The information processing unit 103 according to the third modified example generates a learning model that uses machine learning to learn the relationship between the identified autofluorescence data and the bioparticles P, thereby making it possible to estimate the type of the bioparticles P from the autofluorescence data.

As shown in FIG. 21, first, optical data of the bioparticle P is acquired by the acquisition unit 110 (S301). For example, the acquisition unit 110 may acquire optical data of the bioparticle P that is not labeled with a fluorescent dye from the detection unit 102.

Next, the clustering unit 121 clusters the optical data of the biological particles P using the number of clusters determined in step S102 (S302). For example, the clustering unit 121 may cluster the optical data of the biological particles P using a known clustering method such as k-means, DBSCAN, or hierarchical clustering. Note that the number of clusters used in clustering may be determined based on input from a user, may be determined based on predetermined parameters of the optical data of the biological particles P, or may be determined using the first or second determination method described above.

Next, the evaluation unit 122 identifies the autofluorescence data of the bioparticle P based on the optical data of each cluster clustered by the clustering unit 121 (S303). For example, the evaluation unit 122 may identify the spectrum corresponding to the autofluorescence data of the bioparticle P by extracting, for each channel number, the mean, median, or mode of the optical data of a cluster selected from each of the clusters clustered. The autofluorescence data of the bioparticle P identified by the evaluation unit 122 is stored, for example, in the storage unit 130.

Then, the information processing unit 103 trains the learning model to learn the relationship between the autofluorescence data of the identified bioparticles P and the type of bioparticles P (S304). The relationship between the autofluorescence data of the bioparticles P and the type of bioparticles P may be set, for example, by the user. By machine learning the relationship between the autofluorescence data of a large number of bioparticles P and the type of bioparticles P, a learning model that estimates the relationship between the autofluorescence data of the bioparticles P and the type of bioparticles P is generated.

As a result, the information processing unit 103 can input the autofluorescence data identified separately in the processing of steps S301 to S303 into the generated learning model, thereby estimating the type of bioparticle P corresponding to the input autofluorescence data (S305).

Therefore, the information processing unit 103 according to the third modified example generates a learning model that uses machine learning to identify the relationship between the identified autofluorescence and the bioparticle P, thereby making it possible to estimate the type of bioparticle P from other autofluorescence data.

<3. Hardware Configuration>
Furthermore, a hardware configuration for realizing the information processing unit 103 according to this embodiment will be described with reference to Fig. 22. Fig. 22 is a block diagram showing an example of the hardware configuration of an information processing device 900 that realizes the information processing unit 103 according to this embodiment.

The functions of the information processing unit 103 according to this embodiment may be realized by a combination of software and the hardware described below. The functions of the autofluorescence identification unit 120 may be performed by, for example, the CPU 901. The functions of the acquisition unit 110 may be performed by, for example, the connection port 910 or the communication device 911. The functions of the memory unit 130 may be performed by, for example, the storage device 908. The functions of the output unit 140 may be performed by, for example, the output device 907, the drive 909, the connection port 910, or the communication device 911.

As shown in FIG. 22, the information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, and a RAM (Random Access Memory) 903.

The information processing device 900 may further include a host bus 904a, a bridge 904, an external bus 904b, an interface 905, an input device 906, an output device 907, a storage device 908, a drive 909, a connection port 910, or a communication device 911. The information processing device 900 may have a processing circuit such as a DSP (Digital Signal Processor) or an ASIC (Application Specific Integrated Circuit) instead of or in addition to the CPU 901.

The CPU 901 functions as an arithmetic processing device or control device, and controls operations within the information processing device 900 in accordance with various programs recorded in the ROM 902, RAM 903, storage device 908, or a removable recording medium attached to the drive 909. The ROM 902 stores programs used by the CPU 901, as well as calculation parameters, etc. The RAM 903 temporarily stores programs used in the execution of the CPU 901, as well as parameters used during that execution, etc.

The CPU 901, ROM 902, and RAM 903 are interconnected by a host bus 904a, which is capable of high-speed data transmission. The host bus 904a is connected to an external bus 904b, such as a PCI (Peripheral Component Interconnect/Interface) bus, via a bridge 904, and the external bus 904b is connected to various components via an interface 905.

The input device 906 is a device that accepts input from the user, such as a mouse, keyboard, touch panel, button, switch, or lever. The input device 906 may also be a microphone that detects the user's voice. The input device 906 may also be, for example, a remote control device that uses infrared or other radio waves, or an externally connected device that supports operation of the information processing device 900.

The input device 906 further includes an input control circuit that outputs an input signal generated based on information input by the user to the CPU 901. By operating the input device 906, the user can input various data or instruct the information processing device 900 to perform processing operations.

The output device 907 is a device capable of visually or audibly presenting information acquired or generated by the information processing device 900 to the user. The output device 907 may be, for example, a display device such as an LCD (Liquid Crystal Display), a PDP (Plasma Display Panel), an OLED (Organic Light Emitting Diode) display, a hologram, or a projector, or may be an audio output device such as a speaker or headphones, or a printing device such as a printer. The output device 907 can output information acquired by processing by the information processing device 900 as video such as text or images, or sound such as voice or audio.

The storage device 908 is a data storage device configured as an example of a storage unit of the information processing device 900. The storage device 908 may be configured, for example, by a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, or a magneto-optical storage device. The storage device 908 can store programs executed by the CPU 901, various data, or various data obtained from the outside.

The drive 909 is a device for reading or writing removable recording media such as magnetic disks, optical disks, magneto-optical disks, or semiconductor memories, and is either built into the information processing device 900 or attached externally. For example, the drive 909 can read information recorded on an attached removable recording media and output it to RAM 903. The drive 909 can also write information to an attached removable recording media.

The connection port 910 is a port for directly connecting an external device to the information processing device 900. The connection port 910 may be, for example, a USB (Universal Serial Bus) port, an IEEE 1394 port, or a SCSI (Small Computer System Interface) port. The connection port 910 may also be an RS-232C port, an optical audio terminal, or an HDMI (registered trademark) (High-Definition Multimedia Interface) port. By connecting the connection port 910 to an external device, various types of data can be sent and received between the information processing device 900 and the external device.

The communication device 911 is, for example, a communication interface configured with a communication device for connecting to the communication network 920. The communication device 911 may be, for example, a communication card for a wired or wireless LAN (Local Area Network), Wi-Fi (registered trademark), Bluetooth (registered trademark), or WUSB (Wireless USB). The communication device 911 may also be a router for optical communications, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various types of communications.

The communication device 911 can send and receive signals, for example, via the Internet or with other communication devices, using a predetermined protocol such as TCP/IP. The communication network 920 connected to the communication device 911 is a wired or wireless network, and may be, for example, an Internet communication network, a home LAN, an infrared communication network, a radio wave communication network, or a satellite communication network.

It is also possible to create a program that causes hardware such as the CPU 901, ROM 902, and RAM 903 built into a computer to perform functions equivalent to those of the information processing device 900 described above. It is also possible to provide a computer-readable recording medium on which the program is recorded.

The above describes in detail preferred embodiments of the present disclosure with reference to the accompanying drawings, but the technical scope of the present disclosure is not limited to such examples. It is clear that a person with ordinary skill in the technical field of the present disclosure would be able to conceive of various modified or revised examples within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present disclosure.

Furthermore, the effects described in this specification are merely descriptive or exemplary and are not limiting. In other words, the technology disclosed herein may achieve other effects in addition to or in place of the above-mentioned effects that would be apparent to those skilled in the art from the description herein.

The following configurations also fall within the technical scope of the present disclosure.
(1)
acquiring optical data by irradiating a plurality of biological particles with light;
identifying autofluorescence data of the plurality of biological particles by clustering the optical data;
outputting the autofluorescence data;
An information processing method, including:
(2)
The information processing method according to (1), wherein the optical data is unlabeled data acquired from the plurality of biological particles that are not labeled with a fluorescent dye.
(3)
The information processing method described in (2) further includes performing fluorescence correction to obtain fluorescence data corresponding to the colors of at least one or more of the fluorescent dyes using the autofluorescence data from labeled data obtained from the plurality of biological particles labeled with at least one or more of the fluorescent dyes.
(4)
The information processing method according to (3), wherein a representative value of the autofluorescence data is used for the fluorescence correction.
(5)
The method further includes determining the number of clusters in the clustering;
The information processing method according to (3) or (4), wherein the number of clusters is determined based on the degree of variability of fluorescence data corresponding to the color of the fluorescent dye when the fluorescence correction is performed on the label-free data.
(6)
The information processing method according to (5), wherein the degree of variation is calculated for each of the numbers of clusters within a predetermined range, and the number of clusters with the calculated degree of variation being the lowest is adopted.
(7)
The method further includes determining the number of clusters in the clustering;
The information processing method according to any one of (2) to (4), wherein the number of clusters is determined based on the similarity between optical data of each cluster obtained by clustering the label-free data.
(8)
The information processing method according to (7), wherein the similarity is calculated for each of the cluster numbers within a predetermined range, and the cluster number with the lowest calculated similarity is adopted.
(9)
The information processing method according to any one of (2) to (8), wherein one or more of the optical data of each cluster obtained by clustering the label-free data are identified as the autofluorescence data.
(10)
The information processing method according to any one of (2) to (9), further comprising applying a transformation function that performs a scale transformation to the acquired unlabeled data before the clustering.
(11)
The information processing method according to any one of (1) to (10), further comprising generating a machine learning model using a combination of the autofluorescence data and the type of the bioparticle corresponding to the autofluorescence data.
(12)
an acquisition unit that acquires light data by irradiating light onto a plurality of bioparticles;
an autofluorescence identification unit that identifies autofluorescence data of the plurality of bioparticles by clustering the optical data;
an output unit that outputs the autofluorescence data;
An information processing device comprising:
(13)
a detection device that acquires optical data by irradiating light onto a plurality of biological particles;
an information processing device including: an autofluorescence identification unit that identifies autofluorescence data of the plurality of bioparticles by clustering the optical data; and an output unit that outputs the autofluorescence data;
An information processing system comprising:

REFERENCE SIGNS LIST 100 Biological sample analyzer 101 Light irradiation unit 102 Detection unit 103, 103A Information processing unit 104 Sorting unit 110 Acquisition unit 120, 120A Autofluorescence identification unit 121 Clustering unit 122 Evaluation unit 123 Preprocessing unit 130 Storage unit 140 Output unit 10 Analysis system 200, 300 Server C Flow path P Biological particle S Biological sample

Claims (13)

acquiring optical data by irradiating a plurality of biological particles with light;
identifying autofluorescence data of the plurality of biological particles by clustering the optical data;
outputting the autofluorescence data;
An information processing method, including: The information processing method described in claim 1, wherein the optical data is unlabeled data acquired from the plurality of biological particles that are not labeled with a fluorescent dye. The information processing method of claim 2, further comprising performing fluorescence correction to obtain fluorescence data corresponding to the colors of at least one of the fluorescent dyes using the autofluorescence data from labeled data obtained from the plurality of biological particles labeled with at least one of the fluorescent dyes. The information processing method described in claim 3, wherein a representative value of the autofluorescence data is used for the fluorescence correction. The method further includes determining the number of clusters in the clustering;
The information processing method according to claim 3 , wherein the number of clusters is determined based on a degree of variability in fluorescence data corresponding to the color of the fluorescent dye when the label-free data is subjected to the fluorescence correction. The information processing method of claim 5, wherein the degree of variation is calculated for each of the cluster numbers within a predetermined range, and the cluster number with the lowest calculated degree of variation is adopted. The method further includes determining the number of clusters in the clustering;
The information processing method according to claim 2 , wherein the number of clusters is determined based on a similarity between optical data of each cluster obtained by clustering the label-free data. The information processing method of claim 7, wherein the similarity is calculated for each of the cluster numbers within a predetermined range, and the cluster number with the lowest calculated similarity is adopted. The information processing method described in claim 2, wherein one or more of the optical data in each cluster obtained by clustering the label-free data are identified as the autofluorescence data. The information processing method of claim 2, further comprising applying a transformation function that performs a scale transformation to the acquired unlabeled data prior to the clustering. The information processing method of claim 1, further comprising generating a machine learning model using a combination of the autofluorescence data and the type of bioparticle corresponding to the autofluorescence data. an acquisition unit that acquires light data by irradiating light onto a plurality of bioparticles;
an autofluorescence identification unit that identifies autofluorescence data of the plurality of bioparticles by clustering the optical data;
an output unit that outputs the autofluorescence data;
An information processing device comprising: a detection device that acquires optical data by irradiating light onto a plurality of biological particles;
an information processing device including: an autofluorescence identification unit that identifies autofluorescence data of the plurality of bioparticles by clustering the optical data; and an output unit that outputs the autofluorescence data;
An information processing system comprising: