JPWO2020162595A1 - A method for determining susceptibility to a test substance, a device for determining susceptibility to a test substance, a screening method for an anticancer drug, a method for manufacturing a candidate substance for an anticancer drug, a method for manufacturing a trained model, a device for manufacturing a trained model, and a selection method. - Google Patents

Abstract

Provided is a new determination method capable of determining the susceptibility of tumor cells to a test substance. The method for determining susceptibility to a test substance of the present invention obtains a second harmonic (SHG) obtained by using a coherent anti-Stoke Raman scattering (CARS) microscope for tumor cells contacted with the test substance. The acquisition step includes a determination step of determining the susceptibility of the tumor cells to the test substance based on the SHG.

Description

INDUSTRIAL APPLICABILITY The present invention relates to a method for determining susceptibility to a test substance, a device for determining susceptibility to a test substance, a method for screening an anticancer drug, a method for manufacturing a candidate substance for an anticancer drug, a method for manufacturing a trained model, and a device for manufacturing a trained model. , And the selection method.

As the screening of an anticancer agent, a method in which a target tumor cell and a candidate compound of the anticancer agent coexist and the cell death (survival rate) of the tumor cell is used as an index is used (Non-Patent Document 1).

John G. Moffat et.al., "Phenotypic screening in cancer drug discovery --past, present and future", 2014, Nature Reviews Drug Discovery, volume 13, pages 588-602

An object of the present invention is to provide a new determination method capable of determining the susceptibility of a tumor cell to a test substance.

In order to achieve the above object, the method for determining susceptibility to a test substance (hereinafter, also referred to as “determination method”) of the present invention is coherent anti-Stoke Raman scattering (CARS) for tumor cells brought into contact with the test substance. ) The acquisition process of acquiring the second harmonic (SHG) acquired using a microscope, and
A determination step of determining the susceptibility of the tumor cells to the test substance based on the SHG is included.

The device for determining susceptibility to a test substance (hereinafter, also referred to as “determining device”) of the present invention was obtained by using a coherent anti-Stoke Raman scattering (CARS) microscope for tumor cells contacted with the test substance. Acquisition means for acquiring the second harmonic (SHG),
A determination means for determining the susceptibility of the tumor cells to the test substance based on the SHG is included.

The method for screening an anticancer agent of the present invention (hereinafter, also referred to as “screening method”) includes a determination step for determining the susceptibility of a tumor cell in contact with a test substance to the test substance.
The step of selecting a test substance determined to be sensitive to the tumor cells as a candidate substance for an anticancer drug is included.
The determination step is carried out by the determination method of the present invention.

The method for producing a candidate substance for an anticancer agent of the present invention (hereinafter, also referred to as “manufacturing method”) includes a selection step of selecting a candidate substance for an anticancer agent from a test substance.
The selection step is carried out by the screening method of the present invention.

The method for producing a trained model (hereinafter, also referred to as “learning method”) used for determining the susceptibility of tumor cells of the present invention is to use a coherent anti-Stoke Raman scattering (CARS) microscope for tumor cells in contact with a test substance. The acquisition process for acquiring the second harmonic (SHG) acquired using
It includes a learning step of generating a learned model that outputs a determination result of the susceptibility of the tumor cells to the test substance from the SHG using the pair of the SHG and the susceptibility of the tumor cells to the test substance as teacher data.

The training device for manufacturing a trained model (hereinafter, also referred to as “learning device”) used for determining the susceptibility of tumor cells of the present invention is a coherent anti-Stoke Raman scattering (CARS) microscope for tumor cells contacted with a test substance. The acquisition means for acquiring the second harmonic (SHG) acquired by using, and
It includes a learning means for generating a learned model that outputs a determination result of the susceptibility of a tumor cell to a test substance from the SHG using a pair of the SHG and the susceptibility of the tumor cell to the test substance as teacher data.

In the method for selecting cells for determining susceptibility of a test substance of the present invention (hereinafter, also referred to as “selection method”), a coherent anti-Stoke Raman scattering (CARS) microscope is used for a second harmonic (SHG) of a test tumor cell. ) And the acquisition process
A selection step of selecting a candidate tumor cell to be used for a susceptibility test of the test substance from the test tumor cells based on the SHG is included.

According to the present invention, the susceptibility of tumor cells to a test substance can be determined.

FIG. 1 is a block diagram showing an example of the configuration of the determination device of the first embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the determination device of the first embodiment. FIG. 3 is a flowchart showing an example of the determination method of the first embodiment. FIG. 4 is a schematic diagram showing the distribution of the second harmonic signal in the tumor cells in the first embodiment. FIG. 5 is a block diagram showing an example of the configuration of the learning device of the second embodiment. FIG. 6 is a flowchart showing an example of the learning method of the second embodiment. FIG. 7 is a schematic diagram of the configuration of the optical system of the CARS microscope used in Example 1. FIG. 8 is a photograph showing the SHG image in Example 1.

In the present invention, "cell" means, for example, an isolated cell, a cell mass, tissue, or organ composed of cells. The cell may be, for example, a cultured cell or a cell isolated from a living body. Further, the cell mass, tissue or organ may be, for example, a cell mass, cell sheet, tissue or organ prepared from the cell, or a cell mass, tissue or organ isolated from a living body.

Hereinafter, the present invention will be described in detail with reference to the drawings. However, the present invention is not limited to the following description. In the following FIGS. 1 to 8, the same parts may be designated by the same reference numerals and the description thereof may be omitted. Further, in the drawings, for convenience of explanation, the structure of each part may be shown in a simplified manner as appropriate, and the dimensional ratio of each part may be shown schematically, which is different from the actual one. Further, unless otherwise specified, the respective embodiments can be referred to each other.

<Judgment method and judgment device>
As described above, the method for determining susceptibility to a test substance of the present invention is to obtain a second harmonic (2nd harmonic) obtained by using a coherent anti-Stoke Raman scattering (CARS) microscope for tumor cells in contact with the test substance. It includes an acquisition step of acquiring SHG) and a determination step of determining the susceptibility of the tumor cells to the test substance based on the SHG. In addition, the device for determining susceptibility to a test substance of the present invention uses a coherent anti-Stoke Raman scattering (CARS) microscope to obtain a second harmonic (SHG) of tumor cells in contact with the test substance. The acquisition means to be acquired and the determination means for determining the susceptibility of the tumor cells to the test substance based on the SHG are included. The determination method and determination apparatus of the present invention are characterized in that the susceptibility of the tumor cells to the test substance is determined based on the SHG obtained from the tumor cells brought into contact with the test substance, and other configurations and other configurations and The conditions are not limited.

As a result of diligent research, the present inventors have found that the signal light obtained by using a CARS microscope, specifically, the second harmonic, correlates with the susceptibility of tumor cells to a test substance, and the present invention was developed. It came to be established. Therefore, according to the present invention, the susceptibility of a tumor cell to a test substance can be determined based on the signal light obtained for the test cell using a CAR microscope.

(Embodiment 1)
FIG. 1 shows a block diagram of the determination device according to the present embodiment. As shown in FIG. 1, the determination device 10 of the present embodiment includes the acquisition means 111 and the determination means 112. As shown in FIG. 1, the acquisition means 111 and the determination means 112 may be incorporated in the data processing means (data processing device) 11 which is hardware, or may be software or hardware in which the software is incorporated. The data processing means 11 may include a CPU or the like. Further, the data processing means 11 may include, for example, a ROM, a RAM, or the like described later.

Next, FIG. 2 illustrates a block diagram of the hardware configuration of the determination device 10. The determination device 10 includes, for example, a CPU (central processing unit) 201, a memory 202, a bus 203, a storage device 204, an input device 206, a display 207, a communication device 208, and the like. Each part of the determination device 10 is connected via the bus 203 by each interface (I / F). The hardware configuration of the determination device 10 can also be adopted, for example, as the hardware configuration in the learning device described later.

The CPU 201 operates in cooperation with other configurations by, for example, a controller (system controller, I / O controller, etc.) and takes charge of overall control of the determination device 10. In the determination device 10, for example, the program 205 of the present invention and other programs are executed by the CPU 201, and various information is read and written. Specifically, for example, the CPU 201 functions as the acquisition means 111 and the determination means 112. The determination device 10 includes a CPU as an arithmetic unit, but may include other arithmetic units such as a GPU (Graphics Processing Unit) and an APU (Accelerated Processing Unit), or may include a CPU and a combination thereof. good. The CPU 201 functions as, for example, each means other than the storage means in the second embodiment described later.

The memory 202 includes, for example, a main memory. The main memory is also referred to as a main storage device. When the CPU 201 performs processing, the memory 202 reads, for example, various operation programs such as the program 205 of the present invention stored in the storage device 204 (auxiliary storage device) described later. Then, the CPU 201 reads data from the memory 202, decodes it, and executes the program. The main memory is, for example, a RAM (random access memory). The memory 202 further includes, for example, a ROM (read-only memory).

The bus 203 can also be connected to, for example, an external device. Examples of the external device include an external storage device (external database, etc.), a printer, and the like. The determination device 10 can be connected to the communication network by, for example, the communication device 208 connected to the bus 203, and can also be connected to the external device via the communication network. Further, the determination device 10 can also be connected to a terminal or the like via the communication device 208 and the communication network.

The storage device 204 is also referred to as a so-called auxiliary storage device with respect to the main memory (main storage device), for example. As described above, the storage device 204 stores an operation program including the program 205 of the present invention. The storage device 204 includes, for example, a storage medium and a drive for reading and writing to the storage medium. The storage medium is not particularly limited, and may be, for example, an internal type or an external type, and may be an HD (hard disk), FD (floppy (registered trademark) disk), CD-ROM, CD-R, CD-RW, MO, etc. Examples thereof include a DVD, a flash memory, a memory card, and the like, and the drive is not particularly limited. The storage device 204 may be, for example, a hard disk drive (HDD) in which the storage medium and the drive are integrated.

The determination device 10 further includes, for example, an input device 206 and a display 207. The input device 206 includes, for example, a pointing device such as a touch panel, a track pad, a mouse; a keyboard; an imaging means such as a camera or a scanner; a card reader such as an IC card reader or a magnetic card reader; an audio input means such as a microphone; Be done. Examples of the display 207 include display devices such as LED displays and liquid crystal displays. In the first embodiment, the input device 206 and the display 207 are configured separately, but the input device 206 and the display 207 may be integrally configured like a touch panel display.

Next, an example of the processing of the determination device 10 of the present embodiment will be described with reference to the flowchart of FIG. 3 by taking as an example the case where the tumor cells are obtained with signal light using a CARS microscope.

Prior to the processing of the determination device 10, first, signal light is acquired from the tumor cells that have been brought into contact with the test substance using a CARS microscope. The contact between the test substance and the tumor cells may be , for example, in vitro or in vivo . When the contact is carried out in vitro , the contact can be carried out, for example, by culturing in the coexistence of the test substance and the tumor cells. The conditions in the culture are not particularly limited and can be appropriately set according to the type of the tumor cells. As a specific example, the culture time is, for example, 1 to 96 hours and 12 to 48 hours. The culture temperature is, for example, 25-40 ° C and 35-38 ° C. The culture is carried out, for example, in a moist environment. When the contact is carried out in vivo , the contact can be carried out, for example, by administering the test substance to a subject having the tumor cells. Examples of the subject include humans and non-human animals. Examples of the non-human animal include primates such as monkeys, gorillas, chimpanzees and marmosets, mice, rats, dogs, rabbits, sheep, horses and guinea pigs. The dose, administration route, administration condition, etc. of the test substance are not particularly limited, and can be appropriately determined depending on the solubility of the test substance in a solvent, the absorbability into the body, and the like. Then, after the contact, the tumor cells are collected and subjected to observation with a CARS microscope.

The tumor cell may be, for example, a tumor cell isolated from a living body, that is, a primary cell or a subculture cell thereof, an acclimatized cultured cell, or a cell tumorigenized by a virus, a mutagen, or the like. However, isolated tumor cells or passages thereof are preferred. Further, the tumor cell may be composed of one cell or a plurality of cells. In the latter case, the tumor cell may be, for example, a tissue, organ or organ containing the tumor cell. The origin of the tumor cells is not particularly limited. As a specific example, the tumor cells include, for example, lung cancer, breast cancer, colon cancer, liver cancer, pancreatic cancer, biliary tract cancer, esophageal cancer, gastric cancer, ovarian cancer, cervical cancer, brain tumor, and hematological malignancies. , Tumor cells derived from mesotheloma, skin cancer and the like. The tumor cell may be, for example, a tumor cell sensitive to the test substance, a tumor cell resistant to the test substance, or a tumor cell whose sensitivity to the test substance is unknown. ..

Examples of the test substance include low molecular weight compounds, peptides, proteins, nucleic acids and the like. The test substance may be used alone or in combination of two or more. The test substance may be a substance known to have an antitumor effect or suppress metastasis of a tumor (so-called anticancer agent or metastasis inhibitor), and is known not to suppress an antitumor effect or metastasis of a tumor. It may be a substance having an antitumor effect or a substance whose antitumor effect or suppressing tumor metastasis is unknown. When the test substance is a substance known to have an antitumor effect or suppress metastasis of a tumor, the determination device of the present invention is, for example, a determination device or a test device for determining susceptibility to an anticancer agent or a metastasis inhibitor of cancer. It can be said. Further, the determination method of the present invention can also be, for example, a determination method or a test method for determining the susceptibility of a cancer to an anticancer agent or a metastasis inhibitor.

Then, the tumor cells that have been brought into contact with the test substance in this way are observed with a CARS microscope, and signal light is acquired. Acquisition of signal light by the CARS microscope is performed on all or a part of the tumor cells. In the latter case, it is preferable to acquire the signal light by the CARS microscope, for example, in the central portion of the tumor cell, to acquire the signal light having a cross section including the direction perpendicular to the arrangement surface of the tumor cell. The number of tumor cells used for the observation may be one or a plurality. In the latter case, the acquisition of the signal light by the CARS microscope is performed on some or all of the cells thereof. The CARS microscope is a microscope utilizing coherent anti-Stoke Raman scattering, and its configuration is not particularly limited, and for example, the configuration of Examples described later can be referred to. The CARS microscope includes a light irradiation means for CARS spectroscopy, and the light irradiation means irradiates tumor cells with mixed light of ultra-broadband light and excitation light. Then, in the CARS microscope, CARS light (signal light) is separated from the emitted light emitted from the tumor cell by a diffraction grating or the like. Then, information such as the signal intensity and spatial position of the CARS light is acquired. In the present invention, as the signal light, only the second harmonic (SHG) may be acquired, or other signal lights such as the third harmonic (THG) and two-photon excitation fluorescence may be acquired. .. The wavelength of the ultra-wideband light is, for example, 400 to 2400 nm. The wavelength of the excitation light is, for example, 750 to 1100 nm and 750 to 1064 nm.

Next, the process by the determination device 10 is started. First, the acquisition means 111 of the determination device 10 acquires information on the signal light, more specifically, the signal light acquired by the CARS microscope (S1, acquisition step). The signal light acquired in the acquisition step includes the signal light used in the determination step described later, and as a specific example, it is preferable to include the signal light of the second harmonic (SHG). The wave number of the signal light of the SHG is λ / 2 when the wavelength of the incident laser is λ.

Next, the determination means 112 determines the susceptibility of the tumor cells based on the signal light, specifically, the signal light of SHG (S2, determination step). In the S2 step, it may be determined that the tumor cells are sensitive to the test substance, or may be determined to be resistant to the test substance. Further, in the S2 step, it may be determined whether or not the tumor cells are sensitive to the test substance. In the signal light, each wave number (Raman shift / cm ^-1 ) differs from the substance in the tumor cell from which the signal is derived. Further, when the state of the tumor cell is different, the function and metabolism of the cell in the different state are also different, so that it is presumed that the type of the substance contained in the tumor cell, the content rate of the substance, the localization of the substance, and the like are also different. Therefore, in the present invention, the sensitivity of the tumor cells is determined based on the signal light by utilizing the fact that the difference in the state of the tumor cells occurs, for example, as the difference in the signal light. Hereinafter, the case where the tumor cell is a lung cancer cell will be described as an example, but the present invention is not limited to this, and can be used for estimation of other tumor cells.

First, in the S2 step, a method of determining based on the position (localization) of the SHG signal in the SHG image reconstructed from the SHG signal will be described. As shown in FIG. 4A, in the lung cancer cell C not in contact with the test substance, in the SHG image reconstructed from the SHG signal, the signal S of the SHG is bipolar in the Z-axis direction of the lung cancer cell C. That is, it is localized on the upper end side and the lower end side. Then, when the lung cancer cells C are the lung cancer cells C after contact with the test substance and the lung cancer cells C are sensitive to the test substance, as shown in FIG. 4 (B), the signal S of SHG is shown in the SHG image. Is localized around the equator in the Z-axis direction of lung cancer cells C, that is, in the central part. On the other hand, when the lung cancer cells C are the lung cancer cells C after contact with the test substance and the lung cancer cells C show resistance to the test substance, as shown in FIG. 4 (A), they have not contacted the test substance. In the SHG image, the signal S of SHG is localized at both poles in the Z-axis direction of the lung cancer cell C, that is, the upper end side and the lower end side. Therefore, in the S2 step, it is possible to determine whether or not the lung cancer cell C is susceptible based on the position of the SHG signal light, that is, the position of the SHG signal in the SHG image reconstructed from the SHG signal. The localization is, for example, 50% or more, 60% or more, 70% or more, 80% or more, 90% or more, 95% or more, 96% or more, 97% or more, 98% or more, 99 of all SHG signals. It means that% or more SHG signals are present at a predetermined position. The upper end side means a region between the upper end and 30%, 25%, 20%, 15%, and 10% of the length in the Z-axis direction from the upper end in the Z-axis direction of the tumor cell. The lower end side is a region between the lower end and 30%, 25%, 20%, 15%, and 10% of the length of the tumor cell in the Z-axis direction from the lower end in the Z-axis direction of the tumor cell. means. The central portion means, for example, a region other than the upper end side and the lower end side, and as a specific example, a position in the Z-axis direction of the tumor cell, for example, a position 50% in length from the lower end in the Z-axis direction of the tumor cell. It means a region in the range of ± 5%, ± 10%, + 15%, ± 20%, ± 25%, ± 30% of the length of the tumor cell in the Z-axis direction with reference to.

Next, in the S2 step, a method of determining based on the shape of the SHG signal in the SHG image reconstructed from the SHG signal will be described. As shown in FIG. 4 (A), in the lung cancer cell C not in contact with the test substance, the signal S of SHG forms a smooth arc in the SHG image. Then, when the lung cancer cells C are the lung cancer cells C after contact with the test substance and the lung cancer cells C are sensitive to the test substance, as shown in FIG. 4 (B), the signal S of SHG is shown in the SHG image. Form grains with blurred boundaries. On the other hand, when the lung cancer cells C have come into contact with the test substance and the lung cancer cells C show resistance to the test substance, as shown in FIG. 4A, the lung cancer cells have not come into contact with the test substance. Similar to Lung Cancer Cell C, in the SHG image, the SHG signal forms a smooth arc. Therefore, in S2, it can be determined whether or not the lung cancer cells are susceptible based on the shape of the SHG signal light, that is, the shape of the SHG signal in the SHG image reconstructed from the SHG signal.

Further, as described above, there is a difference in the shape of the signal of the SHG depending on the presence or absence of sensitivity of the lung cancer cell to the test substance, and in particular, the clarity of the extension of the shape is different. Therefore, in the S2 step, the sensitivity of the lung cancer cells to the test substance can be determined based on the dispersion value of the signal light of SHG, that is, the dispersion value of the signal intensity of the signal light of SHG. Specifically, in lung cancer cells sensitive to the test substance, for example, the boundary of the SHG signal is blurred and the distribution of the signal intensity is relatively wide, whereas the resistance to the test substance is resistant. In lung cancer cells, the boundaries of SHG signals are clear and the distribution of signal intensities is relatively narrow. Therefore, in the S2 step, the dispersion value of the SHG signal light of the tumor cell, that is, the dispersion value of the signal intensity of the SHG signal light is compared with the reference value, and the dispersion value of the SHG signal is the reference value. If it is significantly larger, the tumor cells can be determined to be sensitive to the test substance. On the other hand, in the S2 step, when the dispersion value of the SHG signal light of the tumor cell is compared with the reference value, the dispersion value of the SHG signal is equal to (no significant difference) or significantly smaller than the reference value. , The tumor cells can be determined to be resistant to the test substance. The reference value may be, for example, a dispersion value of SHG signal light in lung cancer cells not in contact with the test substance, a dispersion value of SHG signal light in lung cancer cells sensitive to the test substance, and the above-mentioned. It may be a numerical value between the two based on the dispersion value of the signal light of SHG in the lung cancer cells resistant to the test substance.

In the S2 step, for example, a trained model generated by machine learning may be used. The trained model is, for example, a trained model that outputs the determination result of the susceptibility of the tumor to the test substance from the SHG using the pair of the SHG described later and the susceptibility of the tumor cell to the test substance as teacher data. Can be given.

In this way, in the S2 step, it is possible to determine whether or not the tumor cells are sensitive to the test substance. In the first embodiment, in the S2 step, an example of using one determination method has been described, but a plurality of determination methods may be combined. In this case, in the S2 step, when the tumor cells are determined to be sensitive by any one of the determination methods, the tumor cells may be determined to be sensitive to the test substance, or may be determined to be sensitive by a plurality of determination methods. If so, the tumor cells may be determined to be sensitive to the test substance.

In the first embodiment, the case where SHG is used as the signal light has been described as an example, but other signal light may be used.

In the first embodiment, tumor cells have been described as an example of test cells for determining susceptibility to a test substance, but the present invention is not limited to this, and cells other than tumor cells, for example, derived from normal tissues. You may use cells or the like.

In the first embodiment, the case where the determination is made using the hardware resource has been described as an example, but the present invention is not limited to this, and the hardware resource may not be used.

<Screening method>
As described above, the method for screening an anticancer drug of the present invention comprises a determination step of determining the susceptibility of a tumor cell in contact with a test substance to the test substance, and a determination step of determining the susceptibility of the tumor cell. The determination step includes a step of selecting a test substance as a candidate substance for an anticancer agent, and the determination step is carried out by the determination method of the present invention. The screening method of the present invention is characterized in that the determination step is carried out by the determination method of the present invention, and other steps and conditions are not particularly limited. According to the screening method of the present invention, an anticancer drug can be screened. As the screening method of the present invention, the description of the determination method and the determination device of the present invention can be incorporated.

The anticancer agent means, for example, an agent that induces stopping or suppressing tumor development, stopping or suppressing tumor growth, stopping or suppressing tumor progression, stopping or suppressing tumor metastasis, or inducing tumor shrinkage. It may be used in any sense.

<Manufacturing method of candidate substances for anticancer drugs>
As described above, the method for producing a candidate substance for an anticancer agent of the present invention includes a selection step of selecting a candidate substance for an anticancer agent from a test substance, and the selection step is carried out by the screening method of the present invention. The production method of the present invention is characterized in that the selection step is carried out by the screening method of the present invention, and other steps and conditions are not particularly limited. According to the production method of the present invention, a candidate substance for an anticancer agent can be produced. As the screening method of the present invention, the description of the determination method, the determination device, and the screening method of the present invention can be incorporated.

<Manufacturing method and equipment for trained models>
As described above, the method for producing a trained model used for determining the susceptibility of tumor cells of the present invention was obtained for tumor cells contacted with a test substance using a coherent anti-Stokes Slaman scattering (CARS) microscope. Using the combination of the acquisition step of acquiring the second harmonic (SHG) and the SHG and the susceptibility of the tumor cell to the test substance as training data, the determination result of the susceptibility of the tumor cell to the test substance from the SHG is obtained. Includes a training process to generate a trained model to output. In addition, the device for manufacturing the trained model used for determining the susceptibility of the tumor cells of the present invention is the second harmonic obtained by using a coherent anti-Stokes slamman scattering (CARS) microscope for the tumor cells in contact with the test substance. Learning to output the determination result of the susceptibility of the tumor cell to the test substance from the SHG using the pair of the acquisition means for acquiring the wave (SHG), the SHG, and the susceptibility of the tumor cell to the test substance as teacher data. Includes learning means to generate finished models. The learning method and learning apparatus of the present invention use the pair of the SHG acquired by the CARS microscope and the susceptibility of the tumor cells to the test substance as teacher data, and determine the susceptibility of the tumor cells to the test substance from the SHG. It is characterized by generating a trained model that outputs, and other configurations and conditions are not particularly limited. According to the learning method and the learning device of the present invention, it is possible to manufacture a learned model that can be used for the determination method and the determination device of the present invention. The learning method and the learning device of the present invention can be referred to the description of the determination method, the determination device, and the screening method of the present invention.

(Embodiment 2)
FIG. 5 shows a block diagram of the learning device according to the present embodiment. As shown in FIG. 5, the learning device 20 of the present embodiment includes the acquisition means 111 and the learning means 113. As shown in FIG. 5, the acquisition means 111 and the learning means 113 may be incorporated in the data processing means (data processing device) 11 which is hardware, or may be software or hardware in which the software is incorporated. The data processing means 11 may include a CPU or the like. Further, the data processing means 11 may include, for example, the above-mentioned ROM, RAM, and the like. The acquisition means 111 is the same as the acquisition means 111 in the determination device 10 of the first embodiment, and the description thereof can be incorporated.

Next, an example of the processing in the learning device of FIG. 5 will be described with reference to the flowchart of FIG.

First, similarly to S1 of the determination method of the first embodiment, the acquisition means 111 acquires the signal light acquired by using the CARS microscope for the tumor cells in contact with the test substance. The number of the tumor cells is not particularly limited and can be any number. When there are a plurality of the tumor cells, the origin of each tumor cell may be the same or different. In the latter case, some tumor cells are preferably of the same origin. As a specific example, when generating a learned model capable of determining whether it is a lung cancer cell, a breast cancer cell, or a colon cancer cell, it is preferable to use a lung cancer cell, a breast cancer cell, or a colon cancer cell as the tumor cell. Moreover, it is preferable to use a plurality of each tumor cell.

Next, the learning means 113 uses the set of the signal light (for example, SHG) and the susceptibility of the tumor cell to the test substance as training data, and determines the susceptibility of the tumor cell to the test substance from the signal light. Generates a trained model that outputs (S3, training process). Specifically, for each test cell, the signal light obtained in the S1 step is associated with the presence or absence of sensitivity of the tumor cell. The associated signal light may be the entire spectrum of the signal light obtained in the S1 step, a specific signal light, or a calculated value obtained from the specific signal light. When associated with the specific signal light, the specific signal light may be, for example, an SHG signal light. When associating the specific signal light, the learning method of the present embodiment detects the specific signal light in the obtained signal by the detection means, for example, after the S1 step. The detection means may, for example, detect the signal intensity of a specific signal light, or determine the shape and / or position (localization) of the signal light in the signal image obtained by reconstructing the specific signal light. It may be detected. The position is, for example, the localization of the signal light of SHG in the Z-axis direction of the tumor cell. Further, when associating with the calculated value obtained from the specific signal light, the learning method of the present embodiment is, for example, a dispersion value of the specific signal light, that is, a dispersion value of the signal intensity of the specific signal light by the calculation means. May be calculated.

The machine learning method used to generate the trained model is not particularly limited, and for example, a learning technique used for classification can be used. Specific examples of the machine learning method include a support vector machine, an extreme learning machine, and feature learning. In the present embodiment, the machine learning uses supervised learning, but semi-supervised learning may be used. The number of the teacher data is plural, and the upper limit thereof is not particularly limited.

In this way, the trained model can be generated in the S3 step.

<Selection method>
As described above, the method for selecting cells for determining susceptibility of a test substance of the present invention is to acquire a second harmonic (SHG) of a test tumor cell using a coherent anti-Stokes Slaman scattering (CARS) microscope. The step includes a selection step of selecting a candidate tumor cell to be used for the susceptibility test of the test substance from the test tumor cells based on the SHG. The selection method of the present invention is characterized in that the candidate tumor cells are selected based on SHG obtained using a CARS microscope, and other configurations and conditions are not limited. According to the selection method of the present invention, tumor cells suitable for the determination method of the present invention can be selected. As the selection method of the present invention, the description of the determination method, determination device, screening method, learning method and learning device of the present invention can be incorporated.

As the acquisition step, the description of the acquisition step in the determination method of the present invention can be incorporated. The test tumor cell can be referred to, for example, the description of the tumor cell.

In the selection step, candidate tumor cells to be used for the susceptibility test of the test substance are selected from the test tumor cells based on the SHG. The selection step is, for example, the presence or absence of the SHG, the signal intensity of the SHG signal light, the shape of the SHG signal in the SHG image reconstructed from the SHG signal light, and / or the position (localization) of the SHG signal in the SHG image. Can be implemented based on. As a specific example, in the selection step, for example, when SHG is acquired in the test tumor cell, when the signal intensity of the signal light of SHG is a predetermined value or more, the shape of the SHG signal in the SHG image is a boundary. When is a clear arc and / or the position of the SHG signal in the SHG image is localized on the upper end side and / or the lower end side in the Z-axis direction of the candidate tumor cell, the test tumor cell. Is selected as the candidate tumor cell.

<Program>
The program of the present invention is a program capable of executing the determination method, the screening method, the manufacturing method, the learning method, or the selection method of the present invention on a computer. Alternatively, the program of this embodiment may be recorded on a computer-readable recording medium, for example. The recording medium is, for example, a non-transitory computer-readable storage medium. The recording medium is not particularly limited, and examples thereof include a random access memory (RAM), a read-only memory (ROM), a hard disk (HD), an optical disk, a floppy disk (registered trademark) disk (FD), and the like.

Next, examples of the present invention will be described. However, the present invention is not limited by the following examples. Commercially available reagents were used based on those protocols unless otherwise indicated.

[Example 1]
It was confirmed that the susceptibility of the tumor cells to the test substance could be determined based on the signal light obtained by the CARS microscope.

(1) CARS Microscope As the CARS microscope used in Example 1, a multiplex CARS microspectroscopy device was used. FIG. 7 shows a schematic diagram of the configuration of the optical system of the CARS microscope used in Example 1.

As a light source, a cw Q-switched microchip Nd: YAG laser (A) having an oscillation wavelength of 1064 nm, a pulse width of 800 ps, and a repetition frequency of 33 kHz was used. The pulse width is sub-nanoseconds, and the line width is about ^{1 cm -1 or less.} This output was divided into two, one was introduced into the PCF with a pulsed laser with a central wavelength of 1064 nm, which is the fundamental wave as _{ω 1} light, and the other was introduced into the PCF to generate super-continuum light as _{ω 2 light.} ω ₁ Light is a plano-convex lens (B) of f = 400.0 mm (AC254-400-C f = 400.0 mm, φ1 "Achromatic Doublet, ARC: 1050-1700 nm; Thorlabs) for the laser light emitted from the light source body. Collimated, ω ₂ light emits super-continuum light with a wide-band wavelength component emitted from the PCF with a non-axis mirror (Protected Silver Reflective Collimator, 450 nm-20 um, φ4 mm, FC / APC; Thorlabs. ) Collimated and propagated by introducing it into (C).

In addition, ω ₁ light sandwiched a Variable Neutral Density Filter (VND Filter) (D) and a 1064 nm half-wave plate (S333-1064-2; manufactured by Suruga Seiki Co., Ltd.) (E) in the middle of propagation. The VND Filter was used to _{adjust the amount of ω 1} light incident on the sample, and the 1064 nm half-wave plate was used to confirm the polarization dependence of the SHG active molecule described later.

Furthermore, the ω ₁ light contains a weak component on the short wavelength side in addition to the central wavelength of 1064 nm, and in order to efficiently cut the extra spectral component contained in _{the ω 1 light other than the CARS light to be detected.} A 1064 nm narrow Band Pass Filter (1064.1-1 OD7 Ultra Narrow Bandpass; Alluxa) (F) was used. As the bandpass filter, an ultra-narrow bandpass filter that transmits only spectral components having a center wavelength of 1064.1 nm and a half width of 1 nm was used.

ω ₂ light has a broad band that gently extends from the visible region to the near-infrared region by PCF. The wavelength range of _{ω 2} light required for the measurement of CARS light is from 1064 to 1650 nm with respect to the central wavelength of 1064 nm of ω _{1 light.} Therefore, two filters 1050 nm long Pass Filter (G) and an infrared transmission filter (IR80N; manufactured by Kenko Optical Co., Ltd.) (H) that cut the visible light component immediately after collimating _{the ω 2 light are used to make the ω 2} light near red. Only the spectral components spreading in the outer region were sufficiently transmitted. Then, _{after the combined wave of ω 1} light and ω ₂ light, the two lights were propagated to the microscope.

As the microscope, an inverted microscope (eclipse Ti-U, manufactured by Nikon Corporation) custom-made was used. Non-linear optics such as CARS and SHG by _{ω 1} light and ω ₂ light incident on the objective lens (Water immersion, Plan, × 60, 1.27NA; manufactured by Nikon) (J) from the inverted side of the microscope and focused on the sample. The phenomenon occurs. Since it is focused by the objective lens, these nonlinear optical phenomena occur efficiently in the forward direction due to the phase matching condition. The signal light generated at the focal point was focused and collimated by an objective lens (Dry, S Plan Fluor, × 40, 0.60NA; manufactured by Nikon Corporation) (K) on the upright side of the microscope.

The average power measured with a power meter at the position focused on the sample surface by the inverted objective lens was 55 mW for _{ω 1} light and 20 mW for _{ω 2 light, respectively.} In the actual measurement, the sample signal intensity was adjusted by using the above-mentioned VND Filter for _{the high-power ω 1 light.}

The microscope is equipped with a halogen lamp, and an optical image of the sample can be taken with a CCD camera. Since ω ₁ light and ω ₂ light exist coaxially with the light of the halogen lamp in the microscope, the dichroic beam splitter (FF825-SDi01-25 × 36 × 2.0 single edge short path Dichroic beam splitter; opt (L) manufactured by Rhein Co., Ltd. and a dichroic mirror (TFMS-30C05-3 / 20 ultra-wideband multi-film planar mirror manufactured by Sigma Kouki Co., Ltd.) immediately after the upright objective lens were used.

The stage installed in the microscope used a step motor type MicroStage (Micro-Stage (2 axis); Mad City Labs) (N) controlled by a biaxial micro-positioning device. Furthermore, a piezo stage (Nano-LPQ; manufactured by Mad City Labs) (O) with an operating range of 75 μm × 75 μm × 50 μm is installed on the MicroStage, and in addition to a wide in-plane stroke in millimeters, it is even finer. It enables in-plane stage control of the stroke and scanning in the Z direction of the optical axis, that is, in the depth direction with respect to the sample. The MicroStage is capable of controlling a minimum step size of 95 nm and a maximum speed of 2 mm / sec with a highly accurate drive.

Next, the optical system on the detector side was as follows. The signal light collected by the upright objective lens of the microscope is reflected by the dichroic mirror immediately after, and then the dichroic beam splitter (FF685-Di02-25 × 36 685 nm single edge Dichroic beam splitter; Semrock) (P). ), The CARS light in the near infrared region was transmitted, and the light in the visible region was reflected.

For light in the visible region, the background derived from excitation light outside the visible region is blocked by a 633 nm short Pass Filter (Q), and then a spectroscope (Z-300 Series; manufactured by LUCIR) is used by a plano-convex lens (R) with f = 65 mm. ) (S). Control was performed by software (Ementool; manufactured by Zolix) on a PC to which the spectroscope was connected. In this example, the Grating Groove was set to 300 lines / mm, the Grating Blaze was set to 500 nm, and the center wavelength of the spectroscope was set to 410 nm. An electronically cooled CCD camera (iVac300; manufactured by Andor) (T) was used to detect SHG.

_{Light in the near-infrared region passes through a dichroic beam splitter and is ω 1} light and ω ₂ light by a 1064 nm notch filter (1064 Narrow notch filter; Iridian) (U) and a 1050 nm short Pass Filter (3RD1050SP; Omega) (V). Was blocked, and only CARS light was guided to the spectroscope.

After passing through a 1064 nm notch filter and a 1050 nm short pass filter, CARS light is separated by wavelength by a spectroscope (Acton Series LS785; Princeton Instruments) (X) with a plano-convex lens with f = 25 mm, and an electronically cooled CCD camera. (PIXIS 100BR; manufactured by Princeton Instruments) (Y) was detected. The PIXIS 100BR, iVac 316, and iVac 300 are controlled by software on the PC (LightField; Princeton Instruments, Andor SOLIS; Andor), respectively.

(2) Tumor cells Lung adenocarcinoma cells (PC-9) were used as tumor cells. The PC-9 is a lung cancer cell line known to be sensitive to gefitinib. The tumor cells were prepared by placing the preparation in a 24-weldish and culturing on the preparation. Then, gefitinib was added as a test substance, and the cells were cultured for 48 hours.

(3) Measurement A preparation containing each tumor cell after culturing was mounted on a slide glass, and signal light was obtained with the CARS microscope of Example 1 (1). Then, the obtained signal light of SHG was reconstructed to prepare an SHG image. Controls were performed in the same manner except that gefitinib was not added. These results are shown in FIG.

FIG. 8 is a photograph showing an SHG image. In FIG. 8, (A) shows the result of the control without gefitinib, and (B) shows the result of the sample with gefitinib added. As shown in FIG. 8A, in the state where gefitinib was not added, as shown by the arrow, the SHG signal was localized on the upper end side and the lower end side of the PC-9 in the SHG image. On the other hand, as shown in FIG. 8B, in the state of adding gefitinib, it was localized around the equator, that is, in the central part in the SHG image. From these facts, it was found that the susceptibility of tumor cells can be determined by using the signal light obtained by the CARS microscope.

Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above embodiments and examples. Various changes that can be understood by those skilled in the art can be made to the structure and details of the present invention within the scope of the present invention.

This application claims priority on the basis of Japanese application Japanese Patent Application No. 2019-021932 filed on February 8, 2019, and incorporates all of its disclosures herein.

<Additional Notes>
Some or all of the above embodiments and examples may be described as, but not limited to, the following appendixes.
(Appendix 1)
The acquisition step of acquiring the second harmonic (SHG) acquired by using a coherent anti-Stoke Raman scattering (CARS) microscope for the tumor cells contacted with the test substance, and the acquisition process.
A method for determining susceptibility to a test substance, which comprises a determination step for determining the susceptibility of the tumor cells to the test substance based on the SHG.
(Appendix 2)
The determination method according to Appendix 1, wherein in the determination step, the susceptibility of the tumor cell to the test substance is determined based on at least one of the shape and position of the signal light of the SHG.
(Appendix 3)
The determination method according to Appendix 1 or 2, wherein in the determination step, the sensitivity of the tumor cell to the test substance is determined based on the dispersion value of the signal light of the SHG.
(Appendix 4)
In the determination step, the dispersion value of the signal light of the SHG is compared with the reference value, and when the dispersion value of the signal light of the SHG is larger than the reference value, the tumor cell is sensitive to the test substance. The determination method according to Appendix 3, wherein the determination is made.
(Appendix 5)
The determination method according to Appendix 4, wherein the reference value is a dispersion value of SHG signal light in tumor cells that have not come into contact with the test substance.
(Appendix 6)
In the determination step, the susceptibility of the tumor cells to the test substance is determined by using a learned model generated by machine learning that outputs the determination result of the susceptibility of the tumor cells to the test substance based on the SHG. Judgment, the determination method according to any one of Supplementary Provisions 1 to 5.
(Appendix 7)
The determination method according to any one of Supplementary note 1 to 6, wherein in the determination step, the sensitivity of the tumor cell to the test substance is determined based on the localization of the signal light of SHG in the Z-axis direction of the tumor cell.
(Appendix 8)
In the determination step, when the signal light of SHG is localized in the central portion in the Z-axis direction of the tumor cell, it is determined that the tumor cell is sensitive to the test substance, any one of Supplementary note 1 to 7. Judgment method described in.
(Appendix 9)
The determination method according to any one of Supplementary note 1 to 8, wherein the test substance is at least one selected from the group consisting of low molecular weight compounds, peptides, proteins and nucleic acids.
(Appendix 10)
The determination method according to any one of Supplementary note 1 to 9, wherein the tumor cell is a lung cancer cell.
(Appendix 11)
An acquisition means for acquiring a second harmonic (SHG) acquired using a coherent anti-Stoke Raman scattering (CARS) microscope for a tumor cell contacted with a test substance, and an acquisition means.
A device for determining susceptibility to a test substance, which comprises a determination means for determining the susceptibility of the tumor cells to the test substance based on the SHG.
(Appendix 12)
The determination device according to Appendix 11, wherein in the determination means, the susceptibility of the tumor cell to the test substance is determined based on at least one of the shape and position of the signal light of the SHG.
(Appendix 13)
The determination device according to Appendix 11 or 12, wherein in the determination means, the sensitivity of the tumor cell to the test substance is determined based on the dispersion value of the signal light of the SHG.
(Appendix 14)
In the determination means, the dispersion value of the signal light of the SHG is compared with the reference value, and when the dispersion value of the signal light of the SHG is larger than the reference value, the tumor cell is sensitive to the test substance. The determination device according to Appendix 13, wherein the determination device is determined to be.
(Appendix 15)
The determination device according to Appendix 14, wherein the reference value is a dispersion value of SHG signal light in tumor cells that have not come into contact with the test substance.
(Appendix 16)
In the determination means, the susceptibility of the tumor cells to the test substance is determined by using a learned model generated by machine learning that outputs the determination result of the susceptibility of the tumor cells to the test substance based on the SHG. The determination device according to any one of Supplementary note 11 to 15, which is determined.
(Appendix 17)
The determination device according to any one of Supplementary note 11 to 16, wherein in the determination means, the sensitivity of the tumor cell to the test substance is determined based on the localization of the signal light of SHG in the Z-axis direction of the tumor cell. ..
(Appendix 18)
In the determination means, when the signal light of SHG is localized in the central portion of the tumor cell in the Z-axis direction, the tumor cell is determined to be sensitive to the test substance. Judgment device described in Crab.
(Appendix 19)
The determination device according to any one of Supplementary note 11 to 18, wherein the test substance is at least one selected from the group consisting of low molecular weight compounds, peptides, proteins and nucleic acids.
(Appendix 20)
The determination device according to any one of Supplementary note 11 to 19, wherein the tumor cell is a lung cancer cell.
(Appendix 21)
A determination step for determining the susceptibility of a tumor cell in contact with a test substance to the test substance, and
The step of selecting a test substance determined to be sensitive to the tumor cells as a candidate substance for an anticancer drug is included.
The determination step is a method for screening an anticancer drug, which is carried out by the determination method according to any one of Supplementary note 1 to 10.
(Appendix 22)
21. The screening method according to Appendix 21, wherein the test substance is at least one selected from the group consisting of low molecular weight compounds, peptides, proteins and nucleic acids.
(Appendix 23)
Including a selection process for selecting candidate substances for anticancer drugs from test substances, including
The selection step is a method for producing a candidate substance for an anticancer agent, which is carried out by the screening method according to Appendix 21 or 22.
(Appendix 24)
The acquisition step of acquiring the second harmonic (SHG) acquired by using a coherent anti-Stoke Raman scattering (CARS) microscope for the tumor cells contacted with the test substance, and the acquisition process.
It includes a learning step of generating a learned model that outputs a determination result of the susceptibility of a tumor cell to a test substance from the SHG using a pair of the SHG and the susceptibility of the tumor cell to the test substance as teacher data. A method for producing a trained model used to determine the susceptibility of tumor cells.
(Appendix 25)
A signal light detection step of detecting at least one of the shape and position of the signal light of the SHG from the SHG is included.
The manufacturing method according to Appendix 24, wherein in the learning step, the pair of at least one of the shape and position of the signal light of the SHG and the sensitivity of the tumor cell to the test substance is used as teacher data.
(Appendix 26)
A calculation step of calculating the dispersion value of the signal light of the SHG from the SHG is included.
The production method according to Supplementary note 24 or 25, wherein in the learning step, the pair of the dispersion value of the signal light of the SHG and the sensitivity of the tumor cell to the test substance is used as the teacher data.
(Appendix 27)
A localization detection step of detecting the localization of the signal light of the SHG in the Z-axis direction of the tumor cell from the SHG is included.
The description in any of Supplementary note 24 to 26, wherein in the learning step, the pair of the localization of the signal light of SHG in the Z-axis direction of the tumor cell and the sensitivity of the tumor cell to the test substance is used as the teacher data. Production method.
(Appendix 28)
An acquisition means for acquiring a second harmonic (SHG) acquired using a coherent anti-Stoke Raman scattering (CARS) microscope for a tumor cell contacted with a test substance, and an acquisition means.
It includes a learning means for generating a learned model that outputs a determination result of the susceptibility of a tumor cell to a test substance from the SHG using a pair of the SHG and the susceptibility of the tumor cell to the test substance as teacher data. A trained model manufacturing device used to determine the susceptibility of tumor cells.
(Appendix 29)
A signal light detecting means for detecting at least one of the shape and position of the signal light of the SHG from the SHG is included.
The manufacturing apparatus according to Appendix 28, wherein in the learning means, a pair of at least one of the shape and position of the signal light of the SHG and the susceptibility of the tumor cell to a test substance is used as teacher data.
(Appendix 30)
A calculation means for calculating the dispersion value of the signal light of the SHG from the SHG is included.
The manufacturing apparatus according to Supplementary note 28 or 29, wherein in the learning means, the pair of the dispersion value of the signal light of the SHG and the sensitivity of the tumor cell to the test substance is used as the teacher data.
(Appendix 31)
A localization detecting means for detecting the localization of the signal light of the SHG in the Z-axis direction of the tumor cell from the SHG is included.
The method according to any one of Supplementary note 28 to 30, wherein in the learning means, the pair of the localization of the signal light of SHG in the Z-axis direction of the tumor cell and the sensitivity of the tumor cell to the test substance is used as teacher data. manufacturing device.
(Appendix 32)
Acquisition processing to acquire second harmonic generation (SHG) under a coherent anti-Stoke Raman scattering (CARS) microscope for tumor cells in contact with the test substance, and
Using the pair of the SHG and the susceptibility of the tumor cells to the test substance as teacher data, a learning process for generating a trained model that outputs the determination result of the susceptibility of the tumor to the test substance from the SHG is performed on a computer. A program that can be run on.
(Appendix 33)
Acquisition processing to acquire the second harmonic (SHG) acquired using a coherent anti-Stoke Raman scattering (CARS) microscope of tumor cells in contact with the test substance, and
Using the pair of the SHG and the susceptibility of the tumor cells to the test substance as training data, a computer performs a learning process to generate a trained model that outputs the determination result of the susceptibility of the tumor cells to the test substance from the SHG. A program that can be run on.
(Appendix 34)
The acquisition process for acquiring the second harmonic (SHG) of the tumor cells to be examined using a coherent anti-Stoke Raman scattering (CARS) microscope.
A method for selecting cells for determining susceptibility to a test substance, which comprises a selection step of selecting candidate tumor cells to be used for a susceptibility test of the test substance from the test tumor cells based on the SHG.
(Appendix 35)
The selection method according to Appendix 34, wherein in the selection step, the test tumor cell in which the SHG is detected is selected as the candidate tumor cell.
(Appendix 36)
A computer-readable recording medium recording the program according to Appendix 32 or 33.

As described above, according to the present invention, the susceptibility of tumor cells to a test substance can be determined. Therefore, the present invention is extremely useful in screening compounds and the like.

10 Judgment device 11 Data processing means 111 Acquisition means 112 Judgment means 113 Learning means 20 Learning device

Claims (35)

The acquisition step of acquiring the second harmonic (SHG) acquired by using a coherent anti-Stoke Raman scattering (CARS) microscope for the tumor cells contacted with the test substance, and the acquisition process.
A method for determining susceptibility to a test substance, which comprises a determination step for determining the susceptibility of the tumor cells to the test substance based on the SHG. The determination method according to claim 1, wherein in the determination step, the susceptibility of the tumor cell to the test substance is determined based on at least one of the shape and position of the signal light of the SHG. The determination method according to claim 1 or 2, wherein in the determination step, the sensitivity of the tumor cell to the test substance is determined based on the dispersion value of the signal light of the SHG. In the determination step, the dispersion value of the signal light of the SHG is compared with the reference value, and when the dispersion value of the signal light of the SHG is larger than the reference value, the tumor cell is sensitive to the test substance. 3. The determination method according to claim 3. The determination method according to claim 4, wherein the reference value is a dispersion value of SHG signal light in tumor cells that have not come into contact with the test substance. In the determination step, the susceptibility of the tumor cells to the test substance is determined by using a learned model generated by machine learning that outputs the determination result of the susceptibility of the tumor cells to the test substance based on the SHG. The determination method according to any one of claims 1 to 5, wherein the determination is made. The invention according to any one of claims 1 to 6, wherein in the determination step, the susceptibility of the tumor cell to the test substance is determined based on the localization of the signal light of SHG in the Z-axis direction of the tumor cell. Judgment method. Any of claims 1 to 7, wherein in the determination step, when the signal light of SHG is localized in the central portion of the tumor cell in the Z-axis direction, the tumor cell is determined to be sensitive to the test substance. The judgment method described in item 1. The determination method according to any one of claims 1 to 8, wherein the test substance is at least one selected from the group consisting of low molecular weight compounds, peptides, proteins and nucleic acids. The determination method according to any one of claims 1 to 9, wherein the tumor cell is a lung cancer cell. An acquisition means for acquiring a second harmonic (SHG) acquired using a coherent anti-Stoke Raman scattering (CARS) microscope for a tumor cell contacted with a test substance, and an acquisition means.
A device for determining susceptibility to a test substance, which comprises a determination means for determining the susceptibility of the tumor cells to the test substance based on the SHG. The determination device according to claim 11, wherein the determination means determines the susceptibility of the tumor cells to the test substance based on at least one of the shape and position of the signal light of the SHG. The determination device according to claim 11 or 12, wherein the determination means determines the susceptibility of the tumor cells to the test substance based on the dispersion value of the signal light of the SHG. In the determination means, the dispersion value of the signal light of the SHG is compared with the reference value, and when the dispersion value of the signal light of the SHG is larger than the reference value, the tumor cell is sensitive to the test substance. 13. The determination device according to claim 13. The determination device according to claim 14, wherein the reference value is a dispersion value of SHG signal light in tumor cells that have not come into contact with the test substance. In the determination means, the susceptibility of the tumor cells to the test substance is determined by using a learned model generated by machine learning that outputs the determination result of the susceptibility of the tumor cells to the test substance based on the SHG. The determination device according to any one of claims 11 to 15, which is determined. The determination means according to any one of claims 11 to 16, wherein the susceptibility of the tumor cell to the test substance is determined based on the localization of the signal light of SHG in the Z-axis direction of the tumor cell. Judgment device. According to claims 11 to 17, when the signal light of SHG is localized in the central portion of the tumor cell in the Z-axis direction, the determination means determines that the tumor cell is sensitive to the test substance. The determination device according to any one item. The determination device according to any one of claims 11 to 18, wherein the test substance is at least one selected from the group consisting of low molecular weight compounds, peptides, proteins and nucleic acids. The determination device according to any one of claims 11 to 19, wherein the tumor cell is a lung cancer cell. A determination step for determining the susceptibility of a tumor cell in contact with a test substance to the test substance, and
The step of selecting a test substance determined to be sensitive to the tumor cells as a candidate substance for an anticancer drug is included.
The determination step is a method for screening an anticancer drug, which is carried out by the determination method according to any one of claims 1 to 10. The screening method according to claim 21, wherein the test substance is at least one selected from the group consisting of low molecular weight compounds, peptides, proteins and nucleic acids. Including a selection process for selecting candidate substances for anticancer drugs from test substances, including
The selection step is a method for producing a candidate substance for an anticancer agent, which is carried out by the screening method according to claim 21 or 22. The acquisition step of acquiring the second harmonic (SHG) acquired by using a coherent anti-Stoke Raman scattering (CARS) microscope for the tumor cells contacted with the test substance, and the acquisition process.
It includes a learning step of generating a learned model that outputs a determination result of the susceptibility of a tumor cell to a test substance from the SHG using a pair of the SHG and the susceptibility of the tumor cell to the test substance as teacher data. A method for producing a trained model used to determine the susceptibility of tumor cells. A signal light detection step of detecting at least one of the shape and position of the signal light of the SHG from the SHG is included.
The manufacturing method according to claim 24, wherein in the learning step, the pair of at least one of the shape and position of the signal light of the SHG and the sensitivity of the tumor cell to the test substance is used as teacher data. A calculation step of calculating the dispersion value of the signal light of the SHG from the SHG is included.
The production method according to claim 24 or 25, wherein in the learning step, the pair of the dispersion value of the signal light of the SHG and the sensitivity of the tumor cell to the test substance is used as the teacher data. A localization detection step of detecting the localization of the signal light of the SHG in the Z-axis direction of the tumor cell from the SHG is included.
One of claims 24 to 26, wherein in the learning step, the pair of the localization of the signal light of SHG in the Z-axis direction of the tumor cell and the sensitivity of the tumor cell to the test substance is used as training data. The manufacturing method described in. An acquisition means for acquiring a second harmonic (SHG) acquired using a coherent anti-Stoke Raman scattering (CARS) microscope for a tumor cell contacted with a test substance, and an acquisition means.
It includes a learning means for generating a learned model that outputs a determination result of the susceptibility of a tumor cell to a test substance from the SHG using a pair of the SHG and the susceptibility of the tumor cell to the test substance as teacher data. A trained model manufacturing device used to determine the susceptibility of tumor cells. A signal light detecting means for detecting at least one of the shape and position of the signal light of the SHG from the SHG is included.
28. The manufacturing apparatus according to claim 28, wherein in the learning means, a pair of at least one of the shape and position of the signal light of the SHG and the susceptibility of the tumor cell to a test substance is used as teacher data. A calculation means for calculating the dispersion value of the signal light of the SHG from the SHG is included.
The manufacturing apparatus according to claim 28 or 29, wherein in the learning means, a set of a dispersion value of the signal light of the SHG and the sensitivity of the tumor cell to a test substance is used as teacher data. A localization detecting means for detecting the localization of the signal light of the SHG in the Z-axis direction of the tumor cell from the SHG is included.
One of claims 28 to 30, wherein in the learning means, the pair of the localization of the signal light of SHG in the Z-axis direction of the tumor cell and the sensitivity of the tumor cell to the test substance is used as teacher data. The manufacturing equipment described in. Acquisition processing to acquire second harmonic generation (SHG) under a coherent anti-Stoke Raman scattering (CARS) microscope for tumor cells in contact with the test substance, and
Using the pair of the SHG and the susceptibility of the tumor cells to the test substance as teacher data, a learning process for generating a trained model that outputs the determination result of the susceptibility of the tumor to the test substance from the SHG is performed on a computer. A program that can be run on. Acquisition processing to acquire the second harmonic (SHG) acquired using a coherent anti-Stoke Raman scattering (CARS) microscope of tumor cells in contact with the test substance, and
Using the pair of the SHG and the susceptibility of the tumor cells to the test substance as training data, a computer performs a learning process to generate a trained model that outputs the determination result of the susceptibility of the tumor cells to the test substance from the SHG. A program that can be run on. The acquisition process for acquiring the second harmonic (SHG) of the tumor cells to be examined using a coherent anti-Stoke Raman scattering (CARS) microscope.
A method for selecting cells for determining susceptibility to a test substance, which comprises a selection step of selecting candidate tumor cells to be used for a susceptibility test of the test substance from the test tumor cells based on the SHG. The selection method according to claim 34, wherein in the selection step, the test tumor cell in which the SHG is detected is selected as the candidate tumor cell.

Images