WO2020090089A1 - Dispositif, procédé et programme de détermination - Google Patents

Dispositif, procédé et programme de détermination Download PDF

Info

Publication number
WO2020090089A1
WO2020090089A1 PCT/JP2018/040735 JP2018040735W WO2020090089A1 WO 2020090089 A1 WO2020090089 A1 WO 2020090089A1 JP 2018040735 W JP2018040735 W JP 2018040735W WO 2020090089 A1 WO2020090089 A1 WO 2020090089A1
Authority
WO
WIPO (PCT)
Prior art keywords
correlation
stimulus
change
feature
inhibitor
Prior art date
Application number
PCT/JP2018/040735
Other languages
English (en)
Japanese (ja)
Inventor
拓郎 西郷
Original Assignee
株式会社ニコン
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社ニコン filed Critical 株式会社ニコン
Priority to PCT/JP2018/040735 priority Critical patent/WO2020090089A1/fr
Publication of WO2020090089A1 publication Critical patent/WO2020090089A1/fr

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12M—APPARATUS FOR ENZYMOLOGY OR MICROBIOLOGY; APPARATUS FOR CULTURING MICROORGANISMS FOR PRODUCING BIOMASS, FOR GROWING CELLS OR FOR OBTAINING FERMENTATION OR METABOLIC PRODUCTS, i.e. BIOREACTORS OR FERMENTERS
    • C12M1/00—Apparatus for enzymology or microbiology

Definitions

  • the present invention relates to a determination device, a determination method, and a determination program.
  • the correlation attribute calculation unit that calculates the feature amount correlation attribute between the second element different from the first element and the first element for each of the plurality of types of feature amounts, and the correlation attribute calculation unit.
  • the determination device includes a determination unit that determines the correlation attribute between the second element and the first element by using the calculated feature amount correlation attribute for each of a plurality of types of feature amounts.
  • the first change in the plurality of types of characteristic amounts of the first element constituting the cell with respect to the stimulus with the inhibitor added, and the stimulus without the inhibitor added Using the second change with respect to, a correlation calculation unit that calculates a correlation value between the first element and a second element different from the first element for each of a plurality of types of feature values, and a plurality of types calculated by the correlation calculation unit. And an extraction unit that extracts a predetermined feature amount correlation from a plurality of types of feature amount correlations based on the correlation value for each feature amount.
  • the first change in the characteristic amount of the first element constituting the cell with respect to the stimulation with the drug added and the second change with respect to the stimulation in the state without the drug added Is a determination device that includes a determination unit that determines the correlation attribute between the element and the first element.
  • the first change in the plurality of types of characteristic amounts of the first element constituting the cell with respect to the stimulus with the inhibitor added, and the stimulus without the inhibitor added And a second variation different from the first element to calculate a feature quantity correlation attribute between the second element and the first element, which is different from the first element, for each of a plurality of types of feature quantities, and
  • the determination method includes determining the correlation attribute between the second element and the first element using the feature amount correlation attribute for each type of feature amount.
  • the first change in the plurality of types of characteristic amounts of the first element constituting the cell with respect to the stimulus with the inhibitor added, and the stimulus without the inhibitor added Using the second change with respect to the second element and the second element different from the first element to calculate the correlation value for each of a plurality of types of feature values, and the correlation value calculated in the calculation. Based on a plurality of types of feature amount correlations, the predetermined feature amount correlations are extracted.
  • a first change in the characteristic amount of the first element constituting the cell with respect to the stimulus with the drug added and a second change with respect to the stimulus in the state without the drug added.
  • Is used to calculate the characteristic amount correlation attribute between the second element and the first element on which the drug acts, and by using the characteristic amount correlation attribute calculated in the calculation, the second element and the first element are calculated. And a correlation attribute with an element.
  • the computer is in a state in which a plurality of kinds of characteristic amounts of the first element constituting a cell are changed by a stimulus with an inhibitor added, and a state in which the inhibitor is not added.
  • Calculating a feature quantity correlation attribute between a second element different from the first element and the first element for each of a plurality of types of feature quantities by using the second change with respect to the stimulus It is a determination program for executing the determination of the correlation attribute between the second element and the first element by using the feature amount correlation attributes for each of the plurality of types of feature amounts that have been generated.
  • the computer is in a state in which a plurality of types of characteristic amounts of the first element constituting a cell are changed by a stimulus with an inhibitor added, and a state in which the inhibitor is not added. And a second change with respect to the stimulus in step S1 to calculate a correlation value between the second element different from the first element and the first element for each of a plurality of types of feature values, and in the calculation. It is a determination program for executing, based on a correlation value, extracting a predetermined feature amount correlation from a plurality of types of feature amount correlation.
  • the computer is provided with a first change in the characteristic amount of the first element constituting the cell with respect to the stimulus with the drug added, and a change with respect to the stimulus in the state without the drug added.
  • the second element is calculated by calculating the feature quantity correlation attribute between the second element and the first element on which the drug acts, using the two changes, and using the feature quantity correlation attribute calculated in the calculation.
  • a determination program for executing determination of a correlation attribute between the first element and the first element.
  • FIG. 1 It is a figure which shows an example of a structure of the microscope observation system by embodiment of this invention. It is a figure which shows an example of the cell of this embodiment. It is a block diagram showing an example of functional composition of each part with which a judgment device of this embodiment is provided. It is a flow chart which shows an example of a calculation procedure of a calculation part of this embodiment. It is a figure which shows an example of the neural network which the feature-value calculation part of this embodiment uses for calculation of a feature-value. It is a figure which shows an example of the calculation result of the feature-value by the feature-value calculation part of this embodiment. It is a flow chart which shows an example of a calculation procedure of a judgment part of this embodiment.
  • FIG. 1 is a diagram showing an example of the configuration of a microscope observation system 1 according to an embodiment of the present invention.
  • the microscope observation system 1 performs image processing on an image acquired by imaging cells and the like. In the following description, an image acquired by imaging a cell or the like is also simply referred to as a cell image.
  • the microscope observation system 1 includes a determination device 10, a microscope device 20, and a display unit 30.
  • the microscope device 20 is a biological microscope, and includes an electric stage 21 and an imaging unit 22.
  • the electric stage 21 can arbitrarily move the position of the imaging target in a predetermined direction (for example, a certain direction within a two-dimensional horizontal plane, a vertical direction, or an axial rotation direction).
  • the image pickup unit 22 includes an image pickup device such as a CCD (Charge-Coupled Device) or a CMOS (Complementary MOS), and picks up an image of the image pickup target on the electric stage 21. It should be noted that the microscope apparatus 20 may not be provided with the electric stage 21, and the stage may not operate in the predetermined direction.
  • the microscope apparatus 20 includes, for example, a differential interference microscope (DIC), a phase contrast microscope, a fluorescence microscope, a confocal microscope, a super-resolution microscope, a two-photon excitation fluorescence microscope, a light sheet microscope. , Light field microscope, holographic microscope, optical coherence tomography (OCT), and the like.
  • the microscope device 20 images the culture container placed on the electric stage 21. Examples of the culture container include a well plate WP and a slide chamber.
  • the microscope apparatus 20 irradiates the cells cultured in the large number of wells W of the well plate WP with light to capture the transmitted light transmitted through the cells as an image of the cells.
  • the microscope apparatus 20 can acquire images such as a transmission DIC image of cells, a phase difference image, a dark field image, and a bright field image. Further, by irradiating the cells with excitation light that excites the fluorescent substance, the microscope device 20 captures the fluorescence emitted from the biological substance as an image of the cells. Further, the microscope device 20 captures light emission or phosphorescence from a luminescent substance in the cell as an image of the cell.
  • cells are stained alive and time-lapse photography is performed to acquire a change image of cells after cell stimulation.
  • a cell image is acquired by expressing a fluorescent fusion protein or by staining the cells alive with a chemical reagent or the like.
  • cells are fixed and stained to acquire a cell image. Metabolism ceases in fixed cells. Therefore, in the case of observing the time course of intracellular changes with fixed cells after stimulating the cells, it is necessary to prepare a plurality of cell culture vessels seeded with the cells. For example, it may be desired to apply a stimulus to cells and observe changes in cells after a first time and changes in cells after a second time different from the first time. In this case, after stimulating the cells for a first time, the cells are fixed and stained to acquire a cell image.
  • a cell culture container that is different from the cells used for observation at the 1st hour, apply stimulation to the cells, and after 2 hours have elapsed, fix the cells and stain them to obtain a cell image.
  • the number of cells used for observing the intracellular change between the first time and the second time is not limited to one. Therefore, an image of a plurality of cells is acquired in each of the first time and the second time. For example, if the number of cells for which changes in cells are to be observed is 1000, 2000 cells will be imaged during the first and second hours. Therefore, in order to acquire the details of the change in the cell with respect to the stimulus, a plurality of cell images are required at each imaging timing from the stimulus, and a large number of cell images are acquired.
  • the microscope device 20 captures, as an image of the above-described cells, light emission or fluorescence from the coloring substance itself taken into the biological substance, and light emission or fluorescence generated when a substance having a chromophore binds to the biological substance. May be.
  • the microscope observation system 1 can acquire a fluorescence image, a confocal image, a super-resolution image, and a two-photon excitation fluorescence microscope image.
  • the method of acquiring the image of the cell is not limited to the optical microscope.
  • an electron microscope may be used as a method of acquiring an image of cells.
  • the images obtained by different methods may be used to acquire the correlation. That is, the type of cell image may be appropriately selected.
  • the cells in the present embodiment are, for example, primary cultured cells, established cultured cells, cells of tissue sections, and the like.
  • the sample to be observed may be an aggregate of cells, a tissue sample, an organ, or an individual (animal or the like), and an image containing the cells may be acquired.
  • the state of the cells is not particularly limited, and may be a living state or a fixed state.
  • the cell state may be "in-vitro".
  • the information of the living state and the information of the fixed state may be combined.
  • cells may be treated with chemiluminescent or fluorescent protein (for example, chemiluminescent or fluorescent protein expressed from an introduced gene (green fluorescent protein (GFP) or the like)) and observed.
  • chemiluminescent or fluorescent protein for example, chemiluminescent or fluorescent protein expressed from an introduced gene (green fluorescent protein (GFP) or the like)
  • cells may be observed using immunostaining or staining with a chemical reagent. You may observe them in combination.
  • the photoprotein to be used according to the type for discriminating the intracellular nuclear structure (for example, Golgi apparatus).
  • the pretreatment for analyzing the correlation acquisition such as the means for observing these cells and the method for staining the cells, may be appropriately selected according to the purpose.
  • the dynamic information of the cell is obtained by the optimal method
  • the information on the intracellular signal transduction is obtained by the optimal method. It doesn't matter.
  • the pretreatments selected may be different depending on the purpose.
  • the well plate WP has one or a plurality of wells W.
  • the well plate WP has 8 ⁇ 12 96 wells W as shown in FIG.
  • the number of the well plates WP is not limited to this, and it is 48 wells 6 ⁇ 8, 24 wells 6 ⁇ 4, 12 wells 3 ⁇ 4, and 6 wells 2 ⁇ 3. , 12 ⁇ 32 384 wells W or 32 ⁇ 48 1536 wells W.
  • the cells are cultured in the well W under specific experimental conditions. Specific experimental conditions include temperature, humidity, culture period, elapsed time after stimulation is given, type and strength of stimulation, concentration, amount, presence or absence of stimulation, induction of biological characteristics, etc. Including.
  • the stimulus is, for example, a physical stimulus such as electric, sound wave, magnetism or light, or a chemical stimulus by administration of a substance or a drug.
  • Biological characteristics include the stage of cell differentiation, morphology, number of cells, behavior of intracellular molecules, morphology and behavior of organelles, behaviors of each form, nuclear structure, behavior of DNA molecules, etc. It is a characteristic to show.
  • FIG. 2 is a diagram showing an example of the cell CL of the present embodiment.
  • the cell CL1 and the cell CL2 shown in FIG. 2 are cells of the same type.
  • the same kind of stimulation is applied to the cells CL1 and CL2.
  • the constituent elements of the cell CL1 include the constituent element A1, the constituent element B1, the constituent element C1, and the constituent element D1.
  • the constituent elements of the cell CL2 include the constituent element A2, the constituent element B2, the constituent element C2, and the constituent element D2.
  • the component A1 and the component A2, the component B1 and the component B2, the component C1 and the component C2, and the component D1 and the component D2 are components of the same type.
  • cell CL1 and the cell CL2 when the cell CL1 and the cell CL2 are not distinguished, they are also simply referred to as cell CL. Further, when the constituent element A1 and the constituent element A2 are not distinguished from each other, they are simply referred to as the constituent element A. Similarly, when the constituent element B1 and the constituent element B2 are not distinguished from each other, they are also simply referred to as the constituent element B. When the constituent element C1 and the constituent element C2 are not distinguished from each other, they are also simply referred to as the constituent element C. When the constituent element D1 and the constituent element D2 are not distinguished from each other, they are also simply referred to as the constituent element D.
  • the constituent element A, the constituent element B, the constituent element C, and the constituent element D are constituent elements different from each other.
  • the constituent element A is an example of a first element that constitutes a cell
  • the constituent elements B, C, and D are examples of a second element that is different from the first element. That is, as an example, the second element is an element that constitutes a cell.
  • the determination device 10 determines the order of the response of the response of the component to the stimulus in the response that occurs between the components of the cell CL to which the stimulus is applied. In the present embodiment, the order of response of responses of constituent elements to a stimulus is called a correlation attribute.
  • the correlation attribute is the order of the response to the stimulus of the first element constituting the cell and the response to the stimulus of the second element different from the first element.
  • the determination device 10 determines the response of the reaction of the inhibitor and the order of the response to the stimulus of the component of interest, which will be described later.
  • the determination device 10 determines the order of the response of the component on which the inhibitor acts and the response of the component of interest. Further, the determination device 10 can change the type of the component of interest to be determined. Thereby, the determination device 10 can determine the order of the responses of the respective constituent elements on the basis of the response of the reaction in which the inhibitor acts. Therefore, the determination device 10 can determine the order of responses according to the types of components.
  • the stimulus is a chemical stimulus or a physical stimulus that, when applied to the cell CL, causes a reaction between the constituent elements of the cell CL.
  • the stimulus is a chemical stimulus or a physical stimulus that causes a chain reaction that is supposed between the components of the cell CL.
  • the second element is a reaction in which the inhibitor acts.
  • the reaction supposed between the components of the cell CL is a reaction regarding the signal transduction of the cell CL.
  • This reaction may be a reaction that occurs in the cell CL or a reaction that occurs between a plurality of cell CLs.
  • the reaction means a plurality of reactions that occur between a plurality of types of constituent elements contained in the cell CL, and those reactions may occur sequentially.
  • a plurality of respective reactions between the constituent elements are sequentially caused. This reaction is initiated by first applying a stimulus to the cell CL, and a change in the activity of the component of the cell CL to which the stimulus is applied causes a signal to be transmitted to another component.
  • This reaction includes, for example, a reaction in which a protein that is a component of cell CL is phosphorylated and a signal is transmitted to another component by changing the activity of this protein.
  • a signal is transmitted between the respective constituents in the reaction caused between the constituents.
  • a signal is transmitted between the first constituent element and the second constituent element, there is not only one kind of path between them but also plural kinds of paths.
  • these pathways may simultaneously react and transmit a signal.
  • an inhibitor the function of a specific component can be suppressed by the action of the inhibitor. In the state where the inhibitor is added, it is possible to cause a reaction between the components of the cell CL in which the function of a specific component is suppressed by applying a stimulus.
  • the component on which this inhibitor acts in the reaction assumed between the components of the cell CL is called the point of action of the inhibitor.
  • the action of the inhibitor also includes inhibiting the progress of the reaction between the constituents, and in this case, the element on which the inhibitor acts also includes the reaction between the constituents.
  • the determination device 10 can determine the point of action of this inhibitor by determining the order of the response of the reaction of the inhibitor to the stimulus and the response of the constituent elements of the cell CL to the stimulus.
  • the cell CL1 shown in FIG. 2 and the cell CL2 described above are cultured in different well plates.
  • the cell CL1 and the cell CL2 are cells of the same type, and the same type of stimulus is applied.
  • the cells CL1 and CL2 may be cultured in the same well plate. In this case, for example, when a drug solution is used as the stimulus, the drug solution may be dropped on the cultured cells containing the cells CL1 and CL2 to stimulate the cells CL1 and CL2.
  • No inhibitor is added to the well plate in which cell CL1 is cultured.
  • An inhibitor is added to the well plate in which the cells CL2 are cultured.
  • the inhibitor is a compound.
  • the difference between the well plate in which the cell CL1 is cultured and the well plate in which the cell CL2 is cultured depends on whether or not the inhibitor is added.
  • the inhibitor is not limited to the compound, but may be protein or enzyme.
  • gene recombination or gene editing may cause functional inhibition, mutation or deletion of a component, or a low expression state or a non-expression state of a component. Therefore, the inhibitor may be added to the constituent element, or the constituent element may be altered by gene recombination or gene editing. In addition, the inhibitor may inhibit the progress of the reaction between the specific constituents.
  • the determination device 10 compares the experimental result obtained by performing the experiment without adding the inhibitor to the constituent elements of the cell CL1 with the experimental result obtained by adding the inhibitor to the constituent element of the cell CL2 to determine the component of the cell CL. The order of the response of the inhibitory action to the stimulus and the response of the components of the cell CL to the stimulus in the intervening response is determined.
  • the experimental result in which the inhibitor is added to the constituent elements of the cell CL2 is described as the result of the experiment in which the inhibitor is added.
  • the cells to which the inhibitor is added are also referred to as inhibitor-added cells.
  • the experimental results obtained by adding no inhibitor to the components of the cell CL1 are referred to as the results of the control experiment.
  • cells to which the inhibitor is not added are also referred to as control cells. That is, the result of the control experiment is the result of the change of the cell CL1 over time.
  • the determination unit 150 included in the determination device 10 of the present embodiment determines the feature amount obtained from the captured image obtained by capturing the result of the experiment in which the inhibitor is added and the feature amount obtained from the captured image obtained by capturing the result of the control experiment. Compare. For example, when the feature amount is the brightness of the constituent element A, the brightness of the constituent element A2 that captures the result of the experiment in which the inhibitor is added is compared with the brightness of the constituent element A1 that captures the result of the control experiment. To do. Thereby, the determination unit 150 determines the order of the response of the reaction of the inhibitor to the stimulus and the response of the component of the cell CL to the stimulus in the reaction assumed between the components of the cell CL.
  • the determination unit 150 changes the characteristic amounts of the constituent elements of the cell CL with respect to the stimulus in the state where the inhibitor is added, and the characteristic amounts of the constituent elements of the cell CL in the state where the inhibitor is not added. For each of the plurality of types of feature quantities of the constituent elements of the cell CL. The determination unit 150 calculates the ratio of the types of the characteristic amounts of the constituent elements, of which the calculated correlation value is greater than a predetermined magnitude, among the plurality of types of the characteristic amounts of the constituent elements of the cell CL.
  • FIG. 3 is a block diagram showing an example of the functional configuration of each unit included in the determination device 10 of this embodiment.
  • the determination device 10 analyzes the image captured by the microscope device 20 and the image of the stimulated cell.
  • the determination device 10 determines the order of response to the stimulus of the component of interest with respect to the component on which the inhibitor acts.
  • the determination device 10 can determine the order of response of a plurality of types of components to the stimulus to the components on which the inhibitor acts, for each plurality of types. Thereby, the determination device 10 can determine the order of response of the components of the cell CL to the stimulus.
  • the component A of the components of the cell CL will be described as an example of the target to be analyzed by the determination device 10.
  • the determination device 10 analyzes a plurality of constituent elements of the cell CL
  • the constituent elements A and B will be described as an example.
  • the target of analysis by the determination device 10 may be the constituent element C or the constituent element D of the cell CL.
  • the determination device 10 includes a calculation unit 100, a storage unit 300, a display image generation unit 200, and a result output unit 400.
  • the arithmetic unit 100 functions by the processor executing a program stored in the storage unit 300. Further, some or all of the respective functional units of the arithmetic unit 100 may be configured by hardware such as LSI (Large Scale Integration) and ASIC (Application Specific Integrated Circuit).
  • the calculation unit 100 includes an image acquisition unit 101 and a feature amount calculation unit 102 in addition to the determination unit 150 described above.
  • the image acquisition unit 101 acquires the cell image captured by the imaging unit 22 and supplies the acquired cell image to the feature amount calculation unit 102.
  • the cell image acquired by the image acquisition unit 101 includes a plurality of images in which the culture state of cells is time-sequentially imaged.
  • the cell image is a captured image in which the cells to which the above-described inhibitor is added and the control cells are captured.
  • the feature amount calculation unit 102 acquires a cell image from the image acquisition unit 101.
  • the feature amount calculation unit 102 calculates the feature amount of the constituent elements of the cells captured in the cell image acquired from the image acquisition unit 101.
  • the feature amount includes the brightness of the cell image, the cell area in the image, the dispersion of the brightness of the cell image in the image, the shape, and the like. That is, the feature amount is a feature derived from information acquired from the imaged cell image. That is, the feature amount is a feature derived from information acquired from the imaged cell image.
  • the feature amount calculation unit 102 calculates the brightness distribution in the acquired image.
  • the feature amount calculation unit 102 uses a plurality of images having different times with respect to the stimulus, and calculates the time change of the luminance distribution as the change of the feature amount.
  • the change in the feature amount calculated by the feature amount calculation unit 102 is not limited to the time series with different times, and may be any change in the cell state. For example, it does not matter even if the state of differentiation of cells and the amount of drug that stimulates cells are different.
  • the feature amount calculation unit 102 extracts, for example, a change in the size of the brightness or a change in the position of the brightness as the change in the brightness.
  • the feature amount calculation unit 102 extracts, for example, a portion that has changed for each image, such as luminance position information, as a luminance change for each image.
  • the feature amount calculation unit 102 observes each of the plurality of images captured at a predetermined time interval, so that the feature amount of the cells that are less affected by the contraction of the cell, the heartbeat cycle, the cell migration speed, and the stimulation is improved.
  • Changes in the degree of aggregation of nuclear chromatin which is an index of cells that are dying or dying, the rate of change in the number and length of nerve cell projections, the number of synapses in nerve cells, neural activity such as changes in membrane potential, intracellular Extraction of dynamic features such as calcium concentration change, second messenger activity, organelle morphology change, intracellular molecular behavior, nuclear morphology, nuclear structure behavior, DNA molecule behavior, etc. Good.
  • These feature amount extraction methods use, for example, dimension reduction by a neural network, Fourier transform, wavelet transform, and time derivative, and a moving average for noise removal.
  • the feature amount calculation unit 102 calculates the feature amount based on the cell image in which the cells to which the above-described inhibitor is added is imaged and the cell image in which the control cells are imaged.
  • the feature amount calculated from the cell image obtained by imaging the cells to which the inhibitor is added is also referred to as the inhibitor-added feature amount.
  • the inhibitor-added feature amount is calculated from a cell image in which cells to which the inhibitor has been added are imaged.
  • the feature amount calculation unit 102 extracts the feature amount of the constituent element from the cell image in which the cells to which the inhibitor has been added are imaged.
  • the feature amount calculation unit 102 can extract a plurality of types of feature amounts regarding a predetermined component from the cell image.
  • the feature amount calculation unit 102 can extract the feature amount for each of a plurality of types of component elements from the cell image.
  • a feature amount calculated from a cell image obtained by capturing an image of a control cell is also referred to as a control feature amount.
  • the control feature amount is calculated from the cell image in which the control cell is imaged.
  • the characteristic amount calculation unit 102 extracts the characteristic amounts of the constituent elements from the cell image in which the control cells are imaged.
  • the feature amount calculation unit 102 can extract a plurality of types of feature amounts regarding a predetermined component from the cell image.
  • the feature amount calculation unit 102 can extract the feature amount for each of a plurality of types of component elements from the cell image. Further, when the feature amount is the i-th feature amount of the constituent element A, the inhibitor addition feature amount may be referred to as the feature amount Aid, and the control feature amount may be referred to as the feature amount Aic. ..
  • the correlation calculation unit 103 determines the change in the feature amount Aid of the component A with respect to the stimulus in the state where the inhibitor is added, and the change of the feature amount Aic of the component A in the inhibitor.
  • the correlation with the change with respect to the stimulus in the state in which is not added is calculated for each of the plurality of types of the characteristic amount of the component A.
  • the change in the characteristic amount Aid of the constituent A with respect to the stimulus with the inhibitor added, and the change of the characteristic amount Aic of the constituent A with the inhibitor not added The correlation between the characteristic amount Aid of the constituent element A and the characteristic amount Aic of the constituent element A is calculated using the change with respect to the stimulus.
  • the correlation calculation unit 103 calculates, for each of the plurality of types of characteristic amounts of the constituent element A, the correlation between the change in the characteristic amount in the state in which the inhibitor is added and the change in the characteristic amount in the state in which the inhibitor is not added. To do.
  • the correlation calculation unit 103 calculates the correlation by comparing the time change of the feature amount after applying the stimulus.
  • the correlation calculated using the change in the characteristic amount is the change over time after the stimulus of the characteristic amount Aid of the constituent element A2 obtained from the result of the experiment in which the inhibitor is added is applied. And the change over time after the stimulus of the feature amount Aic of the component A1 obtained from the result of the control experiment is applied, the correlation with respect to time is included.
  • the correlation calculated using the change in the feature amount is obtained when the intensity of the stimulus to which the feature amount Aid of the constituent element A2 obtained from the result of the experiment in which the inhibitor is added is changed. Of the stimulus intensity between the change in the stimulus intensity and the change in the intensity of the applied stimulus of the feature amount Aic of the component A1 obtained from the result of the control experiment are included. Be done.
  • the intensity of irritation is, for example, the concentration of the substance or drug to be administered.
  • the strength of stimulation is, for example, the strength of electricity, sound waves, magnetism, light, or the like.
  • the correlation calculation unit 103 calculates the correlation as a correlation value using the change in the feature amount. Therefore, as described above, the correlation calculation unit 103 causes the first change with respect to the stimulus in the state in which the inhibitor is added, and the state in which the inhibitor is not added, with respect to the plurality of types of feature amounts of the first element forming the cell. By using the second change with respect to the stimulus in step 1, the correlation value between the second element different from the first element and the first element is calculated for each of a plurality of types of feature amounts.
  • the feature amount correlation attribute calculation unit 104 calculates the component A from the correlation between the change in the feature amount calculated by the correlation calculation unit 103 with the inhibitor added and the change in the feature amount without the inhibitor added.
  • the feature amount correlation attribute is calculated for each of the plurality of types of feature amounts.
  • the feature amount correlation attribute is the order of response to a stimulus between the reaction point at which the inhibitor acts and the feature amount of the component A of interest.
  • the response of the characteristic amount of the constituent element A is activation of the characteristic amount of the constituent element A. Therefore, the feature quantity correlation attribute is the order in which the feature quantity of the constituent element A for the stimulus is activated and the order in which the reaction point where the inhibitor acts on the stimulus is activated.
  • the feature amount correlation attribute is the order of the response to the feature amount stimulus of the first element forming the cell and the response to the feature amount stimulus of the second element different from the first element.
  • the response of the characteristic amount of the constituent element A is not limited to activation of the characteristic amount of the constituent element A and may be suppressed.
  • the attributes of the correlation may include a causal relation and a relation of suppressing or activating the correlation.
  • the feature amount correlation attribute calculation unit 104 determines, for each of the plurality of types of feature amounts of the constituent element A, a change in the feature amount in the state in which the inhibitor is added and a change in the feature amount in the state in which the inhibitor is not added. Calculate the correlation attribute.
  • the feature value correlation attribute calculation unit 104 calculates the correlation value between the change in the feature amount calculated by the correlation calculation unit 103 in the state in which the inhibitor is added and the change in the feature amount in the state in which the inhibitor is not added.
  • the type of feature amount larger than the predetermined size and the type of feature amount smaller than the predetermined size may be determined.
  • the feature amount correlation attribute calculation unit 104 is an example of a correlation attribute calculation unit.
  • the ratio calculation unit 105 calculates the ratio of the feature amount correlation attribute in the feature amount from the feature amount correlation attribute for each type of feature amount based on the calculation result of the feature amount correlation attribute calculation unit 104.
  • the ratio of feature quantity correlation attributes is, for example, the number of types of feature quantities having a quick response order to a stimulus among correlation attributes of feature quantities for each type of feature quantity.
  • the determination unit 106 uses the ratio calculated by the ratio calculation unit 105 to determine the order of the response of the reaction of the inhibitor to the stimulus and the response of the constituent element A to the stimulus.
  • the ratio calculated by the ratio calculation unit 105 is calculated using the characteristic amount correlation attribute for each of the plurality of types of characteristic amounts calculated by the characteristic amount correlation attribute calculation unit 104.
  • the order of the response of the reaction of the inhibitor to the stimulus and the response of the constituent element A to the stimulus is an example of the correlation attribute between the second element and the first element different from the second element. Therefore, the determination unit 106 uses the feature quantity correlation attributes for each of the plurality of types of feature quantities calculated by the feature quantity correlation attribute calculation unit 104 to correlate the second element with the first element different from the second element. Determine attributes.
  • the comparison unit 107 uses the ratio calculated by the ratio calculation unit 105 and compares the order of the response to the stimulus with the point of action on which the inhibitor acts, which is calculated for each of the plurality of constituent elements. For example, the order of response of the component A to the point of action on which the inhibitor acts is compared with the order of response of the component B to the point of action on which the inhibitor acts, and the order of response of the component A and the component The comparison unit 107 compares the response order of B with that of B. Therefore, the comparison unit 107 calculates the correlation attribute between the point of action on which the inhibitor acts and the component of interest by using the ratio of the feature amount correlation attribute calculated by the ratio calculation unit 105.
  • a component that responds prior to the point of action on which the inhibitor acts is called an upstream component
  • a component that responds after the point of action on which the inhibitor acts is called a downstream component.
  • the display image generation unit 200 includes a signal pathway generation unit 201 and a component element order graph generation unit 202.
  • the signal pathway generation unit 201 generates the signal pathway SP based on the judgment result of the judgment unit 106, the comparison result of the comparison unit 107, and the signal pathway information.
  • the signal pathway information is stored in the signal pathway storage unit 302 included in the storage unit 300.
  • the signal pathway information is information for generating the signal pathway SP.
  • the signal pathway generation unit 201 supplies the generated signal pathway SP to the result output unit 400.
  • the signal pathway SP is a diagram showing a reaction assumed between the constituent element A and the constituent element B in the cell CL.
  • the signal pathway SP indicates, for example, a signal transmission path in the cell CL.
  • constituent elements that transmit signals in a series of reactions that occur in the cell CL and chemical substances that act on those constituent elements are shown together with a directed graph showing the direction of the signal transduction pathway.
  • the signal pathway information includes information in the public database about the signal pathway SP.
  • the signal pathway information includes information on symbols and icons indicating constituent elements of the cell CL and chemical substances acting on those constituent elements, and information on a directed graph indicating the direction of a signal transmission path.
  • the component element order graph generation unit 202 generates the component element order graph EG based on the determination result of the determination unit 106 and the comparison result of the comparison unit 107.
  • the constituent element order graph EG is a graph in which constituent elements of the cell CL are arranged on the basis of the reaction of the inhibitor.
  • the constituent element order graph generation unit 202 supplies the generated constituent element order graph EG to the result output unit 400.
  • the storage unit 300 includes an experimental condition storage unit 301 and a signal pathway storage unit 302.
  • the experimental condition storage unit 301 stores, for each cell image, information on the experimental condition for the cell associated with the cell image.
  • the information on the condition of the experiment includes, for example, the condition of the cell, the condition at the time of acquiring the image, the condition of processing the cell, and the like.
  • the cell condition includes, for example, the type of cell, either control cells or cells to which an inhibitor is added.
  • the conditions at the time of acquiring an image include, for example, imaging conditions such as the type of microscope device used and the magnification at the time of acquiring an image.
  • the conditions for treating the cells include, for example, the staining conditions when the cells are stained, the type of stimulation applied to the cells, and the like.
  • the signal pathway storage unit 302 stores signal pathway information.
  • the result output unit 400 outputs the calculation result of the calculation unit 100 to the display unit 30.
  • the result output unit 400 may output the calculation result of the calculation unit 100 to an output device other than the display unit 30, a storage device, or the like.
  • the display unit 30 displays the calculation result by the calculation unit 100 output from the result output unit 400. Specifically, the display unit 30 displays an image of the signal pathway SP output from the result output unit 400 and the component element order graph EG, or a list of the results.
  • the input unit 40 includes, for example, a touch panel, a mouse, a keyboard, or the like.
  • the input unit 40 receives an operation for inputting experimental conditions.
  • the input unit 40 stores the input experimental condition in the experimental condition storage unit 301 according to the received operation.
  • FIG. 4 is a flowchart showing an example of the calculation procedure of the calculation unit 100 of this embodiment.
  • the calculation procedure shown here is an example, and the calculation procedure may be omitted or the calculation procedure may be added.
  • the image acquisition unit 101 acquires a cell image for each of the well plate in which the cells CL1 are cultured and the well plate in which the cells CL2 are cultured (step S10).
  • This cell image includes images of a plurality of types of living tissues of different sizes such as genes, proteins, and organelles.
  • the cell image includes shape information of the cells CL1 and CL2. Since the cell image includes information such as phenotype, metabolite, protein, gene, etc., the determination device 10 can analyze the correlation between them.
  • the feature amount calculation unit 102 extracts the images of the cells CL1 and CL2 included in the cell image acquired in step S10 for each of the cells CL1 and CL2 (step S20).
  • the feature amount calculation unit 102 extracts images of the cells CL1 and CL2 by performing image processing on the cell images.
  • the feature amount calculation unit 102 extracts the image of the cell CL1 and the cell CL2 by performing contour extraction of the image, pattern matching, or the like.
  • the feature amount calculation unit 102 determines the types of the cells CL1 and CL2 in the images of the cells CL1 and CL2 extracted in step S20 (step S30). Further, the feature amount calculation unit 102 determines the components of the cells CL1 and CL2 included in the images of the cells CL1 and CL2 extracted in step S20, respectively, based on the determination result in step S30 (step S40). ).
  • the components of the cells CL1 and CL2 include organelles such as cell nuclei, lysosomes, Golgi apparatus, mitochondria, and proteins that constitute organelles.
  • the types of the cells CL1 and CL2 are determined in step S30, the types of the cells CL1 and CL2 may not be determined. In this case, if the types of the cell CL1 and the cell CL2 to be introduced are determined in advance, that information may be used. Of course, it is not necessary to specify the types of the cells CL1 and CL2.
  • the feature amount calculation unit 102 calculates the feature amount of the image for each of the constituent elements of the cells CL1 and CL2 determined in step S40 (step S50).
  • a plurality of feature quantities are calculated for each of one cell CL1 and one cell CL2.
  • the feature amount includes a brightness value of a pixel, an area of a certain area in an image, a variance value of brightness of the pixel, and the like.
  • the feature amount of the image of the cell nucleus includes the total brightness value in the nucleus, the area of the nucleus, and the like.
  • the feature quantity of the cytoplasmic image includes the total brightness value in the cytoplasm, the area of the cytoplasm, and the like.
  • the feature amount of the image of the entire cell includes the intracellular total brightness value, the area of the cell CL, and the like.
  • the feature amount of the mitochondrial image includes the fragmentation rate.
  • the feature amount calculation unit 102 may normalize and calculate the feature amount to a value between 0 (zero) and 1, for example. In the present embodiment, a case will be described in which the types of feature amounts and the number of types of feature amounts calculated by the feature amount calculation unit 102 are different for each component. The number of types of feature amount may be different for each component as long as it is one or more. Note that the types of feature amounts and the number of types of feature amounts calculated by the feature amount calculation unit 102 may be common to each component.
  • the feature amount calculated by the feature amount calculation unit 102 may include the feature amount obtained by dimension reduction by the neural network.
  • the neural network NN used by the feature amount calculation unit 102 to calculate the feature amount will be described with reference to FIG.
  • FIG. 5 is a diagram showing an example of the neural network NN used by the feature amount calculation unit 102 of this embodiment to calculate the feature amount.
  • the neural network NN includes a plurality of layers including an input layer, one or more intermediate layers, and an output layer, and information of nodes in each layer is given a predetermined weight for each node with respect to the next and subsequent layers. introduce.
  • the node is a component included in the neural network NN.
  • the input of the input image to the input layer means that the brightness values of the pixels of the input image are input to the input layer, respectively. Therefore, the number of nodes forming the input layer of the neural network NN is equal to the number of pixels forming the input image.
  • the neural network NN classifies the input image into a predetermined number of categories based on the information transmitted to the output layer.
  • the number of nodes in the output layer is equal to the number of categories classified by the neural network NN.
  • the number of nodes in the output layer of the neural network NN is 1000 as an example.
  • the neural network NN is, for example, a convolutional neural network (CNN), and has a convolutional layer, a pooling layer, a connection layer, and a dropout layer as intermediate layers.
  • CNN convolutional neural network
  • the features of the input image are extracted.
  • higher-order features are extracted as the intermediate layer is closer to the output layer side.
  • simple pattern features such as edges of the input image are extracted as the features of the input image.
  • the edge of the input image is the contour of the input image.
  • features of a complicated pattern are extracted as features of the input image.
  • the feature of the input image extracted in the hidden layer is represented by a set of values output from the nodes forming the hidden layer.
  • a set of values output from each node of the intermediate layer L1 adjacent to the output layer of the neural network NN is calculated as the feature amount of the cell image PC1.
  • a set of values output from each node of the intermediate layer L1 is a feature amount dimensionally reduced by the neural network NN.
  • the feature amount calculation unit 102 may calculate the feature amount based on information on the stimulus applied to the cells associated with the cell image. For example, in the case of a cell image captured when a stimulus for reacting an antibody with respect to a cell is applied, the feature amount calculation unit 102 may calculate a feature amount unique to the case where the antibody is reacted. Further, in the case of a cell image taken when a cell is stained or when a fluorescent protein is added to the cell, the feature amount calculation unit 102 stains the cell or when a fluorescent protein is added to the cell. You may calculate the characteristic amount peculiar to. In these cases, the feature amount calculation unit 102 may use the information on the experimental condition for the cell stored in the experimental condition storage unit 301.
  • the experimental condition storage unit 301 does not store the experimental condition information
  • the experimental condition may be input using the input unit 40.
  • the information may be obtained from another device.
  • the microscope device 20 may obtain the information on the experimental condition.
  • information on experimental conditions may be obtained from public databases or documents. In this case, the captured image may be compared with an image contained in a public database or a document, the type of cell contained in the captured image may be specified, and the information may be used.
  • FIG. 6 is a diagram showing an example of the calculation result of the characteristic amount by the characteristic amount calculation unit 102 of this embodiment.
  • the feature amount calculation unit 102 calculates a plurality of feature amounts for each of the components of the cell CL1 and the cell CL2 and for each time.
  • the characteristic amount calculation unit 102 calculates the characteristic amounts of N constituent elements from constituent element 1 to constituent element N.
  • the feature amount calculation unit 102 calculates the feature amount for seven times from time 1 to time 7.
  • the feature amount calculation unit 102 calculates K types of feature amounts from the feature amount k1 to the feature amount kK. That is, in this example, the feature amount calculation unit 102 calculates the feature amount in the directions of the three axes.
  • the axis in the cell direction is described as the axis Nc
  • the axis in the time direction as the axis N
  • the axis in the feature amount direction as the axis d1.
  • the K types of feature quantities from the feature quantity k1 to the feature quantity kK are combinations of the feature quantities of the cell 1.
  • the types and combinations of the characteristic amounts may be different.
  • the feature amount calculation unit 102 supplies the inhibitor addition feature amount, which is the feature amount calculated in step S50, and the control feature amount to the correlation calculation unit 103.
  • the determination unit 150 determines the order of the response of the reaction of the inhibitor acting on the stimulus and the response of the component of the cell CL to the stimulus in the reaction assumed between the components of the cell CL (step S60). ..
  • the inhibitor is U0126
  • the constituent element A is MEK (Mitogen-activated protein / extracellular signal-regulated kinase kinase)
  • the constituent element B is MAPK (Mitogen-activated) protected protein.
  • the element C is Raf and the stimulus is a chemical stimulus by an EGFR (epidermal growth factor receptor) will be described.
  • the determination unit 150 determines the order of the response of the reaction of U0126 to EGFR and the response of MEK to EGFR. Further, the determination unit 150 determines the order of the response of the reaction of U0126 acting on EGFR and the response of MAPK to EGFR. The determination unit 150 also determines the order of the response of MEK to EGFR and the response of Raf to EGFR. Note that the determination unit 150 not only determines the order of response between proteins as in the above example, but also determines the order of response between proteins and morphology such as the area size of the region and the fragmentation rate of mitochondria and the relationship between morphologies. The order of responses may be determined. Here, the details of the calculation procedure of the determination unit 150 will be described with reference to FIG. 7.
  • FIG. 7 is a flowchart showing an example of the calculation procedure of the determination unit 150 of this embodiment.
  • the calculation procedure shown here is an example, and the calculation procedure may be omitted or the calculation procedure may be added.
  • the determination unit 150 repeats the process of determining, for each component, whether the component of interest responds before or after the action point of the inhibitor (step S600). The determination unit 150 determines whether each of MEK, MAPK, and Raf is upstream or downstream of the point of action of U0126.
  • the correlation calculation unit 103 extracts the change in the feature amount with respect to the stimulus with the inhibitor added, for each of the plurality of types of feature amounts of the constituent elements (step S601). That is, the correlation calculation unit 103 extracts the change in the feature amount with respect to the EGFR with U0126 added, for each of the plurality of types of feature amounts of the constituent elements.
  • the constituent element is any one of MEK, MAPK, and Raf constituting the cell CL2 which is the cell to which the inhibitor is added.
  • the correlation calculation unit 103 extracts a change in the feature amount by arranging the feature amounts in time series for each of the K types of feature amounts calculated by the feature amount calculation unit 102 from the cell image obtained by capturing the image of the cell CL2.
  • the correlation calculation unit 103 extracts the change in the feature amount with respect to the stimulus without adding the inhibitor for each of the plurality of types of feature amounts of the constituent elements (step S602). That is, the correlation calculation unit 103 extracts the change in the feature amount with respect to the EGFR in the state where U0126 is not added, for each of the plurality of types of feature amounts of the constituent elements.
  • the constituent element is any one of MEK, MAPK, and Raf constituting the cell CL1 which is a control cell.
  • the correlation calculation unit 103 extracts the change in the feature amount by arranging the feature amounts in time series for each of the K types of feature amounts calculated by the feature amount calculation unit 102 from the cell image obtained by imaging the cell CL1.
  • the correlation calculation unit 103 calculates the correlation between the change in the feature amount with respect to the stimulus with the inhibitor added and the change in the feature amount with respect to the stimulus without the inhibitor added for each of the plurality of types of the feature amount. Is calculated (step S603). That is, for MEK, the correlation calculation unit 103 changes the characteristic amount MEK-i-d with respect to the EGFR with U0126 added, and changes the characteristic amount MEK-i-c with respect to the EGFR without U0126 added. The correlation between and is calculated for each of a plurality of types of feature quantities.
  • the correlation calculation unit 103 determines the change in the characteristic amount MAPK-i-d with respect to the EGFR with U0126 added and the change in the characteristic amount MAPK-i-c with respect to the EGFR without U0126 added. The correlation between them is calculated for each of a plurality of types of feature quantities.
  • the correlation calculation unit 103 determines the change in the characteristic amount Raf-i-d with respect to the EGFR with U0126 added and the change in the characteristic amount Raf-i-c with respect to the EGFR without U0126 added. The correlation between them is calculated for each of a plurality of types of feature quantities.
  • the correlation calculation unit 103 supplies the calculated result to the feature amount correlation attribute calculation unit 104.
  • FIG. 8 is a diagram showing an example of changes in the i-th feature amount of the MEK of this embodiment.
  • the change of the i-th feature amount of MEK is, for example, a change with time of the brightness of MEK.
  • a graph XA2 is a graph showing changes in the i-th feature amount MEK-i-d of MEK with respect to EGFR in the state where U0126 is added.
  • the graph XA1 is a graph showing the change of the i-th feature amount MEK-ic of MEK with respect to EGFR in the state where U0126 is not added.
  • the change in the i-th feature amount shown by these graphs XA1 and XA2 is extracted by the correlation calculation unit 103.
  • the graph XA1 and the graph XA2 are similar in shape. Therefore, in MEK, there is a large correlation between the change in the characteristic amount MEK-i-d with respect to the EGFR with U0126 added and the change in the characteristic amount MEK-i-c with respect to the EGFR without the addition of U0126. ..
  • the correlation calculation unit 103 changes the i-th feature amount MEK-ic of MEK without U0126 addition by the graphical lasso method and the i-th feature amount MEK-i of MEK with U0126 addition. Calculate the correlation with the change in -d.
  • the correlation is calculated as a partial correlation coefficient.
  • the i-th feature amount MEK-i-c change of MEK calculated by the correlation calculation unit 103 without U0126 addition and the i-th change of MEK with U0126 addition are calculated.
  • the correlation with the change in the feature amount MEK-id is larger than the correlation value 0.7.
  • the threshold value of the correlation value is preferably 0.7 or more as a measure of strong correlation. Moreover, the threshold value of the correlation value may be a value other than 0.7.
  • the regularization parameter determined by the correlation calculation unit 103 is a regularization parameter used in the Graphical Lasso method.
  • the Graphical Lasso method is an efficient algorithm for estimating an accuracy matrix from a Gaussian model with L1 regularization. For example, in JEROME FRIEDMAN, TREVOR HASTIE, and ROBERT TIBSHIRANI, Biostatistics (2008), 9, 3 432-441, "Sparse inverse covariance esteation withthera" is described.
  • the value of the regularization parameter used in the Graphical Lasso method is larger than 0 and smaller than 1.
  • the correlation is calculated by, for example, Pearson product moment correlation.
  • FIG. 9 is a diagram showing an example of changes in the j-th feature amount of MAPK of this embodiment.
  • the change in the j-th feature amount of MAPK is, for example, the change over time of the area in the cell image of MAPK.
  • a graph YB2 is a graph showing changes in the j-th feature amount MAPK-jd of MAPK with respect to EGFR in the state where U0126 is added.
  • the graph YB1 is a graph showing changes in the j-th feature amount MAPK-jc of MAPK with respect to EGFR in the state where U0126 is not added.
  • the j-th feature amount MAPK-j-c of MAPK does not show a change with respect to EGFR.
  • the change in the feature amount indicated by the graph YB1 and the graph YB2 is extracted by the correlation calculation unit 103.
  • the graph YB1 and the graph YB2 are not similar in shape. Therefore, in MAPK, the correlation between the change in the feature amount MAPK-j-d with respect to the EGFR with U0126 added and the change in the feature amount MAPK-j-c with respect to the EGFR without U0126 added is small. ..
  • the correlation calculation unit 103 changes the j-th feature amount MAPK-j ⁇ d of MAPK with U0126 added by the graphical lasso method and the j-th feature amount MAPK-j of MAPK without U0126 added. Calculate the correlation with the change in -c.
  • the correlation with the change in the feature amount MAPK-jc is smaller than the correlation value 0.7.
  • the correlation calculation unit 103 with respect to the characteristic amount of the first element constituting the cell, the first change with respect to the stimulus in the state where the inhibitor is added, and the characteristic amount of the first element constituting the cell,
  • the correlation between the second change with respect to the stimulus in the state in which the inhibitor is not added is calculated for each of the plurality of types of feature quantities. Therefore, the correlation calculation unit 103 can determine the effect of the inhibitor on the feature amount by using the correlation.
  • the change of the feature amount with respect to the stimulus with the inhibitor added is referred to as a first change
  • the change of the feature amount with respect to the stimulus without the addition of the inhibitor is referred to as a second change.
  • the feature amount correlation attribute calculation unit 104 changes the feature amount of the first element forming the cell calculated by the correlation calculation unit 103 with respect to the stimulus in the state where the inhibitor is added, and the first element forming the cell.
  • the feature amount correlation attribute between the point of action of the inhibitor and the constituent element A is calculated from the change in the feature amount with respect to the stimulus in the state where the inhibitor is not added (step S604).
  • the feature quantity correlation attribute calculation unit 104 calculates the feature quantity correlation attribute between the point of action on which the inhibitor acts and the feature quantity of the constituent element 1.
  • the correlation between the change in the feature amount of the first element calculated by the correlation calculation unit 103 in the state where the inhibitor is added and the change in the feature amount of the first element when the inhibitor is not added Calculate the correlation value.
  • the feature amount correlation attribute calculation unit 104 calculates the feature amount correlation attribute of the feature amount for which the calculated correlation value is larger than 0.7 as the upstream.
  • the feature amount correlation attribute calculation unit 104 calculates the feature amount correlation attribute of the feature amount for which the calculated correlation value is smaller than 0.7 as the downstream. That is, the characteristic amount correlation attribute calculation unit 104 calculates the characteristic amount correlation attribute based on the correlation value between the first change and the second change.
  • the feature amount correlation attribute calculation unit 104 calculates the feature amount correlation attribute based on the magnitude of the correlation value between the first change and the second change. Further, the characteristic amount correlation attribute calculation unit 104 may extract a predetermined characteristic amount correlation from a plurality of types of characteristic amounts by using the correlation value between the first change and the second change. For example, the feature amount correlation attribute calculation unit 104 may extract the type of feature amount having a correlation value between the first change and the second change for each of a plurality of types of feature amounts that is greater than 0.7.
  • the feature quantity correlation attribute calculation unit 104 determines the i-th feature quantity of MEK as the change in the feature quantity MEK-ic and the change in feature quantity MEK-i-. It is determined that the correlation value with the change in d is a feature amount larger than a predetermined value.
  • the feature value correlation attribute calculation unit 104 determines that the change in the feature value MEK-i-d and the change in the feature value MEK-i-c are the feature values larger than a predetermined size, MEK is U0126. It is determined to be upstream of the point of action. As shown in FIG. 9, the change of the j-th feature amount MAPK-j-c of MAPK without U0126 addition and the j-th feature amount MAPK-j-d of MAPK with U0126 addition. Of the MAPK, the feature quantity correlation attribute calculation unit 104 determines the j-th feature quantity of MAPK as the change of the feature quantity MAPK-ic and the feature quantity MAPK-id.
  • the feature value correlation attribute calculation unit 104 determines that the change in the feature value MAPK-i-d and the change in the feature value MAPK-i-c are the feature values larger than a predetermined size, and thus MAPK is U0126. It is determined to be downstream of the point of action. In this way, the feature amount correlation attribute calculation unit 104 makes a determination for each of a plurality of types of feature amounts of the constituent elements of the cell CL. That is, the feature amount correlation attribute calculation unit 104 determines, for the plurality of types of feature amounts of the first element constituting the cell, the first change with respect to the stimulus with the inhibitor added and the state without the inhibitor added.
  • the characteristic amount correlation attribute between the second element different from the first element and the first element is calculated for each of a plurality of types of characteristic amounts.
  • the feature amount correlation attribute calculation unit 104 supplies the determination result to the ratio calculation unit 105.
  • the ratio calculation unit 105 determines that the correlation value between the change with respect to the stimulus in the state where the inhibitor is added and the change with respect to the stimulus in the state where the inhibitor is not added is more than a predetermined value among the plurality of types of the feature amount.
  • the types of large feature amounts and the types of feature amounts having a correlation value smaller than a predetermined size are totaled (step S605).
  • the ratio calculation unit 105 totals based on the calculation result of the feature amount correlation attribute calculation unit 104.
  • the correlation between the change with respect to the stimulus in the state where the inhibitor is added and the change with respect to the stimulus in the state where the inhibitor is not added which is calculated by the ratio calculation unit 105, has a correlation value larger than a correlation value of 0.7.
  • the number of types is called the upstream determination number. Moreover, the correlation between the change with respect to the stimulus with the inhibitor added and the change with respect to the stimulus without the inhibitor, which is calculated by the ratio calculation unit 105, is smaller than the correlation value 0.7. The number of types is called the downstream determination number.
  • the ratio calculation unit 105 calculates the ratio of the feature amount correlation attribute in the feature amount from the feature amount correlation attribute for each type of feature amount based on the calculation result of the feature amount correlation attribute calculation unit 104. (Step S606).
  • the ratio calculation unit 105 calculates an upstream / downstream index as a ratio of the characteristic amount correlation attribute.
  • the ratio calculation unit 105 supplies the calculated upstream / downstream index to the determination unit 106.
  • the ratio calculation unit 105 calculates the upstream / downstream index based on the equation (1).
  • the number Ind represents an upstream / downstream index
  • the number N U represents an upstream determination number
  • the number N D represents a downstream determination number.
  • the number of upstream determinations is the number of types of feature quantities determined to be upstream.
  • the downstream determination number is the number of types of feature quantities determined to be downstream.
  • the upstream / downstream index is an amount obtained by dividing the difference between the upstream determination number and the downstream determination number by the sum of the upstream determination number and the downstream determination number, as shown in the above equation (1). That is, the upstream / downstream index is, of a plurality of types of the feature amount, a change with respect to the stimulus calculated by the correlation calculation unit 103 in the state where the inhibitor is added, and a change with respect to the stimulus in the state where the inhibitor is not added. It is the ratio of the types of feature quantities whose correlation value is larger than a predetermined value.
  • the ratio calculation unit 105 determines the number of types of feature values whose correlation value between the change with respect to the stimulus with the inhibitor added and the change with respect to the stimulus without the inhibitor added is larger than a predetermined magnitude. And the difference in the number of feature quantities from the number of types of feature quantities having a correlation value smaller than a predetermined magnitude.
  • the correlation value between the change with respect to the stimulus with the inhibitor added and the change with respect to the stimulus without the inhibitor added is the number of types of feature values larger than a predetermined magnitude, and the correlation value. Is calculated as the sum of the number of feature quantities and the number of types of feature quantities smaller than a predetermined size.
  • the ratio calculation unit calculates a ratio by dividing the calculated difference in the number of feature amounts by the sum of the number of feature amounts. Therefore, the ratio calculation unit 105 calculates the upstream / downstream index based on the difference between the upstream determination number and the downstream determination number. That is, the ratio calculation unit 105 determines the number of types of feature values having a correlation value between the change with respect to the stimulus with the inhibitor added and the change with respect to the stimulus without the inhibitor being larger than a predetermined magnitude. And a feature whose correlation value calculated by the correlation calculation unit 103 is larger than a predetermined size among a plurality of types of feature values based on the difference between the number of types of feature values whose correlation value is smaller than a predetermined size. Calculate the percentage of quantity type.
  • the ratio calculation unit 105 determines the number of types of feature values having a correlation value between a change with respect to the stimulus with the inhibitor added and a change with respect to the stimulus without the inhibitor being larger than a predetermined magnitude. May be calculated by the sum of the number of types of feature quantities having a correlation value larger than a predetermined size and the number of types of feature quantities having a correlation value smaller than a predetermined size. In addition, the ratio calculation unit 105 determines the number of types of feature values whose correlation value between the change with respect to the stimulus with the inhibitor added and the change with respect to the stimulus without the inhibitor is smaller than a predetermined magnitude. May be calculated by the sum of the number of types of feature quantities having a correlation value larger than a predetermined size and the number of types of feature quantities having a correlation value smaller than a predetermined size.
  • the ratio calculation unit 105 changes the stimulus calculated by the correlation calculation unit 103 with respect to the stimulus in the state where the inhibitor is added and the change with respect to the stimulus in the state where the inhibitor is not added, among the plurality of types of the feature amount.
  • the ratio of the types of feature quantities whose correlation value between and is larger than a predetermined size is calculated.
  • the ratio calculation unit 105 uses the number of types of feature quantities whose correlation value is larger than a predetermined magnitude and the number of types of feature quantities whose correlation value is smaller than a predetermined magnitude to determine a plurality of feature quantities.
  • the ratio of the types of feature values for which the correlation value calculated by the correlation calculation unit 103 is larger than a predetermined size is calculated.
  • the ratio calculation unit 105 determines that the correlation value between the change with respect to the stimulus in the state where the inhibitor is added and the change with respect to the stimulus in the state where the inhibitor is not added is a predetermined value among the plurality of types of the feature amount.
  • the upstream / downstream index is calculated on the basis of the result of totaling the types of feature amounts larger than the size and the types of feature amounts having a correlation value smaller than a predetermined size.
  • the result of aggregating the type of the feature amount having a correlation value larger than a predetermined size and the type of the feature amount having a correlation value smaller than the predetermined size is the feature amount correlation attribute calculation. It is based on the result calculated by the unit 104.
  • the ratio calculation unit 105 uses the result calculated by the feature amount correlation attribute calculation unit 104 to select, from among the plurality of types of feature amounts, the type of feature amount for which the correlation value calculated by the correlation calculation unit 103 is larger than a predetermined size. Calculate the ratio of.
  • the correlation calculation unit 103 calculates the correlation between the constituent elements in the state in which the inhibitor is not added before starting the processing of step S600 in FIG. 7, and the determination unit 150 in the state in which the inhibitor is not added.
  • the component having a positive correlation between the components may be the target of the processing in step S600 and the subsequent steps.
  • the correlation between the constituent elements in the state where the inhibitor is not added is, for example, the change of the i-th feature amount Aic of the constituent element A with respect to the stimulus in the state where the inhibitor is not added, and the constituent element. It is the correlation between the i-th characteristic amount Bic of B and the change to the stimulus in the state where the inhibitor is not added.
  • the type of the characteristic amount Aic and the type of the characteristic amount Bic are the same.
  • the correlation calculation unit 103 calculates the correlation between the constituent elements in the state in which the inhibitor is not added by the graphical lasso method.
  • the correlation between the constituent elements without adding the inhibitor is calculated as a partial correlation coefficient.
  • the correlation calculation unit 103 based on the calculation result of the correlation between the constituents in the state where the inhibitor is not added, the set of constituents in which the correlation between the constituents in the state where the inhibitor is not added is positive, and the suppression It is determined to be a set of constituents in which the correlation between the constituents in the state where the agent is not added is negative. For example, the correlation between the constituent elements A and B in the state where the inhibitor is not added is positive, and between the constituent elements A and C in the state where the inhibitor is not added.
  • the correlation calculation unit 103 determines that the constituent element A and the constituent element B are a set of constituent elements in which the correlation between the constituent elements in the state where the inhibitor is not added is positive, and the constituent element C Is determined to be a set of constituents having a negative correlation between constituents in the state where no inhibitor is added.
  • the determination unit 150 sets the constituent element A and the constituent element B as the processing targets after step S600.
  • the ratio calculation unit 105 calculates the upstream / downstream determination number based on the correlation between changes with respect to the stimuli in the state in which the inhibitor is not added for the types of the characteristic amounts of the constituent elements. May be weighted.
  • the correlation between changes with respect to stimuli in the state where no inhibitor is added for the type of the feature amount of the constituent element means, for example, that the inhibitor of the i-th feature value Aic of the constituent element A is not added. It is the correlation between the change with respect to the stimulus in the state and the change with respect to the stimulus in the state in which the inhibitor of the jth feature amount Ajc of the component A is not added.
  • the type of the characteristic amount Aic is different from the type of the characteristic amount Ajc.
  • Weighting means multiplying the upstream determination number and the downstream determination number by a predetermined value.
  • the correlation calculation unit 103 calculates the correlation between the changes with respect to the stimulus in the state in which the inhibitor is not added for the types of the feature amounts of the constituent elements.
  • the calculated correlation between changes with respect to the stimulus without adding the inhibitor is supplied to the ratio calculation unit 105.
  • the correlation calculation unit 103 calculates the correlation between the changes with respect to the stimulus in the state in which the inhibitor is not added, regarding the type of the characteristic amount of the constituent element by the graphical lasso method.
  • this correlation is calculated as a partial correlation coefficient.
  • the ratio calculation unit 105 determines that the larger the correlation between the changes with respect to the stimulus in the state in which the inhibitor for the type of the feature amount type of the component calculated by the correlation calculation unit 103 is not added, for the set of the feature amount type of the component elements, , Multiply the upstream determination number and the downstream determination number by a large positive value. In this case, the ratio calculation unit 105 determines whether the i-th feature amount Aic and the j-th feature amount Ajc of the constituent element A are different from each other with respect to the stimulus without adding the inhibitor.
  • the proportion calculation unit 105 determines that the number of upstream determinations and the number of downstream determinations are smaller as the correlation between changes with respect to the stimulus in the state in which the inhibitor is not calculated, which is calculated by the correlation calculation unit 103, is smaller for the set of the types of the characteristic amounts of the constituent elements. Multiply a number by a small positive value.
  • the ratio calculation unit 105 determines whether the i-th feature amount Aic and the j-th feature amount Ajc of the constituent element A are different from each other with respect to the stimulus without adding the inhibitor. As the correlation is smaller, the upstream determination number and the downstream determination number corresponding to the i-th feature amount Aic and the j-th feature amount Ajc of those constituent elements A are multiplied by smaller positive values. . The ratio calculation unit 105 multiplies the upstream determination number and the downstream determination number by a positive value, and then calculates the upstream / downstream index based on the equation (1).
  • the correlation calculation unit 103 adds the inhibitor to the type of the feature quantity of which the correlation value between changes with respect to the stimulus in the state of not adding the inhibitor of the type of the feature quantity of the constituent elements is equal to or larger than a predetermined magnitude.
  • the correlation between the change with respect to the stimulation and the change with respect to the stimulation without the addition of the inhibitor may be calculated.
  • the correlation calculation unit 103 determines the type of the feature amount for which the correlation value between the changes with respect to the stimulus in the state in which the inhibitor is not added is equal to or larger than a predetermined value, before executing the process of step S603.
  • the correlation calculation unit 103 determines the type of the feature amount for which the correlation value between the changes with respect to the stimulus in the state in which the inhibitor is not added is equal to or larger than a predetermined value, in advance, in the experimental condition storage unit 301.
  • the information may be used for the determination.
  • step S603 the correlation calculation unit 103 calculates the correlation between the change in the feature amount with respect to the stimulus with the inhibitor added and the change in the feature amount with respect to the stimulus without the inhibitor added. It is calculated for each type of feature quantity in which the correlation value between changes with respect to the stimulus in the state where no inhibitor is added is equal to or larger than a predetermined value.
  • the subsequent processing in steps S604, S605, and S606 is executed for the types of feature values for which the correlation value between changes with respect to the stimulus in the state in which the inhibitor is not added is equal to or larger than a predetermined value.
  • the feature amount correlation attribute calculation unit 104 changes the feature amount with respect to the stimulus calculated by the correlation calculation unit 103 in the state where the inhibitor is added, and the feature amount with respect to the stimulus in the state where the inhibitor is not added.
  • the feature value having a correlation value larger than a predetermined value with respect to the change the change of the feature value with respect to the stimulus calculated by the correlation calculation unit 103 in the state where the inhibitor is added, and the state where the inhibitor is not added.
  • the type of feature quantity having a correlation value smaller than a predetermined magnitude with respect to the change of the feature quantity with respect to the stimulus, and the feature that the correlation value between the changes with respect to the stimulus without the addition of the inhibitor is not less than the predetermined magnitude.
  • step S605 the ratio calculation unit 105 selects, for the stimulus in the state where the inhibitor is added, among the types of feature values in which the correlation value between changes with respect to the stimulus in the state where the inhibitor is not added is a predetermined value or more.
  • the type of feature whose correlation value between the change of the feature and the change of the feature with respect to the stimulus without addition of the inhibitor is larger than a predetermined size, and the feature with respect to the stimulus with the inhibitor added
  • the type of feature amount having a correlation value smaller than a predetermined magnitude between the change in the feature amount and the change in the feature amount with respect to the stimulus without adding the inhibitor.
  • step S606 the ratio calculation unit 105 selects, for the stimulus in the state where the inhibitor is added, among the types of feature values in which the correlation value between changes with respect to the stimulus in the state where the inhibitor is not added is a predetermined value or more. Correlation value between the change of the feature amount and the change of the feature amount to the stimulus without the addition of the inhibitor is larger than a predetermined size, the number of types of the feature amount and the stimulus with the inhibitor added. On the basis of the difference between the change in the feature amount and the change in the feature amount with respect to the stimulus in the state where no inhibitor is added, the correlation calculation unit 103 The correlation value between the change in the feature amount for the stimulus with the inhibitor added and the change in the feature amount for the stimulus without the inhibitor added is a predetermined value. Large feature amount To calculate the proportion of type.
  • the correlation value between the changes with respect to the stimulus in the state in which the inhibitor is not added, calculated by the correlation calculation unit 103 has a predetermined magnitude.
  • a value of zero may be multiplied with respect to a set of types of feature amounts of constituent elements smaller than the size.
  • the ratio calculation unit 105 may calculate the upstream / downstream index based on the correlation between changes with respect to the stimulus with respect to the type of the characteristic amount of the component without the addition of the inhibitor.
  • the determination unit 106 determines the correlation attribute of whether the constituent element is upstream or downstream of the action point of the inhibitor (step S607). That is, the determination unit 106 determines whether MEK, MAPK, or Raf is upstream or downstream of the point of action of U0126, respectively. Here, the determination unit 106 uses the upstream / downstream index calculated by the ratio calculation unit 105 to determine whether MEK, MAPK, or Raf is upstream or downstream of the point of action of U0126. The determination unit 106 determines that the component whose upstream / downstream index is close to -1 is downstream of the point of action of U0126.
  • the upstream / downstream index being close to ⁇ 1.00 means that the absolute value of the difference between the upstream / downstream index and ⁇ 1.00 is smaller than a predetermined value.
  • the predetermined value is, for example, 0.10.
  • the determination unit 106 determines that the component whose upstream / downstream index is close to 1.00 is not downstream from the point of action of U0126.
  • the determination unit 106 determines whether or not the constituent element that is determined to be not downstream of the point of action of U0126 is upstream of the point of action, based on the signal pathway information stored in the signal pathway storage unit 302.
  • the upstream / downstream index being close to 1.00 means that the absolute value of the difference between the upstream / downstream index and 1.00 is smaller than a predetermined value.
  • the predetermined value is, for example, 0.10.
  • the determination unit 106 determines that MEK and Raf are upstream of the point of action of U0126.
  • the determination unit 106 determines that MAPK is downstream of the point of action of U0126.
  • the determination unit 106 can determine whether the signal pathway information is upstream or downstream of the point of action. For example, the determination unit 106 may determine that the component whose upstream / downstream index is close to 1.00 is upstream of the point of action of U0126, not based on the signal pathway information.
  • the correlation calculation unit 103 calculates the correlation of the component with respect to the stimulus.
  • the feature amount correlation attribute calculation unit 104 extracts, from a plurality of types of constituent elements, constituent elements having a calculated correlation value higher than a predetermined threshold value.
  • the determination unit 106 calculates an upstream / downstream index for the extracted constituent element, and determines upstream and downstream of the action point of the drug.
  • the ratio calculation unit 105 weights the upstream determination number and the downstream determination number
  • the correlation value between the changes with respect to the stimulus in the state in which the inhibitor is not added, calculated by the correlation calculation unit 103 has a predetermined magnitude
  • the value of zero was multiplied for the set of feature quantity types of the constituent elements smaller than the size.
  • the determination unit 106 may determine that the component whose upstream / downstream index is close to 1.00 is upstream of the point of action of U0126.
  • the determination unit 106 may determine that the feature amount having a negative upstream / downstream index is downstream of the point of action of U0126.
  • the correlation calculation unit 103 calculates the correlation between the constituent elements in the state where the inhibitor is not added.
  • the feature value correlation attribute calculation unit 104 extracts a component whose calculated correlation value has a correlation value larger than a predetermined value.
  • the feature amount correlation attribute calculation unit 104 uses the change of the feature amount when the inhibitor is added and the change of the feature amount when the inhibitor is not added, with respect to the extracted constituent elements, to calculate the correlation of the feature amounts. calculate.
  • the ratio calculation unit 105 calculates the upstream / downstream index.
  • the ratio calculation unit 105 can calculate a component having a high upstream index as a component close to the response timing of the action point of the inhibitor.
  • the response timing of the inhibitor with respect to the stimulus can be used as a reference and divided into components that are earlier than the response timing and components that are later than the response timing. it can.
  • the determination unit 106 also estimates the order of the response timing of the inhibitor based on the upstream / downstream index with respect to the component that is earlier than the response timing of the inhibitor, for example. In this case, the determination unit 106 estimates that the upstream / downstream index having an upstream / downstream index close to 1.0 is closer to the response timing of the action point of the inhibitor, and determines the response timing of the plurality of constituent elements. Estimate the order. As a result, the determination device 10 can estimate the signal pathway to the stimulus.
  • the determination unit 106 may determine that the constituent element having a positive upstream / downstream index is upstream of the point of action of U0126.
  • the determination unit 106 may determine that the constituent element having a negative upstream / downstream index is downstream of the point of action of U0126.
  • determining whether any of MEK, MAPK, and Raf is upstream or downstream of the point of action of U0126 depends on the response of the reaction of U0126 to EGFR and any of MEK, MAPK, and Raf to EGFR. The answer is to determine the order. Therefore, the determination unit 106 determines the order of the response of the reaction of the inhibitor to the stimulus and the response of the constituent element to the stimulus, using the ratio calculated by the ratio calculation unit 105.
  • FIG. 10 is a diagram showing an example of the determination result of the determination unit 106 of this embodiment.
  • the determination unit 106 determines that MEK is not downstream because the upstream / downstream index is 1.00 and is close to 1.00.
  • the determination unit 106 determines that MAPK is downstream because the upstream / downstream index is ⁇ 1.00, which is close to ⁇ 1.00.
  • the determining unit 106 determines that the EGFR is neither upstream nor downstream because the upstream / downstream index is 0.21 and is not close to 1.00.
  • the upstream / downstream index of Raf is 0.95. Therefore, the determination unit 106 determines that Raf is not downstream.
  • the determination unit 106 supplies the determination result to the comparison unit 107, the signal pathway generation unit 201, and the component element order graph generation unit 202.
  • the determination unit 150 ends the process of determining, for each component, whether the component is upstream or downstream of the action point of the inhibitor (step S608). That is, the determination unit 150 ends the process of determining whether each of MEK, MAPK, and Raf is upstream or downstream of the point of action of U0126.
  • the comparing unit 107 identifies, for each constituent element, a constituent element near the action point of the inhibitor based on the upstream / downstream index calculated by the ratio calculating unit 105 (step S609). For example, if it is a constituent element near the action point of the inhibitor, many feature amounts are suppressed along with the action of the inhibitor, and it is considered that the upstream / downstream index indicates downstream. That is, the comparison unit 107 specifies the constituent elements near the point of action of U0126 for each of MEK, MAPK, and Raf based on the upstream / downstream index calculated by the ratio calculation unit 105.
  • the comparison unit 107 uses the result determined by the determination unit 106 to determine the first component that is faster than the response of the reaction of U0126 to EGFR and the second component that is later than the response of the reaction of U0126 to the EGFR. Identify the components. That is, the determination device 10 identifies the second element from the correlation attribute determined by the determination unit 106.
  • the fact that the constituent element is faster than the response of the reaction of the inhibitor to the stimulus means that the constituent element is upstream of the point of action of the inhibitor.
  • a component is slower than the response of the inhibitor's response to a stimulus is that the component is downstream of the point of action of the inhibitor.
  • the comparison unit 107 regards the first constituent element upstream of the point of action of U0126 and the third constituent element upstream of the point of action of U0126 as the first constituent element and the third constituent element. Compare which is closer to the point of action of U0126.
  • the first component is, for example, MEK
  • the third component is, for example, Raf.
  • the comparing unit 107 determines that one of the first constituent element and the third constituent element that has a smaller difference between the upstream and downstream indexes and 1.00 is closer to the point of action of U0126. In this way, the comparison unit 107 uses the ratio calculated by the ratio calculation unit 105 to determine whether the response of the first component and the response of the third component are higher than the response of the reaction of the inhibitor to the stimulus.
  • the feature amount correlation attribute calculation unit 104 determines the first change with respect to the stimulus in the state in which the inhibitor is added for the plurality of feature amounts of the third element different from the first element forming the cell and the inhibitor.
  • the feature amount correlation attribute between the second element and the first element is calculated for each of a plurality of types of feature amounts by using the second change with respect to the stimulus in the state of not adding.
  • the comparing unit 107 calculates the feature amount correlation attribute for each of the plurality of types of feature amounts of the first element with respect to the second element, and the plurality of types of feature amounts of the third element with respect to the second element, which are calculated by the feature amount correlation attribute calculating unit 104.
  • the order of response to the stimulus of the first element and the order of response to the stimulus of the second element are compared based on the feature amount correlation attribute for each.
  • the reaction of the inhibitor acting on the stimulus is an example of the second element
  • the first component is an example of the first element
  • the third component is an example of the third element.
  • the comparison unit 107 may compare the order of MEK response and the order of EGFR response to determine which of MEK and EGFR is closer to the point of action of U0126.
  • the comparison unit 107 supplies the identified result to the signal pathway generation unit 201 and the component element order graph generation unit 202.
  • the signal pathway generation unit 201 and the component element order graph generation unit 202 respectively generate images to be displayed on the display unit 30 (step S70).
  • the signal pathway generation unit 201 generates the signal pathway SP as an image to be displayed on the display unit 30.
  • the constituent element order graph generation unit 202 generates a constituent element order graph EG as an image to be displayed on the display unit 30.
  • the component element order graph generation unit 202 generates the component element order graph EG based on the determination result of the determination unit 106 and the comparison result of the comparison unit 107.
  • a specific example of the component element order graph EG will be described with reference to FIGS. 11 and 12.
  • FIG. 11 is a diagram showing a first example of the component element order graph EG of this embodiment.
  • icons indicating MEK, EGFR, and MAPK are displayed at positions corresponding to the respective upstream / downstream indexes with respect to the number line indicating the upstream / downstream indexes.
  • the constituent element order graph generation unit 202 arranges the MEKs that the determination unit 106 has determined to be upstream at the position corresponding to the upstream of the number line.
  • the constituent element order graph generation unit 202 arranges the MAPKs that the determination unit 106 has determined to be downstream at a position corresponding to the downstream of the number line.
  • the constituent element order graph generation unit 202 arranges the EGFR, which the determination unit 106 has determined to be neither upstream nor downstream, at a position corresponding to the origin of the number line.
  • FIG. 12 is a diagram showing a second example of the component element order graph EG of this embodiment.
  • icons indicating MEK, EGFR, and MAPK are displayed at positions corresponding to the respective upstream / downstream indexes with respect to the number line indicating the upstream / downstream indexes.
  • the upstream / downstream index is closer to the origin as it is closer to 1.00, and the upstream / downstream index is farther from the origin as to be far from the origin. ..
  • the upstream / downstream index corresponds to a position closer to the origin as it is closer to ⁇ 1.00, and the upstream / downstream index is farther from ⁇ 1.00 to a position farther from the origin. Correspond to.
  • the component element order graph generation unit 202 arranges the MEKs that the determination unit 106 has determined to be upstream in the vicinity of the origin on the upper side of the number line.
  • the constituent element order graph generation unit 202 arranges the MAPKs that the determination unit 106 has determined to be downstream in the vicinity of the origin on the lower side of the number line.
  • the constituent element order graph generation unit 202 arranges the EGFR, which the determination unit 106 has determined to be neither upstream nor downstream, at a position apart from the origin on the upper side of the number line.
  • the component element order graph generation unit 202 may emphasize and display the icon of the component element whose upstream / downstream index is close to 1.00 or ⁇ 1.00. Displaying an icon in an emphasized manner here means, for example, changing at least one of the saturation, brightness, transparency, thickness, shape, and size of the icon.
  • the icons used by the component element order graph generation unit 202 to indicate MEK, EGFR, and MAPK are examples.
  • the constituent element order graph generation unit 202 may use symbols or characters instead of icons, or may use two or more of icons, symbols, and characters in combination.
  • the signal pathway generation unit 201 generates the signal pathway SP based on the judgment result of the judgment unit 106, the comparison result of the comparison unit 107, and the signal pathway information stored in the signal pathway storage unit 302. In order to generate the signal pathway SP, in addition to the judgment result of the judgment unit 106 and the comparison result of the comparison unit 107, signal pathway information is necessary.
  • FIG. 13 is a diagram showing an example of the signal pathway SP of this embodiment.
  • the signal pathway generation unit 201 arranges the components Q1 to Q10 in the region indicating the cell matrix CY1 and the nucleus N1 based on the signal pathway information.
  • the constituent element Q5 corresponds to Raf
  • the constituent element Q7 corresponds to MEK
  • the constituent element Q9 corresponds to MAPK.
  • the signal pathway generation unit 201 arranges the component Q5 as the determination result of the determination unit 106 and the comparison result of the comparison unit 107 by using Raf being upstream from the point of action of U0126.
  • the signal pathway generation unit 201 arranges the component Q7 by using the fact that MEK is upstream of the point of action of U0126 as the determination result of the determination unit 106 and the comparison result of the comparison unit 107. Further, the signal pathway generation unit 201 arranges the component Q9 by using the fact that MAPK is downstream of the point of action of U0126 as the determination result of the determination unit 106 and the comparison result of the comparison unit 107. From the determination result of the determination unit 106, it is found that the action point of U0126 is between MEK and MAPK in the signal pathway SP.
  • the signal pathway generation unit 201 may draw a line between the icons of the components Q1 to Q10 in the signal pathway SP.
  • the line may have, for example, an arrowhead, a letter, or a circle attached to its tip.
  • the signal pathway generation unit 201 may emphasize and display the icon of the component in the signal pathway SP whose upstream / downstream index is close to 1.00 or ⁇ 1.00. Displaying an icon in an emphasized manner here means, for example, changing at least one of the saturation, brightness, transparency, thickness, shape, and size of the icon.
  • the signal pathway generation unit 201 supplies the generated signal pathway SP to the result output unit 400.
  • the result output unit 400 acquires the signal pathway SP from the signal pathway generation unit 201.
  • the constituent element order graph generation unit 202 supplies the generated constituent element order graph EG to the result output unit 400.
  • the result output unit 400 acquires the constituent element order graph EG from the constituent element order graph generation unit 202.
  • the result output unit 400 causes the display unit 30 to display the acquired signal pathways SP and the component element order graph EG (step S80).
  • the constituent element order graph EG is a graph in which constituent elements to be calculated by the ratio calculation unit 105 are arranged based on the upstream / downstream indexes calculated by the ratio calculation unit 105. Further, the constituent element order graph EG is a graph in which constituent elements are arranged on the basis of the reaction of the inhibitor based on the upstream / downstream index calculated by the ratio calculation unit 105. Therefore, the display unit 30 displays the elements configuring the cell CL to be calculated by the ratio calculation unit 105 side by side based on the ratio calculated by the ratio calculation unit 105. The display unit 30 further displays, based on the ratio calculated by the ratio calculation unit 105, the elements constituting the cells side by side with reference to the reaction of the inhibitor. That is, the display unit 30 displays the first element and the second element based on the order of response to the stimulus.
  • the determination device 10 includes the correlation attribute calculation unit and the determination unit 106.
  • the feature quantity correlation attribute calculation unit 104 of the present exemplary embodiment is an example of a correlation attribute calculation unit.
  • the correlation attribute calculation unit has a first change with respect to the stimulus in the state where the inhibitor is added, and a second change with respect to the stimulus in the state where the inhibitor is not added, with respect to a plurality of types of characteristic amounts of the first element constituting the cell. Using, the feature amount correlation attribute between the second element different from the first element and the first element is calculated for each of a plurality of types of feature amounts.
  • the determination unit 106 determines the correlation attribute between the second element and the first element by using the feature amount correlation attribute for each of the plurality of types of feature amounts calculated by the correlation attribute calculation unit. With this configuration, the determination apparatus 10 according to the present embodiment can determine the correlation attribute between the response of the second element to the stimulus and the response of the constituent element of the cell CL to the stimulus.
  • the correlation attribute is the order of the response to the stimulus of the first element and the response to the stimulus of the second element.
  • the feature quantity correlation attribute is the order of the response to the stimulus of the feature quantity of the first element and the response to the stimulus of the feature quantity of the second element.
  • the response of the second element to the stimulus is obtained by using the order of the response of the feature quantity of the first element to the stimulus and the response of the feature quantity of the second element to the stimulus.
  • the correlation attribute with the response of the component of the cell CL to the stimulus can be determined.
  • the correlation attribute calculation unit calculates the feature amount correlation attribute based on the correlation value between the first change and the second change.
  • the correlation between the response of the second element to the stimulus and the response of the constituent element of the cell CL to the stimulus is based on the correlation value between the first change and the second change.
  • the attributes can be determined.
  • the correlation attribute calculation unit calculates the feature amount correlation attribute based on the magnitude of the correlation value between the first change and the second change.
  • the response of the second element to the stimulus and the response of the constituent element of the cell CL to the stimulus are based on the magnitude of the correlation value between the first change and the second change.
  • the correlation attribute with can be determined.
  • the correlation attribute calculation unit causes the first change with respect to the stimulus in the state in which the inhibitor is added, for the plurality of feature amounts of the third element different from the first element forming the cell. And the second change with respect to the stimulus in the state in which the inhibitor is not added, the characteristic amount correlation attribute between the second element and the first element is calculated for each of a plurality of types of characteristic amounts.
  • the comparison unit 107 calculates the feature amount correlation attribute for each of the plurality of types of feature amounts of the first element with respect to the second element, and the feature for each of the plurality of types of feature amounts of the third element for the second element, which is calculated by the correlation attribute calculation unit.
  • the order of response of the first element to the stimulus and the order of response of the third element to the stimulus are compared based on the quantity correlation attribute.
  • the determination device 10 can compare the order of response to the stimulus of the first element and the order of response to the stimulus of the third element.
  • the determination device 10 includes a display unit 30 that displays the first element and the second element based on the order of responses to stimuli.
  • a display unit 30 that displays the first element and the second element based on the order of responses to stimuli.
  • the determination device 10 identifies the second element from the correlation attribute determined by the determination unit 106. With this configuration, the determination device 10 according to the present embodiment can specify the second element different from the first element.
  • the second element is an element that constitutes a cell.
  • the determination device 10 according to the present embodiment can determine the correlation attribute between the responses of the constituent elements of the cell CL to the stimulus.
  • the second element is a reaction in which the inhibitor acts.
  • the determination device 10 according to the present embodiment can determine the correlation attribute between the response of the reaction of the inhibitor to the stimulus and the response of the constituent element of the cell CL to the stimulus.
  • the determination device 10 includes a correlation calculation unit 103 and an extraction unit.
  • the feature amount correlation attribute calculation unit 104 of the present exemplary embodiment is an example of an extraction unit.
  • the correlation calculation unit 103 has a first change with respect to the stimulus in the state where the inhibitor is added and a second change with respect to the stimulus in the state where the inhibitor is not added, with respect to a plurality of types of feature amounts of the first element constituting the cell. By using, the correlation value between the second element different from the first element and the first element is calculated for each of a plurality of types of feature amounts.
  • the extraction unit extracts a predetermined feature amount correlation from the plurality of types of feature amount correlations based on the correlation value of each of the plurality of types of feature amount calculated by the correlation calculation unit 103.
  • the determination device 10 includes the correlation calculation unit 103 and the ratio calculation unit 105.
  • the correlation calculation unit 103 changes the characteristic amount of the first element constituting the cell CL with respect to the stimulus with the inhibitor added, and the characteristic amount with respect to the stimulus without the inhibitor added.
  • the correlation with the second change is calculated for each of the plurality of types of feature quantities.
  • the ratio calculation unit 105 calculates the ratio of the types of feature amounts, of which the correlation value calculated by the correlation calculation unit 103 is larger than a predetermined size, among the plurality of types of feature amounts.
  • the correlation value between the first change and the second change among the plurality of types of the feature amounts of the constituent elements of the cell CL is larger than a predetermined amount. Since the ratio of the types can be calculated, the order of the response of the reaction of the inhibitor to the stimulus and the response of the constituent elements of the cell to the stimulus can be easily determined.
  • the ratio calculation unit 105 uses the number of types of feature quantities having a correlation value larger than a predetermined size and the number of types of feature quantities having a correlation value smaller than a predetermined size. Of the plurality of types of feature quantities, the ratio of the types of feature quantities for which the correlation value calculated by the correlation calculation unit 103 is larger than a predetermined value is calculated. With this configuration, in the determination device 10 according to the present embodiment, cells are detected using the number of types of feature quantities having a correlation value larger than a predetermined size and the number of types of feature quantities having a correlation value smaller than a predetermined size.
  • the reaction of the inhibitor to the stimulus can be performed more easily than when the number of types of the feature amount is not used.
  • the order of the response and the response of the constituents of the cell to the stimulus can be easily determined.
  • the determination device 10 includes a determination unit 106.
  • the determination unit 106 uses the ratio calculated by the ratio calculation unit 105 to determine the order of the response of the reaction of the inhibitor to the stimulus and the response of the first element to the stimulus.
  • the determination device 10 can determine the order of the response of the reaction of the inhibitor to the stimulus and the response of the first element to the stimulus, and thus the suppression of the first element that constitutes the cell.
  • the order of activation or inhibition of the agent can be determined.
  • the correlation calculation unit 103 determines the correlation between the first change and the second change in the feature amount of the second element as a plurality of types of feature amounts. Then, the ratio calculation unit 105 calculates the ratio of the type of the characteristic amount having the correlation value calculated by the correlation calculation unit 103 larger than a predetermined size among the plurality of types of the characteristic amounts of the second element, and makes the determination. Using the result determined by the unit 106, the first element that is faster than the response of the reaction that the inhibitor acts on the stimulus and the second element that is slower than the response of the reaction that the inhibitor acts on the stimulus are specified.
  • the first element that is faster than the response of the reaction that the inhibitor acts on the stimulus and the second element that is slower than the response of the reaction that the inhibitor acts on the stimulus Since it is possible to specify, it is possible to specify the order of activation or suppression of the elements constituting the cell.
  • the signal pathway generation unit 201 generates a signal pathway SP that is a diagram showing a reaction expected between the first element and the second element.
  • a reaction expected between the first element and the second element can be illustrated, so that it is assumed between the first element and the second element. Can visually understand the reaction.
  • the determination device 10 includes a comparison unit 107.
  • the correlation calculation unit 103 calculates the correlation between the first change and the second change of the feature quantity of the third element for the feature quantity of the third element, and for each of the plurality of types of the feature quantity of the third element.
  • the ratio calculation unit 105 calculates the ratio of the type of the characteristic amount of the third element, of which the correlation value calculated by the correlation calculation unit 103 is larger than a predetermined size, among the plurality of types of the characteristic amount of the third element. ..
  • the comparison unit 107 uses the ratio calculated by the ratio calculation unit 105, and further when the order of the response of the first element and the response of the third element is earlier than the response of the reaction in which the inhibitor acts on the stimulus, The order of response of the first element and the order of response of the third element are compared.
  • the determination device 10 when the response of the first element and the response of the third element are earlier than the response of the reaction in which the inhibitor acts on the stimulus, the response of the first element is obtained. Since it is possible to compare the order of the response of the third element with the order of the response of the third element, a cell is formed when the response of the first element and the response of the third element are earlier than the response of the reaction in which the inhibitor acts on the stimulus. It is possible to specify the order of activation or suppression between the first element and the third element to be performed.
  • the determination device 10 includes a feature quantity correlation attribute calculation unit 104.
  • the feature amount correlation attribute calculation unit 104 determines the type of feature amount for which the correlation value calculated by the correlation calculation unit 103 is larger than a predetermined size, and the type of feature amount for which the correlation value calculated by the correlation calculation unit 103 is smaller than a predetermined size. Are determined respectively.
  • the ratio calculation unit 105 uses the result determined by the feature quantity correlation attribute calculation unit 104 to determine which of the plurality of types of feature quantity the correlation value calculated by the correlation calculation unit 103 is larger than a predetermined magnitude. Calculate the percentage.
  • the first change in the feature amount of the first element that constitutes the cell with respect to the stimulus in the state where the inhibitor is added, and the inhibitor of the feature amount are changed. Since it is possible to determine the type of feature amount having a correlation value larger than a predetermined magnitude and the type of feature amount having a correlation value smaller than a predetermined magnitude with respect to the second change with respect to the stimulus without addition, It is possible to more accurately calculate the proportion of the types of feature values having a correlation value larger than a predetermined value among a plurality of types, as compared with the case where the type of feature values is not determined.
  • the ratio calculation unit 105 suppresses the first change in the feature amount of the first element that constitutes the cell with respect to the stimulus in the state in which the inhibitor is added and the feature amount. Difference between the number of types of feature quantity having a correlation value larger than a predetermined magnitude and the second variation with respect to the stimulus without addition of the agent, and the number of types of feature quantity having a correlation value smaller than the predetermined magnitude Based on the above, among the plurality of types of the feature amount, the ratio of the type of the feature amount whose correlation value calculated by the correlation calculation unit 103 is larger than a predetermined value is calculated.
  • the determination device 10 of the plurality of types of feature amounts, the first change with respect to the stimulus with the inhibitor added, and the feature amount without the inhibitor added.
  • the positive and negative values can be added to the ratio of the types of feature values having a correlation value with the second change with respect to the stimulus greater than a predetermined value, so that the analysis result can be classified into at least two types.
  • the ratio calculation unit 105 suppresses the first change in the feature amount of the first element that constitutes the cell with respect to the stimulus in the state in which the inhibitor is added and the feature amount. Difference between the number of types of feature quantity having a correlation value larger than a predetermined magnitude and the second variation with respect to the stimulus without addition of the agent, and the number of types of feature quantity having a correlation value smaller than the predetermined magnitude Is calculated by the sum of the number of types of feature quantity whose correlation value is larger than a predetermined size and the number of types of feature quantity whose correlation value is smaller than a predetermined size.
  • the determination device 10 according to the present embodiment can standardize the ratio to be calculated. Therefore, even when the number of types of feature amounts used between different analyzes is different, the ratio calculated by those analyzes is different. You can compare each other.
  • the determination device 10 includes a display unit 30.
  • the display unit 30 displays the elements constituting the cells to be calculated by the ratio calculation unit 105 side by side based on the ratio calculated by the ratio calculation unit 105.
  • a cell constituting a cell can be illustrated based on the ratio of the types of feature values having a correlation value with the second change with respect to the stimulus in the state where no inhibitor is added, which is larger than a predetermined size. You can visually understand the order of responses to the stimuli of the elements that make up.
  • the display unit 30 displays the elements constituting the cells side by side, based on the reaction calculated by the inhibitor based on the ratio calculated by the ratio calculation unit 105.
  • the elements constituting the cells can be displayed side by side on the basis of the reaction of the inhibitor, so that the order of the response of the elements constituting the cells to the stimulation is the inhibitor. It is easier to understand than the case where the reaction of is not used as a standard.
  • the feature amount includes a plurality of layers including an input layer, one or more intermediate layers, and an output layer, and a node in each layer is a node for a node in the next layer and thereafter. It is a feature quantity that has been dimensionally reduced by a neural network that transmits information with a predetermined weighting for each. Since the determination device 10 according to the present embodiment can use the feature amount whose dimension is reduced by the neural network for the analysis, the determination device 10 can perform the analysis with higher accuracy than when the feature amount whose dimension is reduced by the neural network is not used.
  • medical agent can suppress the reaction which acts between components.
  • the expression level may be decreased by 10%, or 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, It may be reduced by 100%.
  • the inhibitor may suppress the reaction that acts between the constituents, or may suppress the function of the constituents.
  • the inhibitor may inhibit the functions of a plurality of types of constituent elements. A plurality of types of reactions may be suppressed. Further, the function of the constituent elements and the reaction between the constituent elements may be suppressed.
  • the inhibitor was added as a drug as an example, it is not limited to this.
  • a promoter that promotes the function of the component may be added. That is, it may function as a changing agent that changes the function of the constituent element.
  • the location of action when a drug is added may be estimated from the upstream / downstream indices of the constituent elements.
  • the correlation attribute of the feature amount of the feature amount is calculated from the change of the feature amount when the drug is added and the change of the feature amount when the drug is not added.
  • the upstream / downstream index of the component is calculated from the correlation attributes of a plurality of types of feature quantities.
  • At least one of the component having the value closest to 1.0 of the upstream / downstream index and the component having the value closest to ⁇ 1.0 is specified. It becomes possible to estimate the point of action on which the drug acts based on the information of the specified components. The larger the number of components for which the upstream / downstream index is calculated, the more components can be estimated before and after the point of action responds to the stimulus. By estimating the order of responses of many components, it becomes possible to easily estimate the action point where the drug acts. Thus, even if the point of action of the drug is unknown, it is possible to estimate the reaction or component of the drug by using the upstream / downstream index.
  • a plurality of types of feature amounts are used, but one type of feature amount may be used.
  • the correlation value between the change in the feature amount when the drug is added and the change in the feature amount when the drug is not added is high, the correlation of the constituent elements may be determined.
  • the action point of the drug may be determined from the components determined in this case.
  • An example of analyzing the correlation attribute is described in International Application No. PCT / JP2017 / 023135, and as long as it is permitted by the laws of the country specified or selected in this international application, the contents of this document are described. Is used as a part of the description of the text.
  • the determination apparatus 10 executes the process for a plurality of types of feature amounts of the first element forming the cell has been described, but the present invention is not limited to this.
  • the determination device 10 may perform the process on one or more feature amounts of the first element that constitutes the cell. In this case, the determination device 10 uses the first change in the characteristic amount of the first element forming the cell with respect to the stimulus with the drug added and the second change with respect to the stimulus in the state without the drug added.
  • a determination unit 106 that determines a correlation attribute between the second element and the first element. Further, in this case, the determination unit 106 identifies the second element based on the correlation attribute determined by the determination unit 106. Further, in this case, the feature amount correlation attribute calculation unit 104 calculates the feature amount correlation attribute for the plurality of types of feature amounts of the first element, and the determination unit 106 calculates the feature amount correlation attribute calculation unit 104.
  • the correlation attribute of the second element and the first element is determined using the characteristic correlation attribute for each type of characteristic amount.
  • the “computer system” may include an OS and hardware such as peripheral devices. Further, the “computer system” also includes a homepage providing environment (or display environment) if a WWW system is used.
  • the "computer-readable recording medium” is a writable non-volatile memory such as a flexible disk, a magneto-optical disk, a ROM, a flash memory, a portable medium such as a CD-ROM, a hard disk built in a computer system, or the like. Storage device.
  • the "computer-readable recording medium” means a volatile memory (for example, a DRAM (Dynamic) in a computer system serving as a server or a client when a program is transmitted through a network such as the Internet or a communication line such as a telephone line. Random Access Memory)) that holds the program for a certain period of time.
  • the program may be transmitted from a computer system that stores the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium.
  • the "transmission medium” for transmitting the program refers to a medium having a function of transmitting information such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
  • the program may be for realizing a part of the functions described above. Further, it may be a so-called difference file (difference program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system.

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Wood Science & Technology (AREA)
  • Biotechnology (AREA)
  • Organic Chemistry (AREA)
  • Zoology (AREA)
  • Microbiology (AREA)
  • Sustainable Development (AREA)
  • Biomedical Technology (AREA)
  • Biochemistry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Genetics & Genomics (AREA)
  • Medicinal Chemistry (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Apparatus Associated With Microorganisms And Enzymes (AREA)

Abstract

Le dispositif de détermination comprend : une unité de calcul d'attribut de corrélation qui, pour une pluralité de types de quantités caractéristiques d'un premier élément constituant des cellules, utilise un premier changement des quantités caractéristiques par rapport à un stimulus dans un état dans lequel un inhibiteur est ajouté, et un second changement des quantités caractéristiques par rapport à un stimulus dans un état dans lequel un inhibiteur n'est pas ajouté, afin de calculer des attributs de corrélation de quantité caractéristique entre le premier élément et un second élément différent du premier élément pour chacun de la pluralité de types de quantités caractéristiques; et une unité de détermination qui utilise les attributs de corrélation de quantité de caractéristiques pour chacun de la pluralité de types de quantités de caractéristiques calculées par l'unité de calcul d'attribut de corrélation afin de déterminer des attributs de corrélation entre le second élément et le premier élément.
PCT/JP2018/040735 2018-11-01 2018-11-01 Dispositif, procédé et programme de détermination WO2020090089A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/040735 WO2020090089A1 (fr) 2018-11-01 2018-11-01 Dispositif, procédé et programme de détermination

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/040735 WO2020090089A1 (fr) 2018-11-01 2018-11-01 Dispositif, procédé et programme de détermination

Publications (1)

Publication Number Publication Date
WO2020090089A1 true WO2020090089A1 (fr) 2020-05-07

Family

ID=70462176

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/040735 WO2020090089A1 (fr) 2018-11-01 2018-11-01 Dispositif, procédé et programme de détermination

Country Status (1)

Country Link
WO (1) WO2020090089A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009139336A (ja) * 2007-12-10 2009-06-25 Olympus Corp カルシウム測定方法
WO2016103501A1 (fr) * 2014-12-26 2016-06-30 国立大学法人東京大学 Dispositif d'analyse, procédé et programme d'analyse, procédé de production de cellules et cellules
WO2018193612A1 (fr) * 2017-04-21 2018-10-25 株式会社ニコン Dispositif de calcul de corrélation, procédé de calcul de corrélation, et programme de calcul de corrélation
WO2018235251A1 (fr) * 2017-06-23 2018-12-27 株式会社ニコン Dispositif d'analyse, programme d'analyse et procédé d'analyse

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009139336A (ja) * 2007-12-10 2009-06-25 Olympus Corp カルシウム測定方法
WO2016103501A1 (fr) * 2014-12-26 2016-06-30 国立大学法人東京大学 Dispositif d'analyse, procédé et programme d'analyse, procédé de production de cellules et cellules
WO2018193612A1 (fr) * 2017-04-21 2018-10-25 株式会社ニコン Dispositif de calcul de corrélation, procédé de calcul de corrélation, et programme de calcul de corrélation
WO2018235251A1 (fr) * 2017-06-23 2018-12-27 株式会社ニコン Dispositif d'analyse, programme d'analyse et procédé d'analyse

Similar Documents

Publication Publication Date Title
JP7270058B2 (ja) 予測的組織パターン特定のためのマルチプルインスタンスラーナ
US20190087954A1 (en) Pathology case review, analysis and prediction
Nketia et al. Analysis of live cell images: Methods, tools and opportunities
JP2023501126A (ja) 組織画像分類用のマルチインスタンス学習器
JP6670757B2 (ja) 判定装置、解析方法、および解析プログラム
US11321836B2 (en) Image-processing device, image-processing method, and image-processing program for setting cell analysis area based on captured image
JP6756339B2 (ja) 画像処理装置、及び画像処理方法
US11379983B2 (en) Analysis device, analysis program, and analysis method
Arjmand et al. Deep learning in liver biopsies using convolutional neural networks
Delestro et al. In vivo large-scale analysis of Drosophila neuronal calcium traces by automated tracking of single somata
US20200372652A1 (en) Calculation device, calculation program, and calculation method
US20200043159A1 (en) Analysis device, analysis method, and program
JPWO2018087861A1 (ja) 解析装置、解析方法、及びプログラム
WO2018193612A1 (fr) Dispositif de calcul de corrélation, procédé de calcul de corrélation, et programme de calcul de corrélation
US11645859B2 (en) Analysis device, analysis method, analysis program and display device
WO2020090089A1 (fr) Dispositif, procédé et programme de détermination
WO2019159247A1 (fr) Dispositif de calcul, programme d'analyse et procédé d'analyse
Walter Bioimage Informatics for Phenomics.
WO2018109826A1 (fr) Dispositif d'analyse, programme d'analyse et procédé d'analyse
JP6999118B2 (ja) 画像処理装置
US20240085405A1 (en) Image processing device, analysis device, image processing method, image processing program, and display device
Issaev Robust image-to-image translation tool for fibrotic quantification of whole-slide images
Robinson et al. Spatial quantification of the synaptic activity phenotype across large populations of neurons with Markov random fields
Ranjbaran et al. A survey on Organoid Image Analysis Platforms

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18938816

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18938816

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP