WO2024257774A1 - 創薬支援装置、創薬支援装置の作動方法、および創薬支援装置の作動プログラム - Google Patents
創薬支援装置、創薬支援装置の作動方法、および創薬支援装置の作動プログラム Download PDFInfo
- Publication number
- WO2024257774A1 WO2024257774A1 PCT/JP2024/021249 JP2024021249W WO2024257774A1 WO 2024257774 A1 WO2024257774 A1 WO 2024257774A1 JP 2024021249 W JP2024021249 W JP 2024021249W WO 2024257774 A1 WO2024257774 A1 WO 2024257774A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- candidate substance
- dose
- drug discovery
- predicted value
- fluctuation waveform
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B40/20—Supervised data analysis
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/02—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving viable microorganisms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/5005—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells
- G01N33/5008—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics
- G01N33/502—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics for testing non-proliferative effects
- G01N33/5023—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics for testing non-proliferative effects on expression patterns
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/5005—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells
- G01N33/5008—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics
- G01N33/5044—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics involving specific cell types
- G01N33/5061—Muscle cells
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
- G16B5/20—Probabilistic models
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
Definitions
- the technology disclosed herein relates to a drug discovery support device, an operating method for a drug discovery support device, and an operating program for a drug discovery support device.
- TdP Torsades de Pointes
- iPS cardiomyocytes human iPS (induced pluripotent stem) cell-derived cardiomyocytes (hereinafter referred to as iPS cardiomyocytes) have ion channels expressed in human cardiac tissue, such as Na channels and Ca channels, in addition to hERG channels. For this reason, iPS cardiomyocytes have been verified as a tool capable of evaluating the presence or absence of QT prolongation in drug candidate substances.
- the usefulness of a method for evaluating the presence or absence of QT prolongation by measuring the electrical activity of iPS cardiomyocytes as an electrocardiogram-like waveform using a planar microelectrode array has been demonstrated through a large-scale multi-center validation study, and the method has been included in the follow-up study of the ICH S7B guideline.
- the electrocardiogram-like waveform is the waveform of fluctuations in the extracellular potential of iPS cardiomyocytes.
- the method of measuring the electrical activity of iPS cardiomyocytes using MEAs can reveal the presence or absence of QT prolongation.
- QT prolongation occurs, it is not possible to determine the mechanism of action of the candidate substance, such as which ion channel's ion flow is inhibited or activated by the candidate substance, causing QT prolongation. Therefore, K. H. Jaeger, et al “Identifying Drug Response by Combining Meas elements of the Membrane Potential, the Cytosolic Calcium Co centration, and the Extracellular Potential in Microphysio Logical Systems” Frontiers in Pharmacology 08 February 2021.
- Non-Patent Document 1 and Fabien Raphel, et al., "A greedy classifier optimization strategy to assess ion channel blocking activity and pro-arrhythmia in hiPSC-cardiomyocytes," PLOS Computational Biology, September 25, 2020.
- Non-Patent Document 2 describe a technique that contributes to the estimation of the mechanism of action of candidate substances.
- the height of the first peak and the conduction velocity of the fluctuating waveform are derived as features from the fluctuating waveform of the extracellular potential of iPS cardiomyocytes measured with an MEA, and the derived features are input into a prediction model, causing the prediction model to output a predicted value of the degree of inhibition of the candidate substance to the Na channel (a numerical value indicating the extent to which the flow of Na ions in the Na channel is inhibited by the candidate substance).
- the degree of inhibition of the candidate substance to the hERG channel (a numerical value indicating the extent to which the flow of K ions in the hERG channel is inhibited by the candidate substance) is obtained by measuring the intracellular potential of iPS cardiomyocytes.
- the degree of inhibition of the candidate substance to the Ca channel is obtained by measuring the calcium concentration.
- Non-Patent Document 2 a simulation model is used to generate a waveform of intracellular potential fluctuations in iPS cardiomyocytes, and the generated waveform of intracellular potential fluctuations in iPS cardiomyocytes is converted into a waveform of extracellular potential fluctuations in iPS cardiomyocytes caused by an MEA. Then, an algorithm is proposed to predict the degree of inhibition of candidate substances on hERG channels, Na channels, and Ca channels based on feature quantities derived from the waveform of extracellular potential fluctuations in iPS cardiomyocytes.
- index values that indicate the dose-response relationship of the candidate substance such as the median inhibitory concentration (IC50)
- IC50 median inhibitory concentration
- One embodiment of the technology disclosed herein provides a drug discovery support device that can easily estimate the mechanism of action of a candidate substance, an operating method for the drug discovery support device, and an operating program for the drug discovery support device.
- the drug discovery support device disclosed herein includes a processor, and the processor acquires a first predicted value for each ion channel and each added amount obtained by outputting a first predicted value of the inhibition degree indicating the degree to which the flow of ions in multiple ion channels present in the iPS cardiomyocytes is inhibited by the candidate substance from a prediction model based on a first fluctuation waveform, which is a fluctuation waveform of the extracellular potential of iPS cardiomyocytes, which are cardiomyocytes derived from human iPS cells, measured when a candidate substance for a pharmaceutical is added to the iPS cardiomyocytes while changing the amount of addition, derives an index value indicating the dose-response relationship of the candidate substance for each ion channel based on the first predicted value for each added amount, and presents to a user estimated reference information corresponding to the index value, which is referenced to estimate the mechanism of action of the candidate substance.
- a first fluctuation waveform which is a fluctuation waveform of the extracellular potential of
- the processor preferably searches for a dose-response curve that fits the first predicted value for each added amount, and derives the index value from the dose-response curve found.
- the first predicted value is not only a predicted value of the degree of inhibition, but also a predicted value of the degree of activation indicating the degree to which the flow of ions in the ion channel is activated by the candidate substance, and there are two types of dose-response curves: a first dose-response curve when the flow of ions in the ion channel is inhibited by the candidate substance, and a second dose-response curve when the flow of ions in the ion channel is activated by the candidate substance, and it is preferable that the processor derives the index value from either the first or second dose-response curve, whichever is more suitable for the first predicted value for each added amount.
- the processor preferably presents the discovered dose-response curve to the user as estimated reference information.
- the curve used to find the dose-response curve is preferably a logistic curve.
- the first predicted value is preferably obtained by inputting the feature amount derived from the first fluctuation waveform into a prediction model.
- the processor acquires the first fluctuation waveform, derives features from the first fluctuation waveform, and inputs the features into the prediction model to output the first predicted value from the prediction model.
- the processor preferably performs noise reduction processing on the first fluctuation waveform prior to deriving the feature quantity.
- the first fluctuation waveform has a periodicity corresponding to the pulsation of iPS cardiomyocytes, and the processor preferably performs an averaging process of multiple periodic portions of the first fluctuation waveform as noise reduction processing.
- the measurement of the first fluctuation waveform is preferably performed using multiple electrodes for one iPS cardiomyocyte, and the processor selects one of the multiple first fluctuation waveforms measured by the multiple electrodes as the first fluctuation waveform from which the feature value is derived in accordance with preset conditions.
- the feature preferably includes the conduction velocity of the first fluctuation waveform.
- the feature is preferably normalized by a reference feature derived from a reference first fluctuation waveform measured when the candidate substance is not added to the iPS cardiomyocytes.
- the first predicted value be obtained by inputting the experimental values in addition to the feature quantities into the prediction model.
- the prediction model is a model that has been trained in two ways: when experimental values are input and when they are not.
- the first predicted value is preferably obtained by inputting a second predicted value of an index value indicating the dose-response relationship of the candidate substance, which is derived based on structural information of the candidate substance, in addition to the feature amount, into the prediction model.
- the predictive model is preferably a model trained using training data including simulation data.
- the simulation data is preferably generated using a first simulation model that reproduces a second fluctuation waveform, which is a fluctuation waveform of the intracellular potential of an iPS cardiomyocyte, and a second simulation model that converts the second fluctuation waveform into the first fluctuation waveform.
- the method of operating the drug discovery support device disclosed herein includes obtaining a first predicted value for each ion channel and each added amount obtained by outputting a first predicted value of the inhibition degree indicating the degree to which the flow of ions in multiple ion channels present in the iPS cardiomyocytes is inhibited by the candidate substance from a prediction model based on a first fluctuation waveform, which is a fluctuation waveform of the extracellular potential of iPS cardiomyocytes, which are cardiomyocytes derived from human iPS cells, measured when a candidate substance for a pharmaceutical is added to the iPS cardiomyocytes while changing the amount of addition, deriving an index value indicating the dose-response relationship of the candidate substance for each ion channel based on the first predicted value for each added amount, and presenting to a user estimated reference information corresponding to the index value, which is referenced to estimate the mechanism of action of the candidate substance.
- the operating program of the drug discovery support device disclosed herein causes a computer to execute processes including: acquiring a first predicted value for each ion channel and each added amount, which is obtained by outputting a first predicted value of the inhibition degree indicating the degree to which the flow of ions in multiple ion channels present in the iPS cardiomyocytes is inhibited by the candidate substance from a prediction model based on a first fluctuation waveform, which is a fluctuation waveform of the extracellular potential of iPS cardiomyocytes, which are cardiomyocytes derived from human iPS cells, measured when a drug candidate substance is added to the iPS cardiomyocytes while changing the amount of addition; deriving an index value indicating the dose-response relationship of the candidate substance for each ion channel based on the first predicted value for each added amount; and presenting to a user estimated reference information corresponding to the index value, which is referenced to estimate the mechanism of action of the candidate substance.
- the technology disclosed herein can provide a drug discovery support device that can easily estimate the mechanism of action of a candidate substance, an operating method for the drug discovery support device, and an operating program for the drug discovery support device.
- FIG. 2 is a diagram showing a drug discovery support server, a user terminal, and a well plate.
- 1 is a table showing the amount of drug candidate substance added per well.
- FIG. 2 is a block diagram showing computers constituting a drug discovery support server and a user terminal.
- FIG. 2 is a block diagram showing a processing unit of a CPU of the drug discovery support server.
- FIG. 13 is a diagram illustrating a process performed by a preprocessing unit.
- FIG. 13 is a diagram illustrating a noise reduction process.
- FIG. FIG. FIG. 13 is a diagram illustrating a process performed by a feature amount derivation unit.
- FIG. 13 is a diagram showing how a feature amount is normalized by a reference feature amount.
- FIG. 11 is a diagram showing feature amount information.
- FIG. 1 is a diagram showing a group of prediction models.
- FIG. 13 is a diagram illustrating a process of a prediction unit that inputs feature amounts to each prediction model and causes each prediction model to output a first predicted value.
- FIG. 13 is a diagram showing prediction result information.
- FIG. 1 illustrates the processing in the learning phase of a predictive model for hERG channels.
- FIG. 1 shows a family of dose-response curves. 1 is a graph showing a first dose-response curve. 2 is a graph showing a second dose-response curve.
- 13 is a flowchart showing a processing procedure of a search unit.
- FIG. 13 is a diagram showing how a first predicted value is derived for each ion channel and for each added amount.
- FIG. 13 is a diagram showing how a first predicted value is derived for each ion channel and for each added amount.
- FIG. 13 is a diagram showing how the squared error of the second dose-response curve searched for is smaller than the squared error of the first dose-response curve searched for, and how the median effective concentration is derived from the second dose-response curve searched for.
- 2 is a block diagram showing a processing unit of a CPU of a user terminal;
- FIG. 13 is a diagram showing a waveform input screen.
- FIG. 13 is a diagram showing an evaluation result display screen.
- 13 is a flowchart showing a processing procedure of the drug discovery support server.
- FIG. 13 is a diagram showing a second embodiment in which, in addition to feature quantities, experimental values of index values showing the dose-response relationship of a candidate substance are input to a prediction model.
- FIG. 13 is a diagram showing the processing in the learning phase of the hERG channel prediction model of the second embodiment.
- FIG. 13 is a diagram showing a third embodiment in which, in addition to the feature amount, a second predicted value of an index value indicating the dose-response relationship of a candidate substance, which is derived based on structural information of the candidate substance, is input to a prediction model.
- FIG. 13 is a diagram illustrating a fourth embodiment in which simulation data is included in the learning data of a prediction model. 13 is a table showing another example of allocation of candidate substances to each well and the amounts of the candidate substances to be added.
- the drug discovery support server 10 is connected to a user terminal 11 via a network 12.
- the drug discovery support server 10 is an example of a "drug discovery support device" according to the technology of the present disclosure.
- the user terminal 11 is installed, for example, in a pharmaceutical company that develops drugs, or an organization that is contracted by a pharmaceutical company to develop drugs, that is, a contract research organization (CRO).
- CRO contract research organization
- the user terminal 11 is operated by a user U who is involved in drug development at the pharmaceutical company or the contract research organization.
- the network 12 is, for example, a wide area network (WAN) such as the Internet or a public communication network. Note that, although only one user terminal 11 is connected to the drug discovery support server 10 in FIG. 1, multiple user terminals 11 of multiple pharmaceutical companies or contract research organizations are actually connected to the drug discovery support server 10.
- WAN wide area network
- a well plate 13 is connected to the user terminal 11.
- the well plate 13 has a number of wells 14.
- the wells 14 are arranged at equal intervals in the vertical and horizontal directions.
- the well 14 is a cylindrical depression that is open at the top.
- the inside of the well 14 is filled with culture medium, in which iPS cardiomyocytes 15, which are cardiomyocytes derived from human iPS cells, are cultured.
- the iPS cardiomyocytes 15 are sheet-shaped and have grown to the point where they can beat spontaneously.
- the well plate 13 is placed in a thermostatic bath (not shown).
- candidate pharmaceutical substances are added to wells 14 No. 1 to 40. More specifically, candidate substances are added in an amount AA1 to wells 14 No. 1 to 10, and candidate substances are added in an amount AA2 to wells 14 No. 11 to 20.
- candidate substances are added in an amount AA3 to wells 14 No. 21 to 30, and candidate substances are added in an amount AA4 to wells 14 No. 31 to 40.
- the magnitude relationship between the amounts AA1 to AA4 is AA1 ⁇ AA2 ⁇ AA3 ⁇ AA4.
- candidate substances are not added to wells 14 No. 41 to 48. In this way, candidate substances are added to iPS cardiomyocytes 15 while the amount AA is changed.
- the amount of additive AA is not limited to the four types shown in the example. For example, it may be two types or ten types.
- a planar microelectrode array 16 is provided on the bottom surface of the well 14.
- the planar microelectrode array 16 is composed of a plurality of microelectrodes 17 arranged in a square.
- the microelectrodes 17 are an example of an "electrode” according to the technology disclosed herein. Note that the number of microelectrodes 17 is not limited to the illustrated 64, and may be 16, 100, etc.
- the microelectrodes 17 are exposed on the bottom surface of the well 14 and come into contact with the iPS cardiomyocytes 15.
- the microelectrodes 17 are connected to a potential measurement circuit (not shown).
- the potential measurement circuit measures the electrical signal from each of the multiple microelectrodes 17, i.e., the extracellular potential of the iPS cardiomyocytes 15. Therefore, the extracellular potential is measured for each of the multiple microelectrodes 17, in this example, 64 microelectrodes 17.
- This method of measuring the extracellular potential using a planar microelectrode array 16 is extremely simple and inexpensive compared to a method called manual patch clamp, in which electrodes are inserted directly into the iPS cardiomyocytes 15 to measure the extracellular potential.
- the measurement results of the extracellular potential from the potential measurement circuit are input to the user terminal 11.
- a first variation waveform 18 is generated, which is a variation waveform that shows the change over time in the measurement results of the extracellular potential.
- the measurement of the extracellular potential is performed for a preset period, for example 10 minutes. Therefore, the first variation waveform 18 shows the change over time in the measurement results of the extracellular potential for the preset period.
- the number of the well 14 and the number of the microelectrode 17 where the extracellular potential was measured are associated and stored in the first variation waveform 18.
- the first fluctuation waveform 18 has a periodicity that corresponds to the pulsation of the iPS cardiomyocytes 15.
- the first fluctuation waveform 18 is a collection of multiple periodic portions 19 separated by one beat interval ISI (Interspike Interval).
- the user terminal 11 transmits an evaluation request 20 to the drug discovery support server 10.
- the evaluation request 20 is a request for the drug discovery support server 10 to evaluate the presence or absence of cardiotoxicity of a candidate drug substance.
- the evaluation request 20 includes a plurality of first variation waveforms 18.
- the evaluation request 20 also includes a terminal ID (Identification Data) for uniquely identifying the user terminal 11 that transmitted the evaluation request 20.
- the drug discovery support server 10 derives estimated reference information 21.
- the drug discovery support server 10 distributes the estimated reference information 21 to the user terminal 11 that sent the evaluation request 20.
- the user terminal 11 makes the estimated reference information 21 available for viewing by the user U.
- the estimated reference information 21 is information that is referenced by the user U to estimate the mechanism of action of a candidate substance.
- the mechanism of action of a candidate substance means, for example, when QT prolongation occurs in iPS cardiomyocytes 15, which of the multiple ion channels present in iPS cardiomyocytes 15 has its ion flow inhibited or activated by the candidate substance, causing QT prolongation.
- the multiple ion channels present in iPS cardiomyocytes 15 are the hERG channel through which K ions flow, the Na channel through which Na ions flow, and the Ca channel through which Ca ions flow. These ion channels play a very important role in the pulsation of iPS cardiomyocytes 15. For this reason, it is believed that QT prolongation, which causes fatal arrhythmia, occurs when the flow of each ion in these ion channels is inhibited or activated.
- the computers that make up the drug discovery support server 10 and the user terminal 11 are basically of the same configuration, and include storage 30, memory 31, a CPU (Central Processing Unit) 32, a communication unit 33, a display 34, and an input device 35. These are interconnected via a bus line 36.
- CPU Central Processing Unit
- Storage 30 is a hard disk drive built into the computer that constitutes the drug discovery support server 10 and the user terminal 11, or connected via a cable or network. Alternatively, storage 30 is a disk array with multiple hard disk drives connected in series. Storage 30 stores control programs such as an operating system, various application programs (hereinafter referred to as APs (Application Programs)), and various data associated with these programs. Note that a solid state drive may be used instead of a hard disk drive.
- APs Application Programs
- Memory 31 is a work memory for CPU 32 to execute processing.
- CPU 32 loads programs stored in storage 30 into memory 31 and executes processing according to the programs. In this way, CPU 32 comprehensively controls each part of the computer.
- CPU 32 is an example of a "processor" according to the technology of this disclosure. Note that memory 31 may be built into CPU 32.
- the communication unit 33 is a network interface that controls the transmission of various information via the network 12, etc.
- the display 34 displays various screens.
- the various screens are equipped with an operation function using a GUI (Graphical User Interface).
- the computers that make up the drug discovery support server 10 and the user terminal 11 accept input of operation instructions from the input device 35 via the various screens.
- the input device 35 is a keyboard, mouse, touch panel, microphone for voice input, etc.
- the computer parts constituting the drug discovery support server 10 are distinguished by adding the suffix "A" to their reference numbers (storage 30 and CPU 32), and the computer parts constituting the user terminal 11 are distinguished by adding the suffix "B" to their reference numbers (storage 30, CPU 32, display 34, and input device 35).
- an operating program 40 is stored in storage 30A of drug discovery support server 10.
- Operating program 40 is an AP for causing a computer to function as drug discovery support server 10.
- operating program 40 is an example of an "operating program of a drug discovery support device" according to the technology of the present disclosure.
- Storage 30 also stores a group of prediction models 41 and a group of dose-response curves 42, etc.
- the CPU 32A of the computer constituting the drug discovery support server 10 works in cooperation with the memory 31 etc. to function as a request reception unit 45, a read/write (hereinafter abbreviated as RW (Read Write)) control unit 46, a preprocessing unit 47, a feature derivation unit 48, a prediction unit 49, a search unit 50, and a screen distribution control unit 51.
- RW Read Write
- the request receiving unit 45 receives various requests from the user terminal 11, including the evaluation request 20. When the evaluation request 20 is received, the request receiving unit 45 outputs the first fluctuation waveform 18 included in the evaluation request 20 to the RW control unit 46. Although not shown in the figure, the request receiving unit 45 also outputs the terminal ID of the user terminal 11 included in the evaluation request 20 to the screen distribution control unit 51.
- the RW control unit 46 controls the storage of various data in storage 30A and the reading of various data from storage 30A.
- the RW control unit 46 controls the storage of the first fluctuation waveform 18 in storage 30A and the reading of the first fluctuation waveform 18 from storage 30A.
- the RW control unit 46 outputs the read first fluctuation waveform 18 to the preprocessing unit 47.
- the RW control unit 46 also reads the prediction model group 41 from storage 30A and outputs the read prediction model group 41 to the prediction unit 49.
- the RW control unit 46 reads the dose-response curve group 42 from storage 30A and outputs the read dose-response curve group 42 to the search unit 50.
- the preprocessing unit 47 performs preprocessing on the first fluctuation waveform 18.
- the preprocessing unit 47 outputs the preprocessed first fluctuation waveform 18 (hereinafter referred to as the first fluctuation waveform 18AT) to the feature derivation unit 48.
- the feature derivation unit 48 derives multiple types of feature quantities 65 from the first fluctuation waveform 18AT, for example, using a machine learning model that outputs feature quantities 65 (see FIG. 9) when the first fluctuation waveform 18AT is input.
- the feature derivation unit 48 generates feature quantity information 55 that compiles the multiple types of derived feature quantities 65, and outputs the feature quantity information 55 to the prediction unit 49.
- the prediction unit 49 causes the prediction model group 41 to predict the degree of the effect of the candidate substance on each ion channel of the iPS cardiomyocytes 15 based on the feature amount 65 of the feature amount information 55.
- the prediction unit 49 generates prediction result information 56 summarizing the prediction results of the degree of the effect of the candidate substance on each ion channel of the iPS cardiomyocytes 15, and outputs the prediction result information 56 to the search unit 50.
- the search unit 50 searches for a dose-response curve that matches the prediction result information 56 based on the group of dose-response curves 42.
- the search unit 50 derives an index value indicating the dose-response relationship of the candidate substance from the dose-response curve that has been searched for.
- the search unit 50 generates estimated reference information 21 according to the index value, and outputs the estimated reference information 21 to the screen distribution control unit 51.
- the screen distribution control unit 51 controls the distribution of various screens to the user terminal 11. Specifically, the screen distribution control unit 51 distributes and outputs various screens to the user terminal 11 that is the sender of the various requests in the form of screen data for web distribution created using a markup language such as XML (Extensible Markup Language). At this time, the screen distribution control unit 51 identifies the user terminal 11 that is the sender of the various requests based on the terminal ID from the request receiving unit 45.
- XML Japanesescript (registered trademark) Object Notation
- the various screens include a waveform input screen 90 (see FIG. 23) for inputting the first variation waveform 18, and an evaluation result display screen 95 (see FIG. 24) for presenting the estimated reference information 21 to the user U.
- the CPU 32A also includes an instruction receiving unit that receives various operation instructions from the input device 35.
- the preprocessing unit 47 performs a noise reduction process 60 and a selection process 61 as preprocessing for the first fluctuation waveform 18.
- An example of the noise reduction process 60 is the process shown in FIG. 6, and an example of the selection process 61 is the process shown in FIG. 7 and FIG. 8.
- the pre-processing unit 47 performs the noise reduction process 60 in the following manner.
- the pre-processing unit 47 extracts a plurality of periodic portions 19 from a first fluctuation waveform 18 measured at a certain microelectrode 17 in a certain well 14.
- a set number of periodic portions 19 that satisfy a preset selection criterion are selected (step ST10).
- the selection criterion is, for example, that the pulsation interval ISI is within a set range, that the maximum amplitude is equal to or less than a set value, and/or that the S/N ratio is equal to or less than a set value.
- the set number is, for example, 30.
- the pre-processing unit 47 averages the selected number of periodic parts 19 to obtain the periodic part 19AV (step ST11). This completes the noise reduction process 60.
- the noise reduction process 60 is an average process of the multiple periodic parts 19 of the first fluctuation waveform 18.
- the pre-processing unit 47 repeats the processes of steps ST10 and ST11 until there are no more first fluctuation waveforms 18 that have not been subjected to the noise reduction process 60.
- the pre-processing unit 47 applies the noise reduction process 60 to all the first fluctuation waveforms 18. Therefore, the number of periodic parts 19AV generated is equal to the number of first fluctuation waveforms 18.
- FIG. 6 shows an example in which the noise reduction process 60 is applied to the first fluctuation waveform 18 measured at the microelectrode No. 1 17 of the well No. 1 14.
- the noise reduction process 60 may be a smoothing process using a low-pass filter applied to the first fluctuation waveform 18.
- the pre-processing unit 47 selects one periodic portion 19AV_E from among multiple periodic portions 19AV generated from the first fluctuation waveform 18 measured at each microelectrode 17 of a certain well 14. At this time, the pre-processing unit 47 selects the periodic portion 19AV_E according to preset conditions (step ST20).
- the periodic portion 19AV_E is the subject from which the feature deriving unit 48 derives the feature 65.
- the periodic portion 19AV_E is an example of a "first fluctuation waveform from which a feature is derived" according to the technology disclosed herein.
- the selection process 61 is a process for selecting a so-called golden channel.
- selecting the periodic portion 19AV_E according to preset conditions refers to, for example, selecting according to the method disclosed in International Patent No. 2022/176310.
- the method disclosed in International Patent No. 2022/176310 is a method of selecting one waveform (periodic portion 19AV_E in this example) from multiple selection target waveforms by repeating clustering analysis between multiple selection target waveforms (multiple periodic portions 19AV in this example) and multiple teacher waveforms labeled as whether they are ideal waveforms or not.
- conditions may be set based on features obtained from an ideal waveform, and a periodic portion 19AV_E that satisfies the conditions may be selected.
- the pre-processing unit 47 repeats the process of step ST20 until there are no wells 14 to which the selection process 61 has not been applied. In other words, the pre-processing unit 47 applies the selection process 61 to all wells 14. Therefore, periodic portions 19AV_E are selected in the number of wells 14.
- the pre-processing unit 47 outputs the periodic portions 19AV_E in the number of wells 14 as the first fluctuation waveform 18AT to the feature derivation unit 48.
- FIG. 7 shows an example in which the periodic portion 19AV relating to the microelectrode 17 No. 7 is selected as the periodic portion 19AV_E from the multiple periodic portions 19AV relating to each microelectrode 17 of the well 14 No. 1. Also, FIG.
- the periodic portion 19AV relating to the microelectrode 17 No. 7 is selected as the periodic portion 19AV_E from the multiple periodic portions 19AV relating to each microelectrode 17 of the well 14 No. 48.
- the well 14 No. 48 is a well 14 to which no candidate substance is added. Therefore, the periodic portion 19AV_E selected in FIG. 8 is an example of a "reference first fluctuation waveform" relating to the technology of the present disclosure.
- the feature deriving unit 48 derives the following features 65 from the periodic portion 19AV_E: FPD (Field Potential Duration) cF, DA (Depolarization Amplitude), RC (Repolarization Center), RW (Repolarization Width), RA (Repolarization Amplitude), AUCr (Area Under Curve of the repolarization wave), and CV (Conduction Velocity).
- DA is the amplitude of the depolarization wave P1.
- RC is the time interval (repolarization center) from the depolarization wave P1 to the rising edge of the repolarization wave P2.
- RW is the time interval (repolarization width) of the repolarization wave P2.
- RA is the amplitude of the repolarization wave P2.
- AUCr is the area under the curve of the repolarization wave P2.
- CV is the conduction velocity of the first fluctuation waveform 18.
- FPDcF (FPD), DA, RC, RW, RA, and AUCr are characteristic quantities listed in Non-Patent Document 2.
- CV is a feature value listed in Non-Patent Document 1. CV is calculated based on the arrangement positions of the microelectrodes 17.
- the feature derivation unit 48 divides the feature 65 derived from the periodic portion 19AV_E of wells 14 No. 1 to 40 to which the candidate substance was added by the reference feature 65S derived from the periodic portion 19AV_E of wells 14 No. 41 to 48 to which the candidate substance was not added, to standardize it as feature 65AS.
- the feature information 55 is a collection of the feature 65AS of wells 14 No. 1 to 40.
- the reference feature 65S is, for example, a representative value such as the average value or median value of the feature 65 derived from the periodic portion 19AV_E of wells 14 No. 41 to 48.
- the prediction model group 41 is composed of a prediction model 70 for hERG channels, a prediction model 71 for Na channels, and a prediction model 72 for Ca channels.
- the prediction model 70 for hERG channels predicts the inhibition degree (hereinafter, sometimes referred to as inhibition degree DI; see FIG. 17) indicating the degree of inhibition of the K ion flow in the hERG channel by a candidate substance, or the activity degree (hereinafter, sometimes referred to as activity degree DAC; see FIG. 18) indicating the degree of activation.
- the prediction model 71 for Na channels predicts the inhibition degree indicating the degree of inhibition of the Na ion flow in the Na channel by a candidate substance, or the activity degree indicating the degree of activation.
- the prediction model 72 for Ca channels predicts the inhibition degree indicating the degree of inhibition of the Ca ion flow in the Ca channel by a candidate substance, or the activity degree indicating the degree of activation.
- Each of these prediction models 70 to 72 is a machine learning model constructed by a machine learning method such as a neural network.
- each of the prediction models 70 to 72 is a machine learning model that supports multi-label regression using a technique such as regressor chain. Therefore, each of the prediction models 70 to 72 is a model that takes into account the correlation between each ion channel.
- the prediction unit 49 inputs the feature amount 65AS to each prediction model 70-72, causing each prediction model 70-72 to output first predicted values 75A, 75B, and 75C.
- the first predicted value 75A output from the hERG channel prediction model 70 is a predicted value of the degree of inhibition indicating the degree to which the flow of K ions in the hERG channel is inhibited by the candidate substance, or the degree of activity indicating the degree of activation.
- the first predicted value 75B output from the Na channel prediction model 71 is a predicted value of the degree of inhibition indicating the degree to which the flow of Na ions in the Na channel is inhibited by the candidate substance, or the degree of activity indicating the degree of activation.
- the first predicted value 75C output from the Ca channel prediction model 72 is a predicted value of the degree of inhibition indicating the degree to which the flow of Ca ions in the Ca channel is inhibited by the candidate substance, or the degree of activity indicating the degree of activation.
- These first predicted values 75A-75C take a value greater than 0 and less than 1 if the flow of ions is predicted to be inhibited by the candidate substance, and take a value greater than 1 if the flow of ions is predicted to be activated by the candidate substance. If the flow of ions is predicted to be neither inhibited nor activated by the candidate substance, the first predicted values 75A-75C will be 1. In the following, unless there is a particular need to distinguish between them, the first predicted values 75A-75C will simply be referred to as first predicted values 75.
- the prediction result information 56 is a collection of first predicted values 75A-75C for each of wells 14 No. 1-40.
- the prediction result information 56 is a collection of first predicted values 75A-75C for each ion channel and each added amount.
- the prediction unit 49 also uses a prediction model other than the prediction models 70-72 to predict whether or not QT prolongation will occur in the iPS cardiomyocytes 15 due to the addition of the candidate substance.
- the prediction result information 56 also includes the prediction result of whether or not QT prolongation will occur in the iPS cardiomyocytes 15.
- the prediction model that predicts whether or not QT prolongation will occur in the iPS cardiomyocytes 15 receives the feature amount 65AS as in the prediction models 70-72. Alternatively, the first prediction values 75A-75C are input.
- a prediction model 70 for hERG channels is trained using training data 78.
- Training data 78 is a set of training features 65ASL and correct answer data 75ACA.
- Training features 65ASL are features 65AS of a candidate substance that was actually tested in the past.
- Correct answer data 75ACA are the results of actual measurement of the inhibition or activity of the candidate substance that provided the training features 65ASL in a test that was actually conducted in the past.
- the learning feature 65ASL is input to the prediction model 70 for the hERG channel.
- This causes the prediction model 70 for the hERG channel to output a first predicted value 75AL for learning.
- the first predicted value 75AL for learning is compared with the correct answer data 75ACA, and a loss calculation is performed for the prediction model 70 for the hERG channel using a loss function based on the comparison result.
- the internal parameters of the prediction model 70 for the hERG channel such as the filter coefficient, are updated according to the result of the loss calculation, and the prediction model 70 for the hERG channel is updated according to the update setting.
- the above series of processes including input of the learning features 65ASL to the prediction model 70 for the hERG channel, output of the first predicted value 75AL for learning from the prediction model 70 for the hERG channel, loss calculation, update setting, and update of the prediction model 70 for the hERG channel, are repeated while the learning data 78 is changed. Then, when the prediction accuracy of the first predicted value 75AL for learning with respect to the correct answer data 75ACA reaches a preset level, the repetition of the above series of processes is terminated.
- the prediction model 70 for the hERG channel whose prediction accuracy has thus reached a preset level is stored in the storage 30A. Note that learning may be terminated when the above series of processes have been repeated a predetermined number of times, regardless of the prediction accuracy. Furthermore, learning of the prediction model 70 for the hERG channel may be continued even after storage in the storage 30A.
- the group of dose-response curves 42 is composed of a first dose-response curve 80 and a second dose-response curve 81.
- the first dose-response curve 80 is a dose-response curve when the flow of ions in the ion channel is inhibited by a candidate substance.
- the second dose-response curve 81 is a dose-response curve when the flow of ions in the ion channel is activated by a candidate substance.
- the first dose-response curve 80 is a logistic curve represented by the following formula (1).
- the first dose-response curve 80 draws an inverted S-shaped curve in which the degree of inhibition DI gradually decreases from 1 to 0 as the amount of addition AA increases.
- the second dose-response curve 81 is a logistic curve represented by the following formula (2).
- DAC activity
- AA the amount of the candidate substance added as in the case of the first dose-response curve 80
- EC50 Median Effective Concentration
- M the asymptote value.
- the second dose-response curve 81 draws an S-shaped curve in which activity DAC gradually increases from 1 to M as added amount AA increases.
- the search unit 50 performs processing according to the procedure shown in FIG. 19 as an example.
- the search unit 50 derives the first predicted values 75A-75C for each added amount AA (step ST30). More specifically, as shown in FIG. 20 as an example, the search unit 50 sets the representative values of the first predicted values 75A-75C for wells 14 No. 1-10 as first predicted values 75A1-75C1 for added amount AA1, and sets the representative values of the first predicted values 75A-75C for wells 14 No. 11-20 as first predicted values 75A2-75C2 for added amount AA2. Similarly, the search unit 50 sets the representative values of the first predicted values 75A-75C for wells 14 No.
- first predicted values 75A3-75C3 for added amount AA3 sets the representative values of the first predicted values 75A-75C for wells 14 No. 22-30 as first predicted values 75A4-75C5 for added amount AA5.
- the representative value of the first predicted values 75A-75C for wells 14 31-40 is set as the first predicted value 75A4-75C4 for the addition amount AA4. This results in a complete set of first predicted values 75 for each ion channel and each addition amount.
- the representative value may be, for example, the average value, the median value, or the like.
- the search unit 50 searches for a first dose-response curve 80 that matches the first predicted values 75A-75C for each added amount of an ion channel (step ST31). Specifically, the search unit 50 changes the IC50 of the first dose-response curve 80, and calculates the squared error between the first dose-response curve 80 and the first predicted values 75A-75C for each added amount each time. The first dose-response curve 80 having the IC50 that minimizes the squared error is then determined to be the first dose-response curve 80 that matches the first predicted values 75A-75C for each added amount.
- the search unit 50 also searches for a second dose-response curve 81 that fits the first predicted values 75A-75C for each added amount of a certain ion channel (step ST32). Specifically, the search unit 50 changes the M and EC50 of the second dose-response curve 81, and calculates the squared error between the second dose-response curve 81 and the first predicted values 75A-75C for each added amount each time. Then, the second dose-response curve 81 having the M and EC50 that minimize the squared error is determined to be the second dose-response curve 81 that fits the first predicted values 75A-75C for each added amount.
- the search unit 50 compares the magnitude of the square error of the first dose-response curve 80 searched in step ST31 with the square error of the second dose-response curve 81 searched in step ST32 (step ST33). If the square error of the first dose-response curve 80 searched is smaller than the square error of the second dose-response curve 81 searched (YES in step ST33), that is, if the first dose-response curve 80 is a better fit to the first predicted values 75A to 75C for each added amount than the second dose-response curve 81, the search unit 50 derives the half inhibitory concentration IC50 from the first dose-response curve 80 searched (step ST34).
- the half inhibitory concentration IC50 derived from the first dose-response curve 80 is an example of an "index value" according to the technology disclosed herein.
- the search unit 50 derives the half effective concentration EC50 from the searched second dose-response curve 81 (step ST35).
- the half effective concentration EC50 derived from this second dose-response curve 81 is also an example of the "index value" according to the technology of the present disclosure.
- the search unit 50 repeats the processing of steps ST31 to ST35 until the half inhibitory concentration IC50 or half effective concentration EC50 of all ion channels is derived (NO in step ST36). In other words, the search unit 50 derives the half inhibitory concentration IC50 or half effective concentration EC50 of all ion channels.
- the search unit 50 outputs the first predicted value 75, the searched first dose-response curve 80 or the searched second dose-response curve 81, and the derived half inhibitory concentration IC50 or half effective concentration EC50 to the screen delivery control unit 51 as estimated reference information 21.
- the search unit 50 also outputs the prediction result of whether or not QT prolongation will occur in the iPS cardiomyocytes 15 due to the addition of the candidate substance to the screen delivery control unit 51 as estimated reference information 21.
- the estimated reference information 21 may be only the half inhibitory concentration IC50 or the half effective concentration EC50.
- FIG. 21 shows an example in which the Na channel is the target.
- the square error of the searched second dose-response curve 81 shown by the solid line is smaller than the square error of the searched first dose-response curve 80 shown by the dashed line.
- the example shows a case in which the half effective concentration EC50 is derived from the searched second dose-response curve 81.
- an evaluation AP 85 is stored in the storage 30B of the user terminal 11.
- the evaluation AP 85 is installed in the user terminal 11 by the user U.
- the evaluation AP 85 is an AP for causing the drug discovery support server 10 to evaluate the presence or absence of cardiotoxicity of a candidate substance.
- the CPU 32B of the user terminal 11 works in cooperation with the memory 31 etc. to function as a browser control unit 87.
- the browser control unit 87 controls the operation of a dedicated web browser for the evaluation AP 85.
- the browser control unit 87 reproduces various screens based on various screen data from the drug discovery support server 10, and displays the reproduced various screens on the display 34B.
- the browser control unit 87 also accepts various operation instructions input by the user U from the input device 35B via the various screens.
- the browser control unit 87 transmits various requests, including an evaluation request 20, to the drug discovery support server 10 in response to the operation instructions.
- a waveform input screen 90 as shown in FIG. 23 is displayed on the display 34B as an example.
- the waveform input screen 90 is provided with an input box 91 for the first variation waveform 18.
- a file of the first variation waveform 18 can be dropped into the input box 91.
- the user U selects the evaluation button 92.
- the browser control unit 87 When the evaluation button 92 is selected, the browser control unit 87 generates an evaluation request 20 including the first variation waveform 18 input into the input box 91, and transmits the generated evaluation request 20 to the drug discovery support server 10.
- an evaluation result display screen 95 as shown in FIG. 24 is displayed on the display 34B under the control of the browser control unit 87.
- the evaluation result display screen 95 displays the estimated reference information 21. That is, the evaluation result display screen 95 displays a graph of the first dose-response curve 80 or the second dose-response curve 81 with a plot of the first predicted value 75, and the median inhibitory concentration IC50 or median effective concentration EC50 for each ion channel.
- the evaluation result display screen 95 also displays the prediction result of whether or not the candidate substance will cause QT prolongation in iPS cardiomyocytes 15. In this way, the estimated reference information 21 is presented to the user U in the form of screen data distribution.
- a Save button 96 and an OK button 97 are provided at the bottom of the evaluation result display screen 95.
- the Save button 96 is selected, the display contents of the evaluation result display screen 95, including the estimated reference information 21, are stored in the storage 30B of the user terminal 11.
- the OK button 97 is selected, the display of the evaluation result display screen 95 is erased.
- the CPU 32A of the drug discovery support server 10 functions as a request reception unit 45, an RW control unit 46, a preprocessing unit 47, a feature derivation unit 48, a prediction unit 49, a search unit 50, and a screen delivery control unit 51, as shown in FIG. 4.
- the CPU 32B of the user terminal 11 functions as a browser control unit 87, as shown in FIG. 22.
- the display 34B of the user terminal 11 displays the waveform input screen 90 shown in FIG. 23 under the control of the browser control unit 87.
- the user U inputs the file of the desired first fluctuation waveform 18 into the input box 91 on the waveform input screen 90 and selects the evaluation button 92, an evaluation request 20 is sent from the browser control unit 87 to the drug discovery support server 10.
- the request receiving unit 45 receives the evaluation request 20 (YES in step ST100).
- the first fluctuation waveform 18 included in the evaluation request 20 is output from the request receiving unit 45 to the RW control unit 46, and is stored in the storage 30A under the control of the RW control unit 46 (step ST110).
- the terminal ID of the user terminal 11 included in the evaluation request 20 is output from the request receiving unit 45 to the screen distribution control unit 51.
- the first fluctuation waveform 18 is read from the storage 30A by the RW control unit 46 (step ST120).
- the first fluctuation waveform 18 is output from the RW control unit 46 to the pre-processing unit 47.
- the first fluctuation waveform 18 is subjected to a noise reduction process 60 and a selection process 61 as pre-processing (step ST130).
- the first fluctuation waveform 18AT composed of the periodic portion 19AV_E for each well 14 is output from the pre-processing unit 47 to the feature derivation unit 48.
- the feature 65AS is derived from the periodic portion 19AV_E (step ST140). Then, the feature information 55 shown in FIG. 11, which is a collection of the feature 65AS for each well 14, is output from the feature derivation unit 48 to the prediction unit 49.
- the feature amount 65AS is input to each prediction model 70-72, and first prediction values 75A-75C are output from each prediction model 70-72 (step ST150).
- the search unit 50 searches for a first dose-response curve 80 or a second dose-response curve 81 that fits the first predicted value 75 for each added amount. Then, from the searched first dose-response curve 80 or second dose-response curve 81, the half inhibitory concentration IC50 or half effective concentration EC50 is derived as an index value (step ST160).
- Estimated reference information 21 including the searched first dose-response curve 80 or second dose-response curve 81, the derived half inhibitory concentration IC50 or half effective concentration EC50, etc. is output from the search unit 50 to the screen distribution control unit 51.
- the screen delivery control unit 51 generates screen data for the evaluation result display screen 95 shown in FIG. 24 based on the estimated reference information 21.
- the screen data for the evaluation result display screen 95 is delivered to the user terminal 11 that sent the evaluation request 20 under the control of the screen delivery control unit 51 (step ST170).
- the screen data of the evaluation result display screen 95 is reproduced, and the reproduced evaluation result display screen 95 is displayed on the display 34B. In this way, the estimated reference information 21 is presented to the user U.
- the prediction unit 49 of the drug discovery support server 10 obtains a first predicted value 75 for each of multiple ion channels present in the iPS cardiomyocytes 15, which are cardiomyocytes derived from human iPS cells, and for each added amount of a drug candidate substance.
- the first predicted value 75 is output from the prediction models 70-72 based on the first fluctuation waveform 18.
- the first fluctuation waveform 18 is a fluctuation waveform of the extracellular potential of the iPS cardiomyocytes 15, and is measured when the candidate substance is added to the iPS cardiomyocytes 15 while changing the added amount.
- the first predicted value 75 is a predicted value of the degree of inhibition indicating the degree to which the flow of ions in the multiple ion channels is inhibited by the candidate substance.
- the search unit 50 derives the median inhibitory concentration IC50, which is an index value indicating the dose-response relationship of the candidate substance, for each ion channel based on the first predicted value 75 for each added amount.
- the screen delivery control unit 51 presents the estimated reference information 21 to the user U by delivering screen data of the evaluation result display screen 95, which includes the estimated reference information 21, to the user terminal 11.
- the estimated reference information 21 is information corresponding to the median inhibitory concentration IC50, which is an index value, and is referenced to estimate the mechanism of action of the candidate substance.
- the user U can grasp at a glance the extent to which the flow of ions in each ion channel is inhibited by the candidate substance. Therefore, for example, if QT prolongation occurs in iPS cardiomyocytes 15, it becomes possible to easily estimate the mechanism of action by which the candidate substance led to the expression of QT prolongation, such as which ion channel's flow of ions was inhibited by the candidate substance to cause QT prolongation. Conversely, if QT prolongation does not occur in iPS cardiomyocytes 15, it becomes possible to easily estimate the mechanism of action by which the candidate substance did not lead to the expression of QT prolongation. If it becomes possible to easily estimate the mechanism of action by a candidate substance, it becomes easy to obtain guidelines for the structure of a candidate substance that does not cause QT prolongation, which will greatly promote the development of pharmaceuticals.
- the search unit 50 searches for the first dose-response curve 80 or the second dose-response curve 81 that fits the first predicted value 75 for each added amount, and derives the half inhibitory concentration IC50 or the half effective concentration EC50 from the first dose-response curve 80 or the second dose-response curve 81 that has been searched for. This makes it possible to derive a more reliable half inhibitory concentration IC50 or half effective concentration EC50.
- the first predicted value 75 is not only a predicted value of the degree of inhibition, but also a predicted value of the degree of activation indicating the degree to which the flow of ions in the ion channel is activated by the candidate substance.
- dose-response curves There are two types of dose-response curves: a first dose-response curve 80 when the flow of ions in the ion channel is inhibited by the candidate substance, and a second dose-response curve 81 when the flow of ions in the ion channel is activated by the candidate substance.
- the search unit 50 derives the half inhibitory concentration IC50 or half effective concentration EC50 from the first dose-response curve 80 or the second dose-response curve 81, whichever is more suitable for the first predicted value 75 for each added amount. Therefore, the mechanism of action of the candidate substance can be estimated by taking into account not only the inhibitory effect of the candidate substance on the flow of ions in the ion channel but also the activating effect. Also, a more reliable half inhibitory concentration IC50 or half effective concentration EC50 can be derived.
- the screen distribution control unit 51 presents the first dose-response curve 80 or the second dose-response curve 81 to the user U as the estimated reference information 21. This allows the user U to immediately understand which ion channel's ion flow is inhibited or activated by the candidate substance.
- the curve used to search for the dose-response curve is a logistic curve. Logistic curves are commonly used to search for dose-response curves. Therefore, following the conventional method, it is possible to easily search for a dose-response curve that fits the first predicted value 75 for each added amount. Note that the curve used to search for the dose-response curve may be a probit curve, etc.
- the first predicted value 75 is obtained by inputting the feature quantity 65AS derived from the first fluctuation waveform 18 into the prediction models 70 to 72. This makes it easy to improve the prediction accuracy of the first predicted value 75. Note that instead of or in addition to the feature quantity 65AS, the first fluctuation waveform 18 itself may be input to the prediction models 70 to 72.
- the request receiving unit 45 receives the evaluation request 20 to obtain the first fluctuation waveform 18.
- the feature derivation unit 48 derives the feature 65AS from the first fluctuation waveform 18.
- the prediction unit 49 inputs the feature 65AS to the prediction models 70-72, causing the prediction models 70-72 to output the first predicted values 75A-75C.
- the drug discovery support server 10 single-handedly undertakes the process of obtaining the first fluctuation waveform 18, the process of deriving the feature 65AS from the first fluctuation waveform 18, and the process of outputting the first predicted values 75A-75C using the prediction models 70-72.
- the processing load of the CPU 32B of the user terminal 11 can be reduced, for example, compared to a case in which the CPU 32B of the user terminal 11 is responsible for the process of deriving the feature 65AS from the first fluctuation waveform 18 and the process of outputting the first predicted values 75A-75C using the prediction models 70-72.
- the CPU 32B of the user terminal 11 may be responsible for the process of deriving the feature amount 65AS and the process of outputting the first predicted values 75A to 75C.
- a CPU of a device other than the drug discovery support server 10 and the user terminal 11 may be responsible for the process of deriving the feature amount 65AS and the process of outputting the first predicted values 75A to 75C.
- the pre-processing unit 47 performs noise reduction processing 60 on the first fluctuation waveform 18 prior to deriving the feature quantity 65AS. This makes it possible to derive a more reliable feature quantity 65AS, and as a result, the prediction accuracy of the first predicted value 75 can be improved.
- the first fluctuation waveform 18 has a periodicity according to the pulsation of the iPS cardiomyocytes 15.
- the pre-processing unit 47 performs an averaging process of multiple periodic portions 19 of the first fluctuation waveform 18 as noise reduction process 60. This makes it possible to effectively reduce noise on the first fluctuation waveform 18.
- the first fluctuation waveform 18 is measured using multiple microelectrodes 17 for one iPS cardiomyocyte 15.
- the preprocessing unit 47 selects one of the multiple first fluctuation waveforms 18 (periodic portion 19AV) measured by the multiple microelectrodes 17 according to preset conditions as the first fluctuation waveform 18 (periodic portion 19AV_E) from which the feature value 65AS is derived. This makes it possible to derive a more reliable feature value 65AS, and as a result, improves the prediction accuracy of the first predicted value 75.
- Feature quantity 65AS includes the conduction velocity CV of first fluctuation waveform 18.
- the conduction velocity CV of first fluctuation waveform 18 contributes to improving the prediction accuracy of first predicted value 75, particularly first predicted value 75B related to the Na channel. This makes it possible to further improve the prediction accuracy of first predicted value 75.
- the feature amount 65AS is normalized by the reference feature amount 65S derived from the reference first fluctuation waveform (such as the periodic portion 19AV_E shown in FIG. 8) measured when the candidate substance was not added to the iPS cardiomyocytes 15. This makes it possible to eliminate individual differences in the iPS cardiomyocytes 15.
- the IC50 (EC50) experimental value 110 is input to each prediction model 70 to 72 in addition to the feature amount 65AS, and the first prediction values 75A to 75C are output from each prediction model 70 to 72.
- the learning data 112 of the prediction model 70 for the hERG channel includes the learning experimental value 110L in addition to the learning feature 65ASL and the correct answer data 75ACA of the first embodiment. Some of the learning data 112 includes the learning experimental value 110L, while others do not.
- the prediction model 70 for the hERG channel is trained in two ways: when the learning experimental value 110L is input, and when it is not.
- the processing in the learning phase of the prediction model 71 for the Na channel and the prediction model 72 for the Ca channel is basically the same, except for the contents of the learning data 112. For this reason, the illustration and description of the prediction model 71 for the Na channel and the prediction model 72 for the Ca channel are omitted.
- the first predicted value 75 is obtained by inputting the IC50 (EC50) experimental value 110 into the prediction models 70 to 72 in addition to the feature amount 65AS. Since there is an additional clue for prediction, that is, the IC50 (EC50) experimental value 110, the prediction accuracy of the first predicted value 75 can be further improved.
- prediction models 70 to 72 are models that have been trained in two ways: when IC50 (EC50) experimental value 110 is input and when it is not. Therefore, it is possible to handle both cases where IC50 (EC50) experimental value 110 is present and where it is not.
- an experimental IC50 (EC50) value 110 from a hERG test is shown as an example, but this is not limiting. If there are experimental values related to Na channels and/or Ca channels, they may be input into the prediction models 70 to 72.
- the prediction unit 49 derives second predicted values 116A, 116B, and 116C of the index value indicating the dose-response relationship of the candidate substance based on the structural information 115 of the candidate substance. Then, in addition to the feature amount 65AS, the derived second predicted values 116A to 116C are input to each of the prediction models 70 to 72, and the prediction models 70 to 72 are caused to output first predicted values 75A to 75C.
- the structural information 115 is a character string expressing the chemical structure of the candidate substance using the Simplified Molecular Input Line Entry System (SMILES) notation.
- the structural information 115 is input to the index value prediction model 117.
- the index value prediction model 117 is a machine learning model such as LightGBM (Light Gradient Boosting Machine) that derives a descriptor from the structural information 115 using RDKit and outputs second predicted values 116A to 116C in response to the input of the descriptor.
- the second predicted value 116A is a predicted value of the half inhibitory concentration IC50 or half effective concentration EC50 for the hERG channel.
- the second predicted value 116B is a predicted value of the half inhibitory concentration IC50 or half effective concentration EC50 for the Na channel.
- the second predicted value 116C is a predicted value of the half maximal inhibitory concentration IC50 or half maximal effective concentration EC50 for the Ca channel.
- the first predicted values 75A-75C are obtained by inputting the second predicted values 116A-116C of the index value indicating the dose-response relationship of the candidate substance, which is derived based on the structural information 115 of the candidate substance, in addition to the feature amount 65AS, into the prediction models 70-72. Since the second predicted values 116A-116C provide more clues for prediction, the prediction accuracy of the first predicted value 75 can be further improved. Also, when the IC50 (EC50) experimental value 110 of the second embodiment is not available, the second predicted values 116A-116C can be input into the prediction models 70-72 instead of the IC50 (EC50) experimental value 110.
- the structural information 115 is not limited to a character string that represents the chemical structure of the candidate substance using the SMILES notation shown as an example. It may be a MOL (Molecular Design Limited) file that represents the chemical structure of the candidate substance, or an SDF (Structure-Data File), etc. In any case, it is preferable for the description method to be capable of uniquely determining a three-dimensional structure such as an isomer, and it is even more preferable for the description method to be capable of representing the three-dimensional coordinate information of the molecule.
- the index value prediction model 117 may be a graph neural network that derives a graph structure of the candidate substance from the structural information 115 and makes a prediction based on the graph structure.
- the index value prediction model 117 may also make a prediction by a docking simulation based on the structural information 115 and the three-dimensional structure of each ion channel.
- the second embodiment and the third embodiment may be combined. That is, in addition to the feature amount 65AS, the IC50 (EC50) experimental value 110 and the second predicted values 116B and 116C derived based on the structural information 115 of the candidate substance may be input to the prediction models 70-72, so that the first predicted values 75A-75C may be output from the prediction models 70-72.
- the IC50 (EC50) experimental value 110 and the second predicted values 116B and 116C derived based on the structural information 115 of the candidate substance may be input to the prediction models 70-72, so that the first predicted values 75A-75C may be output from the prediction models 70-72.
- the learning data 78 is generated from data of tests that have actually been conducted in the past, but this is not limiting.
- the learning data 78 may include simulation data.
- the first simulation model 120 uses the degree of inhibition or activity of ion flow in each ion channel as a parameter to reproduce, through simulation, a second fluctuation waveform 121SM according to the set degree of inhibition or activity.
- the second fluctuation waveform 121SM is a fluctuation waveform of the intracellular potential of an iPS cardiomyocyte 15.
- the first simulation model 120 outputs the second fluctuation waveform 121SM to the second simulation model 122.
- the second simulation model 122 converts the second fluctuation waveform 121SM into the first fluctuation waveform 18SM.
- the learning feature 65ASL and the correct answer data 75ACA derived based on this first fluctuation waveform 18SM are used as the learning data 78.
- the second simulation model 122 a bidomain model or an EMI (Extracellular-Membrane-Intracellular) model can be used as the second simulation model 122.
- the prediction models 70 to 72 are models trained using the training data 78 including the feature amount 65AS and the like based on the first variation waveform 18SM, which is simulation data. Therefore, even if there is a relatively small amount of data from tests that have actually been conducted in the past, the amount of training data 78 can be enriched. As a result, the prediction accuracy of the first predicted values 75A to 75C by the prediction models 70 to 72 can be improved.
- the first fluctuation waveform 18SM is generated using a first simulation model 120 that reproduces the second fluctuation waveform 121SM, which is the fluctuation waveform of the intracellular potential of the iPS cardiomyocyte 15, and a second simulation model 122 that converts the second fluctuation waveform 121SM into the first fluctuation waveform 18SM. Therefore, it is possible to generate a first fluctuation waveform 18SM that is more suitable for the learning data 78.
- the allocation of candidate substances and the amount of added candidate substance AA to each well 14 is not limited to the example shown in Table 25 in FIG. 2.
- Table 130 shows an example in which the candidate substance is changed every five wells 14, such as candidate substance Z1 to wells 14 No. 1 to 5, candidate substance Z2 to wells 14 No. 6 to 10, etc.
- Table 130 also shows an example in which the candidate substance is added in an amount of added candidate substance AA1 to wells 14 No. 1, 6, etc., candidate substance is added in an amount of added candidate substance AA2 to wells 14 No. 2, 7, etc., candidate substance is added in an amount of added candidate substance AA3 to wells 14 No. 3, 8, etc., candidate substance is added in an amount of added candidate substance AA4 to wells 14 No. 4, 9, etc., and no candidate substance is added to wells 14 No. 5, 10, etc.
- the index value is not limited to the exemplary median inhibitory concentration IC50 and median effective concentration EC50.
- the median lethal concentration LC50 Median Lethal Concentration
- LC50 Median Lethal Concentration
- the drug discovery support server 10 may be installed in a pharmaceutical company or a pharmaceutical development contract organization, or in a data center independent of the pharmaceutical company or the pharmaceutical development contract organization.
- the estimated reference information 21 itself may be delivered to the user terminal 11.
- the user terminal 11 generates the evaluation result display screen 95 based on the estimated reference information 21 under the control of the browser control unit 87.
- the method of presenting the estimated reference information 21 to the user U is not limited to the example of presenting it by distributing screen data.
- the estimated reference information 21 may be presented to the user U by printing it on a paper medium, or by attaching it to an e-mail and sending it to the user terminal 11.
- the hardware configuration of the computer constituting the drug discovery support server 10 can be modified in various ways.
- the drug discovery support server 10 can be composed of multiple computers separated as hardware in order to improve processing power and reliability.
- the functions of the request reception unit 45, RW control unit 46, and preprocessing unit 47, and the functions of the feature derivation unit 48, prediction unit 49, search unit 50, and screen distribution control unit 51 are distributed and assigned to two computers.
- the drug discovery support server 10 is composed of two computers. Some or all of the functions of the drug discovery support server 10 may be assigned to the user terminal 11.
- the hardware configuration of the computer of the drug discovery support server 10 can be changed as appropriate according to the required performance such as processing power, safety, and reliability.
- APs such as the operating program 40 can of course be duplicated or stored in multiple storage devices in order to ensure safety and reliability.
- the hardware structure of the processing unit that performs various processes, such as the request receiving unit 45, RW control unit 46, pre-processing unit 47, feature derivation unit 48, prediction unit 49, search unit 50, screen delivery control unit 51, and browser control unit 87, can use the various processors shown below.
- the various processors include the CPUs 32A and 32B, which are general-purpose processors that execute software (operation program 40 and evaluation AP 85) and function as various processing units, as well as programmable logic devices (PLDs) such as FPGAs (Field Programmable Gate Arrays), which are processors whose circuit configuration can be changed after manufacture, and dedicated electrical circuits such as ASICs (Application Specific Integrated Circuits), which are processors with circuit configurations designed specifically to execute specific processes.
- PLDs programmable logic devices
- FPGAs Field Programmable Gate Arrays
- ASICs Application Specific Integrated Circuits
- a single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs and/or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.
- Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, as typified by client and server computers, and this processor functions as multiple processing units. Second, a form in which a processor is used to realize the functions of the entire system, including multiple processing units, with a single IC (Integrated Circuit) chip, as typified by system-on-chip (SoC). In this way, the various processing units are configured as a hardware structure using one or more of the various processors listed above.
- SoC system-on-chip
- the hardware structure of these various processors can be an electrical circuit that combines circuit elements such as semiconductor elements.
- a processor is provided.
- the processor a first fluctuation waveform which is a fluctuation waveform of an extracellular potential of an iPS cardiomyocyte, which is a cardiomyocyte derived from a human iPS cell, the first fluctuation waveform being measured when a candidate substance for a drug is added to the iPS cardiomyocyte while changing the amount of addition, and a first predicted value of an inhibition degree indicating a degree to which the flow of ions in a plurality of ion channels present in the iPS cardiomyocyte is inhibited by the candidate substance is output from a prediction model, the first predicted value being obtained for each of the ion channels and for each of the added amounts; deriving an index value indicating a dose-response relationship of the candidate substance for each of the ion channels based on the first predicted value for each of the added amounts; presenting to a user putative reference information corresponding to the index value, the putative reference information being referred to for presuming a mechanism of action of
- the processor Finding a dose-response curve that fits the first predicted value for each dose; 2.
- the first predicted value is a predicted value of the inhibition degree and also a predicted value of the activity degree indicating the degree to which the candidate substance activates the flow of ions through the ion channel;
- the dose-response curve is a first dose-response curve when the flow of ions through the ion channel is inhibited by the candidate substance; a second dose-response curve when the ion flow through the ion channel is activated by the candidate substance;
- the processor The drug discovery support device according to claim 2, wherein the index value is derived from one of the first dose-response curve and the second dose-response curve, whichever is more suitable for the first predicted value for each added amount.
- the processor Acquiring the first variation waveform; Deriving the feature amount from the first fluctuation waveform; The drug discovery support device according to claim 6, wherein the feature amount is input to the prediction model, and the first predicted value is output from the prediction model.
- the processor The drug discovery support device according to claim 7, further comprising: performing noise reduction processing on the first fluctuation waveform prior to deriving the feature amount.
- the first fluctuation waveform has a periodicity corresponding to the pulsation of the iPS cardiomyocytes, The processor, The drug discovery support device according to claim 8, wherein the noise reduction processing comprises averaging processing of a plurality of periodic portions of the first fluctuation waveform.
- the measurement of the first fluctuation waveform is performed with respect to one of the iPS cardiomyocytes using a plurality of electrodes;
- the processor A drug discovery support device described in any one of appendix 7 to appendix 9, which selects one of the multiple first fluctuation waveforms measured by the multiple electrodes as the first fluctuation waveform from which the feature is derived in accordance with preset conditions.
- the drug discovery support device according to any one of supplementary items 6 to 10, wherein the feature amount includes a conduction velocity of the first fluctuation waveform.
- [Additional Item 12] A drug discovery support device described in any one of appendix 6 to appendix 11, wherein the feature is normalized by a reference feature derived from a reference first fluctuation waveform measured when the candidate substance is not added to the iPS cardiomyocytes. [Additional Item 13] If there is an experimental value of the index value showing a dose-response relationship of the candidate substance, 13. The drug discovery support device according to any one of supplementary items 6 to 12, wherein the first predicted value is obtained by inputting the experimental value in addition to the feature amount into the prediction model. [Additional Item 14] 14.
- the drug discovery support device is a model that has been trained in two ways, a case in which the experimental value is input and a case in which the experimental value is not input.
- the prediction model is a model that has been trained in two ways, a case in which the experimental value is input and a case in which the experimental value is not input.
- the first predicted value is obtained by inputting a second predicted value of the index value indicating a dose-response relationship of the candidate substance, which is derived based on structural information of the candidate substance, in addition to the feature amount, into the prediction model.
- the prediction model is a model trained using training data including simulation data.
- the technology disclosed herein can be appropriately combined with the various embodiments and/or various modified examples described above. Furthermore, it is not limited to the above embodiments, and various configurations can be adopted without departing from the gist of the technology. Furthermore, the technology disclosed herein extends to not only programs, but also storage media that non-temporarily store programs, and computer program products that include programs.
- a and/or B is synonymous with “at least one of A and B.”
- a and/or B means that it may be just A, or just B, or a combination of A and B.
- the same concept as “A and/or B” is also applied when three or more things are linked together with “and/or.”
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biotechnology (AREA)
- General Health & Medical Sciences (AREA)
- Hematology (AREA)
- Urology & Nephrology (AREA)
- Medical Informatics (AREA)
- Cell Biology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Microbiology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Pathology (AREA)
- Medicinal Chemistry (AREA)
- General Physics & Mathematics (AREA)
- Food Science & Technology (AREA)
- Toxicology (AREA)
- Tropical Medicine & Parasitology (AREA)
- Organic Chemistry (AREA)
- Probability & Statistics with Applications (AREA)
- Physiology (AREA)
- Bioethics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Software Systems (AREA)
Abstract
Description
一例として図1に示すように、創薬支援サーバ10は、ユーザ端末11にネットワーク12を介して接続されている。創薬支援サーバ10は、本開示の技術に係る「創薬支援装置」の一例である。ユーザ端末11は、例えば医薬品を開発する製薬会社、または製薬会社から医薬品の開発業務を受託する機関、すなわち医薬品開発業務受託機関(CRO:Contract Research Organization)に設置される。ユーザ端末11は、製薬会社または医薬品開発業務受託機関において医薬品の開発に携わるユーザUが操作する。ネットワーク12は、例えばインターネットあるいは公衆通信網等のWAN(Wide Area Network)である。なお、図1においては1台のユーザ端末11しか創薬支援サーバ10に接続されていないが、実際には複数の製薬会社または医薬品開発業務受託機関の複数台のユーザ端末11が創薬支援サーバ10に接続されている。
従来、安全性薬理試験S7Bとして、hERGチャネルへの候補物質の阻害作用を評価するhERG試験が一般的に行われている。このため、候補物質によっては、創薬支援サーバ10による評価の以前にhERG試験が既に行われていて、hERGチャネルに係る半数阻害濃度IC50または半数効果濃度EC50の実験値(以下、IC50(EC50)実験値と表記する)110を計測済みのものがある。そこで第2実施形態では、一例として図26に示すように、hERG試験のIC50(EC50)実験値110がある場合、特徴量65ASに加えてIC50(EC50)実験値110を各予測モデル70~72に入力し、各予測モデル70~72から第1予測値75A~75Cを出力させる。
一例として図28に示す第3実施形態では、予測部49は、候補物質の構造情報115に基づいて、候補物質の用量反応関係を示す指標値の第2予測値116A、116B、および116Cを導出する。そして、特徴量65ASに加えて、導出した第2予測値116A~116Cを各予測モデル70~72に入力し、各予測モデル70~72から第1予測値75A~75Cを出力させる。
上記第1実施形態では、過去に実際に行われた試験のデータから学習データ78を生成しているが、これに限らない。一例として図29に示すように、シミュレーションデータを学習データ78に含めてもよい。
プロセッサを備え、
前記プロセッサは、
ヒトiPS細胞由来の心筋細胞であるiPS心筋細胞の細胞外電位の変動波形である第1変動波形であって、添加量を変更しながら医薬品の候補物質を前記iPS心筋細胞に添加した場合に計測された第1変動波形に基づいて、前記iPS心筋細胞に存在する複数のイオンチャネルのイオンの流通が前記候補物質によって阻害された程度を示す阻害度の第1予測値を予測モデルから出力させることで得られた、前記イオンチャネル毎、かつ、前記添加量毎の前記第1予測値を取得し、
前記添加量毎の前記第1予測値に基づいて、前記イオンチャネル毎に、前記候補物質の用量反応関係を示す指標値を導出し、
前記指標値に応じた推定参照情報であって、前記候補物質による作用機序を推定するために参照される推定参照情報をユーザに提示する、
創薬支援装置。
[付記項2]
前記プロセッサは、
前記添加量毎の前記第1予測値に適合する用量反応曲線を探索し、
探索した前記用量反応曲線から前記指標値を導出する付記項1に記載の創薬支援装置。
[付記項3]
前記第1予測値は、前記阻害度の予測値であることに加えて、前記イオンチャネルのイオンの流通が前記候補物質によって活性された程度を示す活性度の予測値でもあり、
前記用量反応曲線は、
前記イオンチャネルのイオンの流通が前記候補物質によって阻害された場合の第1用量反応曲線と、
前記イオンチャネルのイオンの流通が前記候補物質によって活性された場合の第2用量反応曲線との2種類があり、
前記プロセッサは、
前記第1用量反応曲線および前記第2用量反応曲線のうち、前記添加量毎の前記第1予測値により適合するほうから前記指標値を導出する付記項2に記載の創薬支援装置。
[付記項4]
前記プロセッサは、
探索した前記用量反応曲線を前記推定参照情報として前記ユーザに提示する付記項2または付記項3に記載の創薬支援装置。
[付記項5]
前記用量反応曲線の探索に用いる曲線はロジスティック曲線である付記項2から付記項4のいずれか1項に記載の創薬支援装置。
[付記項6]
前記第1予測値は、前記第1変動波形から導出された特徴量を前記予測モデルに入力することで得られる付記項1から付記項5のいずれか1項に記載の創薬支援装置。
[付記項7]
前記プロセッサは、
前記第1変動波形を取得し、
前記第1変動波形から前記特徴量を導出し、
前記特徴量を前記予測モデルに入力することで、前記予測モデルから前記第1予測値を出力させる付記項6に記載の創薬支援装置。
[付記項8]
前記プロセッサは、
前記特徴量の導出に先立ち、前記第1変動波形に対してノイズ低減処理を施す付記項7に記載の創薬支援装置。
[付記項9]
前記第1変動波形は前記iPS心筋細胞の拍動に応じた周期性を有し、
前記プロセッサは、
前記ノイズ低減処理として、前記第1変動波形の複数の周期性部分の加算平均処理を行う付記項8に記載の創薬支援装置。
[付記項10]
前記第1変動波形の計測は、1つの前記iPS心筋細胞に対して複数の電極により行われ、
前記プロセッサは、
予め設定された条件にしたがって、複数の前記電極により計測された複数の前記第1変動波形のうちの1つを、前記特徴量を導出する第1変動波形として選出する付記項7から付記項9のいずれか1項に記載の創薬支援装置。
[付記項11]
前記特徴量は前記第1変動波形の伝導速度を含む付記項6から付記項10のいずれか1項に記載の創薬支援装置。
[付記項12]
前記特徴量は、前記候補物質を前記iPS心筋細胞に添加しなかった場合に計測された基準第1変動波形から導出された基準特徴量により規格化されている付記項6から付記項11のいずれか1項に記載の創薬支援装置。
[付記項13]
前記候補物質の用量反応関係を示す前記指標値の実験値がある場合、
前記第1予測値は、前記特徴量に加えて前記実験値を前記予測モデルに入力することで得られる付記項6から付記項12のいずれか1項に記載の創薬支援装置。
[付記項14]
前記予測モデルは、前記実験値が入力される場合と入力されない場合の2通りで学習が行われたモデルである付記項13に記載の創薬支援装置。
[付記項15]
前記第1予測値は、前記特徴量に加えて、前記候補物質の構造情報に基づいて導出された、前記候補物質の用量反応関係を示す前記指標値の第2予測値を前記予測モデルに入力することで得られる付記項6から付記項14のいずれか1項に記載の創薬支援装置。
[付記項16]
前記予測モデルは、シミュレーションデータを含む学習データを用いて学習されたモデルである付記項1から付記項15のいずれか1項に記載の創薬支援装置。
[付記項17]
シミュレーションデータは、前記iPS心筋細胞の細胞内電位の変動波形である第2変動波形を再現する第1シミュレーションモデルと、前記第2変動波形を前記第1変動波形に変換する第2シミュレーションモデルとを用いて生成される付記項16に記載の創薬支援装置。
Claims (19)
- プロセッサを備え、
前記プロセッサは、
ヒトiPS細胞由来の心筋細胞であるiPS心筋細胞の細胞外電位の変動波形である第1変動波形であって、添加量を変更しながら医薬品の候補物質を前記iPS心筋細胞に添加した場合に計測された第1変動波形に基づいて、前記iPS心筋細胞に存在する複数のイオンチャネルのイオンの流通が前記候補物質によって阻害された程度を示す阻害度の第1予測値を予測モデルから出力させることで得られた、前記イオンチャネル毎、かつ、前記添加量毎の前記第1予測値を取得し、
前記添加量毎の前記第1予測値に基づいて、前記イオンチャネル毎に、前記候補物質の用量反応関係を示す指標値を導出し、
前記指標値に応じた推定参照情報であって、前記候補物質による作用機序を推定するために参照される推定参照情報をユーザに提示する、
創薬支援装置。 - 前記プロセッサは、
前記添加量毎の前記第1予測値に適合する用量反応曲線を探索し、
探索した前記用量反応曲線から前記指標値を導出する請求項1に記載の創薬支援装置。 - 前記第1予測値は、前記阻害度の予測値であることに加えて、前記イオンチャネルのイオンの流通が前記候補物質によって活性された程度を示す活性度の予測値でもあり、
前記用量反応曲線は、
前記イオンチャネルのイオンの流通が前記候補物質によって阻害された場合の第1用量反応曲線と、
前記イオンチャネルのイオンの流通が前記候補物質によって活性された場合の第2用量反応曲線との2種類があり、
前記プロセッサは、
前記第1用量反応曲線および前記第2用量反応曲線のうち、前記添加量毎の前記第1予測値により適合するほうから前記指標値を導出する請求項2に記載の創薬支援装置。 - 前記プロセッサは、
探索した前記用量反応曲線を前記推定参照情報として前記ユーザに提示する請求項2に記載の創薬支援装置。 - 前記用量反応曲線の探索に用いる曲線はロジスティック曲線である請求項2に記載の創薬支援装置。
- 前記第1予測値は、前記第1変動波形から導出された特徴量を前記予測モデルに入力することで得られる請求項1に記載の創薬支援装置。
- 前記プロセッサは、
前記第1変動波形を取得し、
前記第1変動波形から前記特徴量を導出し、
前記特徴量を前記予測モデルに入力することで、前記予測モデルから前記第1予測値を出力させる請求項6に記載の創薬支援装置。 - 前記プロセッサは、
前記特徴量の導出に先立ち、前記第1変動波形に対してノイズ低減処理を施す請求項7に記載の創薬支援装置。 - 前記第1変動波形は前記iPS心筋細胞の拍動に応じた周期性を有し、
前記プロセッサは、
前記ノイズ低減処理として、前記第1変動波形の複数の周期性部分の加算平均処理を行う請求項8に記載の創薬支援装置。 - 前記第1変動波形の計測は、1つの前記iPS心筋細胞に対して複数の電極により行われ、
前記プロセッサは、
予め設定された条件にしたがって、複数の前記電極により計測された複数の前記第1変動波形のうちの1つを、前記特徴量を導出する第1変動波形として選出する請求項7に記載の創薬支援装置。 - 前記特徴量は前記第1変動波形の伝導速度を含む請求項6に記載の創薬支援装置。
- 前記特徴量は、前記候補物質を前記iPS心筋細胞に添加しなかった場合に計測された基準第1変動波形から導出された基準特徴量により規格化されている請求項6に記載の創薬支援装置。
- 前記候補物質の用量反応関係を示す前記指標値の実験値がある場合、
前記第1予測値は、前記特徴量に加えて前記実験値を前記予測モデルに入力することで得られる請求項6に記載の創薬支援装置。 - 前記予測モデルは、前記実験値が入力される場合と入力されない場合の2通りで学習が行われたモデルである請求項13に記載の創薬支援装置。
- 前記第1予測値は、前記特徴量に加えて、前記候補物質の構造情報に基づいて導出された、前記候補物質の用量反応関係を示す前記指標値の第2予測値を前記予測モデルに入力することで得られる請求項6に記載の創薬支援装置。
- 前記予測モデルは、シミュレーションデータを含む学習データを用いて学習されたモデルである請求項1に記載の創薬支援装置。
- シミュレーションデータは、前記iPS心筋細胞の細胞内電位の変動波形である第2変動波形を再現する第1シミュレーションモデルと、前記第2変動波形を前記第1変動波形に変換する第2シミュレーションモデルとを用いて生成される請求項16に記載の創薬支援装置。
- ヒトiPS細胞由来の心筋細胞であるiPS心筋細胞の細胞外電位の変動波形である第1変動波形であって、添加量を変更しながら医薬品の候補物質を前記iPS心筋細胞に添加した場合に計測された第1変動波形に基づいて、前記iPS心筋細胞に存在する複数のイオンチャネルのイオンの流通が前記候補物質によって阻害された程度を示す阻害度の第1予測値を予測モデルから出力させることで得られた、前記イオンチャネル毎、かつ、前記添加量毎の前記第1予測値を取得すること、
前記添加量毎の前記第1予測値に基づいて、前記イオンチャネル毎に、前記候補物質の用量反応関係を示す指標値を導出すること、並びに、
前記指標値に応じた推定参照情報であって、前記候補物質による作用機序を推定するために参照される推定参照情報をユーザに提示すること、
を含む創薬支援装置の作動方法。 - ヒトiPS細胞由来の心筋細胞であるiPS心筋細胞の細胞外電位の変動波形である第1変動波形であって、添加量を変更しながら医薬品の候補物質を前記iPS心筋細胞に添加した場合に計測された第1変動波形に基づいて、前記iPS心筋細胞に存在する複数のイオンチャネルのイオンの流通が前記候補物質によって阻害された程度を示す阻害度の第1予測値を予測モデルから出力させることで得られた、前記イオンチャネル毎、かつ、前記添加量毎の前記第1予測値を取得すること、
前記添加量毎の前記第1予測値に基づいて、前記イオンチャネル毎に、前記候補物質の用量反応関係を示す指標値を導出すること、並びに、
前記指標値に応じた推定参照情報であって、前記候補物質による作用機序を推定するために参照される推定参照情報をユーザに提示すること、
を含む処理をコンピュータに実行させる創薬支援装置の作動プログラム。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202480038844.7A CN121285858A (zh) | 2023-06-15 | 2024-06-11 | 药物研发支援装置、药物研发支援装置的工作方法及药物研发支援装置的工作程序 |
| EP24823389.2A EP4730345A1 (en) | 2023-06-15 | 2024-06-11 | Drug discovery assistance device, method for operating drug discovery assistance device, and program for operating drug discovery assistance device |
| JP2025527948A JPWO2024257774A1 (ja) | 2023-06-15 | 2024-06-11 | |
| US19/417,122 US20260100242A1 (en) | 2023-06-15 | 2025-12-11 | Drug discovery support apparatus, method for operating drug discovery support apparatus, and program for operating drug discovery support apparatus |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2023098741 | 2023-06-15 | ||
| JP2023-098741 | 2023-06-15 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US19/417,122 Continuation US20260100242A1 (en) | 2023-06-15 | 2025-12-11 | Drug discovery support apparatus, method for operating drug discovery support apparatus, and program for operating drug discovery support apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024257774A1 true WO2024257774A1 (ja) | 2024-12-19 |
Family
ID=93851956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2024/021249 Ceased WO2024257774A1 (ja) | 2023-06-15 | 2024-06-11 | 創薬支援装置、創薬支援装置の作動方法、および創薬支援装置の作動プログラム |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20260100242A1 (ja) |
| EP (1) | EP4730345A1 (ja) |
| JP (1) | JPWO2024257774A1 (ja) |
| CN (1) | CN121285858A (ja) |
| WO (1) | WO2024257774A1 (ja) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005090957A (ja) * | 2001-10-16 | 2005-04-07 | Mochida Pharmaceut Co Ltd | 心房細動治療薬のスクリーニング方法 |
| US20140363841A1 (en) * | 2012-01-20 | 2014-12-11 | Singapore Health Services Pte Ltd | Induced pluripotent stem cell (ipsc)-derived cardiomyocyte-like cells and uses thereof |
| US20150193575A1 (en) * | 2013-12-13 | 2015-07-09 | The Governors Of The University Of Alberta | Systems and methods of selecting compounds with reduced risk of cardiotoxicity |
| WO2022176310A1 (ja) | 2021-02-17 | 2022-08-25 | 富士フイルム株式会社 | 情報処理装置、情報処理方法、プログラム、及び薬剤評価方法 |
-
2024
- 2024-06-11 JP JP2025527948A patent/JPWO2024257774A1/ja active Pending
- 2024-06-11 WO PCT/JP2024/021249 patent/WO2024257774A1/ja not_active Ceased
- 2024-06-11 EP EP24823389.2A patent/EP4730345A1/en active Pending
- 2024-06-11 CN CN202480038844.7A patent/CN121285858A/zh active Pending
-
2025
- 2025-12-11 US US19/417,122 patent/US20260100242A1/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005090957A (ja) * | 2001-10-16 | 2005-04-07 | Mochida Pharmaceut Co Ltd | 心房細動治療薬のスクリーニング方法 |
| US20140363841A1 (en) * | 2012-01-20 | 2014-12-11 | Singapore Health Services Pte Ltd | Induced pluripotent stem cell (ipsc)-derived cardiomyocyte-like cells and uses thereof |
| US20150193575A1 (en) * | 2013-12-13 | 2015-07-09 | The Governors Of The University Of Alberta | Systems and methods of selecting compounds with reduced risk of cardiotoxicity |
| WO2022176310A1 (ja) | 2021-02-17 | 2022-08-25 | 富士フイルム株式会社 | 情報処理装置、情報処理方法、プログラム、及び薬剤評価方法 |
Non-Patent Citations (4)
| Title |
|---|
| FABIEN RAPHEL ET AL.: "A greedy classifier optimization strategy to assess ion channel blocking activity and pro-arrhythmia in hiPSC-cardiomyocytes", PLOS COMPUTATIONAL BIOLOGY, 25 September 2020 (2020-09-25) |
| FABIEN RAPHEL: "A greedy classifier optimization strategy to assess ion channel blocking activity and pro-arrhythmia in hiPSC-cardiomyocytes", PLOS COMPUTATIONAL BIOLOGY, PUBLIC LIBRARY OF SCIENCE, US, vol. 16, no. 9, 25 September 2020 (2020-09-25), US , pages e1008203, XP093163108, ISSN: 1553-734X, DOI: 10.1371/journal.pcbi.1008203 * |
| K. H. JAEGER ET AL.: "Identifying Drug Response by Combining Measurements of the Membrane Potential", CYTOSOLIC CALCIUM CONCENTRATION, AND THE EXTRACELLULAR POTENTIAL IN MICROPHYSIOLOGICAL SYSTEMS'' FRONTIERS IN PHARMACOLOGY, 8 February 2021 (2021-02-08) |
| KAROLINE HORGMO JÆGER: "Identifying Drug Response by Combining Measurements of the Membrane Potential, the Cytosolic Calcium Concentration, and the Extracellular Potential in Microphysiological Systems", FRONTIERS IN PHARMACOLOGY, FRONTIERS RESEARCH FOUNDATION, CH, vol. 11, CH , XP093163015, ISSN: 1663-9812, DOI: 10.3389/fphar.2020.569489 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN121285858A (zh) | 2026-01-06 |
| EP4730345A1 (en) | 2026-04-22 |
| JPWO2024257774A1 (ja) | 2024-12-19 |
| US20260100242A1 (en) | 2026-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elliott et al. | Epigenetics and gestational diabetes: a review of epigenetic epidemiology studies and their use to explore epigenetic mediation and improve prediction | |
| Gintant et al. | Evolution of strategies to improve preclinical cardiac safety testing | |
| US12411128B2 (en) | Methods and apparatuses for prediction of mechanism of activity of compounds | |
| JP5905781B2 (ja) | 相互作用予測装置、相互作用予測方法、および、プログラム | |
| US20130144584A1 (en) | Network modeling for drug toxicity prediction | |
| Lowey et al. | Hypertrophic cardiomyopathy R403Q mutation in rabbit β-myosin reduces contractile function at the molecular and myofibrillar levels | |
| Zampieri et al. | Metabolomics-driven understanding of genotype-phenotype relations in model organisms | |
| Passini et al. | The virtual assay software for human in silico drug trials to augment drug cardiac testing | |
| Jonasson et al. | Behaviors of individual microtubules and microtubule populations relative to critical concentrations: dynamic instability occurs when critical concentrations are driven apart by nucleotide hydrolysis | |
| Pueyo et al. | Experimentally-based computational investigation into beat-to-beat variability in ventricular repolarization and its response to ionic current inhibition | |
| Xue et al. | Effect of membrane stiffness and cytoskeletal element density on mechanical stimuli within cells: an analysis of the consequences of ageing in cells | |
| Palacio-Rodriguez et al. | Transition rates and efficiency of collective variables from time-dependent biased simulations | |
| Scholma et al. | Biological networks 101: Computational modeling for molecular biologists | |
| Pham et al. | The frail scale–a risk stratification in older patients with acute coronary syndrome | |
| Procopio et al. | Experimental modeling and identification of cardiac biomarkers release in acute myocardial infarction | |
| Gennebäck et al. | Using OPLS-DA to find new hypotheses in vast amounts of gene expression data—Studying the progression of cardiac hypertrophy in the heart of aorta ligated rat | |
| Maximova et al. | Protein–ligand dissociation rate constant from all-atom simulation | |
| Kohjitani et al. | Gradient-based parameter optimization method to determine membrane ionic current composition in human induced pluripotent stem cell-derived cardiomyocytes | |
| Quevedo et al. | A strategic solution to optimize molecular docking simulations using fully-flexible receptor models | |
| Schaeftlein et al. | Population pharmacokinetics meets microdialysis: benefits, pitfalls and necessities of new analysis approaches for human microdialysis data | |
| Liu et al. | GPT4Kinase: high-accuracy prediction of inhibitor-kinase binding affinity utilizing large language model | |
| Stanley et al. | High throughput molecular dynamics for drug discovery | |
| WO2024257774A1 (ja) | 創薬支援装置、創薬支援装置の作動方法、および創薬支援装置の作動プログラム | |
| Fiorillo et al. | Comparison of the Hi-C, GAM and SPRITE methods by use of polymer models of chromatin | |
| JP6188121B2 (ja) | 多階層網羅的データに基づく細胞内分子間ネットワーク自動推定方法 |
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: 24823389 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2025527948 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2025527948 Country of ref document: JP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: CN2024800388447 Country of ref document: CN |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 202517127061 Country of ref document: IN |
|
| WWP | Wipo information: published in national office |
Ref document number: 202517127061 Country of ref document: IN |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024823389 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2024823389 Country of ref document: EP Effective date: 20260115 |
|
| ENP | Entry into the national phase |
Ref document number: 2024823389 Country of ref document: EP Effective date: 20260115 |
|
| ENP | Entry into the national phase |
Ref document number: 2024823389 Country of ref document: EP Effective date: 20260115 |
|
| ENP | Entry into the national phase |
Ref document number: 2024823389 Country of ref document: EP Effective date: 20260115 |
|
| WWP | Wipo information: published in national office |
Ref document number: 2024823389 Country of ref document: EP |