Simulation device, simulation method, and program

Abstract

This simulation device is provided with: a selection unit that selects target coordinates in a structural space; an addition unit that adds a potential to the target coordinates; a calculation unit that calculates time evolution of the structural space in a first time interval by a first principle calculation; and a prediction unit that predicts time evolution in a second time interval on the basis of a prediction model in which the time is used as an explanatory variable and the target coordinates that have changed due to the application of an artificial force derived from the potential are used as objective variables.

Description

Simulation device, simulation method and program

[0001] The present disclosure relates to a simulation device, a simulation method, and a program.

[0002] There are known techniques for obtaining free energy surfaces using molecular simulations. In this type of technique, a reaction path search method (metadynamics) is sometimes used to avoid falling into a local optimum. Metadynamics is a method that adds a Gaussian potential to the sampled reaction coordinate, avoiding the re-sampling of already sampled reaction coordinates and enabling global sampling.

[0003] For example, Patent Document 1 discloses an invention that uses metadynamics to search for stable binding structures using the dihedral angle between a target molecule and a drug candidate molecule as a collective variable in order to efficiently search for multiple stable binding structures.

[0004] International Publication No. 2019 / 130529

[0005] However, conventional techniques have the problem of high computational costs for obtaining a free energy surface. For example, even when metadynamics is used, the search for a local optimum requires repeated sampling within a narrow range, which increases the overall computational complexity required to obtain a free energy surface.

[0006] In view of the above-described technical challenges, one aspect of the present disclosure aims to obtain a free energy surface with low calculation cost.

[0007] The present disclosure has the following configuration.

[0008] <1> A simulation device comprising: a selection unit configured to select target coordinates in a structural space; an addition unit configured to add a potential to the target coordinates; a calculation unit configured to calculate a time evolution of the structural space in a first time interval by first-principles calculation; and a prediction unit configured to predict the time evolution in a second time interval based on a prediction model in which time is an explanatory variable and the target coordinates changed by the application of an artificial force derived from the potential are used as a target variable.

[0009] <2> The simulation device according to <1> above, further comprising a learning unit configured to generate the prediction model by learning a calculation result of the time evolution.

[0010] <3> The simulation device according to <1> or <2> above, further comprising a decision unit configured to decide whether to execute the calculation unit or the prediction unit in a next time interval based on a difference between the calculation result of the time evolution and the prediction result of the time evolution in the same time interval.

[0011] <4> The simulation device according to <3> above, wherein the determination unit is configured to be executed after the prediction unit predicts the time evolution for a predetermined number of time intervals.

[0012] <5> The simulation device according to any one of <1> to <4>, wherein the potential is a Gaussian function potential, and the artificial force is calculated by the following formula, where b is a distance between the target coordinate in a current time interval and the target coordinate in a past time interval, and a and c are fitting functions:

[0013] Simulation device.

[0014] <6> The simulation device according to <5>, wherein the prediction model uses the target coordinates modulated based on the artificial force as a response variable, and the modulation is F meta is the artificial force, m is the mass of particles forming the structure corresponding to the target coordinate, and Δt is the length of the time interval, calculated by the following formula:

[0015] Simulation device.

[0016] <7> A simulation method in which a computer executes the following steps: selecting target coordinates in a structural space; adding a potential to the target coordinates; calculating the time evolution of the structural space in a first time interval by first-principles calculation; and predicting the time evolution in a second time interval based on a prediction model in which time is an explanatory variable and the target coordinates changed by the addition of an artificial force derived from the potential are used as a target variable.

[0017] <8> A program causing a computer to execute the following steps: selecting target coordinates in a structural space; adding a potential to the target coordinates; calculating the time evolution of the structural space in a first time interval by first-principles calculation; and predicting the time evolution in a second time interval based on a prediction model in which time is an explanatory variable and the target coordinates changed by the addition of an artificial force derived from the potential are used as a target variable.

[0018] According to one aspect of the present disclosure, a free energy surface can be obtained with low computational cost.

[0019] Fig. 1 is a block diagram showing an example of the overall configuration of an information processing system. Fig. 2 is a block diagram showing an example of the hardware configuration of a computer. Fig. 3 is a block diagram showing an example of the functional configuration of the information processing system. Fig. 4 is a flowchart showing an example of a simulation method.

[0020] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted.

[0021] [Embodiment] One embodiment of the present disclosure is an information processing system that executes a molecular simulation. The information processing system in this embodiment has a function of executing a molecular simulation to obtain a free energy surface.

[0022] There is a technology for calculating state quantities such as free energy by simulating particles such as atoms or molecules. In this type of technology, coordinates for calculating the state quantities are sampled from the structural space, and the state quantities of those coordinates are repeatedly calculated using first-principles calculations, etc. In this case, there is a possibility that sufficient sampling cannot be obtained due to limitations such as computational cost relative to time or size, resulting in a local solution.

[0023] Here, the structural space is a space that includes all structures that indicate the positional and bonding relationships of each particle that constitutes a substance. The coordinates of the structural space correspond to one structure and indicate the conformation of the particles included in that structure. An example of a structural space is the structural space of a reactive molecular system in which multiple molecules undergo a chemical reaction.

[0024] One method for preventing the system from falling into a local solution is a reaction path search method known as metadynamics. In metadynamics, a potential based on a penalty function is added to the sampled coordinates, filling the free energy surface with potential and preventing the system from returning to previously sampled coordinates. Metadynamics reduces the probability of falling into a local solution and enables global sampling.

[0025] Note that a Gaussian function is often used as the penalty function. Hereinafter, a potential based on a Gaussian function will also be referred to as a "Gaussian function-type potential."

[0026] In metadynamics, when filling a free energy surface with potential, the particle moves back and forth between similar coordinates before escaping the free energy surface near that coordinate. In other words, metadynamics involves repeated sampling within a narrow range in the search for a local optimum. Therefore, in order to obtain a free energy surface using metadynamics, a large computational cost is spent on sampling near the local optimum. On the other hand, since there are few conformations that a particle can take near the local optimum, it is expected that by learning these conformations, the sampling behavior can be predicted quickly and accurately.

[0027] An embodiment of the present disclosure aims to obtain a free energy surface with low computational cost. In this embodiment, the time evolution of a structural space in a first time interval is calculated using first-principles calculations, and the time evolution of the structural space in a second time interval is predicted based on a prediction model that has learned the results of the time evolution calculation. In one aspect, this embodiment makes it possible to obtain a free energy surface of a reacting molecular system in a short time with high accuracy.

[0028] <Overall Configuration> The overall configuration of the information processing system according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of the overall configuration of the information processing system according to this embodiment.

[0029] 1, an information processing system 1000 in this embodiment includes a simulation device 10 and a terminal device 20. The simulation device 10 and the terminal device 20 are connected to each other so as to be able to communicate data with each other via a communication network N1 such as a local area network (LAN) or the Internet.

[0030] The simulation device 10 is an information processing device such as a personal computer, workstation, or server that executes a molecular simulation. The simulation device 10 receives simulation conditions indicating conditions for executing a molecular simulation from a terminal device 20. The simulation device 10 executes a molecular simulation in accordance with the simulation conditions and transmits the simulation results to the terminal device 20. In this embodiment, the molecular simulation is, as an example, a simulation for obtaining a free energy surface in a reaction molecular system.

[0031] The terminal device 20 is an information processing terminal such as a personal computer, a smartphone, or a tablet terminal operated by a user of the information processing system 1000. The terminal device 20 transmits simulation conditions input by the user to the simulation device 10. The terminal device 20 displays the simulation results received from the simulation device 10 to the user.

[0032] The overall configuration of the information processing system 1000 shown in Fig. 1 is one example, and various system configuration examples are possible depending on the application and purpose. For example, the information processing system 1000 may include multiple simulation devices 10 and one or more terminal devices 20. For example, the simulation device 10 may be realized by multiple computers, or may be realized as a cloud computing service. The classification of devices such as the simulation device 10 and the terminal device 20 shown in Fig. 1 is one example.

[0033] <Hardware Configuration> The hardware configuration of the information processing system 1000 according to this embodiment will be described with reference to FIG.

[0034] <Computer> The simulation device 10 and the terminal device 20 in this embodiment are realized by, for example, a computer. Fig. 2 is a block diagram showing an example of the hardware configuration of a computer 500 in this embodiment.

[0035] 2, the computer 500 includes a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, a RAM (Random Access Memory) 503, a HDD (Hard Disk Drive) 504, an input device 505, a display device 506, a communication I / F (Interface) 507, and an external I / F 508. The CPU 501, the ROM 502, and the RAM 503 form a so-called computer. The hardware components of the computer 500 are connected to each other via a bus line 509. The input device 505 and the display device 506 may be connected to the external I / F 508 for use.

[0036] The CPU 501 is a computing device that reads programs and data from a storage device such as the ROM 502 or the HDD 504 onto the RAM 503 and executes processing to realize overall control and functions of the computer 500 .

[0037] The ROM 502 is an example of a non-volatile semiconductor memory (storage device) that can retain programs and data even when the power is turned off. The ROM 502 functions as a main storage device that stores various programs, data, etc. required for the CPU 501 to execute various programs installed in the HDD 504. Specifically, the ROM 502 stores boot programs such as a Basic Input / Output System (BIOS) and an Extensible Firmware Interface (EFI) that are executed when the computer 500 starts up, as well as data such as OS (Operating System) settings and network settings.

[0038] The RAM 503 is an example of a volatile semiconductor memory (storage device) in which programs and data are erased when the power is turned off. The RAM 503 is, for example, a dynamic random access memory (DRAM) or a static random access memory (SRAM). The RAM 503 provides a working area in which various programs installed in the HDD 504 are expanded when executed by the CPU 501.

[0039] The HDD 504 is an example of a non-volatile storage device that stores programs and data. The programs and data stored in the HDD 504 include an OS, which is basic software that controls the entire computer 500, and applications that provide various functions on the OS. Note that the computer 500 may use a storage device that uses flash memory as a storage medium (e.g., an SSD (Solid State Drive)) instead of the HDD 504.

[0040] The input device 505 includes a touch panel, operation keys and buttons, a keyboard and mouse, a microphone for inputting sound data such as voice, and the like, which are used by the user to input various signals.

[0041] The display device 506 is composed of a display such as a liquid crystal display or organic electroluminescence (EL) display for displaying a screen, a speaker for outputting sound data such as voice, and the like.

[0042] The communication I / F 507 is an interface that connects to a communication network and enables the computer 500 to perform data communication.

[0043] The external I / F 508 is an interface with external devices, such as a drive device 510.

[0044] The drive device 510 is a device for loading a recording medium 511. The recording medium 511 here includes media that record information optically, electrically, or magnetically, such as CD-ROMs, flexible disks, and magneto-optical disks. The recording medium 511 may also include semiconductor memories that record information electrically, such as ROMs and flash memories. This allows the computer 500 to read from and / or write to the recording medium 511 via the external I / F 508.

[0045] The various programs to be installed in the HDD 504 are installed, for example, by setting the distributed recording medium 511 in a drive device 510 connected to the external I / F 508 and reading the various programs recorded on the recording medium 511 by the drive device 510. Alternatively, the various programs to be installed in the HDD 504 may be installed by being downloaded via the communication I / F 507 from a network different from the communication network.

[0046] <Functional Configuration> The functional configuration of the information processing system in this embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example of the functional configuration of the information processing system in this embodiment.

[0047] <Simulation Device> As shown in FIG. 3 , the simulation device 10 in this embodiment includes a construction unit 101, a selection unit 102, an addition unit 103, a calculation unit 104, a learning unit 105, a storage unit 106, a prediction unit 107, a determination unit 108, and an output unit 109.

[0048] The construction unit 101, selection unit 102, addition unit 103, calculation unit 104, learning unit 105, prediction unit 107, determination unit 108, and output unit 109 are realized by processing that is executed by the CPU 501 in accordance with a program loaded from the HDD 504 onto the RAM 503 shown in Fig. 2. The storage unit 106 is realized by the HDD 504 shown in Fig. 2.

[0049] The constructing unit 101 receives simulation conditions from the terminal device 20. The simulation conditions include information indicating a plurality of substances that cause a desired chemical reaction. The constructing unit 101 constructs a structural space of a reaction molecular system in accordance with the simulation conditions.

[0050] The selection unit 102 selects a reaction coordinate to be used for calculating the state quantity from the structure space constructed by the construction unit 101. In this embodiment, the state quantity is free energy, for example. Hereinafter, the reaction coordinate to be used for calculating the free energy will also be referred to as the "target coordinate."

[0051] The adder 103 adds a potential to the target coordinates selected by the selector 102. In the present embodiment, as an example, a Gaussian function potential is added. The Gaussian function potential to be added to the target coordinates is generated based on a structure corresponding to the target coordinates.

[0052] The calculation unit 104 calculates the time evolution of the structural space by first-principles calculation. In this embodiment, the first-principles calculation is, for example, a calculation method based on density functional theory (DFT). The calculation unit 104 calculates the time evolution in a predetermined time interval. The length of the time interval corresponds to the time step size in the molecular simulation. The time step size may be set arbitrarily.

[0053] In this embodiment, the calculation unit 104 changes the target coordinates in the next time interval by adding an artificial force to the target coordinates in the previous time interval. The artificial force is derived from the Gaussian function potential added to the structural space by the adder 103.

[0054] Specifically, the artificial force is F defined by equation (1): meta In addition, the artificial force F meta is applied to each particle included in the structure corresponding to the target coordinate. For simplicity, the index indicating the particle is omitted in equation (1), but the artificial force F meta is calculated.

[0055]

[0056] Here, b is the distance between the target coordinate in the current time interval and the target coordinate in the past time interval, and a and c are fitting functions.

[0057] Artificial force F on target coordinates meta When the object coordinate is added, the modulation R defined by Eq. (2) meta Artificial force F meta is added to each particle, so the modulation R meta is also calculated for each particle. In equation (2), as in equation (1), the index indicating the particle is omitted.

[0058]

[0059] However, F meta is the artificial force, m is the mass of the particle, and Δt is the length of the time interval (time step size).

[0060] The learning unit 105 generates a prediction model by learning the calculation results of the time evolution calculated by the calculation unit 104. When there is a learned prediction model, the learning unit 105 updates the prediction model by learning the calculation results of the time evolution newly calculated by the calculation unit 104.

[0061] The prediction model is a machine learning model that uses time as an explanatory variable and coordinates as a target variable. The coordinates output by the prediction model are target coordinates sampled at the input time. The target coordinates calculated by the calculation unit 104 are calculated based on the artificial force F calculated by Equation (1). meta By adding the modulation R defined by equation (2), meta Therefore, the coordinates output by the prediction model are the target coordinates that have received the artificial force F meta The addition of modulated R meta is the predicted value of the target coordinate.

[0062] The structure of the prediction model can be selected arbitrarily, but for example, the MD-GAN (Molecular dynamics - Generative Adversarial Network) disclosed in Reference 1 can be used. The MD-GAN is a multilayer neural network that can predict the time evolution in molecular dynamics calculations within the framework of a generative adversarial network.

[0063] [Reference 1] Katsuhiro Endo, Katsufumi Tomobe, Kenji Yasuoka, "Multi-Step Time Series Generator for Molecular Dynamics," Thirty-Second AAAI Conference on Artificial Intelligence, Vol. 32, No. 1 (2018)

[0064] The learned prediction model is stored in the storage unit 106. The prediction model stored in the storage unit 106 is generated or updated by the learning unit 105.

[0065] The prediction unit 107 predicts the time evolution of the structural space based on the prediction model read from the storage unit 106. The prediction unit 107 predicts the time evolution in a predetermined time interval. The time interval in which the prediction unit 107 predicts the time evolution is different from the time interval in which the calculation unit 104 calculated the time evolution. The length of the time interval may be the same as the length of the time interval in which the calculation unit 104 calculated the time evolution. Therefore, the prediction unit 107 inputs the time when a predetermined time interval has elapsed from the current time (hereinafter also referred to as the "target time") into the prediction model. The prediction unit 107 obtains the prediction result including the target coordinates output from the prediction model.

[0066] The decision unit 108 decides whether to execute the calculation unit 104 or the prediction unit 107 based on the calculation result of the time evolution calculated by the calculation unit 104 and the prediction result of the time evolution predicted by the prediction unit 107. The decision unit 108 compares the error between the calculation result and the prediction result in the same time interval with a predetermined threshold value to decide whether to execute the calculation unit 104 or the prediction unit 107 in the next time interval.

[0067] The output unit 109 determines whether or not a simulation termination condition is satisfied. In this embodiment, the termination condition is that a desired chemical reaction has occurred. That is, the output unit 109 determines whether or not a desired chemical reaction has occurred in the current structure space.

[0068] When the simulation termination condition is satisfied, the output unit 109 outputs the simulation result. The simulation result includes state information indicating the current state of the structure space. The state information is, for example, information indicating the free energy surface.

[0069] <Terminal Device> As shown in FIG. 3 , the terminal device 20 in this embodiment includes an input unit 201 and a display unit 202 .

[0070] The input unit 201 and the display unit 202 are realized by the processing that the CPU 501 executes by a program loaded onto the RAM 503 from the HDD 504 shown in FIG.

[0071] The input unit 201 receives input of simulation conditions in response to a user's operation, and transmits the simulation conditions to the simulation device 10.

[0072] The display unit 202 receives the simulation results from the simulation device 10. The display unit 202 outputs the simulation results to the display device 506 or the like.

[0073] <Processing Procedure> A simulation method executed by the information processing system 1000 in this embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of the simulation method in this embodiment.

[0074] In step S1, the input unit 201 of the terminal device 20 accepts input of simulation conditions in response to a user's operation. The simulation conditions include information indicating multiple substances that will cause the chemical reaction desired by the user. Next, the input unit 201 transmits the simulation conditions to the simulation device 10.

[0075] In the simulation device 10, the construction unit 101 receives simulation conditions from the terminal device 20. Next, the construction unit 101 constructs a structure space of a reaction molecular system in accordance with the simulation conditions. Then, the construction unit 101 sends the constructed structure space to the selection unit 102.

[0076] In step S2, the selection unit 102 of the simulation device 10 receives the structural space from the construction unit 101. Next, the selection unit 102 selects target coordinates from the structural space using metadynamics. Then, the selection unit 102 sends the structural space in which the target coordinates have been selected to the addition unit 103.

[0077] In step S3, the adder 103 of the simulation device 10 receives the structure space from the selector 102. Next, the adder 103 generates a Gaussian function potential based on the structure corresponding to the target coordinates. Subsequently, the adder 103 adds the Gaussian function potential to the target coordinates. Then, the adder 103 sends the structure space in which the Gaussian function potential has been added to the target coordinates to the calculator 104.

[0078] In step S4, the calculation unit 104 of the simulation device 10 receives the structural space from the addition unit 103. Next, the calculation unit 104 calculates the time evolution of the structural space in the next time interval by first-principles calculation. Then, the calculation unit 104 sends the calculation result of the time evolution to the learning unit 105.

[0079] Specifically, the calculation unit 104 first calculates the artificial force F from the Gaussian function potential added in step S3 according to equation (1). meta Next, the calculation unit 104 derives the artificial force F meta The modulation R meta Next, the calculation unit 104 calculates the modulation R meta The structure corresponding to the target coordinates is changed based on the above, and the target coordinates corresponding to the changed structure are selected.

[0080] The calculation unit 104 repeatedly executes step S4 until a sufficient amount of calculation results for generating a predictive model is accumulated. The amount sufficient for generating a predictive model is set in advance depending on the type of predictive model. When a sufficient amount of calculation results is accumulated, the calculation unit 104 sends the structure space to the prediction unit 107.

[0081] In step S5, the learning unit 105 of the simulation device 10 receives the calculation results of the time evolution from the calculation unit 104. Next, the learning unit 105 learns the calculation results of the time evolution to generate a prediction model in which time is an explanatory variable and coordinates are a target variable. The learning unit 105 then stores the learned prediction model in the storage unit 106.

[0082] In step S6, the prediction unit 107 of the simulation device 10 receives the structure space from the calculation unit 104. Next, the prediction unit 107 reads out the trained prediction model from the storage unit 106.

[0083] Next, the prediction unit 107 calculates the target time by adding the length of the next time interval to the current time. Next, the prediction unit 107 inputs the target time into the trained prediction model. The prediction model predicts the target coordinates at the input target time. At this time, a Gaussian function potential based on the structure corresponding to the target coordinates is added to the target coordinates. The prediction model outputs predicted values ​​of the target coordinates. The prediction unit 107 acquires the prediction result output by the prediction model. The prediction result includes the target coordinates when the next time interval has passed.

[0084] The prediction unit 107 repeatedly executes step S6 until it has predicted time evolution for a predetermined number of time intervals. The number of repetitions may be set arbitrarily, and may be, for example, 100. When it has predicted time evolution for the predetermined number of time intervals, the prediction unit 107 sends the predicted result of the time evolution to the determination unit 108.

[0085] In step S7, the calculation unit 104 of the simulation device 10 calculates the time evolution of the structural space in the current time interval using first-principles calculations. In other words, the calculation unit 104 calculates the time evolution in the current time interval based on the predicted result of the time evolution in the immediately preceding time interval. The calculation unit 104 sends the calculation result of the time evolution to the determination unit 108.

[0086] In step S8, the determination unit 108 of the simulation device 10 receives the prediction result of the time evolution in the current time interval from the prediction unit 107. The determination unit 108 also receives the calculation result of the time evolution in the current time interval from the calculation unit 104.

[0087] Next, the determination unit 108 compares the predicted result of the time evolution in the current time interval with the calculated result. Subsequently, the determination unit 108 determines whether the prediction error is equal to or less than a predetermined threshold. The prediction error is the distance between the target coordinates indicated by the predicted result and the target coordinates indicated by the calculated result. In other words, the determination unit 108 determines whether the target coordinates predicted by the prediction model in the current time interval are significantly different from the target coordinates calculated by the first-principles calculation.

[0088] If the prediction error is equal to or smaller than the threshold (YES), the determination unit 108 sends the structure space to the output unit 109 and proceeds to step S9. On the other hand, if the prediction error is greater than the threshold (NO), the determination unit 108 sends the structure space to the addition unit 103 and returns to step S3.

[0089] In step S9, the output unit 109 of the simulation device 10 receives the structural space from the determination unit 108. Next, the output unit 109 determines whether or not a desired chemical reaction has occurred based on the structural space. If a chemical reaction has occurred (YES), the output unit 109 proceeds to step S10. On the other hand, if a chemical reaction has not occurred (NO), the output unit 109 returns the process to step S6.

[0090] In step S10, the output unit 109 of the simulation device 10 outputs the simulation result. The simulation result includes information indicating the free energy surface. The output unit 109 transmits the simulation result to the terminal device 20.

[0091] In the terminal device 20, the display unit 202 receives the simulation results from the simulation device 10. Next, the display unit 202 outputs the simulation results to the display device 506. The user can refer to the simulation results output to the display device 506 of the terminal device 20 and use the calculation results of the free energy surface.

[0092] For example, the user can use the calculation results of the free energy surface to search for raw materials in a reaction molecular system. Furthermore, for example, the user can obtain actual measured values ​​of an actual reaction molecular system through experiments or manufacturing, update the prediction model based on the simulation results and the actual measured values, and repeatedly search for and predict reaction paths.

[0093] After returning from step S8 to step S3, the simulation device 10 executes the processes from step S3 to step S8 again. In step S5 from the second time onwards, the trained prediction model is updated based on the new calculation result calculated in the immediately preceding step S4. On the other hand, after returning from step S9 to step S6, the simulation device 10 executes the processes from step S6 to step S8 again. That is, the determination unit 108 determines whether to execute the calculation unit 104 or the prediction unit 107 in the next time interval based on the error between the calculation result and the prediction result in the same time interval.

[0094] In this way, the simulation device 10 quickly predicts the time evolution of the structural space using the prediction model as long as the prediction error by the prediction model is equal to or less than a threshold, and when the prediction error exceeds the threshold, calculates the time evolution of the structural space with high accuracy using first-principles calculation. This allows the simulation device 10 to quickly and accurately calculate the time evolution of the structural space, and therefore to quickly and accurately obtain a free energy surface.

[0095] <Effects of the Embodiment> The simulation device 10 in this embodiment adds a potential to target coordinates in a structural space, calculates the time evolution of the structural space in a first time interval using first-principles calculations, and predicts the time evolution of the structural space in a second time interval based on a prediction model. The prediction model uses time as an explanatory variable and the target coordinates changed by the application of an artificial force derived from the potential as a target variable. By predicting the time evolution of the structural space in a portion of the time interval, the simulation device 10 can reduce the number of first-principles calculations. Therefore, according to this embodiment, a free energy surface can be obtained with low calculation cost.

[0096] The simulation apparatus 10 generates a prediction model by learning the calculation results of the time evolution. The simulation apparatus 10 updates the prediction model every time it calculates the time evolution using first-principles calculations. Therefore, according to this embodiment, it is possible to accurately predict the time evolution of the structural space.

[0097] The simulation device 10 determines whether to perform a first-principles calculation or a prediction model in the next time interval based on the difference between the calculation result of the time evolution and the predicted result of the time evolution in the same time interval. If the target coordinates move significantly due to time evolution, the accuracy of the prediction result may decrease. Therefore, according to this embodiment, it is possible to obtain a free energy surface with high accuracy.

[0098] The simulation apparatus 10 predicts the time evolution for a predetermined number of time intervals and then calculates the time evolution using first-principles calculations. The simulation apparatus 10 can reduce the calculation cost the more times it executes the prediction model. Therefore, according to this embodiment, it is possible to obtain a free energy surface with significantly reduced calculation cost.

[0099] [Supplementary Note] Each function of the above-described embodiments can be realized by one or more processing circuits. Here, the term "processing circuit" in this specification includes a processor programmed to execute each function by software, such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit) implemented by an electronic circuit, as well as devices such as an ASIC (Application Specific Integrated Circuit), DSP (Digital Signal Processor), FPGA (Field Programmable Gate Array), and conventional circuit modules designed to execute each of the above-described functions.

[0100] Although the embodiments of the present disclosure have been described in detail above, the embodiments disclosed herein are illustrative in all respects and are not limiting. The embodiments can be modified and improved in various ways without departing from the scope and spirit of the appended claims. The matters described in the above embodiments can be configured in other ways as long as they are not inconsistent, and can be combined as long as they are not inconsistent.

[0101] This application claims priority from Japanese Patent Application No. 2023-118565, filed on July 20, 2023, with the Japan Patent Office, the entire contents of which are incorporated herein by reference.

[0102] REFERENCE SIGNS LIST 10 Simulation device 20 Terminal device 101 Construction unit 102 Selection unit 103 Addition unit 104 Calculation unit 105 Learning unit 106 Storage unit 107 Prediction unit 108 Determination unit 109 Output unit 201 Input unit 202 Display unit 1000 Information processing system

Claims

1. A selection unit configured to select the target coordinates in the structural space, An addition unit configured to add a potential to the aforementioned target coordinates, A calculation unit configured to calculate the time evolution of the structural space in a first time interval by first-principles calculations, A prediction unit is configured to predict the time evolution in a second time interval based on a prediction model in which time is the explanatory variable and the target coordinates changed by the application of an artificial force derived from the potential are the dependent variable, A simulation device equipped with the following features.

2. A simulation apparatus according to claim 1, The system further comprises a learning unit configured to generate the predictive model by learning the calculation results of the aforementioned time evolution. Simulation device.

3. A simulation apparatus according to claim 1, The system further includes a decision unit configured to determine whether to execute the calculation unit or the prediction unit in the next time interval, based on the difference between the calculated result of the time evolution and the predicted result of the time evolution in the same time interval. Simulation device.

4. A simulation apparatus according to claim 3, The determination unit is configured to be executed after the prediction unit has predicted the time evolution over a predetermined number of time intervals. Simulation device.

5. A simulation apparatus according to any one of claims 1 to 4, The aforementioned potential is a Gaussian function type potential, The aforementioned artificial force is calculated by the following equation, where b is the distance between the target coordinates in the current time interval and the target coordinates in past time intervals, and a and c are fitting functions: [Math 1] Simulation device.

6. A simulation apparatus according to claim 5, The prediction model uses the target coordinates that have been modulated based on the artificial force as the objective variable. The aforementioned modulation is F meta Let be the artificial force, let m be the mass of the particle forming the structure corresponding to the target coordinate, and let Δt be the length of the time interval, and it is calculated by the following equation: [Math 2] Simulation device.

7. Computers Procedure for selecting target coordinates in structural space, A procedure for adding a potential to the aforementioned target coordinates, A procedure for calculating the time evolution of the structural space in a first time interval by first-principles calculations, A procedure for predicting the time evolution in a second time interval based on a prediction model in which time is the explanatory variable and the target coordinates changed by the application of an artificial force derived from the potential are the dependent variable, A simulation method for performing this.

8. On the computer, Procedure for selecting target coordinates in structural space, A procedure for adding a potential to the aforementioned target coordinates, A procedure for calculating the time evolution of the structural space in a first time interval by first-principles calculations, A procedure for predicting the time evolution in a second time interval based on a prediction model in which time is the explanatory variable and the target coordinates changed by the application of an artificial force derived from the potential are the dependent variable, A program to execute.

Images