Information processing device, information processing method, and program
The information processing device and method provide a clear visualization of toxicity evaluation routes and their changes, addressing the complexity of understanding condition impacts on toxicity evaluations by using flowcharts and line thickness to represent route alterations, enhancing evaluation clarity and accuracy.
Patent Information
- Application Number
- PCT/JP2024/020081
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-01
- Filing Date
- 2024-05-31
- Publication Date
- 2024-12-05
AI Technical Summary
Existing toxicity evaluation methods are complex and make it difficult to understand the impact of changing determination conditions on toxicity evaluation results, especially when the evaluation flow is intricate, as it is challenging to visualize the changes in the evaluation route after modifying the conditions.
An information processing device and method that displays the toxicity evaluation flowchart with changing determination conditions, where the route taken before and after the change is clearly identifiable, using a flowchart that visually represents the changes in route and thickness of connecting lines indicating the number of compounds passing through altered paths, allowing users to grasp the effect of condition changes on evaluation results.
Enables users to visually understand the changes in the toxicity evaluation route and their impact, improving the clarity and accuracy of toxicity evaluations by illustrating the pre- and post-change evaluation routes and highlighting the significance of changes in determination conditions.
Smart Images

Figure JP2024020081_05122024_PF_FP_ABST
Abstract
Description
Information processing device, information processing method, and program
[0001] The technology disclosed herein relates to an information processing device, an information processing method, and a program.
[0002] In recent years, in the field of chemical substances, toxicity assessment using computer-based in silico methods has become common. Toxicity assessment of chemical substances requires not only obtaining a toxicity assessment result but also various considerations from the viewpoint of the cause of toxicity manifestation or the tendency of compounds that are likely to manifest toxicity.
[0003] JP 2013-522649 A discloses a method for predicting the teratogenicity of a test compound, comprising the steps of: (a) culturing hSLCs (i) in the presence of a first known teratogenic compound; and (ii) in the absence of the first known teratogenic compound; (b) detecting a plurality of metabolites having a molecular weight of less than about 3,000 daltons associated with hSLCs exposed to the first known teratogenic compound compared to hSLCs not exposed to the first known teratogenic compound, and identifying a difference in the metabolic response of hSLCs exposed to the first known teratogenic compound compared to hSLCs not exposed to the first known teratogenic compound; and (c) analyzing the difference in metabolic response and identifying the metabolic response of hSLCs to the first known teratogenic compound. (d) repeating steps a) through c) multiple times, each time with a different known teratogenic compound; (e) classifying the mass features resulting from each exposure to the teratogenic compound to obtain a first reference profile of mass features; (f) comparing the profile of mass features resulting from exposure of hSLCs to the test compound with the first reference profile to predict the teratogenicity of the test compound; (g) if the test compound is predicted to be a teratogen, adding the profile of mass features to the first reference profile to obtain a second reference profile, wherein the second reference profile has a higher predictive accuracy than the first reference profile; and (h) repeating steps f) and g) multiple times, each time with a different test compound, to obtain a final reference profile.
[0004] International Publication WO2011 / 055820 discloses a system including a measurement data acquisition means for acquiring a plurality of measurement data obtained under different conditions for each of a plurality of types of metabolites and / or metabolic enzymes, a pathway map data acquisition means for acquiring data representing an in vivo metabolic pathway map, an association strength calculation means for calculating the association strength between each of the metabolites and / or metabolic enzymes and each metabolic pathway based on the measurement data acquired by the measurement data acquisition means, a display means, and a display content determination means for determining the content to be displayed on the display means, and the display content determination means displays two or more metabolic pathways on the display means so that the association strength can be distinguished. The display means is capable of displaying content representing two or more metabolic pathways, and further comprises a pathway selection input receiving means for receiving a selection input of one of the metabolic pathways from the user when content representing two or more metabolic pathways is displayed on the display means. The display content determination means displays a metabolic pathway map on the display means for the metabolic pathway selected by the selection input received by the pathway selection input receiving means, and determines the display content to be displayed on the display means so that increases or decreases in measurement values indicated by measurement value data for metabolites and / or metabolic enzymes present on the metabolic pathway map can be identified.
[0005] Japanese Patent Application Laid-Open No. 2004-93234 describes a toxicity determination system characterized by having: simultaneous differential equations based on gene pathway information related to the metabolism or sequence of a toxic drug; a storage means for storing reaction rate coefficients of the simultaneous differential equations, the relationship between linear stability and Jacobian stability according to the reaction rate coefficients, and a determination of whether the toxic drug is toxic based on the value of the reaction rate coefficient; an input means for inputting gene expression distribution data into the simultaneous differential equations; and a display means for inputting the gene expression distribution data into the simultaneous differential equations to determine the reaction rate coefficients and display a determination of whether the toxic drug is toxic.
[0006] The techniques described in the above-mentioned JP-A 2013-522649, WO 2011 / 055820, and JP-A 2004-93234 take into consideration toxicity assessment techniques, but do not consider assessment using a toxicity assessment flowchart (hereinafter also simply referred to as a "toxicity assessment flow") used in toxicity assessment. The toxicity assessment flow has multiple assessment steps, and the subsequent toxicity assessment path branches depending on the assessment result at each assessment step.
[0007] In order to improve the accuracy of toxicity evaluation, a user may change the judgment conditions of the judgment steps in the toxicity evaluation flow. However, for example, when the toxicity evaluation flow is complex, it is difficult to grasp the impact on the evaluation results when the judgment conditions of the toxicity evaluation flow are changed.
[0008] One embodiment of the technology of the present disclosure provides an information processing device, an information processing method, and a program that, when the judgment conditions in toxicity assessment are changed, can determine what path a compound that has changed in the evaluation path after the change took in the toxicity assessment flow used in the toxicity assessment.
[0009] A first aspect of the technology of the present disclosure is an information processing device that includes a processor, and the processor executes control to output a flowchart showing a procedure for obtaining toxicity evaluation results for multiple target compounds that are the subject of toxicity evaluation, in which multiple preset processing steps are arranged in chronological order, and the processing steps include a judgment processing step in which judgment conditions can be changed and a subsequent path branches depending on the judgment result.After a toxicity evaluation result has been obtained for at least one target compound among the multiple target compounds in accordance with the procedure, the judgment conditions in the judgment processing step are changed, and a toxicity evaluation result is obtained in accordance with the procedure under the changed judgment conditions, in the control to output the flowchart, if a change has occurred between the pre-change path taken to reach the toxicity evaluation result before the judgment conditions were changed and the changed path taken to reach the toxicity evaluation result after the judgment conditions were changed, the processor, in the control to output the flowchart, displays the path in which the change has occurred in an identifiable manner.
[0010] A second aspect of the technology of the present disclosure is an information processing device according to the first aspect, in which, when toxicity evaluation results are obtained for multiple target compounds before and after a change in judgment conditions, the display manner of the pathway in which a change has occurred in the flowchart is changed depending on the number of target compounds that have passed through the pathway in which a change has occurred in the toxicity evaluation.
[0011] A third aspect of the technology of the present disclosure is an information processing device according to the second aspect, in which a flowchart shows a plurality of processing steps and connecting lines connecting the processing steps arranged one after the other in chronological order, and a path is indicated by the connecting lines, and the display aspect is the thickness of the connecting lines.
[0012] A fourth aspect of the technology of the present disclosure is the information processing device according to the third aspect, wherein the thickness of the bond line increases as the number of target compounds that have passed through the pathway in which a change has occurred increases.
[0013] A fifth aspect of the technology of the present disclosure is an information processing device according to the first aspect, in which a flowchart shows a plurality of processing steps and bond lines connecting the processing steps arranged one after the other in chronological order, and a path is indicated by the bond lines, and when a processing step or bond line shown in the flowchart is selected, an image showing a target compound that has passed through the path indicated by the processing step or bond line in a toxicity assessment is displayed.
[0014] A sixth aspect of the technology of the present disclosure is the information processing device according to the fifth aspect, in which the image includes structural data indicating a molecular structure of the target compound.
[0015] A seventh aspect of the technology of the present disclosure is the information processing device according to the sixth aspect, in which the image includes structural data indicating a common structure, which is a partial structure included as a part of the target compound and is a structure common to multiple target compounds that have passed through a selected processing step or bond line.
[0016] An eighth aspect of the technology of the present disclosure is an information processing method that includes executing control to output a flowchart showing a procedure for obtaining toxicity evaluation results for multiple target compounds that are the subject of toxicity evaluation, in which multiple preset processing steps are arranged in chronological order, and the processing steps include a judgment processing step in which judgment conditions can be changed and a subsequent path branches depending on the judgment result, and in which, after a toxicity evaluation result has been obtained for at least one target compound among the multiple target compounds in accordance with the procedure, the judgment conditions in the judgment processing step are changed, and a toxicity evaluation result is obtained in accordance with the procedure under the changed judgment conditions, if a change occurs between the pre-change path taken to arrive at the toxicity evaluation result before the judgment conditions were changed and the changed path taken to arrive at the toxicity evaluation result after the judgment conditions were changed, the path in which the change occurred is displayed in an identifiable manner in the control to output the flowchart.
[0017] A ninth aspect of the technology of the present disclosure is a process including causing a computer to execute control to output a flowchart showing a procedure for obtaining toxicity evaluation results for multiple target compounds that are the subject of toxicity evaluation, wherein the flowchart includes a plurality of preset processing steps arranged in chronological order, and the processing steps include a judgment processing step in which the judgment conditions can be changed and a subsequent path branches depending on the judgment result. In this case, after a toxicity evaluation result has been obtained for at least one target compound among the multiple target compounds according to the procedure, the judgment conditions in the judgment processing step are changed, and a toxicity evaluation result is obtained according to the procedure under the changed judgment conditions. In this case, in the control to output the flowchart, if a change occurs between the pre-change path taken to reach the toxicity evaluation result before the judgment conditions were changed and the changed path taken to reach the toxicity evaluation result after the judgment conditions were changed, the path in which the change occurred is displayed in an identifiable manner.
[0018] The technology disclosed herein provides an information processing device, an information processing method, and a program that, when the judgment conditions in toxicity assessment are changed, are capable of determining what path a compound that has changed in the assessment path after the change has taken in the flowchart used for toxicity assessment.
[0019] 1 is a conceptual diagram showing an example of a schematic configuration of an information processing system. FIG. 1 is a block diagram showing an example of a hardware configuration of an electrical system of a server. FIG. 2 is a conceptual diagram showing an example of a usage mode of the information processing system. FIG. 3 is a functional block diagram showing an example of main functions of a processor of a server. FIG. 4 is a conceptual diagram showing an example of a usage mode of the information processing system. FIG. 5 is a conceptual diagram showing an example of a processing content of a toxicity evaluation unit. FIG. 6 is a conceptual diagram showing an example of a usage mode of the information processing system. FIG. 7 is a conceptual diagram showing an example of a processing content of a condition setting unit and a toxicity evaluation unit. FIG. 8 is a conceptual diagram showing an example of a processing content of a difference derivation unit. FIG. 9 is a conceptual diagram showing an example of a processing content of an image generation unit. FIG. 10 is a conceptual diagram showing an example of a mode in which a display image is displayed on a display device. FIG. 11 is a flowchart showing an example of the flow of server control processing. FIG. 12 is a conceptual diagram showing an example of a processing content of an image generation unit. FIG. 13 is a conceptual diagram showing an example of a mode in which a display image is displayed on a display device. FIG. 14 is a block diagram showing an example of a hardware configuration of an electrical system of a client terminal. FIG. 15 is a functional block diagram showing an example of a main function of a processor of a client terminal.
[0020] An example of an embodiment of an information processing device, an information processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.
[0021] 1 , an information processing system 10 includes a client terminal 12 and a server 14. In the information processing system 10, the client terminal 12 and the server 14 are connected to each other via a network 16 so as to be able to communicate with each other.
[0022] The information processing system 10 is used, for example, to evaluate the properties of chemical substances (e.g., to evaluate the toxicity to the human body). By using the information processing system 10, a user 18 (e.g., a researcher) can predict and evaluate experimental results using computer simulations (i.e., evaluation using in silico techniques). For example, it is possible to obtain toxicity evaluation results for newly developed or under-developed chemical substances without conducting toxicity evaluation tests using actual chemical substances (i.e., in vitro or in vivo toxicity evaluation tests).
[0023] The client terminal 12 is a terminal used by a user 18. The server 14 receives a processing request from the client terminal 12 via the network 16 and provides a service according to the request to the requesting client terminal 12 via the network 16. For example, when the server 14 receives a processing request to execute a process related to the evaluation of the properties of a chemical substance as a processing request, the server 14 transmits the evaluation results to the client terminal 12. In this embodiment, the server 14 is an example of an "information processing device" according to the technology of the present disclosure.
[0024] For example, the server 14 is realized by a mainframe, but this is merely one example, and the server may be realized by cloud computing, or by network computing such as fog computing, edge computing, or grid computing. Here, the server 14 is given as an example of a device provided outside the client terminal 12, but this is merely one example, and the server 14 may be replaced by at least one personal computer or the like.
[0025] The network 16 is configured, for example, as at least one of a WAN (Wide Area Network) and a LAN (Local Area Network). Furthermore, the connection method between the client terminal 12 and the network 16 and the connection method between the server 14 and the network 16 may each be a wireless communication method or a wired communication method. The network 16 establishes communication between the client terminal 12 and the server 14 and transmits and receives various information between the client terminal 12 and the server 14.
[0026] A reception device 20 is connected to the client terminal 12. The reception device 20 receives instructions from the user 18. The reception device 20 includes a keyboard 21, a mouse 22, and the like. The keyboard 21 and the mouse 22 shown in FIG. 1 are merely examples. The reception device 20 may include only either the keyboard 21 or the mouse 22. Furthermore, instead of the keyboard 21 and / or the mouse 22, the reception device 20 may be, for example, at least one of a proximity input device that receives proximity input, a voice input device that receives voice input, and a gesture input device that receives gesture input. The proximity input device is, for example, a touch panel or a tablet.
[0027] A display device 24 is connected to the client terminal 12. Examples of the display device 24 include an EL (Electro-Luminescence) display and a liquid crystal display. The display device 24 displays various information (e.g., images and text) under the control of the client terminal 12.
[0028] Although a personal computer is shown as an example of the client terminal 12 here, this is merely an example. Mobile terminals such as smartphones and tablet terminals may also be used as the client terminal 12. Furthermore, although an example in which one client terminal 12 is connected to one server 14 via the network 16 is shown here, this is merely an example. Of course, the information processing system 10 may include multiple client terminals 12 and multiple servers 14.
[0029] 2 , the server 14 includes a computer 26, a communication I / F (Interface) 28, and a bus 36. The computer 26 includes a processor 30, a storage 32, and a RAM (Random Access Memory) 34. The processor 30, the storage 32, the RAM 34, and the communication I / F 28 are connected to the bus 36. In this embodiment, the computer 26 is an example of a "computer" according to the technology of the present disclosure, and the processor 30 is an example of a "processor" according to the technology of the present disclosure.
[0030] Memory is connected to the processor 30. The memory includes a storage 32 and a RAM 34. The processor 30 includes, for example, a central processing unit (CPU) and a graphics processing unit (GPU). The GPU operates under the control of the CPU and is responsible for executing image processing.
[0031] The storage 32 is a non-volatile storage device that stores various programs, various parameters, etc. Examples of the storage 32 include flash memory (e.g., an EEPROM (Electrically Erasable and Programmable Read Only Memory) and an SSD (Solid State Drive)) and / or a HDD (Hard Disk Drive). Note that flash memory and HDD are merely examples, and at least one of a flash memory, an HDD magnetoresistive memory, and a ferroelectric memory may be used as the storage 32.
[0032] The RAM 34 is a memory that temporarily stores information and is used as a work memory by the processor 30. The RAM 34 may be, for example, a dynamic random access memory (DRAM) or a static random access memory (SRAM).
[0033] The communication I / F 28 is connected to the network 16. The communication I / F 28 is responsible for sending and receiving information to and from an external communication device (e.g., the client terminal 12) via the network 16. For example, the communication I / F 28 transmits information in response to a request from the processor 30 to the external communication device via the network 16. The communication I / F 28 also receives information transmitted from the external communication device and outputs the received information to the processor 30 via the bus 36.
[0034] An evaluation processing program 32A is stored in the storage 32. The evaluation processing program 32A is a program that provides a simulation for evaluating the toxicity of chemical substances. The processor 30 reads the evaluation processing program 32A from the storage 32 and executes the read evaluation processing program 32A on the RAM 34 to perform toxicity evaluation processing. The toxicity evaluation processing is realized by the processor 30 operating as a first acquisition unit 30A, a toxicity evaluation unit 30B, and a condition setting unit 30C.
[0035] The storage 32 also stores a derivation processing program 32B. The derivation processing program 32B is a program for deriving changes in pathways in toxicity assessment before and after updating the toxicity determination flow. The processor 30 reads the derivation processing program 32B from the storage 32 and executes the read derivation processing program 32B on the RAM 34 to perform difference derivation processing. The difference derivation processing is realized by the processor 30 operating as a second acquisition unit 30D and a difference derivation unit 30E.
[0036] Furthermore, a generation processing program 32C is stored in the storage 32. The generation processing program 32C is a program that generates a display image 64 (see FIG. 10 , etc.) that is output to the client terminal 12. The processor 30 reads the generation processing program 32C from the storage 32 and executes the read generation processing program 32C on the RAM 34 to perform image generation processing. The image generation processing is realized by the processor 30 operating as a third acquisition unit 30F, an image generation unit 30G, and an output unit 30H. In this embodiment, the generation processing program 32C is an example of a "program" according to the technology of the present disclosure.
[0037] Here, consider a case where a user 18 uses the information processing system 10 to evaluate the toxicity of a newly developed chemical substance A to the human body (hereinafter, also simply referred to as "toxicity evaluation"). Here, toxicity refers to the toxicity that the user 18 is interested in as an evaluation item, and examples include mutagenicity, sensitization, and irritation. Mutagenicity refers to the property of causing irreversible changes in the genetic information of an organism (the base sequence of DNA (deoxyribonucleic acid) or the structure or number of chromosomes). Sensitization refers to the property of causing an allergic reaction when exposed to a chemical substance. Irritation refers to the property of a chemical substance or the like causing irritation (e.g., pain or a burning sensation) to the sense of touch or the like.
[0038] When performing a toxicity assessment, as shown in FIG. 3 , the user 18 inputs a compound list 58 into the client terminal 12 via the reception device 20. The compound list 58 is a list of chemical substances to be subjected to toxicity assessment. For example, the number of compounds to be subjected to toxicity assessment in a single toxicity assessment may range from several thousand to several tens of thousands. Examples of chemical substances include low-molecular-weight compounds (e.g., molecular weights less than 1,000), sugars, peptides, proteins, and nucleic acids. The compound list 58 includes multiple pieces of compound information 58A. The compound information 58A is information that can identify the chemical structure of a compound. More specifically, the compound information 58A is text information describing the chemical structure, such as a structural formula, a composition formula, and an amino acid sequence, or numerical information obtained by converting such text information into numerical values. The compound list 58 may also be a list of information indicating Chemical Abstract Service (CAS) numbers or names of chemical substances. In this case, the client terminal 12 or the server 14 refers to table data or the like that records the correspondence between the CAS number or the name of the chemical substance and the chemical structure, and reads out the compound information 58A that corresponds to the input chemical substance.
[0039] The compound list 58 may also be a list of image data showing the chemical structures of compounds as compound graphs (i.e., data structures with atoms as nodes and bonds as edges). In this case, the client terminal 12 or the server 14 refers to table data or the like that records the correspondence between the compound graphs and the compound information 58A, and reads out the compound information 58A that corresponds to the selected compound graph.
[0040] 3 , a screen for selecting a compound list 58 is displayed on the screen of the display device 24, and the user 18 performs a selection operation on the selection screen to select, for example, the compound list 58. On the selection screen, for example, the user 18 clicks an input soft key 56 by operating a pointer 54 displayed on the screen of the display device 24 via the mouse 22. As a result, the compound list 58 is transmitted from the client terminal 12 to the server 14, and a processing request for toxicity evaluation of the compounds is made.
[0041] Although the above description has been given with reference to an example in which a plurality of pieces of compound information 58A are listed and input at one time, it goes without saying that each of the plurality of pieces of compound information 58A may be input individually or may be input in a plurality of lists. Furthermore, a single piece of compound information 58A may be input, and the toxicity of a single compound and its metabolites may be evaluated.
[0042] As an example, as shown in FIG. 4 , a compound list 58 is output from the client terminal 12 to the server 14. A toxicity evaluation process is executed in the processor 30 of the server 14. The toxicity evaluation process is a process for evaluating the toxicity of a compound. In the toxicity evaluation process, the first acquisition unit 30A outputs the acquired compound list 58 to the toxicity evaluation unit 30B. The toxicity evaluation unit 30B evaluates the toxicity of a plurality of compounds (i.e., a group of compounds) indicated by compound information 58A in the compound list 58.
[0043] Specifically, the toxicity evaluation unit 30B executes toxicity evaluation processing in accordance with a toxicity determination flow 33. The toxicity determination flow 33 is described in an evaluation processing program 32A, and is schematically shown in Fig. 4 as stored in the storage 32. The toxicity determination flow 33 is a determination flow used to evaluate toxicity.
[0044] The toxicity determination flow 33 includes multiple processing steps. The multiple processing steps are set in advance and arranged in chronological order according to the toxicity evaluation procedure. The processing steps also include a determination processing step, and the subsequent path branches depending on the determination result in the determination processing step. The determination items in each determination processing step are predetermined. Examples of the determination items include whether a compound permeates a cell membrane or whether a compound satisfies a substructure rule. The substructure rule is a provision regarding a chemical structure and is a rule that identifies a predetermined substructure (e.g., a substructure of interest to the user 18). Examples of the substructure rule include the presence or absence of a benzene ring in a chemical structure and the number of benzene rings. The determination conditions in the determination processing steps are changeable.
[0045] The toxicity evaluation unit 30B inputs the compound list 58 into the toxicity determination flow 33. In the toxicity determination flow 33, the toxicity evaluation unit 30B executes a determination regarding toxicity evaluation for each determination step on the compound information 58A. The toxicity evaluation unit 30B outputs pre-update evaluation information 62A as a toxicity evaluation result according to each toxicity determination flow 33 executed. Steps ST1 to ST5 described below are examples of "processing steps" according to the technology of the present disclosure, and steps ST2 to ST5 are examples of "determination processing steps" according to the technology of the present disclosure.
[0046] As an example, as shown in Figure 5, compound information 58A is input to the toxicity determination flow 33. In the toxicity determination flow 33, in step ST1, descriptor calculation is performed on the compound information 58A. Examples of descriptors include the molar mass of the compound or LogP (a value obtained by taking the common logarithm of the octanol / water partition coefficient). After the processing in step ST2 is performed, the toxicity evaluation proceeds to step ST3.
[0047] In step ST2, a determination is made as to whether or not the compound permeates the cell membrane based on the result of the descriptor calculation performed in step ST1. The numerical value indicated by the descriptor is compared with a threshold, and a determination is made as to whether or not the compound permeates the cell membrane based on the comparison result. If the determination in step ST2 is positive, the toxicity evaluation proceeds to step ST3. If the determination in step ST2 is negative, a negative evaluation result (i.e., no toxicity) is output as the result of the toxicity evaluation. This is because the compound does not permeate the cell membrane and is therefore considered to have little effect on the body.
[0048] In step ST3, the compounds are classified according to the partial structures of the compounds in step ST3. Specifically, partial structure rules are applied to the compound information 58A. This determines whether the compounds have partial structures. Then, the compounds are classified based on the determination result of whether the molecular structure of each compound contains a partial structure. That is, the compounds are sorted into predetermined categories according to the combination of partial structures that the compound has. Note that there may be multiple partial structure rules, and for each of the multiple partial structure rules, it is determined whether the compound to be evaluated for toxicity has a partial structure. After the processing of step ST3 is executed, the toxicity evaluation proceeds to step ST4.
[0049] Depending on the classification result in step ST3, the toxicity assessment proceeds to step ST4. In step ST4, a determination is made using a first trained model. The first trained model realizes a toxicity determination function, for example, by performing machine learning using training data on a neural network. The training data may be, for example, a data set obtained from past experimental results, in which information capable of identifying a classified test substance is used as example data and information capable of identifying a toxicity determination result is used as ground truth data.
[0050] Furthermore, depending on the classification result in step ST3, the toxicity assessment proceeds to step ST5. In step ST5, a determination is made using a second trained model. The second trained model is a trained model different from the first trained model. The second trained model realizes a toxicity determination function, for example, by performing machine learning using training data on a neural network. Examples of training data include training data that is a data set obtained from past experimental results, in which information that can identify the classified test substance is used as example data and information that can identify the toxicity determination result is used as correct answer data.
[0051] After the determinations in steps ST4 and ST5, a final toxicity evaluation result is output. The toxicity evaluation result is either positive (i.e., toxic) or negative (i.e., non-toxic).
[0052] Although an example in which a positive or negative result (for example, a value of 1 for positive and 0 for negative) is output as the toxicity evaluation result has been given here, this is merely an example. A value indicating the probability of being positive or negative (for example, a score between 0 and 1) may also be output as the toxicity evaluation result.
[0053] 5 shows the path and processing steps taken in the toxicity assessment of compound A in the toxicity determination flow 33, and shows an example in which compound A was ultimately assessed as positive. In addition to information indicating the toxicity assessment result, the pre-update evaluation information 62A also includes information indicating the path leading to the toxicity assessment result in the toxicity determination flow 33 (hereinafter simply referred to as the "evaluation path"), information indicating an explanation of the assessment items, and information indicating details of the assessment result for each processing step.
[0054] In this way, the toxicity determination flow 33 outputs pre-update evaluation information 62A in accordance with the input compound information 58A. In the pre-update evaluation information 62A, the evaluation results and pathways are linked for each compound (see FIG. 4). In this way, the toxicity evaluation process is executed. The toxicity evaluation unit 30B outputs the pre-update evaluation information 62A to the second acquisition unit 30D.
[0055] Incidentally, when evaluating the toxicity of a compound using the toxicity evaluation flow 33, the user may change the evaluation conditions in the evaluation processing step. The purpose of changing the evaluation conditions may be, for example, to improve the accuracy of the toxicity evaluation. For example, the user may consider the evaluation results obtained using a certain toxicity evaluation flow 33 and make adjustments to the evaluation conditions based on organic chemistry theory (e.g., adding a partial structure rule or changing the threshold value for membrane permeability). This may improve the accuracy of the toxicity evaluation using the updated toxicity evaluation flow 33.
[0056] However, when the toxicity determination flow 33 is updated, it is difficult to understand how the update has affected the toxicity assessment by the toxicity determination flow 33. For example, when the toxicity determination flow 33 is complex (for example, when there are a large number of determination processing steps), it is difficult to understand how changes made to the determination processing steps affect changes in the assessment results.
[0057] Therefore, in this embodiment, a difference derivation process is executed in the processor 30. The difference derivation process is a process for deriving changes that have occurred in toxicity assessment before and after updating the toxicity determination flow 33. As shown in FIG. 6 as an example, the user 18 inputs a descriptor list 60 and a structural rule list 61 to the client terminal 12 via the reception device 20. The descriptor list 60 is a list of descriptors used for determination in the determination processing step of the updated toxicity determination flow 33. The descriptor list 60 includes multiple pieces of descriptor information 60A. The descriptor information 60A includes information that identifies the descriptors used in the processing step for performing descriptor calculation (e.g., step ST1 shown in FIG. 5) and that identifies the changed descriptors. The descriptor information 60A also includes information that identifies the thresholds used in the determination processing step for comparing the descriptor calculation results with thresholds (e.g., step ST2 shown in FIG. 5).
[0058] The structural rule list 61 is a list of partial structural rules. The structural rule list 61 includes multiple structural rule information 61A. The structural rule information 61A is information that can identify a partial structure. More specifically, the structural rule information 61A is text information describing the chemical structure of the partial structure, such as the structural formula, composition formula, or amino acid sequence, or numerical information obtained by converting such text information into numerical values. The structural rule list 61 may also be a list of information indicating the names of chemical structures. In this case, the client terminal 12 or the server 14 refers to table data or the like that records the correspondence between the names of chemical structures and the chemical structures, and reads out the structural rule information 61A corresponding to the input partial structure.
[0059] The structural rule list 61 may also be a list of image data showing the chemical structure of the partial structure as a compound graph (i.e., a data structure in which atoms are nodes and bonds are edges). In this case, the client terminal 12 or the server 14 refers to table data or the like that records the correspondence between the compound graph and the structural rule information 61A, and reads out the structural rule information 61A that corresponds to the selected compound graph.
[0060] 6 , a screen for selecting a descriptor list 60 and a structure rule list 61 is displayed on the screen of the display device 24, and the user 18 performs a selection operation on the selection screen to select, for example, the descriptor list 60 and the structure rule list 61. On the selection screen, for example, the user 18 clicks an input soft key 56 by operating a pointer 54 displayed on the screen of the display device 24 via the mouse 22. As a result, the descriptor list 60 and the structure rule list 61 are transmitted from the client terminal 12 to the server 14, and a processing request for updating the toxicity determination flow 33 is made.
[0061] As an example, as shown in FIG. 7 , the first acquisition unit 30A outputs the acquired descriptor list 60 and structure rule list 61 to the condition setting unit 30C. The condition setting unit 30C changes the judgment conditions for the judgment processing step of the toxicity judgment flow 33 based on the descriptor list 60 and structure rule list 61. Specifically, the condition setting unit 30C changes the descriptors used in the processing step in which descriptor calculation is performed, according to the descriptor information 60A indicated by the descriptor list 60. Furthermore, the condition setting unit 30C changes the threshold value used in the judgment processing step in which the descriptor calculation result is compared with a threshold value, according to the descriptor information 60A. The example shown in FIG. 7 illustrates an example in which the descriptors in step ST1 are changed based on the descriptor list 60, and further, the threshold value for the membrane permeability check in step ST2 is changed.
[0062] The condition setting unit 30C changes the partial structure rule used in the determination processing step to which the partial structure rule is applied, in accordance with the structural rule information 61A indicated by the structural rule list 61. In the example shown in Fig. 7, the partial structure rule applied in step ST3 is changed based on the structural rule list 61. For example, if a benzene ring is cited as the partial structure, the structural formula determined to be a benzene ring by the structural rule list 61 is changed. Then, the condition setting unit 30C outputs the updated toxicity determination flow 33 to the toxicity evaluation unit 30B.
[0063] The toxicity evaluation unit 30B evaluates the toxicity of a plurality of compounds (i.e., a compound group) indicated by the compound information 58A in the compound list 58 using the updated toxicity determination flow 33. The compound group to be evaluated here is the same as the compound group for which toxicity evaluation was performed using the toxicity determination flow 33 before the update. The toxicity evaluation unit 30B outputs the results of the toxicity evaluation performed using the updated toxicity determination flow 33 to the second acquisition unit 30D as updated evaluation information 62B. Like the pre-update evaluation information 62A, the updated evaluation information 62B includes information indicating the results of the toxicity evaluation, as well as information indicating the evaluation path, information indicating an explanation of the determination items, and information indicating details of the determination results for each processing step.
[0064] In the example shown in FIG. 7 , the toxicity evaluation of compound A shows the path and judgment steps taken in the updated toxicity determination flow 33, and an example is shown in which compound A is ultimately evaluated as negative. Here, the evaluation path in the toxicity evaluation of compound A shown in FIG. 7 differs from the evaluation path in the toxicity evaluation of compound A shown in FIG. 5 . Specifically, the judgment result in step ST3 for compound A is different due to the change in the judgment conditions in step ST3, resulting in a change in the subsequent evaluation path. Furthermore, the conclusion of the toxicity evaluation result is also different, in that the toxicity evaluation result of compound A was positive before the change in the judgment conditions, but changed to negative after the update of the judgment conditions. In this way, changing the judgment conditions in the judgment processing steps in the toxicity determination flow 33 may cause a change in the path in the toxicity evaluation of a compound. Note that, here, a case is shown in which a change in the evaluation path in the toxicity determination flow 33 occurs for compound A, but of course, changes in the evaluation path can also occur for other compounds.
[0065] In this case, as shown in FIG. 8 as an example, the second acquisition unit 30D outputs pre-update evaluation information 62A and post-update evaluation information 62B to the difference derivation unit 30E. The difference derivation unit 30E executes a difference derivation process. Specifically, the difference derivation unit 30E compares, for each compound, the evaluation path indicated by the pre-update evaluation information 62A with the evaluation path indicated by the post-update evaluation information 62B. The difference derivation unit 30E then extracts, in the post-update evaluation information 62B, compounds whose evaluation path has changed from the pre-update evaluation information 62A, and generates difference evaluation information 62C. The difference evaluation information 62C is information that can identify compounds whose evaluation path has changed and the evaluation path after the change when the judgment conditions are changed.
[0066] 8 shows an example in which, as a result of comparing the pre-update evaluation information 62A with the post-update evaluation information 62B, compounds A and C whose evaluation pathways have changed are extracted, and information indicating these compounds and their evaluation pathways is generated as difference evaluation information 62C. The difference derivation unit 30E then outputs the difference evaluation information 62C to the third acquisition unit 30F.
[0067] 9 , the third acquisition unit 30F outputs the difference evaluation information 62C and the toxicity determination flow 33 to the image generation unit 30G. The image generation unit 30G generates a display image 64 based on the difference evaluation information 62C and the toxicity determination flow 33. The display image 64 includes a flow image 64A. The flow image 64A is an example of a "flowchart" according to the technology of the present disclosure.
[0068] The flow image 64A is an image showing the procedure for obtaining the results of toxicity assessment of a group of compounds using the toxicity determination flow 33. The flow image 64A includes a plurality of step symbols 64A1 and connecting lines 64A2. The connecting lines 64A2 indicate the path of toxicity assessment in the toxicity determination flow 33. The step symbols 64A1 are symbols indicating the content of each processing step in the toxicity determination flow 33. Here, as an example, text explaining the content of the processing step is shown within a rectangular frame.
[0069] The bond lines 64A2 are lines connecting step symbols 64A1 arranged one behind the other in chronological order, and are shown here as arrows as an example. In the flow image 64A, for compounds in which a change has occurred in the evaluation pathway indicated by the difference evaluation information 62C, the evaluation pathway after the change is displayed in an identifiable manner. The bond lines 64A2 are an example of a "bond line" according to the technology of the present disclosure.
[0070] Furthermore, the display mode of the evaluation path after the change is changed depending on the number of compounds that have passed through the evaluation path after the change. In the example shown in Fig. 9, in the flow image 64A, the thickness of the bond line 64A2 indicating the evaluation path after the change of a compound whose evaluation path has changed is changed depending on the number of compounds that have passed through the bond line 64A2. This shows the evaluation path after the change of a compound whose evaluation path has changed. In the example shown in Fig. 9, the thickness of the bond line 64A2 is displayed thicker as the number of compounds that have passed through the bond line 64A2 increases.
[0071] 9, the difference evaluation information 62C includes the evaluation results and the evaluation paths for each compound whose evaluation path has changed, such as compound A and compound C. When generating the flow image 64A, the image generation unit 30G, as an example, counts the number of compounds passing through the paths between each processing step of the toxicity determination flow 33 based on the evaluation path for each compound extracted from the difference evaluation information 62C, and increases the thickness of the corresponding connection line 64A2 as the number of paths increases.
[0072] In the example shown in FIG. 9 , first, for compounds whose evaluation pathways have changed, the bond line 64A2 corresponding to the path leading to "classification by substructure" is thicker than the path leading from the processing step of "membrane permeability check" to a negative result. This indicates that, for compounds whose evaluation pathways have changed, a greater number of compounds pass through the path from the processing step of "membrane permeability check" to "classification by substructure." Furthermore, the thickness of the two bond lines 64A2 branching from the processing step of "classification by substructure" indicates that more compounds pass through the path leading to the "second trained model" than the path leading to the "first trained model." Furthermore, for compounds whose evaluation pathways have changed, the thickness of the two bond lines 64A2 leading from the "second trained model" to "positive" and "negative" indicates that a greater number of compounds are determined to be "negative" in the "second trained model."
[0073] As described above, the difference evaluation information 62C lists only compounds whose evaluation paths have changed before and after the change in the judgment conditions. By changing the thickness of the bond lines 64A2, as in the example flow image 64A shown in Fig. 9, it is possible to grasp what evaluation paths have been followed by many of the compounds whose evaluation paths have changed as described in the difference evaluation information 62C.
[0074] Although the embodiment in which the thickness of the bond line 64A2 is changed depending on the number of compounds that have passed through the path where a change has occurred has been described above, this is merely an example. For example, instead of or in addition to the thickness of the bond line 64A2, the color of the bond line 64A2 (e.g., the more compounds there are, the redder it becomes, and the fewer compounds there are, the bluer it becomes) and / or the line type (e.g., the more compounds there are, the more solid the line becomes, and the fewer compounds there are, the dotted line becomes) may be changed depending on the number of compounds.
[0075] Furthermore, in the flow image 64A, each step symbol 64A1 is linked to information indicating a compound that has passed through the processing step based on the difference evaluation information 62C. Furthermore, each bond line 64A2 is linked to information indicating a compound that has passed through the bond line 64A2 based on the difference evaluation information 62C. Specifically, in the flow image 64A, the step symbols 64A1 and bond lines 64A2 corresponding to the evaluation path indicated by the difference evaluation information 62C are associated with the compounds indicated by the difference evaluation information 62C.
[0076] 10, a pre-update flow image 65 may be displayed together with a flow image 64A in the display image 64. The pre-update flow image 65 is an image showing the evaluation path taken by the compound indicated by the difference evaluation information 62C in the toxicity determination flow 33 before the update (see FIG. 5). The image generation unit 30G generates the pre-update flow image 65 based on the toxicity determination flow 33 before the update and the difference evaluation information 62C, similar to the flow image 64A. Then, the image generation unit 30G arranges the pre-update flow image 65 and the flow image 64A side by side in the display image 64.
[0077] In the pre-update flow image 65, the display mode of the evaluation path is also changed depending on the number of compounds that have passed through the evaluation path. In the example shown in FIG. 10 , for compounds whose evaluation path has changed, the thickness of the bond line 64A2 indicating the evaluation path before the change is changed depending on the number of compounds that have passed through the bond line 64A2. This shows the evaluation path before the change for the compound whose evaluation path has changed. In the example shown in FIG. 10 , the thickness of the bond line 64A2 is displayed thicker the greater the number of compounds that have passed through the bond line 64A2. In the example shown in FIG. 10 , in the pre-update flow image 65, there are relatively more evaluation paths that start from "classification by partial structure" through the "first trained model" and lead to "negative." In contrast, in the flow image 64A, there are relatively more evaluation paths that start from "classification by partial structure" through the "second trained model" and lead to "positive."
[0078] In this way, when a change occurs in the evaluation pathway, it is easy to identify the pathway in which the change occurred by comparing the pre-update flow image 65 with the flow image 64A. Furthermore, in each of the pre-update flow image 65 and the flow image 64A, the display mode of the evaluation pathway is changed depending on the number of compounds that have passed through the evaluation pathway. This makes it easy to compare the evaluation pathways before and after the change for compounds in which the evaluation pathway has changed.
[0079] The image generation unit 30G outputs the generated display image 64 to the output unit 30H. As an example, as shown in Fig. 11 , the output unit 30H of the server 14 executes control to output the display image 64 to the client terminal 12. In other words, the server 14 transmits information indicating the display image 64 to the client terminal 12. A screen 24A including the display image 64 is displayed on the display device 24 of the client terminal 12.
[0080] As described above, the display image 64 includes a flow image 64A. In toxicity evaluation using the toxicity determination flow 33, for some compounds in the compound group (e.g., the above-described compound A), changes have occurred between the evaluation path before and after the change in the determination conditions. The flow image 64A then displays the path in which the change has occurred in an identifiable manner. In the example shown in FIG. 11 , the evaluation path taken by a compound whose evaluation path has changed in the updated toxicity determination flow 33 is displayed in the flow image 64A showing the updated toxicity determination flow 33.
[0081] In the example shown in FIG. 11 , a step symbol 64A1 is selected via the pointer 54 in the flow image 64A. In this case, a detailed image 64B is displayed. The detailed image 64B includes a compound image 64B1 showing a compound that passed through the selected processing step in the toxicity assessment. Here, the step symbol 64A1 corresponding to the processing step of the toxicity assessment using the second trained model is selected, and the compound image 64B1 shows structural formulas showing the molecular structures of three compounds that were the subject of the toxicity assessment using the second trained model. As structural data other than structural formulas, for example, a compound graph or text describing the molecular structure may be displayed. The compound image 64B1 is an example of "structural data showing the molecular structure of the target compound" according to the technology of the present disclosure.
[0082] Although the embodiment in which structural data is displayed in the compound image 64B1 has been described above, this is merely an example. For example, the name, CAS number, and / or molecular formula of the compound may be displayed instead of or together with the structural data.
[0083] In addition, although an example has been given here in which, when a step symbol 64A1 is selected, a detailed image 64B of a compound that has passed through the processing step corresponding to the step symbol 64A1 is displayed, this is merely an example. When a step symbol 64A1 is selected, a compound that has been input to the processing step corresponding to the step symbol 64A1 or a compound that has been output from the processing step may be displayed in the detailed image 64B in a switchable manner.
[0084] Also, although an example in which the step symbol 64A1 is selected has been given here, the bond line 64A2 may also be selected, in which case a compound image 64B1 corresponding to the compound that passed through the bond line 64A2 in the toxicity evaluation is displayed.
[0085] Next, the control processing in the server 14 according to this embodiment will be described with reference to Fig. 12. The server control processing is processing executed by the server 14, and includes the toxicity evaluation processing, difference derivation processing, and image generation processing described above. Fig. 12 is a flowchart showing an example of the server control processing. The processing flow shown in Fig. 12 is an example of an "information processing method" according to the technology of the present disclosure.
[0086] 12 as an example, first, in step ST10, the first acquisition unit 30A determines whether or not the compound list 58 and the processing request have been acquired. If it is determined in step ST10 that the compound list 58 and the processing request have been acquired, the determination is affirmative, and the server control processing proceeds to step ST12. If it is determined in step ST10 that the compound list 58 and the processing request have not been acquired, the determination is negative, and the server control processing returns to step ST10.
[0087] In step ST12, the toxicity evaluation unit 30B performs toxicity evaluation on the compounds indicated in the compound list 58 acquired in step ST10 using the toxicity determination flow 33. This results in pre-update evaluation information 62A. After the processing of step ST12 is executed, the server control processing proceeds to step ST14.
[0088] In step ST14, the first acquisition unit 30A determines whether or not the descriptor list 60 and the structure rule list 61 have been acquired. If it is determined in step ST14 that the descriptor list 60 and the structure rule list 61 have been acquired, the determination is affirmative, and the server control process proceeds to step ST16. If it is determined in step ST14 that the descriptor list 60 and the structure rule list 61 have not been acquired, the determination is negative, and the server control process returns to step ST14.
[0089] In step ST16, the condition setting unit 30C updates the toxicity determination flow 33 based on the descriptor list 60 and the structural rule list 61 acquired in step ST14. Specifically, the condition setting unit 30C changes the determination conditions in the determination step of the toxicity determination flow 33 in accordance with the descriptor list 60 and the structural rule list 61. After the processing of step ST16 is executed, the server control processing proceeds to step ST18.
[0090] In step ST18, the toxicity evaluation unit 30B performs toxicity evaluation on the compounds indicated in the compound list 58 acquired in step ST10 using the updated toxicity determination flow 33. This results in updated evaluation information 62B. After the processing of step ST18 is executed, the server control processing proceeds to step ST20.
[0091] In step ST20, the difference derivation unit 30E compares the pre-update evaluation information 62A obtained in step ST12 with the post-update evaluation information 62B obtained in step ST18. This produces difference evaluation information 62C indicating compounds whose toxicity evaluation pathways have changed before and after the update. After the processing of step ST20 is executed, the server control processing proceeds to step ST22.
[0092] In step ST22, the image generation unit 30G generates a display image 64 based on the difference evaluation information 62C. The display image 64 includes a flow image 64A. The flow image 64A shows the evaluation pathway after the change for a compound that has undergone a change in the evaluation pathway indicated by the difference evaluation information 62C. After the processing of step ST22 is executed, the server control processing proceeds to step ST24.
[0093] In step ST24, the output unit 30H executes control to output the display image 64 generated by the image generation unit 30G in step ST22 to the client terminal 12. Specifically, the output unit 30H transmits the display image 64 to the client terminal 12. After the processing of step ST24 is executed, the server control processing proceeds to step ST26.
[0094] In step ST26, the output unit 30H determines whether a condition for terminating the server control process (hereinafter referred to as the "termination condition") has been satisfied. One example of the termination condition is that an instruction to terminate the server control process has been accepted. If the termination condition has not been satisfied in step ST26, the determination is negative, and the server control process proceeds to step ST10. If the termination condition has been satisfied in step ST26, the determination is positive, and the server control process ends.
[0095] As described above, in the information processing system 10 according to the first embodiment, the toxicity evaluation unit 30B in the processor 30 of the server 14 evaluates the toxicity of a compound. The condition setting unit 30C updates the toxicity determination flow 33 based on the descriptor list 60 and the structural rule list 61. The toxicity evaluation unit 30B then evaluates the toxicity of the compound using the updated toxicity determination flow 33. The difference derivation unit 30E generates difference evaluation information 62C by comparing the pre-update evaluation information 62A with the post-update evaluation information 62B. The image generation unit 30G generates a flow image 64A based on the difference evaluation information 62C. The flow image 64A displays identifiable paths that have changed between paths before and after the change of the evaluation conditions. The output unit 30H then controls the output of a display image 64 including the flow image 64A. This makes it easier to visually grasp, in the flow image 64A, the path that a compound that has changed in the evaluation path after the change when the evaluation conditions for toxicity evaluation are changed. As a result, the user can easily understand the effect of a change in the judgment conditions on the evaluation results.
[0096] For example, in conventional software, the user would estimate the impact on the entire flow by comparing the output results between processing steps that existed before and after in chronological order, but it was difficult to see at a glance how a change in the judgment conditions affected the evaluation results. With this configuration, the user can visually see what path a compound that has undergone a change in its evaluation path took in the toxicity judgment flow 33. This makes it easier for the user to understand the impact of a change in the judgment conditions on the evaluation results.
[0097] Furthermore, in the information processing system 10 according to the first embodiment, the display mode of the pathway in which a change has occurred in the flow image 64A is changed depending on the number of compounds that have passed through the pathway in which a change has occurred in the toxicity evaluation. This makes it easier to understand what pathway a compound that has changed in the evaluation results after the evaluation conditions have been changed has taken in the toxicity evaluation flow 33.
[0098] Furthermore, in the information processing system 10 according to the first embodiment, the flow image 64A includes a plurality of step symbols 64A1 and bond lines 64A2 connecting the step symbols 64A1 arranged one after the other in chronological order. Furthermore, in the flow image 64A, paths are indicated by the bond lines 64A2. The thickness of the bond lines 64A2 is changed depending on the number of compounds that have passed through a path in which a change has occurred. This makes it easier to visually grasp the number of compounds that have passed through a path in which a change has occurred.
[0099] Furthermore, in the information processing system 10 according to the first embodiment, the thickness of the bond line 64A2 in the flow image 64A increases as the number of compounds that have passed through a pathway in which a change has occurred increases. A large number of compounds that have passed through a pathway in which a change has occurred means that the influence of a change in the judgment conditions is large. As a result, by visually checking pathways with thick bond lines, it is possible to grasp pathways that are greatly influenced by a change in the judgment conditions. In other words, it is easy to visually grasp pathways that are greatly influenced by a change in the judgment conditions.
[0100] Furthermore, in the information processing system 10 according to the first embodiment, when a step symbol 64A1 is selected in the flow image 64A, a compound image 64B1 indicating a compound that has passed through the step symbol 64A1 in the toxicity evaluation is displayed. This makes it possible to grasp, for each processing step in the flow image 64A, compounds whose evaluation path has changed after a change in the judgment conditions.
[0101] Furthermore, in the information processing system 10 according to the first embodiment, the compound image 64B1 includes structure data indicating the molecular structure of the compound, which makes it possible to grasp the molecular structure of a compound whose evaluation path has changed after the change in the judgment conditions.
[0102] It should be noted that the flow of toxicity assessment in the toxicity determination flow 33 shown in the first embodiment is merely an example. The flow of toxicity assessment in the toxicity determination flow 33 can be selected or changed as appropriate by the user. Furthermore, the processing steps shown in the flow image 64A do not necessarily have to be all of the processing steps included in the toxicity determination flow 33, and a configuration in which only some of the processing steps are displayed may be used. For example, a configuration in which only processing steps in which the user 18 is interested may be displayed as the flow image 64A.
[0103] In the first embodiment, an example in which the detailed image 64B includes structure data indicating the molecular structure of the compound that has passed through the step symbol 64A1 has been described, but the technology of the present disclosure is not limited to this. In this first modification, the detailed image 64B includes, together with the compound image 64B1, structure data indicating a common structure shared among the compounds that have passed through the processing step.
[0104] 13 , the third acquisition unit 30F outputs the difference evaluation information 62C and the toxicity determination flow 33 to the image generation unit 30G. The image generation unit 30G generates a display image 64 based on the difference evaluation information 62C and the toxicity determination flow 33. The display image 64 includes a flow image 64A that shows the toxicity determination flow 33.
[0105] In the flow image 64A, a step symbol 64A1 is linked to information indicating a compound that has passed through the processing step corresponding to the step symbol 64A1 based on difference evaluation information 62C. Furthermore, each bond line 64A2 is linked to information indicating a compound that has passed through the bond line 64A2 based on difference evaluation information 62C. Furthermore, a common structure that is a structure common to a plurality of compounds (here, compounds A and C) is linked to the compound in the difference evaluation information 62C. Thus, the step symbol 64A1 and the bond line 64A2 are linked not only with information indicating the compound, but also with information indicating the common structure of the compound.
[0106] The image generation unit 30G outputs the generated display image 64 to the output unit 30H. As an example, as shown in Fig. 14 , the output unit 30H of the server 14 executes control to output the display image 64 to the client terminal 12. In the example shown in Fig. 14 , a step symbol 64A1 is selected in a flow image 64A via the pointer 54. In this case, a detailed image 64B is displayed.
[0107] The detailed image 64B includes a compound image 64B1 and a common structure image 64B2. The common structure image 64B2 is an image showing the common structure of multiple compounds that have passed through the processing steps. The common structure is a partial structure contained as a part of the compound that has passed through the processing step, and is a structure common to multiple compounds.
[0108] Here, a step symbol 64A1 corresponding to a processing step of toxicity assessment using the second trained model is selected, and a structural formula showing the common structure of the compounds that were the subject of toxicity assessment using the second trained model is shown in the common structure image 64B2. The common structure image 64B2 is an example of "structural data showing a common structure" according to the technology of the present disclosure.
[0109] As described above, in the information processing system 10 according to the first modification, the detailed image 64B includes a common structure image 64B2 that shows structural data indicating the common structure of compounds that have passed through the processing steps. This makes it possible to understand what common structures are present for multiple compounds that have undergone changes in the evaluation path after a change in the evaluation conditions. Furthermore, for example, by understanding the common molecular structure, it becomes easier to consider what common structure is the cause of the effect of a change in the evaluation path due to a change in the evaluation conditions.
[0110] Here, an example is given in which step symbol 64A1 is selected, but bond line 64A2 may also be selected, in which case a common structure image 64B2 corresponding to the compound that passed through bond line 64A2 in the toxicity evaluation is displayed.
[0111] Second Embodiment In the first embodiment described above, an example was given in which the toxicity assessment process, difference derivation process, and image generation process were performed in the server 14, but the technology of the present disclosure is not limited to this. In the second embodiment, the toxicity assessment process and difference derivation process are performed in the server 14, and the image generation process is performed in the client terminal 12. In this embodiment, the client terminal 12 is an example of an "information processing device."
[0112] 15 , the client terminal 12 includes a computer 38, a reception device 20, a display device 24, a communication I / F 40, an external I / F 42, and a bus 50. The computer 38 includes a processor 44, a storage 46, and a RAM 48. The processor 44, the storage 46, the RAM 48, the reception device 20, the display device 24, the communication I / F 40, and the external I / F 42 are connected to the bus 50. In the present embodiment, the processor 44 is an example of a “processor” according to the technology of the present disclosure.
[0113] The hardware configuration of the computer 38 (i.e., the processor 44, the storage 46, and the RAM 48) is basically the same as the hardware configuration of the computer 26, so a description of the hardware configuration of the computer 38 will be omitted here.
[0114] The communication I / F 40 is connected to the network 16. The communication I / F 40 controls the exchange of information with an external communication device (e.g., the server 14) via the network 16. For example, the communication I / F 40 transmits information in response to a request from the processor 44 to the external communication device via the network 16. The communication I / F 40 also receives information transmitted from the external communication device and outputs the received information to the processor 44 via the bus 50.
[0115] The external I / F 42 controls the exchange of various information with an external device (not shown) located outside the client terminal 12. The external device may be, for example, at least one of a smart device, a personal computer, a server, a USB (Universal Serial Bus) memory, a memory card, a printer, etc. An example of the external I / F 42 is a USB interface. The external device is directly or indirectly connected to the USB interface.
[0116] A control processing program 46A is stored in the storage 46. The control processing program 46A is a program for executing image generation and display control. The processor 30 reads the control processing program 46A from the storage 46 and executes the read control processing program 46A on the RAM 48 to perform image generation processing. The image generation processing is realized by the processor 44 operating as an acquisition unit 44A, an image generation unit 44B, and a display control unit 44C. In the present embodiment, the computer 38 is an example of a "computer" according to the technology of the present disclosure, and the control processing program 46A is an example of a "program" according to the technology of the present disclosure.
[0117] 16 , in the processor 30 of the server 14, the toxicity assessment unit 30B outputs pre-update evaluation information 62A and post-update evaluation information 62B obtained by the toxicity assessment process to the output unit 30H. Furthermore, the difference derivation unit 30E executes the difference derivation process and outputs difference evaluation information 62C obtained based on the pre-update evaluation information 62A and post-update evaluation information 62B to the output unit 30H. The output unit 30H outputs the difference evaluation information 62C to the client terminal 12 via the network 16.
[0118] In the processor 44 of the client terminal 12, the acquisition unit 44A acquires difference evaluation information 62C via the network 16. The acquisition unit 44A also acquires the toxicity determination flow 33. The acquisition unit 44A then outputs the difference evaluation information 62C and the toxicity determination flow 33 to the image generation unit 44B. The image generation unit 44B generates a display image 64 based on the difference evaluation information 62C and the toxicity determination flow 33. The image generation unit 44B then outputs the generated display image 64 to the display control unit 44C. The display control unit 44C controls a GUI (Graphical User Interface) to display the display image 64 including the flow image 64A, thereby causing the display device 24 to display the display image 64 including the flow image 64A.
[0119] [Third Embodiment] In the first embodiment described above, an example was given in which the toxicity assessment process, difference derivation process, and image generation process were performed in the server 14, but the technology of the present disclosure is not limited to this. In the third embodiment, the toxicity assessment process, difference derivation process, and image generation process are performed in the client terminal 12. In this embodiment, the client terminal 12 is an example of an "information processing device."
[0120] 17 as an example, a compound list 58 is received at the client terminal 12 via the reception device 20. At the processor 44 of the client terminal 12, a toxicity evaluation unit 44E performs toxicity evaluation on the group of compounds indicated by the compound list 58 using a toxicity determination flow 33. At the client terminal 12, a descriptor list 60 and a structure rule list 61 are also received via the reception device 20. The toxicity determination flow 33 is updated based on the descriptor list 60 and the structure rule list 61. The toxicity evaluation unit 44E performs toxicity evaluation on the compounds indicated by the compound list 58 using the updated toxicity determination flow 33.
[0121] Furthermore, the difference derivation unit 44D generates difference evaluation information 62C based on the pre-update evaluation information 62A and the post-update evaluation information 62B. Then, the image generation unit 44B generates a display image 64 based on the difference evaluation information 62C and the toxicity determination flow 33. The display control unit 44C causes the display device 24 to display the display image 64 including the flow image 64A.
[0122] In the above-described embodiments, an example has been described in which the descriptor list 60 and the structural rule list 61 are input to change the judgment conditions of the judgment steps of the toxicity judgment flow 33. However, the technology of the present disclosure is not limited to this. For example, the judgment conditions may be changed by directly inputting the judgment conditions in the toxicity judgment flow 33 by the user.
[0123] In the above embodiment, the pre-update evaluation information 62A is obtained by executing the toxicity evaluation process, but the technology of the present disclosure is not limited to this. For example, the server 14 or the client terminal 12 may receive pre-update evaluation information 62A that has already been obtained (e.g., pre-update evaluation information 62A obtained as a result of processing by an external device, or pre-update evaluation information 62A obtained in the past), and execute the image generation process.
[0124] In the above embodiment, an example was described in which the evaluation processing program 32A, the derivation processing program 32B, and the generation processing program 32C are stored in the storage 32. However, the technology of the present disclosure is not limited to this. For example, the evaluation processing program 32A, the derivation processing program 32B, and the generation processing program 32C may be stored in a portable storage medium such as an SSD or a USB memory. The storage medium is a non-transitory computer-readable storage medium. The evaluation processing program 32A, the derivation processing program 32B, and the generation processing program 32C stored in the storage medium are installed on the computer 26. The processor 30 executes control processing of the server 14 in accordance with the evaluation processing program 32A, the derivation processing program 32B, and the generation processing program 32C. Similarly, the control processing program 46A may be stored in a storage medium instead of the storage 46.
[0125] In the above embodiment, the computers 26 and 38 are exemplified, but the technology of the present disclosure is not limited to this, and devices including an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), and / or a PLD (Programmable Logic Device) may be applied instead of the computers 26 and 38. Furthermore, instead of the computers 26 and 38, a combination of a hardware configuration and a software configuration may be used.
[0126] The hardware resources for executing the various processes described in the above embodiments can be various processors, as follows: Examples of processors include a CPU, which is a general-purpose processor that functions as a hardware resource for executing toxicity assessment processing, difference derivation processing, and / or image generation processing (hereinafter also simply referred to as "various processes") by executing software, i.e., a program. Examples of processors include dedicated electronic circuits, such as FPGAs, PLDs, or ASICs, which are processors having a circuit configuration designed specifically for executing specific processes. Each processor has built-in or connected memory, and each processor uses the memory to execute various processes.
[0127] The hardware resources that execute various processes 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 (for example, a combination of multiple FPGAs, or a combination of a processor and an FPGA). Also, the hardware resources that execute various processes may be a single processor.
[0128] As an example of a system configured with a single processor, first, one processor is configured by combining one or more processors with software, and this processor functions as a hardware resource that executes various processes. Second, there is a system that uses a processor that realizes the functions of the entire system, including multiple hardware resources that execute various processes, on a single IC (Integrated Circuit) chip, as typified by SoC (System-on-a-chip). In this way, various processes are realized using one or more of the above-mentioned various processors as hardware resources.
[0129] Furthermore, the hardware structure of these various processors can be, more specifically, electronic circuits that combine circuit elements such as semiconductor devices. The various processes described above are merely examples. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be rearranged, without departing from the spirit of the invention.
[0130] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.
[0131] In this specification, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."
[0132] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.
[0133] The following is further disclosed in relation to the above embodiment: <Supplementary Note 1> An information processing device including a processor, wherein the processor executes control to output a flowchart showing a procedure for obtaining toxicity evaluation results for a plurality of target compounds that are the subject of toxicity evaluation, the flowchart including a plurality of preset processing steps arranged in chronological order, the processing steps including a determination processing step in which judgment conditions are changeable and a subsequent path branches depending on the judgment result, and wherein, after the toxicity evaluation result has been obtained for at least one of the plurality of target compounds according to the procedure, the judgment conditions in the determination processing step are changed, and the toxicity evaluation result is obtained according to the procedure under the changed judgment conditions, the processor, in controlling to output the flowchart, when a change has occurred between the path taken before the change to arrive at the toxicity evaluation result before the change to the judgment conditions and the path taken after the change to arrive at the toxicity evaluation result after the change to the judgment conditions, displays the path in which the change has occurred in an identifiable manner. <Supplementary Note 2> The information processing device according to Supplementary Note 1, wherein, when the toxicity evaluation results are obtained for a plurality of the target compounds before and after the change in the judgment conditions, the display mode of the pathway in which the change occurred in the flowchart is changed according to the number of the target compounds that passed through the pathway in which the change occurred in the toxicity evaluation. <Supplementary Note 3> The information processing device according to Supplementary Note 2, wherein the flowchart shows a plurality of the processing steps and bond lines connecting the processing steps arranged one after the other in chronological order, and the pathway is indicated by the bond lines, and the display mode is the thickness of the bond lines. <Supplementary Note 4> The information processing device according to Supplementary Note 3, wherein the thickness of the bond lines becomes thicker as the number of the target compounds that passed through the pathway in which the change occurred increases.<Supplementary Note 5> The information processing device according to any one of Supplementary Notes 1 to 4, wherein the flowchart indicates a plurality of the processing steps and bond lines connecting the processing steps arranged one after the other in chronological order, and the path is indicated by the bond lines, and when a processing step or the bond line indicated in the flowchart is selected, an image indicating the target compound that has passed through the path indicated by the processing step or the bond line is displayed in the toxicity assessment. <Supplementary Note 6> The information processing device according to Supplementary Note 5, wherein the image includes structural data indicating a molecular structure of the target compound. <Supplementary Note 7> The information processing device according to Supplementary Note 6, wherein the image includes structural data indicating a common structure that is a partial structure included as a part of the target compound and is a structure common to a plurality of the target compounds that have passed through the selected processing step or the bond line.
[0134] The disclosure of Japanese Patent Application No. 2023-091157, filed on June 1, 2023, is incorporated herein by reference in its entirety. All documents, patent applications, and technical standards mentioned herein are incorporated herein by reference to the same extent as if each individual document, patent application, and technical standard was specifically and individually indicated to be incorporated by reference.
Claims
1. An information processing device comprising a processor, the processor executes control to output a flowchart showing a procedure for obtaining toxicity evaluation results for a plurality of target compounds that are the subject of toxicity evaluation, the flowchart including a plurality of preset processing steps arranged in chronological order, the processing steps including a judgment processing step in which judgment conditions can be changed and a subsequent path branches depending on the judgment result, and when, after the toxicity evaluation result has been obtained for at least one of the plurality of target compounds in accordance with the procedure, the judgment conditions in the judgment processing step are changed, and the toxicity evaluation result is obtained according to the procedure under the changed judgment conditions, the processor, in controlling to output the flowchart, displays in an identifiable manner the path in which the change has occurred, if a change has occurred between the pre-change path taken to arrive at the toxicity evaluation result before the change in the judgment conditions and the changed path taken to arrive at the toxicity evaluation result after the change in the judgment conditions.
2. The information processing device of claim 1, wherein, when toxicity evaluation results are obtained for a plurality of the target compounds before and after the change in the judgment conditions, the display manner of the pathway in which the change occurred in the flowchart is changed according to the number of the target compounds that passed through the pathway in which the change occurred in the toxicity evaluation.
3. The information processing device according to claim 2, wherein the flowchart shows a plurality of the processing steps and connecting lines connecting the processing steps arranged one after the other in chronological order, and the path is indicated by the connecting lines, and the display mode is the thickness of the connecting lines.
4. The information processing device according to claim 3, wherein the thickness of the bond line increases as the number of target compounds that have passed through the pathway in which the change has occurred increases.
5. The information processing device of claim 1, wherein the flowchart shows a plurality of the processing steps and connection lines connecting the processing steps arranged one after the other in chronological order, and the path is indicated by the connection lines, and when the processing step or the connection line shown in the flowchart is selected, an image showing the target compound that has passed through the processing step or the path indicated by the connection line in the toxicity evaluation is displayed.
6. The information processing device according to claim 5, wherein the image includes structural data showing the molecular structure of the target compound.
7. The information processing device according to claim 6, wherein the image includes structural data indicating a common structure, which is a partial structure contained as a part of the target compound and is a structure common to a plurality of the target compounds that have passed through the selected processing step or bond line.
8. An information processing method comprising: executing control to output a flowchart showing a procedure for obtaining toxicity evaluation results for a plurality of target compounds that are the subject of toxicity evaluation, the flowchart including a plurality of preset processing steps arranged in chronological order, the processing steps including a judgment processing step in which judgment conditions can be changed and a subsequent path branches depending on the judgment result, wherein, after the toxicity evaluation result has been obtained for at least one of the plurality of target compounds according to the procedure, the judgment conditions in the judgment processing step are changed, and the toxicity evaluation result is obtained according to the procedure under the changed judgment conditions, in the control to output the flowchart, if a change has occurred between the path before the change in the judgment conditions that was taken to reach the toxicity evaluation result before the change in the judgment conditions and the path after the change in the judgment conditions that was taken to reach the toxicity evaluation result after the change in the judgment conditions, the path in which the change has occurred is displayed in an identifiable manner.
9. A program for causing a computer to execute a process including executing control to output a flowchart showing a procedure for obtaining toxicity evaluation results for a plurality of target compounds that are the subject of toxicity evaluation, the flowchart including a plurality of preset processing steps arranged in chronological order, the processing steps including a judgment processing step in which judgment conditions can be changed and in which a subsequent path branches depending on the judgment result, wherein, after the toxicity evaluation result has been obtained for at least one of the plurality of target compounds according to the procedure, the judgment conditions in the judgment processing step are changed, and the toxicity evaluation result is obtained according to the procedure under the changed judgment conditions, in the control to output the flowchart, if a change has occurred between the path before the change in the judgment conditions that was taken to reach the toxicity evaluation result before the change in the judgment conditions and the path after the change in the judgment conditions that was taken to reach the toxicity evaluation result after the change in the judgment conditions, the path in which the change has occurred is displayed in an identifiable manner.
Citation Information
Patent Citations
Toxicity presence or absence determination method
JP2004093234A
Electronic apparatus
JP2023091157A
Support device, support method, and computer program
WO2011055820A1
Prediction of human developmental toxicity of pharmaceuticals using human stem cell-like cells and metabolomics
JP2013522649A
Cited By
Information processing system, information processing method, and program
WO2026205461A1
