Information processing device, information processing method, and computer-readable storage medium

Abstract

An information processing device performs the following processing: performing a first search for a partial structure contained in partial structure data that establishes a correspondence between a partial structure of a chemical substance and an index value representing a performance or structure of the partial structure from structural data representing the structure of a chemical substance to be processed; performing a second search for a chemical substance containing a partial structure extracted by the first search from past data that establishes a correspondence between the structure of the chemical substance and an index value representing the performance or structure of the chemical substance obtained through experiments; deriving the reliability of the index value of the partial structure based on the total number of chemical substances extracted by the second search and the index value corresponding to the chemical substance; and controlling the display of the partial structure extracted by the first search and the reliability of the partial structure on a display device.

Description

Technical Field

[0001] The present invention relates to an information processing device, an information processing method and an information processing program. Background Art

[0002] In the Re-publication No. 2009 / 118845, the following content is disclosed: the index values ​​such as the presence or absence of carcinogenicity and toxicity of the prediction target compound and the virtual compound generated based on the prediction target compound are predicted, the reliability of the prediction value of the prediction target compound is calculated based on each prediction result, and its reliability is displayed.

[0003] Japanese Patent Application Publication No. 2015-052990 discloses searching for an overall structure diagram from a structural formula database based on the compound name, decomposing the compound name into partial structure names, and providing structural indicators in the decomposed partial structures that help establish a corresponding association with the overall structure. Summary of the Invention

[0004] Technical issues to be solved by the invention

[0005] In the field of chemistry, when developing chemical substances, screening is performed based on indicators such as carcinogenicity and toxicity. This screening considers the presence of partial structures (hereinafter referred to as "structures of interest") that may adversely affect predefined indicators.

[0006] However, the structure of interest is often defined by the empirical knowledge of experts, which can be less reliable. Even if screening is performed based on this partial structure, it may not be adequate. The techniques described in Re-publication No. 2009 / 118845 and Japanese Patent Application Laid-Open No. 2015-052990 do not consider the reliability of the partial structure.

[0007] The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an information processing device, an information processing method, and an information processing program that can support appropriate filtering.

[0008] Means for solving technical problems

[0009] The information processing device of the present invention has at least one processor, wherein the processor performs the following processing: performing a first search for a partial structure contained in partial structure data that establishes a correspondence between the partial structure of the chemical substance and the index value representing the performance or structure of the partial structure from structural data representing the structure of the chemical substance representing the processing object, performing a second search for chemical substances including partial structures extracted by the first search from past data that establishes a correspondence between the structure of the chemical substance and the index value representing the performance or structure of the chemical substance obtained through experiments, deriving a reliability representing the accuracy of the index value of the partial structure extracted by the first search based on the total number of chemical substances extracted by the second search and the index value corresponding to the chemical substance, and controlling the display of the partial structure extracted by the first search and the reliability of the partial structure on a display device.

[0010] Furthermore, in the information processing apparatus of the present invention, the processor may perform control to discriminately display the reliability of a partial structure of the chemical substance to be processed.

[0011] Furthermore, in the information processing device of the present invention, the processor may control the display of the reliability in descending order when a plurality of partial structures are extracted by the first search.

[0012] Furthermore, in the information processing device of the present invention, the processor may perform weighting according to the total number of chemical substances extracted by the second search when deriving the reliability.

[0013] Furthermore, the information processing method of the present invention enables the processor of the information processing device to perform the following processing: performing a first search for a partial structure contained in partial structure data that establishes a correspondence between the partial structure of the chemical substance and the index value representing the performance or structure of the partial structure from structural data representing the structure of the chemical substance to be processed; performing a second search for chemical substances including the partial structure extracted by the first search from past data that establishes a correspondence between the structure of the chemical substance and the index value representing the performance or structure of the chemical substance obtained through experiments; deriving a reliability that represents the accuracy of the index value of the partial structure extracted by the first search based on the total number of chemical substances extracted by the second search and the index value corresponding to the chemical substance; and controlling the display of the partial structure extracted by the first search and the reliability of the partial structure on a display device.

[0014] Furthermore, the information processing program of the present invention is used to cause the processor of the information processing device to perform the following processing: performing a first search for a partial structure contained in partial structure data that establishes a correspondence between the partial structure of the chemical substance and the index value representing the performance or structure of the partial structure from structural data representing the structure of the chemical substance to be processed; performing a second search for chemical substances including the partial structure extracted by the first search from past data that establishes a correspondence between the structure of the chemical substance and the index value representing the performance or structure of the chemical substance obtained through experiments; deriving a reliability that represents the accuracy of the index value of the partial structure extracted by the first search based on the total number of chemical substances extracted by the second search and the index value corresponding to the chemical substance; and controlling the display of the partial structure extracted by the first search and the reliability of the partial structure on a display device.

[0015] Effects of the Invention

[0016] According to the present invention, appropriate screening can be supported. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a block diagram showing an example of the hardware configuration of an information processing device.

[0018] Figure 2 This is a diagram for explaining a graph showing the structure of a chemical substance.

[0019] Figure 3 This is a diagram for explaining some structural data.

[0020] Figure 4 This is a diagram showing an example of partial structural data.

[0021] Figure 5 This is a diagram showing an example of past data.

[0022] Figure 6 This is a block diagram showing an example of the functional structure of an information processing device.

[0023] Figure 7 This is a diagram showing an example of a reliability display screen.

[0024] Figure 8 This is a flowchart showing an example of reliability display processing. DETAILED DESCRIPTION

[0025] Hereinafter, embodiments for implementing the technology of the present invention will be described in detail with reference to the accompanying drawings.

[0026] First, refer to Figure 1 , the hardware structure of the information processing device 10 involved in this embodiment is described. Figure 1As shown, information processing device 10 includes a CPU (Central Processing Unit) 20, a memory 21 serving as a temporary storage area, and a nonvolatile storage unit 22. Furthermore, information processing device 10 includes a display 23 such as a liquid crystal display, input devices 24 such as a keyboard and a mouse, and a network interface (I / F) 25 for connecting to a network. CPU 20, memory 21, storage unit 22, display 23, input device 24, and network I / F 25 are connected to a bus 26. Examples of information processing device 10 include a personal computer and a server computer.

[0027] The storage unit 22 is implemented by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. The storage unit 22, serving as a storage medium, stores an information processing program 30. The CPU 20 reads the information processing program 30 from the storage unit 22, expands it into the memory 21, and executes the expanded information processing program 30.

[0028] Furthermore, the storage unit 22 stores partial configuration data 32 and past data 34. Figures 2 to 5 , partial structure data 32 and past data 34 are explained.

[0029] As an example, Figure 2 As shown, the information processing device 10 according to this embodiment processes structural data representing the structure of a chemical substance in a graph format as structural data representing the structure of the chemical substance. In this structural data, atoms are represented as nodes, and couplings are represented as edges. Furthermore, the format of the structural data is not limited to a graph. For example, a string format such as a DNA (deoxyribonucleotide acid) base sequence can also be used as the structural data format.

[0030] And, as an example, Figure 3 As shown, the structure that constitutes a part of a chemical substance may affect the index value representing the performance or structure of the chemical substance. Hereinafter, the structure that constitutes a part of a chemical substance is referred to as a "partial structure". Examples of index values ​​representing the performance of a chemical substance include the presence or absence of carcinogenicity, the presence or absence of toxicity, and the degree of solubility in water. In addition, examples of index values ​​representing the structure of a chemical substance include molecular weight and the number of ring structures. Hereinafter, when collectively referring to index values ​​representing the performance of a chemical substance and index values ​​representing the structure, they are simply referred to as "index values".

[0031] Figure 4 An example of partial structure data 32 is shown in FIG. Figure 4As shown, the partial structure data 32 associates the partial structure of a chemical substance with the type and value of the index value of the partial structure. The partial structure data 32 also includes multiple combinations of partial structures, the type and value of the index value of the partial structure. Figure 4 The partial graph in the text is structural data that represents a partial structure in a graphical form. This partial structure data 32 is pre-created based on, for example, the experience and knowledge of an expert. Furthermore, in partial structure data 32, one indicator value may be associated with one partial structure, or multiple indicator values ​​may be associated with one partial structure.

[0032] Figure 5 An example of past data 34 is shown in FIG. Figure 5 As shown, the structure of a chemical substance is associated with the type and value of its index value obtained through experiments in the past data 34. Furthermore, the past data 34 includes multiple combinations of the structure of a chemical substance and the type and value of its index value. Figure 5 The graph in the table is structural data that graphically represents the overall structure of a chemical substance. Past data 34 is pre-created based on measured values ​​obtained through past experiments. In past data 34, a single indicator value can be associated with the structure of a single chemical substance, or multiple indicator values ​​can be associated with the structure of a single chemical substance.

[0033] As described above, since past data 34 is actually measured values ​​obtained through past experiments, the reliability of the index values ​​included in past data 34 is relatively high. On the other hand, since the index values ​​included in partial structure data 32 are based on expert experience, etc., their reliability may be relatively low. Therefore, the information processing device 10 according to this embodiment has a function for deriving the reliability of the index values ​​of the partial structure of the chemical substance constituting the processing target using partial structure data 32 and past data 34.

[0034] Next, refer to Figure 6 , the functional structure of the information processing device 10 involved in this embodiment is described. Figure 6 As shown, the information processing device 10 includes a receiving unit 40, a first search unit 42, a second search unit 44, a deriving unit 46, and a display control unit 48. The receiving unit 40, the first search unit 42, the second search unit 44, the deriving unit 46, and the display control unit 48 function as the CPU 20 executing the information processing program 30.

[0035] The receiving unit 40 receives structural data representing the structure of a chemical substance to be processed input by a user. The user inputs structural data representing the structure of the chemical substance using a molecular design editor such as ChemDraw (registered trademark).

[0036] The first search unit 42 performs a first search for a partial structure included in the partial structure data 32 from the structure data received by the receiving unit 40 . The second search unit 44 performs a second search for a chemical substance including the partial structure extracted by the first search performed by the first search unit 42 from the past data 34 .

[0037] The deriving unit 46 derives a reliability indicating the accuracy of the index value of the partial structure extracted by the first search performed by the first search unit 42 based on the total number of chemical substances extracted by the second search performed by the second search unit 44 and the index value corresponding to the chemical substance. When deriving the reliability, the deriving unit 46 weights the reliability according to the total number of chemical substances extracted by the second search performed by the second search unit 44. Specifically, the deriving unit 46 derives the reliability according to the following formula (1).

[0038] [Formula 1]

[0039]

[0040] The "number of matches" in formula (1) refers to the number of chemical substances whose index values ​​and index values, among the chemical substances extracted by the second search, match the index values ​​and index values ​​of the partial structures extracted by the first search. As a specific example, the case where the structure data received by the receiving unit 40 includes "Partial Chart B" and "Toxicity" and "HIGH" are associated with "Partial Chart B" in the partial structure data 32 will be described. Furthermore, in this case, the past data 34 contains 99 chemical substances that include "Partial Chart B," and of these 99 chemical substances, 90 have a "High" toxicity rating and 9 have a "Low" toxicity rating. This example will be described.

[0041] At this time, the number of coincidences in formula (1) is "90," and the total number of chemical substances is "99." Therefore, at this time, as shown in the following formula (2), the deriving unit 46 derives the reliability of the index value of "Partial Graph B" as "0.9."

[0042] [Formula 2]

[0043]

[0044] The method for deriving reliability is not limited to the method using formula (1). For example, if the ratio of the number of coincidences to the total number of chemical substances is higher and the number of coincidences is greater, a formula other than formula (1) may be used to derive reliability, thereby deriving higher reliability.

[0045] The display control unit 48 controls the display 23 to display the partial structure extracted by the first search and the reliability derived by the derivation unit 46 for the partial structure. In this case, the display control unit 48 controls the display so that the reliability can be distinguished from the partial structure of the target chemical substance. Furthermore, if multiple partial structures are extracted by the first search, the display control unit 48 controls the display of the reliability levels in descending order.

[0046] Figure 7 FIG. 4 shows an example of a reliability display screen displayed on the display 23 under the control of the display control unit 48. Figure 7 As shown, the reliability display screen involved in this embodiment includes two display areas A1 and A2. In the display area A1, a diagram representing the structure of the chemical substance to be processed is displayed, and the reliability of the index value of the partial structure can be distinguishably displayed. The partial structure surrounded by a circle in the display area A1 represents the partial structure extracted by the first search. In addition, the circles in the display area A1 respectively represent areas filled with a predetermined transmittance and a color corresponding to the reliability. For example, two threshold values ​​TH1 and TH2 (TH1>TH2) are defined in advance for the reliability, and the colors corresponding to the reliability are pre-set, such as red when the reliability of the index value is above the threshold TH1, yellow when it is above the threshold TH2 and less than the threshold TH1, and green when it is less than the threshold TH2. In Figure 7 In the example, the dotted circle is colored red, the one-dot chain circle is colored yellow, and the two-dot chain circle is colored green. Since the colors vary depending on the reliability of the index value of the partial structure, the reliability can be determined.

[0047] Display area A2 displays the type and value of the index associated with each partial structure extracted by the first search, the reliability of that index, and the number of matches and total number of chemical substances used to derive the reliability. Furthermore, if multiple partial structures were extracted by the first search, display area A2 displays the reliability in descending order.

[0048] Next, refer to Figure 8 The function of the information processing device 10 according to the present embodiment will be described. Figure 8 The reliability display process is executed when an execution command is input by the user via the input device 24, for example.

[0049] exist Figure 8In step S10, the receiving unit 40 receives the structure data representing the structure of the chemical substance to be processed input by the user. In step S12, the first search unit 42 performs a first search for a partial structure included in the partial structure data 32 from the structure data received in step S10.

[0050] In step S14, the second search unit 44 performs a second search for chemical substances including the partial structure extracted in the first search in step S12 from the past data 34. In step S16, as described above, the deriving unit 46 derives the reliability of the index value of the partial structure extracted in the first search in step S12 based on the total number of chemical substances extracted in the second search in step S14 and the index values ​​corresponding to the chemical substances according to equation (1).

[0051] In step S18, as described above, the display control unit 48 controls the display 23 to display the partial structure extracted by the first search in step S12 and the reliability derived in step S16 for the partial structure. Figure 7 If the process of step S18 is completed, the reliability display process is completed.

[0052] By viewing the reliability display screen displayed on the display 23 , the user can understand, for example, a high-risk partial structure and a high-reliability partial structure in the chemical substance designed by the user.

[0053] As described above, according to this embodiment, appropriate screening can be supported.

[0054] In the above-described embodiment, various processors described below can be used as the hardware configuration of the processing unit that executes various processes, such as the receiving unit 40, the first search unit 42, the second search unit 44, the derivation unit 46, and the display control unit 48. These various processors include, in addition to general-purpose processors (CPUs) that execute software (programs) and function as various processing units, as described above, processors whose circuit configuration can be modified after manufacturing, such as FPGAs (Field Programmable Gate Arrays), programmable logic devices (PLDs), and ASICs (Application Specific Integrated Circuits), processors with circuit configurations specifically designed to execute various processes, such as dedicated electrical circuits.

[0055] A single processing unit may be composed of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs or a combination of a CPU and an FPGA). Furthermore, a single processor may constitute multiple processing units.

[0056] As examples of multiple processing units composed of a single processor, there are firstly a method, such as computers such as clients and servers, in which a single processor is composed of a combination of one or more CPUs and software, and this processor functions as multiple processing units. Secondly, there is a method, such as a system on a chip (SoC), in which a processor is used to implement the functions of the entire system including multiple processing units using a single IC (Integrated Circuit) chip. In this way, the various processing units are composed of one or more of the above-mentioned processors as a hardware structure.

[0057] Furthermore, as the hardware configuration of these various processors, more specifically, a circuit (circuitry) formed by combining circuit elements such as semiconductor elements can be used.

[0058] Furthermore, in the above embodiment, the information processing program 30 is described as being pre-stored (installed) in the storage unit 22, but the present invention is not limited thereto. The information processing program 30 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory device. Furthermore, the information processing program 30 may be downloaded from an external device via a network.

[0059] The entire disclosure of Japanese Patent Application No. 2020-216936, filed on December 25, 2020, is incorporated herein by reference. Furthermore, all documents, patent applications, and technical specifications described in this specification are incorporated herein by reference as if each individual document, patent application, or technical specification were specifically and individually disclosed as being incorporated by reference.

Claims

1. An information processing device comprising at least one processor, The processor performs the following processing: A first search is performed by searching for a partial structure included in the partial structure data in which a partial structure of the chemical substance is associated with an index value representing a performance or structure of the partial structure from the structure data representing the structure of the chemical substance to be processed, performing a second search for chemical substances including the partial structure extracted by the first search, by searching for chemical substances including the partial structure extracted by the first search, based on past data that associates the structure of the chemical substance with an index value indicating the performance or structure of the chemical substance obtained through experiments; deriving a reliability indicating the accuracy of the index value of the partial structure extracted by the first search based on the total number of chemical substances extracted by the second search and the index values ​​corresponding to the chemical substances, Control is performed to display the partial structure extracted by the first search and the reliability of the partial structure on a display device.

2. The information processing device according to claim 1, wherein The processor performs the following processing: Control is performed so that the reliability can be discriminated and displayed on a partial structure of the chemical substance to be processed.

3. The information processing device according to claim 1 or 2, wherein: The processor performs the following processing: When a plurality of partial structures are extracted by the first search, control is performed to display the reliability in descending order of the reliability.

4. The information processing device according to claim 1 or 2, wherein: The processor performs weighting corresponding to the total number of chemical substances extracted by the second search when deriving the reliability.

5. An information processing method, comprising causing a processor of an information processing device to perform the following processing: A first search is performed by searching for a partial structure included in the partial structure data in which a partial structure of the chemical substance is associated with an index value representing a performance or structure of the partial structure from the structure data representing the structure of the chemical substance to be processed, performing a second search for chemical substances including the partial structure extracted by the first search, by searching for chemical substances including the partial structure extracted by the first search, based on past data that associates the structure of the chemical substance with an index value indicating the performance or structure of the chemical substance obtained through experiments; deriving a reliability indicating the accuracy of the index value of the partial structure extracted by the first search based on the total number of chemical substances extracted by the second search and the index values ​​corresponding to the chemical substances, Control is performed to display the partial structure extracted by the first search and the reliability of the partial structure on a display device.

6. A computer-readable storage medium storing an information processing program, wherein the information processing program is configured to cause a processor of an information processing device to execute the following processing: A first search is performed by searching for a partial structure included in the partial structure data in which a partial structure of the chemical substance is associated with an index value representing a performance or structure of the partial structure from the structure data representing the structure of the chemical substance to be processed, performing a second search for chemical substances including the partial structure extracted by the first search, by searching for chemical substances including the partial structure extracted by the first search, based on past data that associates the structure of the chemical substance with an index value indicating the performance or structure of the chemical substance obtained through experiments; deriving a reliability indicating the accuracy of the index value of the partial structure extracted by the first search based on the total number of chemical substances extracted by the second search and the index values ​​corresponding to the chemical substances, Control is performed to display the partial structure extracted by the first search and the reliability of the partial structure on a display device.

Images