Information processing device, information processing method, and information processing program

Abstract

This information processing device is provided with at least one processor. The processor performs a process comprising: receiving the inputs of partial structure data indicating a partial structure of a chemical substance, and a condition regarding an index value indicating performance of the chemical substance; with respect to each of a plurality of known chemical substances, extracting, from a database in which structure data indicating the structure of the chemical substance is recorded, a known chemical substance having an input partial structure that is the partial structure indicated by the partial structure data and satisfying the condition; extracting a partial structure other than the input partial structure included in the structure of the extracted known chemical substance, as a co-occurring partial structure; and displaying the extracted co-occurring partial structure.

Description

[Technical Field]

[0001] The disclosed technology relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] The following technologies are known as technologies related to chemical substance design support. For example, Japanese Patent Application Laid-Open No. 2019-40422 describes a compound design device that includes a substructure selection means for selecting an arbitrary substructure of a compound, a substructure detection means for detecting substructures that co-occur with the substructure selected by the substructure selection means in compound data, and a co-occurrence quantification means for quantifying the degree of co-occurrence for multiple substructures detected by the substructure detection means. Summary of the Invention [Problem to be solved by the invention]

[0003] The partial structure that constitutes part of a chemical substance can have a significant impact on the performance of that chemical substance. Therefore, when designing the structure of a chemical substance that exhibits desired performance for the purpose of manufacturing, it is necessary to understand what partial structure the chemical substance should have. However, the performance of a chemical substance varies not only depending on the presence of a partial structure, but also on the positional relationship and combination of that partial structure with other structures contained in the chemical substance. Because the factors that affect the performance of a chemical substance are complex, it is not easy to design the structure of a chemical substance while fully understanding such factors.

[0004] The disclosed technology has been made in consideration of the above points, and aims to support the structural design of chemical substances that exhibit desired performance. [Means for solving the problem]

[0005] The information processing device according to the disclosed technology is an information processing device having at least one processor, which receives input of partial structure data indicating the partial structure of a chemical substance and conditions related to index values ​​indicating the performance of the chemical substance, extracts, for each of a plurality of known chemical substances, from a database in which structural data indicating the structure of the chemical substance is recorded, known chemical substances that include an input partial structure that is a partial structure indicated by the partial structure data and that satisfy the conditions, extracts partial structures other than the input partial structure that are included in the structure of the extracted known chemical substance as co-occurring partial structures, and performs processing to display the extracted co-occurring partial structures.

[0006] The processor may perform processing to display the extracted co-occurring substructures while indicating their connection relationships with the input substructures. The processor may calculate a co-occurrence probability for the extracted co-occurring substructure, which is the probability that the extracted co-occurring substructure appears with the input substructure. When multiple co-occurring substructures having different structures are extracted, the processor may perform processing to display the extracted multiple co-occurrence substructures in order of co-occurrence probability. The processor may perform processing to display the extracted co-occurring substructures together with the co-occurrence probability calculated for the co-occurring substructures.

[0007] The information processing method according to the disclosed technology is a method in which a processor included in an information processing device executes the following processes: accepts input of partial structure data indicating the partial structure of a chemical substance and conditions related to index values ​​indicating the performance of the chemical substance; extracts, for each of a plurality of known chemical substances, known chemical substances that include an input partial structure that is a partial structure indicated by the partial structure data and that satisfies the conditions, from a database in which structure data indicating the structure of the chemical substance is recorded; extracts partial structures other than the input partial structure that are included in the structure of the extracted known chemical substance as co-occurring substructures; and displays the extracted co-occurring substructures.

[0008] The information processing program according to the disclosed technology is a program for causing a processor provided in an information processing device to execute the following process: accept input of partial structure data indicating the partial structure of a chemical substance and conditions related to index values ​​indicating the performance of the chemical substance; extract, for each of a plurality of known chemical substances, from a database in which structure data indicating the structure of the chemical substance is recorded, known chemical substances that include an input partial structure that is a partial structure indicated by the partial structure data and that satisfy the conditions; extract, as co-occurring substructures, substructures other than the input substructure that are included in the structure of the extracted known chemical substance; and display the extracted co-occurring substructures. [Effects of the Invention]

[0009] The disclosed technology makes it possible to support the structural design of chemical substances that exhibit desired performance. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of a hardware configuration of an information processing device according to an embodiment of the disclosed technology. [Figure 2] FIG. 1 is a diagram showing an example of structural data of chemical substances expressed in a graph format. [Figure 3] FIG. 1 is a diagram showing an example of a chemical substance database according to an embodiment of the disclosed technique. [Figure 4] FIG. 10 is a diagram illustrating an example of a substructure database according to an embodiment of the disclosed technique. [Figure 5] FIG. 1 is a functional block diagram illustrating an example of a functional configuration of an information processing device according to an embodiment of the disclosed technology. [Figure 6] FIG. 10 is a diagram illustrating an example of an input substructure according to an embodiment of the disclosed technology. [Figure 7] 10A and 10B are diagrams illustrating an example of a display form of a co-occurring substructure according to an embodiment of the disclosed technique. [Figure 8] 10 is a flowchart illustrating an example of the flow of a display process according to an embodiment of the disclosed technology. [Figure 9] FIG. 1 shows the structure of a carboxylic acid. [Figure 10] FIG. 1 shows the structure of maleic acid. [Figure 11] FIG. 10 is a diagram showing the structure of a carboxy group, which is an example of an input partial structure. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an example of an embodiment of the disclosed technology will be described with reference to the drawings. In each drawing, the same or equivalent components and parts are given the same reference numerals, and redundant description will be omitted as appropriate.

[0012] 1 is a diagram showing an example of a hardware configuration of an information processing device 10 according to an embodiment of the disclosed technology. The information processing device 10 includes a CPU (Central Processing Unit) 101, a memory 102 as a temporary storage area, and a storage unit 103. The information processing device 10 also includes a display unit 104 such as a liquid crystal display, an input unit 105 including input devices such as a keyboard and a mouse, and a network I / F (Interface) 106 connected to a network. The CPU 101, memory 102, storage unit 103, display unit 104, input unit 105, and network I / F 106 are each connected to a bus 108.

[0013] The storage unit 103 is realized by a non-volatile storage medium such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory. The storage unit 103 stores an information processing program 110, a chemical substance database 120, and a substructure database 130. The CPU 101 reads the information processing program 110 from the storage unit 103, and then loads and executes it in the memory 102. An example of the information processing device 10 is a server computer. The CPU 101 is an example of a processor in the disclosed technology.

[0014] The information processing device 10 is used for structural design of chemical substances and has a function as a molecular design editor. Structural data representing the structure of chemical substances handled by the information processing device 10 according to this embodiment is expressed in a graph format. FIG. 2 is a diagram showing an example of structural data 200 of chemical substances expressed in a graph format. In the structural data 200 expressed in a graph format, atoms constituting the chemical substance are represented by nodes 201, and bonds between atoms are represented by edges 202. Note that the format of the structural data handled by the information processing device 10 is not limited to a graph format, and may be, for example, a character string format such as a DNA (DeoxyriboNucleic Acid) base sequence.

[0015] FIG. 3 is a diagram showing an example of the chemical substance database 120 stored in the storage unit 103. The chemical substance database 120 records, for each of a plurality of known chemical substances, structural data that represents the overall structure of the chemical substance. The structural data is expressed in a graph format. Each piece of structural data is associated with at least one index value that represents the performance of the chemical substance. Examples of the index value include boiling point, melting point, glass transition temperature, partition coefficient, density, viscosity, thermal expansion coefficient, and molecular weight. The index value may be, for example, an actual measured value obtained through past experiments or a nominal value.

[0016] FIG. 4 is a diagram showing an example of the substructure database 130 stored in the storage unit 103. The substructure database 130 records substructure data representing each of a plurality of known substructures. A substructure is a part of a structure constituting a chemical substance. Examples of substructures include the structures of functional groups such as a carboxyl group, an aldehyde group, and a hydroxyl group. The structural data of the substructures is expressed in a graphical format. Each piece of structural data of a substructure is associated with at least one index value representing the performance of the substructure. Examples of the index value include the degree of carcinogenicity, toxicity, and water solubility. The index value may be, for example, an actual measured value or a nominal value obtained through past experiments.

[0017] 5 is a functional block diagram showing an example of the functional configuration of the information processing device 10. The information processing device 10 is configured to include a reception unit 11, a first search unit 12, a second search unit 13, a calculation unit 14, and a display processing unit 15. When the CPU 101 executes the information processing program 110, the information processing device 10 functions as the reception unit 11, the first search unit 12, the second search unit 13, the calculation unit 14, and the display processing unit 15.

[0018] A user who designs the structure of a chemical substance using the information processing device 10 inputs a substructure that may be contained in the chemical substance to be designed into the information processing device 10. The substructure input to the information processing device 10 is hereinafter referred to as an input substructure. The input substructure can be input to the information processing device 10 by operating the input unit 105. The receiving unit 11 receives substructure data indicating the input substructure input by the user. FIG. 6 is a diagram showing an example of an input substructure 300.

[0019] Furthermore, the user formulates conditions related to specific index values ​​based on the performance that the chemical substance to be designed should have, and inputs the formulated conditions into the information processing device 10. For example, when designing the structure of a chemical substance having a boiling point of 150°C or less, information indicating "boiling point of 150°C or less" is input as a condition related to the index value. The condition related to the index value can be input into the information processing device 10 by operating the input unit 105. The receiving unit 11 receives the condition related to the specific index value input by the user. There may be two or more conditions related to the specific index value. The receiving unit 11 supplies the received input substructure and the condition related to the specific index value to the first search unit 12.

[0020] The first search unit 12 searches for and extracts chemical substances that include the input substructure and satisfy the conditions related to the index value from the chemical substance database 120. That is, the first search unit 12 extracts chemical substances that include the input substructure and can exhibit required performance from multiple known chemical substances included in the chemical substance database 120. If multiple chemical substances that include the input substructure and satisfy the conditions related to the index value are present in the chemical substance database 120, the first search unit 12 extracts all of the corresponding chemical substances. The first search unit 12 supplies structural data indicating the structures of the extracted chemical substances to the second search unit 13 and the calculation unit 14. The structures of the chemical substances extracted by the first search unit 12 are hereinafter referred to as extracted chemical structures.

[0021] The second search unit 13 extracts substructures other than the input substructure contained in the extracted chemical structure as co-occurring substructures. That is, a co-occurring substructure is a substructure that exists together with the input substructure in a certain chemical substance. The second search unit 13 extracts co-occurring substructures by referring to the substructure database 130. That is, if the second search unit 13 finds a substructure other than the input substructure in the extracted chemical structure that matches a substructure recorded in the substructure database 130, it extracts the substructure as a co-occurring substructure. If the second search unit 13 finds multiple substructures that meet the above criteria in the extracted chemical structure, it extracts all of the corresponding substructures as co-occurring substructures. The second search unit 13 supplies substructure data indicating the co-occurring substructures to the display processing unit 15 and the calculation unit 14.

[0022] The calculation unit 14 calculates the co-occurrence probability, which is the probability that a co-occurring substructure appears together with an input substructure. When multiple co-occurring substructures having different structures are extracted, the calculation unit 14 calculates the co-occurrence probability for each of the multiple co-occurring substructures. The co-occurrence probability may be expressed, for example, by the following formula (1). In formula (1), P is the co-occurrence probability, A is the number of extractions of a certain type of co-occurring substructure extracted by the second search unit 13, and B is the number of extractions of chemical substances extracted by the first search unit 12. Note that B may also be the total number of chemical substances recorded in the chemical substance database 120. A co-occurrence substructure with a relatively high co-occurrence probability is considered to be more likely to satisfy the condition related to the index value when it exists together with the input substructure. P = A / B × 100 [%] (1)

[0023] The display processing unit 15 performs processing to display the co-occurring substructure extracted by the second search unit 13 on the display unit 104. Figure 7 is a diagram showing an example of the display form of the co-occurring substructure 310 displayed on the display screen 104A of the display unit 104.

[0024] The display processing unit 15 performs processing to display the extracted co-occurring substructure 310 while indicating its connection with the input substructure 300. The co-occurring substructure 310 and the input substructure 300 are displayed in a graph format. For example, if the co-occurring substructure 310 and the input substructure 300 are directly connected, the connection point is represented by an edge. The display processing unit 15 may perform processing to display the co-occurring substructure 310 and the input substructure 300 so that they can be distinguished from each other. For example, processing may be performed to display the nodes constituting the co-occurring substructure 310 and the nodes constituting the input substructure 300 in different colors. The display processing unit 15 may perform processing to display only the co-occurring substructure 310 out of the co-occurring substructure 310 and the input substructure 300. The display processing unit 15 may also perform processing to display the entire structure including both the input substructure 300 and the co-occurring substructure 310, i.e., the entire structure of the chemical substance extracted by the first search unit 12.

[0025] When multiple co-occurring substructures having different structures are extracted, the display processing unit 15 performs processing to arrange and display the extracted multiple co-occurring substructures in order of the co-occurrence probabilities calculated by the calculation unit 14. For example, as shown in Fig. 7, the display processing unit 15 may perform processing to arrange and display the extracted multiple co-occurring substructures 310 in order from highest to lowest co-occurrence probabilities from left to right on the display screen 104A. Alternatively, the display processing unit 15 may arrange and display the extracted co-occurring substructures in order from highest to lowest co-occurrence probabilities from top to bottom on the display screen 104A. The display processing unit 15 may perform processing to display the co-occurring substructures together with their co-occurrence probabilities.

[0026] FIG. 8 is a flowchart showing an example of the flow of display processing carried out by the CPU 101 executing the information processing program 110.

[0027] In step S1, the receiving unit 11 receives substructure data indicating an input substructure input by the user operating the input unit 105. In step S2, the receiving unit 11 receives conditions related to specific index values ​​input by the user operating the input unit 105. The conditions related to the specific index values ​​are formulated based on the performance that the chemical substance to be designed should have.

[0028] In step S3, the first search unit 12 searches for and extracts known chemical substances from the chemical substance database 120 that include the input substructure received in step S1 and that satisfy the conditions related to the index value received in step S2.

[0029] In step S4, the second search unit 13 refers to the substructure database 130 to extract substructures other than the input substructure that are included in the structure of the known chemical substance extracted in step S3 (i.e., the extracted chemical structure) as co-occurring substructures.

[0030] In step S5, the calculation unit 14 calculates the co-occurrence probability, which is the probability that the co-occurring substructure extracted in step S4 appears together with the input substructure. The calculation unit 14 calculates the co-occurrence probability based on, for example, the above formula (1).

[0031] In step S6, the display processing unit 15 performs processing to display the co-occurring substructures extracted in step S4 on the display unit 104. Specifically, the display processing unit 15 performs processing to display the co-occurring substructures while indicating their connection relationships with the input substructure. When multiple co-occurring substructures with different structures are extracted, the display processing unit 15 performs processing to display the extracted multiple co-occurring substructures in order of co-occurrence probability.

[0032] The partial structure that constitutes a part of a chemical substance can have a significant effect on the performance of that chemical substance. Therefore, when designing a chemical substance that will exhibit the desired performance, it is necessary to understand what partial structure the chemical substance should have.

[0033] Here, the carboxylic acids shown in Figure 9 generally form dimers through hydrogen bonds. Chemical substances that form hydrogen bonds, such as carboxylic acids, have higher boiling points than chemical substances of similar molecular weight that do not form hydrogen bonds. On the other hand, maleic acid shown in Figure 10 is a carboxylic acid, but because two carboxy groups are adjacent to each other, it does not form hydrogen bonds with other molecules. For this reason, maleic acid has a relatively low boiling point, even though it is a carboxylic acid.

[0034] In this way, the performance of a chemical substance (e.g., boiling point) varies not only depending on the presence of a partial structure, but also on the positional relationship and combination of that partial structure with other structures contained in the chemical substance. Because the factors that affect the performance of a chemical substance are complex, it is not easy to design the structure of a chemical substance while fully understanding such factors.

[0035] According to the information processing device 10 of the embodiment of the disclosed technology, known chemical substances that include the input substructure and satisfy the conditions for a specific index value (i.e., performance requirements) are extracted, and substructures other than the input substructure contained in the structure of the extracted chemical substance are extracted as co-occurring substructures and displayed.

[0036] For example, assume that the carboxy group shown in Fig. 11 is input to the information processing device 10 as the input substructure, and "boiling point 150°C or less" is input as the condition for a specific index value. In this case, maleic acid shown in Fig. 10 is extracted as a known chemical substance that contains the input substructure and satisfies the condition. Then, of the two carboxy groups contained in maleic acid, the carboxy group that is different from the input substructure is extracted and displayed as a co-occurring substructure.

[0037] In this way, the information processing device 10 presents to the user as co-occurring substructures substructures that may satisfy the index value conditions when present together with the input substructure. The user can adopt the presented co-occurring substructures as candidates for substructures to be included in the chemical substance to be designed. In this way, the information processing device 10 according to the embodiment of the disclosed technology can support the structural design of chemical substances that exhibit desired performance.

[0038] Furthermore, the information processing device 10 displays co-occurring substructures extracted from the structures of known chemical substances extracted from the chemical substance database 120, thereby increasing the likelihood that the displayed co-occurring substructures will be useful for achieving desired performance. Furthermore, the information processing device 10 displays the extracted co-occurring substructures in a state where their connection relationships with the input substructure are indicated, thereby enabling more effective design support. Furthermore, when multiple co-occurring substructures with different structures are extracted, the information processing device 10 displays the extracted multiple co-occurring substructures in order of co-occurrence probability, thereby making it possible to clearly indicate co-occurring substructures that are relatively likely to satisfy the conditions related to the index value.

[0039] In this embodiment, a case has been exemplified in which a substructure included in an extracted chemical structure that matches a substructure recorded in the substructure database 130 is extracted as a co-occurring substructure, but the present invention is not limited to this. A substructure selected randomly or according to a predetermined rule from the extracted chemical structure may also be extracted as a co-occurring substructure.

[0040] In the above embodiment, the following various processors can be used as the hardware structure of processing units that perform various processes, such as the reception unit 11, the first search unit 12, the second search unit 13, the calculation unit 14, and the display processing unit 15. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to perform specific processes, such as a programmable logic device (PLD), a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0041] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0042] Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server. Second, a form in which a processor is used to realize the functions of the entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0043] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0044] In the above embodiment, the information processing program 110 is pre-stored (installed) in the storage unit 103, but the present invention is not limited to this. The information processing program 110 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. The information processing program 110 may also be downloaded from an external device via a network.

[0045] The disclosure of Japanese Patent Application No. 2021-001610, filed on January 7, 2021, is incorporated herein by reference in its entirety. In addition, all documents, patent applications, and technical standards described 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 including at least one processor, The processor: Accepting input of partial structure data indicating a partial structure of a chemical substance and conditions related to index values ​​indicating the performance of the chemical substance; extracting, for each of a plurality of known chemical substances, known chemical substances that include an input substructure that is a substructure represented by the substructure data and that satisfy the conditions from a database that records structural data representing the structure of the chemical substance; extracting substructures other than the input substructure contained in the extracted structure of the known chemical substance as co-occurring substructures; Display the extracted co-occurring substructures An information processing device that performs processing.

2. The processor performs processing to display the extracted co-occurring substructures while indicating their connection with the input substructure. The information processing device according to claim 1 .

3. The processor: Calculating the co-occurrence probability of the extracted co-occurring substructure, which is the probability that the co-occurring substructure appears together with the input substructure. When a plurality of co-occurring substructures having different structures are extracted, the extracted co-occurring substructures are arranged and displayed in order of the co-occurrence probability.

3. The information processing device according to claim 1.

4. The processor performs processing to display the extracted co-occurring substructures together with the co-occurrence probabilities calculated for the co-occurring substructures. The information processing device according to claim 3 .

5. Accepting input of partial structure data indicating a partial structure of a chemical substance and conditions related to index values ​​indicating the performance of the chemical substance; extracting, for each of a plurality of known chemical substances, known chemical substances that include an input substructure that is a substructure represented by the substructure data and that satisfy the conditions from a database that records structural data representing the structure of the chemical substance; extracting substructures other than the input substructure contained in the extracted structure of the known chemical substance as co-occurring substructures; Display the extracted co-occurring substructures An information processing method in which processing is executed by a processor included in an information processing device.

6. Accepting input of partial structure data indicating a partial structure of a chemical substance and conditions related to index values ​​indicating the performance of the chemical substance; extracting, for each of a plurality of known chemical substances, known chemical substances that include an input substructure that is a substructure represented by the substructure data and that satisfy the conditions from a database that records structural data representing the structure of the chemical substance; extracting substructures other than the input substructure contained in the extracted structure of the known chemical substance as co-occurring substructures; Display the extracted co-occurring substructures An information processing program for causing a processor included in an information processing device to execute processing.

Images