Chemical reaction data mining method, system, storage medium and terminal

By identifying and assembling R groups in template reactions, chemical reaction data mining is automatically realized, solving the problems of low efficiency and poor reliability of artificial recognition of reactants, and improving the automation, efficiency and accuracy of data mining.

CN118538308BActive Publication Date: 2024-11-22HYDROCARBON DIGITAL (CHENGDU) INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410934283.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-12
Publication Date
2024-11-22
Estimated Expiration
2044-07-12

AI Technical Summary

Technical Problem

In the prior art, the reactants in the template reaction have problems such as large workload, low efficiency and difficult to guarantee reliability.

Method used

By identifying whether the reactants and product molecules in the template reaction contain R groups, determining the molecular structure and connection positions of the R groups, and automatically assembling the chemical reactions to achieve mining of chemical reaction data.

Benefits of technology

It improves the automation, efficiency and accuracy of chemical reaction data mining, reduces manual operation time and labor costs, avoids interference from human factors, and ensures the reliability of calculation results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118538308B_ABST
    Figure CN118538308B_ABST
Patent Text Reader

Abstract

The present invention discloses a chemical reaction data mining method, system, storage medium and terminal, and relates to the field of data mining. The method comprises: step S100: identifying whether the reactant molecule and / or the product molecule contain an R group, and when the R group is not contained, the data mining process is terminated; when at least one reactant molecule and at least one product molecule contain an R group, steps S200 to S600 are executed; step S200: identifying the position information of the R group in the reactant molecule and / or the product molecule; step S300: determining the molecular structure of the R group; step S400: when the position of the R group is variable, determining the connection position of the R group in the reactant molecule; when the position of the R group is fixed, step S500 is executed; step S500: adding the R group to the reactant molecule of the template reaction to obtain the reactant molecule corresponding to the candidate product molecule; step S600: repeating steps S300 to S500 to complete the mining of chemical reaction data. The method has the advantages of high automation, high efficiency and high accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data mining, and in particular to a chemical reaction data mining method, system, storage medium and terminal. Background Art

[0002] With the advancement of science and technology, the amount of chemical reaction data is increasing day by day, and these chemical reaction data are of great significance to chemical research and development. At present, the main chemical reaction databases are SciFinder database and Reaxys database. The data in SciFinder database and Reaxys database mainly come from literature and patents.

[0003] In chemical literature, chemical reaction data are mostly presented in the form of a template reaction and a series of product molecules. The products and reactants in the template reaction are generally based on the Markush formula, containing an R group with variable type and / or position, to represent multiple chemical reactions. This representation method is not conducive to enriching and improving the chemical reaction database.

[0004] To this end, the traditional method is to extract all the chemical reaction data contained in the template reaction through manual identification, that is, to manually determine the reactants in the template reaction based on each candidate product molecule, so as to obtain the chemical reaction corresponding to the candidate product molecule. For a large number of candidate products, the manual identification method has a large workload, low efficiency, and difficult to ensure reliability.

[0005] Therefore, there is an urgent need to provide a general chemical reaction data mining method. Summary of the invention

[0006] The present invention discloses a chemical reaction data mining method, system, storage medium and terminal to solve the technical problems in the related art of manually determining reactants in a template reaction based on candidate product molecules, which has the disadvantages of large workload, low efficiency and difficulty in ensuring reliability.

[0007] In order to solve the above problems, the present invention adopts the following technical solutions:

[0008] A first aspect of the present invention provides a chemical reaction data mining method.

[0009] The chemical reaction data mining method of the present invention comprises the following steps:

[0010] Step S100: Identify whether the reactant molecule and / or product molecule in the template reaction contains an R group,

[0011] When all reactant molecules and all product molecules in the template reaction do not contain R groups, the data mining process ends;

[0012] When at least one reactant molecule and / or at least one product molecule in the template reaction contains an R group, executing steps S200 to S600 to perform chemical reaction data mining;

[0013] Step S200: identifying the position information of the R group in the reactant molecule and / or the product molecule, where the position information of the R group includes variable position and fixed position;

[0014] Step S300: determining the molecular structure of the R group based on the product molecule in the reaction between the candidate product molecule and the template;

[0015] Step S400: when the position of the R group is variable, determining the connection position of the R group in the reactant molecule based on the reactant molecule in the reaction between the candidate product molecule and the template;

[0016] When the position of the R group is fixed, step S500 is performed;

[0017] Step S500: adding R groups to reactant molecules of the template reaction to obtain reactant molecules corresponding to the candidate product molecules, and assembling chemical reactions based on the candidate product molecules and the generated reactant molecules;

[0018] Step S600: Repeat steps S300 to S500 to traverse all candidate product molecules to complete the mining of chemical reaction data.

[0019] Further, identifying whether the reactant molecule and / or product molecule in the template reaction contains an R group comprises the following steps:

[0020] Iterate over the atoms in each reactant molecule and / or each product molecule in the template reaction,

[0021] If the molecule contains R atoms, confirm that the corresponding reactant molecules and / or product molecules contain R groups,

[0022] If the molecule does not contain an R atom, confirm that the corresponding reactant molecules and / or product molecules do not contain an R group.

[0023] Further, identifying the position information of the R group in the reactant molecule and / or the product molecule comprises the following steps:

[0024] Determine the position information of the R group based on the connection position of the R group,

[0025] When the chemical bonds of the R group cross the chemical bonds in the molecule, the position of the R group can be changed;

[0026] When the R group is attached to an atom in a molecule, the position of the R group is fixed.

[0027] Further, based on the product molecule in the reaction between the candidate product molecule and the template, determining the molecular structure of the R group comprises the following steps:

[0028] The substructure matching information of the candidate product molecule and the template product molecule is calculated, and the molecular structure of the R group is determined based on the difference between the candidate product molecule and the template product molecule.

[0029] Further, determining the molecular structure of the R group comprises the following steps:

[0030] Step S310: calculating the substructure matching information between the candidate product molecule and the template product molecule, taking the template product molecule as the substructure, determining the atom number in the candidate product molecule that matches the substructure, and the atom number in the candidate product molecule that does not match the substructure;

[0031] Step S320: extract all atoms that do not match the substructure from the candidate molecules, and determine the molecules composed of the atom numbers that do not match the substructure in the candidate product molecules as R groups.

[0032] Further, based on the reactant molecule in the reaction between the candidate product molecule and the template, determining the connection position of the R group in the reactant molecule comprises the following steps:

[0033] The maximum common substructure information of the candidate product molecule and the reactant molecule in the template reaction is calculated, and the connection position of the R group in the reactant molecule is determined based on the mapping relationship between each atom in the maximum common substructure in the candidate product molecule and the reactant molecule.

[0034] Further, determining the connection position of the R group in the reactant molecule comprises the following steps:

[0035] Step S410: Calculate the maximum common substructure information of the candidate product molecule and the reactant molecule in the reaction between the template, and obtain the atom number of the maximum common substructure matching in the candidate product molecule and the reactant molecule;

[0036] Step S420: Generate an atom mapping by matching the matching atom numbers in the candidate product molecules with the matching atom numbers in the reactant molecules one by one;

[0037] Step S430: Determine the connection position of the R group in the reactant according to the connection position of the R group in the candidate molecule and the atomic mapping relationship.

[0038] A second aspect of the present invention provides a chemical reaction data mining system.

[0039] The chemical reaction data mining system of the present invention comprises:

[0040] A first identification module is used to identify whether the reactant molecule and / or the product molecule in the template reaction contains an R group, and when all the reactant molecules and all the product molecules in the template reaction do not contain an R group, the data mining process is terminated; when at least one reactant molecule and / or at least one product molecule in the template reaction contains an R group, steps S200 to S600 of the chemical reaction data mining method described in any technical solution of the present invention are executed to perform chemical reaction data mining;

[0041] A second recognition module is used to recognize the position information of the R group in the reactant molecule and / or the product molecule, where the position information of the R group includes variable position and fixed position;

[0042] A first determination module is used to determine the molecular structure of the R group based on the product molecule in the reaction between the candidate product molecule and the template;

[0043] A second determination module is used to determine the connection position of the R group in the reactant molecule based on the reactant molecule in the reaction between the candidate product molecule and the template when the position of the R group is variable;

[0044] When the position of the R group is fixed, the step S500 of executing the chemical reaction data mining method according to any technical solution of the present invention is performed;

[0045] The assembly module is used to add R groups to the reactant molecules of the template reaction, obtain the reactant molecules corresponding to the candidate product molecules, and assemble the chemical reaction based on the candidate product molecules and the generated reactant molecules.

[0046] A third aspect of the present invention provides a storage medium.

[0047] The storage medium of the present invention stores computer instructions, and when the computer instructions are executed, the steps of the chemical reaction data mining method described in any technical solution of the present invention are executed.

[0048] A fourth aspect of the present invention provides a terminal.

[0049] The terminal of the present invention comprises a memory and a processor, wherein the memory stores computer instructions that can be executed on the processor, and the processor executes the steps of the chemical reaction data mining method described in any technical solution of the present invention when executing the computer instructions.

[0050] The technical solution adopted by the present invention can achieve the following beneficial effects:

[0051] The chemical reaction data mining method of the present invention can determine the molecular structure of the R group and the connection position of the R group in the reactant molecule based on the candidate product molecule, the product molecule in the template reaction and the reactant molecule in the template reaction, thereby obtaining the reactant molecule corresponding to the candidate product molecule; then, by traversing all the candidate product molecules, all the chemical reaction data of the candidate product molecules can be mined. In this way, for a large number of candidate products, compared with the traditional way of manually mining the chemical reaction data of the template reaction, the chemical reaction data mining method of the present invention has a high degree of automation and can reduce the time and labor cost of manual operation; the chemical reaction data mining method of the present invention performs calculations according to the above rules, avoiding the interference of human factors, thereby ensuring the accuracy and reliability of the calculation results; the chemical reaction data mining method of the present invention can process a large amount of data in a short time, thereby improving the mining efficiency.

[0052] It can be seen that the chemical reaction data mining method of the present invention has the advantages of high automation, high efficiency and high accuracy, and solves the technical problems in the related art of manually determining the reactants in the template reaction based on the candidate product molecules, which has the problems of large workload, low efficiency and difficulty in ensuring reliability.

[0053] On the other hand, the chemical reaction data mining method of the present invention, before determining the molecular structure of the R group and the connection position of the R group in the reactant molecule, also includes a step of identifying whether the reactant molecule and / or the product molecule in the template reaction contains the R group. When all reactant molecules and all product molecules in the template reaction do not contain the R group, the data mining process is directly terminated without performing steps S200 to S600. This method can not only reduce the subsequent calculation amount and further improve the efficiency of chemical reaction data mining; it can also simplify the data mining process and reduce the error rate of the mining process.

[0054] On the third aspect, the chemical reaction data mining method of the present invention further includes the step of identifying the position information of the R group before determining the connection position of the R group in the reactant molecule. When the position of the R group is fixed, there is no need to perform the step of "determining the connection position of the R group in the reactant molecule". This method can not only reduce the subsequent calculation amount and further improve the efficiency of chemical reaction data mining; it can also simplify the data mining process and improve the calculation accuracy, avoiding the problem of inaccurate determination of the connection position of the R group due to calculation errors when judging the connection position of the R group. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 is a flow chart of a chemical reaction data mining method according to an embodiment of the present application;

[0057] Figure 2 It is a module diagram of the chemical reaction data mining system of the embodiment of the present application;

[0058] Figure 3 It is a module diagram of the terminal of the embodiment of the present application.

[0059] In the figure: 11, first identification module; 12, second identification module; 13, first determination module; 14, second determination module; 15, assembly module; 21, memory; 22, processor. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0061] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0062] The following is combined with Figures 1 to 3 , the chemical reaction data mining method, system, storage medium and terminal provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0063] The first aspect of this embodiment provides a detailed description of the chemical reaction data mining method of the present application.

[0064] Figure 1 FIG. 4 shows a flow chart of the chemical reaction data mining method of this embodiment. Figure 1 As shown, the chemical reaction data mining method of this embodiment includes the following steps:

[0065] Step S100: Identify whether the reactant molecule and / or product molecule in the template reaction contains an R group.

[0066] When all reactant molecules and all product molecules in the template reaction do not contain R groups, the data mining process ends.

[0067] When at least one reactant molecule and / or at least one product molecule in the template reaction contains an R group, steps S200 to S600 are executed to perform chemical reaction data mining. In the case where there are multiple reactant molecules and multiple product molecules in the template reaction, as long as at least one reactant molecule or at least one product molecule contains an R group, steps S200 to S600 are executed to perform chemical reaction data mining.

[0068] The molecule that does not contain the R group in the template reaction is an immutable molecule; the molecule that contains the R group in the template reaction is a variable molecule. The variable molecule includes a variable type and / or a variable position of the R group. Exemplarily, the type of the R group can be -H, -OH, -CH3, -F, -Cl, -Br, -I, etc. Exemplarily, the position of the R group can be variable or fixed.

[0069] The chemical reaction data mining method of this embodiment, before determining the molecular structure of the R group and the connection position of the R group in the reactant molecule, also includes the step of identifying whether the reactant molecule and / or product molecule in the template reaction contains the R group. When all reactant molecules and all product molecules in the template reaction do not contain the R group, the data mining process is directly terminated without performing steps S200 to S600. This method can not only reduce the subsequent calculation amount and further improve the efficiency of chemical reaction data mining; it can also simplify the data mining process and reduce the error rate of the mining process.

[0070] For template reactions, usually the reactant molecules have R groups, and the corresponding product molecules also have R groups. When identifying whether there are R groups in the template reaction, it is only necessary to identify whether there are R groups in the reactant molecules or the product molecules, without having to identify whether there are R groups in the product molecules after identifying whether there are R groups in the reactant molecules. This method is conducive to improving the recognition efficiency of R groups.

[0071] Preferably, before step S100, an image recognition process may be included, that is, the template reaction, reactant molecules, product molecules and candidate product molecules in the chemical literature are recognized by image recognition. The image recognition method may adopt an existing method.

[0072] By identifying template reactions, reactant molecules, product molecules and candidate product molecules through images, it is convenient to conduct chemical reaction data mining based on template reactions, reactant molecules, product molecules and candidate product molecules. In addition, compared with the input method, the template reactions, reactant molecules, product molecules and candidate product molecules through images have the advantages of high efficiency and accuracy.

[0073] Step S200: Identify the position information of the R group in the reactant molecule and / or the product molecule. The position information of the R group includes variable position and fixed position. The position information of the R group refers to which atom of the reactant molecule in the template reaction is connected to the R group. The variable position of the R group means that the R group can be connected to different atoms of the reactant molecule in the template reaction; the fixed position of the R group means that the R group is only connected to a fixed atom of the reactant molecule in the template reaction.

[0074] Preferably, the position information of the R group in the reactant molecule or the product molecule is identified. For the template reaction, the reactant molecule usually has an R group, and the corresponding product molecule also has an R group. When identifying the position information of the R group, it is only necessary to identify the position information of the R group in the reactant molecule or the product molecule, without identifying the position information of the R group in the product molecule after identifying the position information of the R group in the reactant molecule. This method is conducive to improving the efficiency of identifying the position information of the R group.

[0075] The chemical reaction data mining method of this embodiment identifies the position information of the R group in the reactant molecule and / or the product molecule, which can provide a basis for the subsequent determination of the connection position of the R group in the reactant molecule.

[0076] Step S300: Based on the product molecule in the reaction between the candidate product molecule and the template, determine the molecular structure of the R group. The molecular structure of the R group includes the atoms that the R group is specifically composed of and the connecting atoms between the R group and the reactant molecule in the reaction between the template and the template.

[0077] Step S400: when the position of the R group is variable, determining the connection position of the R group in the reactant molecule based on the reactant molecule in the reaction between the candidate product molecule and the template.

[0078] When the position of the R group is fixed, step S500 is performed.

[0079] The chemical reaction data mining method of the present embodiment further includes a step of identifying the position information of the R group before determining the connection position of the R group in the reactant molecule. When the position of the R group is fixed, there is no need to perform the step of "determining the connection position of the R group in the reactant molecule". This method can not only reduce the subsequent calculation amount and further improve the efficiency of chemical reaction data mining; it can also simplify the data mining process and improve the calculation accuracy, avoiding the problem of inaccurate determination of the connection position of the R group due to calculation errors when judging the connection position of the R group.

[0080] Step S500: adding R groups to reactant molecules of the template reaction to obtain reactant molecules corresponding to the candidate product molecules, and assembling chemical reactions based on the candidate product molecules and the generated reactant molecules.

[0081] By obtaining the reactant molecules corresponding to the candidate product molecules and then combining the immutable molecules in the template reaction into a specific chemical reaction, the mining of the chemical reaction data corresponding to the candidate product can be completed.

[0082] Step S600: Repeat steps S300 to S500 to traverse all candidate product molecules to complete the mining of chemical reaction data. When at least one reactant molecule and / or at least one product molecule in the template reaction contains an R group, for a large number of candidate product molecules, it is only necessary to repeat steps S300 to S500 to complete the mining of chemical reaction data for each candidate product molecule.

[0083] The chemical reaction data mining method of the present embodiment can determine the molecular structure of the R group and the connection position of the R group in the reactant molecule based on the candidate product molecules, the product molecules in the template reaction and the reactant molecules in the template reaction, thereby obtaining the reactant molecule corresponding to the candidate product molecule; and then by traversing all the candidate product molecules, all the chemical reaction data of the candidate product molecules can be mined. In this way, for a large number of candidate products, compared with the traditional method of manually mining the chemical reaction data of the template reaction, the chemical reaction data mining method of the present embodiment has a high degree of automation and can reduce the time and labor cost of manual operation; the chemical reaction data mining method of the present embodiment performs calculations according to the above rules, avoiding the interference of human factors, thereby ensuring the accuracy and reliability of the calculation results; the chemical reaction data mining method of the present embodiment can process a large amount of data in a short time, thereby improving the mining efficiency.

[0084] It can be seen that the chemical reaction data mining method of this embodiment has the advantages of high automation, high efficiency and high accuracy, and solves the technical problems in the related technology of manually determining the reactants in the template reaction based on the candidate product molecules, which has the problems of large workload, low efficiency and difficulty in ensuring reliability.

[0085] According to an optional embodiment, identifying whether a reactant molecule and / or a product molecule in a template reaction contains an R group comprises the following steps:

[0086] Traverse the atoms in each reactant molecule and / or each product molecule in the template reaction, and if the molecule contains R atoms, confirm that the corresponding reactant molecule and / or product molecule contains R groups. If the molecule does not contain R atoms, confirm that the corresponding reactant molecule and / or product molecule does not contain R groups.

[0087] By identifying whether each reactant molecule and / or each product molecule has an R atom, it is possible to intuitively determine whether the reactant molecule and / or the product molecule has an R group. This method is conducive to quickly identifying whether each reactant molecule and / or each product molecule has an R group, thereby improving the recognition efficiency and accuracy of the R group.

[0088] According to an optional embodiment, identifying the position information of the R group in the reactant molecule and / or the product molecule comprises the following steps:

[0089] The position information of the R group is determined based on the connection position of the R group. Exemplarily, when the chemical bond of the R group crosses the chemical bond in the molecule, the position of the R group is variable; when the R group is connected to an atom in the molecule, the position of the R group is fixed.

[0090] By identifying whether the chemical bonds of the R group cross with the chemical bonds in the molecule, the position of the R group can be intuitively determined. This method is conducive to identifying the position information of the R group through image recognition, thereby improving the recognition efficiency and accuracy of the R group position information.

[0091] According to an optional embodiment, determining the molecular structure of the R group based on the product molecule in the reaction between the candidate product molecule and the template comprises the following steps:

[0092] The substructure matching information of the candidate product molecule and the template product molecule is calculated, and the molecular structure of the R group is determined based on the difference between the candidate product molecule and the template product molecule.

[0093] The substructure of the template product molecule refers to the structure of the template product molecule except the R group.

[0094] Preferably, determining the molecular structure of the R group comprises the following steps:

[0095] Step S310: Calculate the substructure matching information of the candidate product molecule and the template product molecule, take the template product molecule as the substructure, determine the atom number in the candidate product molecule that matches the substructure, and the atom number in the candidate product molecule that does not match the substructure. Exemplarily, Rdkit can be used to calculate the substructure matching information of the candidate product molecule and the template product molecule. Exemplarily, the candidate product molecule can be stored according to mol code, sdf file or smiles code. Exemplarily, the template reaction can be stored according to the rxnfile file. After the candidate product molecule and the template product molecule are read into the memory, the corresponding atom number is determined.

[0096] Step S320: extract all atoms that do not match the substructure from the candidate molecule, and determine the molecule composed of the atom numbers that do not match the substructure in the candidate product molecule as the R group.

[0097] The chemical reaction data mining method of the preferred technical solution of this embodiment determines the molecular structure of the R group based on the degree of matching between the candidate product molecule and the template product molecule. This method can be applied to different template reactions and candidate product molecules, and has strong variability and adaptability. In addition, this method can also improve the reliability of determining the molecular structure of the R group, and the consistency and repeatability of the determination results are good.

[0098] According to an optional embodiment, based on the reactant molecule in the reaction between the candidate product molecule and the template, determining the connection position of the R group in the reactant molecule comprises the following steps:

[0099] The maximum common substructure information of the candidate product molecule and the reactant molecule in the template reaction is calculated, and the connection position of the R group in the reactant molecule is determined based on the mapping relationship between each atom in the maximum common substructure in the candidate product molecule and the reactant molecule.

[0100] Preferably, determining the attachment position of the R group in the reactant molecule comprises the following steps:

[0101] Step S410: Calculate the maximum common substructure information of the candidate product molecule and the reactant molecule in the reaction between the template and obtain the atom number of the maximum common substructure matching in the candidate product molecule and the reactant molecule.

[0102] The maximum common substructure information refers to the largest structural unit shared by the candidate product molecule and the reactant molecule in the template reaction.

[0103] Step S420: Generate an atom mapping by matching the matching atom numbers in the candidate product molecules with the matching atom numbers in the reactant molecules one by one.

[0104] Step S430: Determine the connection position of the R group in the reactant according to the connection position of the R group in the candidate molecule and the atomic mapping relationship.

[0105] The chemical reaction data mining method of the preferred technical solution of this embodiment determines the connection position of the R group in the reactant molecule based on the mapping relationship between each atom in the largest common substructure of the candidate product molecule and the reactant molecule in the template reaction. This method is also applicable to different template reactions and candidate product molecules, and has strong variability and adaptability. In addition, this method can also improve the reliability of determining the position of the R group, and the consistency and repeatability of the determination results are good.

[0106] The chemical reaction data mining method of this embodiment is described below by taking a specific template reaction as an example.

[0107] The obtained template reaction is shown below:

[0108] .

[0109] The candidate product molecules obtained are shown in the following molecules 1 to 14:

[0110] .

[0111] Step S100: Identify the reactant molecule and the product molecule in the template reaction. The second reactant molecule and the product molecule contain an R group, indicating that the first reactant molecule is an immutable molecule, and the second reactant molecule and the product molecule are mutable molecules.

[0112] Step S200: Identify the position information of the R group in the reactant molecule and the product molecule. The chemical bond of the R group crosses the carbon-carbon double bond in the molecule, and the position of the R group is variable.

[0113] Step S300: Determine the molecular structure of the R group based on the product molecule in the reaction between the candidate product molecule and the template. Specifically, determining the molecular structure of the R group includes the following steps:

[0114] The template product molecule is the following molecule 1, and the candidate product molecule is the following molecule 2. Rdkit is used to calculate the substructure matching information of the candidate product molecule and the template product molecule, and the template product molecule is used as the substructure to find the matching atom number and the unmatched atom number in the candidate product molecule.

[0115] As shown in the following molecule 3, the atoms in the candidate product molecule that match the template product molecule are numbered [0, 1, 14, 15, 2, 3, 10, 4, 5, 7, 9, 13, 8, 11, 12, 16, 17], and the number of the unmatched atoms is [6]. Therefore, it can be determined that the R group is a molecule composed of atoms [6], and the molecular structure of the R group is obtained. At the same time, the information of the connecting bond of the R group is retained, and the atom to be connected is set to "*". The molecular structure of the R group is as described in the following molecule 4.

[0116] .

[0117] Step S400: Since the position of the R group is variable, it is also necessary to determine the connection position of the R group in the reactant molecule based on the reactant molecule in the reaction between the candidate product molecule and the template. Determining the connection position of the R group in the reactant molecule includes the following steps:

[0118] Step S410: Calculate the maximum common substructure information of the candidate product molecule and the reactant molecule in the reaction between the template and obtain the atom number of the maximum common substructure matching in the candidate product molecule and the reactant molecule.

[0119] As shown below, molecule 1 and molecule 2 are the candidate product molecule and the reactant molecule in the template reaction, respectively. By using RDKIT to calculate the maximum common substructure information of the candidate product molecule and the reactant molecule, the atomic number matching the maximum common substructure in the candidate product molecule and the reactant molecule can be obtained.

[0120] As shown in the following molecules 1 and 2, the matching numbers of the largest common substructure in the candidate product molecules are [3, 15, 14, 4, 13, 8, 11, 5, 1, 10, 7], and the matching numbers in the reactant molecules are [0, 8, 2, 7, 6, 5, 12, 11, 3, 4, 1].

[0121] .

[0122] Step S420: Generate an atom mapping by matching the atom numbers of the candidate product molecules with the atom numbers of the reactant molecules, that is, {3:0, 15:8, 14:2, 4:7, 13:6, 8:5, 11:12, 5:11, 1:3, 10:4, 7:1}.

[0123] Step S430: Determine the connection position of the R group in the reactant according to the connection position of the R group in the candidate molecule and the atomic mapping relationship. Specifically,

[0124] In the candidate product molecule, the R group is connected to atom No. 7. According to the generated atomic mapping relationship, atom No. 7 corresponds to atom No. 1 of the reactant molecule in the template reaction. Therefore, the R group is connected to atom No. 1 in the reactant molecule, thereby determining the position of the R group in the reactant molecule.

[0125] Step S500: adding R groups to reactant molecules of the template reaction to obtain reactant molecules corresponding to the candidate product molecules, and assembling chemical reactions based on the candidate product molecules and the generated reactant molecules.

[0126] Specifically, the molecular structure of the R group obtained in step S300 (molecule 4 in step S300) is connected to molecule 2 in step S400, and the R group determined in step S400 corresponds to atom No. 1 of the reactant molecule, thereby generating a reactant molecule corresponding to the candidate product molecule.

[0127] The specific connection process is to add all the bonds and atoms of the R group to the reactant molecule of the template reaction as shown in the following molecule 1, connect the atom No. 1 in the reactant molecule of the template reaction with the atom No. 12 connected to the "*" atom of the R group, and then delete the "*" atom to complete the replacement of the R group, thereby generating the specific structure of the reactant molecule corresponding to the candidate product molecule, as shown in the following molecule 2:

[0128] .

[0129] The newly generated reactant molecules, the candidate product molecules and other immutable molecules are assembled to generate a specific chemical reaction, thereby extracting the reaction data corresponding to the candidate product. The assembly result is shown in the following formula:

[0130] .

[0131] Step S600: Repeat steps S300 to S500 to traverse all candidate product molecules to complete the mining of chemical reaction data. The following chemical reactions are chemical reactions corresponding to candidate product molecules 1 to candidate product molecules 14.

[0132] .

[0133] The second aspect of this embodiment provides a detailed description of the chemical reaction data mining system of the present application.

[0134] Figure 2 FIG. 4 shows a module diagram of the chemical reaction data mining system of this embodiment. Figure 2 As shown, the chemical reaction data mining system of this embodiment includes:

[0135] The first recognition module 11 is used to identify whether the reactant molecule and / or the product molecule in the template reaction contains an R group, and when all the reactant molecules and all the product molecules in the template reaction do not contain an R group, the data mining process is terminated; when at least one reactant molecule and / or at least one product molecule in the template reaction contains an R group, steps S200 to S600 of the chemical reaction data mining method of any technical solution in this embodiment are used to perform chemical reaction data mining;

[0136] A second recognition module 12 is used to recognize the position information of the R group in the reactant molecule and / or the product molecule, where the position information of the R group includes variable position and fixed position;

[0137] A first determination module 13, for determining the molecular structure of the R group based on the product molecule in the reaction between the candidate product molecule and the template;

[0138] A second determination module 14, for determining the connection position of the R group in the reactant molecule based on the reactant molecule in the reaction between the candidate product molecule and the template when the position of the R group is variable;

[0139] When the position of the R group is fixed, step S500 of the chemical reaction data mining method of any technical solution in this embodiment is performed;

[0140] The assembly module 15 is used to add R groups to the reactant molecules of the template reaction, obtain reactant molecules corresponding to the candidate product molecules, and assemble chemical reactions based on the candidate product molecules and the generated reactant molecules.

[0141] The chemical reaction data mining system of this embodiment can implement the steps of the chemical reaction data mining method of any technical solution in this embodiment to achieve efficient and accurate mining of chemical reaction data.

[0142] The third aspect of this embodiment provides a detailed description of the storage medium of the present application.

[0143] The storage medium of this embodiment stores computer instructions, which execute the steps of the chemical reaction data mining method of any technical solution in this embodiment when the computer instructions are executed. The specific implementation of the steps of the chemical reaction data mining method can be referred to the previous method embodiment, which will not be repeated here.

[0144] The storage medium of this embodiment has computer instructions for executing the steps of the chemical reaction data mining method of any technical solution in this embodiment, so as to realize efficient and accurate mining of chemical reaction data.

[0145] Based on this understanding, the technical solution of this embodiment, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0146] The fourth aspect of this embodiment provides a detailed description of the terminal of the present application.

[0147] Figure 3 FIG. 2 shows a module diagram of the terminal of this embodiment. Figure 3 As shown, the terminal of this embodiment includes a memory 21 and a processor 22. The memory 21 stores computer instructions that can be run on the processor 22. When the processor 22 runs the computer instructions, the steps of the chemical reaction data mining method of any technical solution in this embodiment are executed. The specific implementation of the steps of the chemical reaction data mining method can be referred to the previous method embodiment, which will not be repeated here.

[0148] The terminal of this embodiment executes the steps of the chemical reaction data mining method of any technical solution in this embodiment to realize efficient and accurate mining of chemical reaction data.

[0149] Processor 22 may be a single-core or multi-core central processing unit or a specific integrated circuit, or one or more integrated circuits configured to implement the present invention.

[0150] Embodiments of the subject matter and functional operations described in this specification may be implemented in: tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagated signal, such as a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode and transmit information to a suitable receiver device for execution by the data processing device.

[0151] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by special-purpose logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application-specific integrated circuits), and the apparatus can also be implemented as special-purpose logic circuits.

[0152] Processors suitable for executing computer programs include, for example, general and / or special microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more large-capacity storage devices for storing data, such as a disk, a magneto-optical disk, or an optical disk, or the computer will be operably coupled to this large-capacity storage device to receive data from it or to transmit data to it, or both. However, a computer does not necessarily have such a device. In addition, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0153] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claim protection, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.

[0154] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0155] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A chemical reaction data mining method, characterized in that: The steps include: Step S100: Identify whether the reactant molecule and / or product molecule in the template reaction contains an R group, When all reactant molecules and all product molecules in the template reaction do not contain R groups, the data mining process ends; When at least one reactant molecule and / or at least one product molecule in the template reaction contains an R group, executing steps S200 to S600 to perform chemical reaction data mining; Step S200: identifying the position information of the R group in the reactant molecule and / or the product molecule, where the position information of the R group includes variable position and fixed position; Step S300: calculating the substructure matching information between the candidate product molecule and the template product molecule, and determining the molecular structure of the R group based on the difference between the candidate product molecule and the template product molecule; Step S400: Calculate the maximum common substructure information of the reactant molecule in the reaction between the candidate product molecule and the template, and determine the connection position of the R group in the reactant molecule based on the mapping relationship between each atom in the maximum common substructure in the candidate product molecule and the reactant molecule; When the position of the R group is fixed, step S500 is performed; Step S500: adding R groups to reactant molecules of the template reaction to obtain reactant molecules corresponding to the candidate product molecules, and assembling chemical reactions based on the candidate product molecules and the generated reactant molecules; Step S600: repeat steps S300 to S500 to traverse all candidate product molecules to complete the mining of chemical reaction data; in, Determine the molecular structure of the R group, including the following steps: Step S310: calculating the substructure matching information between the candidate product molecule and the template product molecule, taking the template product molecule as the substructure, determining the atom number in the candidate product molecule that matches the substructure, and the atom number in the candidate product molecule that does not match the substructure; Step S320: extracting all atoms that do not match the substructure from the candidate molecules, and determining the molecules composed of the atom numbers that do not match the substructure in the candidate product molecules as R groups; Determining the attachment position of the R group in the reactant molecule comprises the following steps: Step S410: Calculate the maximum common substructure information of the candidate product molecule and the reactant molecule in the reaction between the template, and obtain the atom number of the maximum common substructure matching in the candidate product molecule and the reactant molecule; Step S420: Generate an atom mapping by matching the matching atom numbers in the candidate product molecules with the matching atom numbers in the reactant molecules one by one; Step S430: Determine the connection position of the R group in the reactant according to the connection position of the R group in the candidate molecule and the atomic mapping relationship.

2. The chemical reaction data mining method according to claim 1, characterized in that: Identifying whether a reactant molecule and / or a product molecule in a template reaction contains an R group comprises the following steps: Iterate over the atoms in each reactant molecule and / or each product molecule in the template reaction, If the molecule contains R atoms, confirm that the corresponding reactant molecules and / or product molecules contain R groups, If the molecule does not contain an R atom, confirm that the corresponding reactant molecules and / or product molecules do not contain an R group.

3. The chemical reaction data mining method according to claim 2, characterized in that: Identifying the position information of R groups in reactant molecules and / or product molecules comprises the following steps: Determine the position information of the R group based on the connection position of the R group, When the chemical bonds of the R group cross the chemical bonds in the molecule, the position of the R group can be changed; When the R group is attached to an atom in a molecule, the position of the R group is fixed.

4. A chemical reaction data mining system, characterized in that: Used to implement the chemical reaction data mining method according to any one of claims 1 to 3, the chemical reaction data mining system comprises: A first identification module, used to identify whether the reactant molecule and / or the product molecule in the template reaction contains an R group, and when all the reactant molecules and all the product molecules in the template reaction do not contain an R group, the data mining process is terminated; when at least one reactant molecule and / or at least one product molecule in the template reaction contains an R group, steps S200 to S600 of the chemical reaction data mining method according to any one of claims 1 to 3 are executed to perform chemical reaction data mining; A second recognition module is used to recognize the position information of the R group in the reactant molecule and / or the product molecule, where the position information of the R group includes variable position and fixed position; The first determination module is used to calculate the substructure matching information between the candidate product molecule and the template product molecule, and determine the molecular structure of the R group based on the difference between the candidate product molecule and the template product molecule; The second determination module is used to calculate the maximum common substructure information of the reactant molecule in the reaction between the candidate product molecule and the template, and determine the connection position of the R group in the reactant molecule based on the mapping relationship between each atom in the maximum common substructure in the candidate product molecule and the reactant molecule; When the position of the R group is fixed, step S500 of executing the chemical reaction data mining method according to any one of claims 1 to 3; The assembly module is used to add R groups to the reactant molecules of the template reaction, obtain the reactant molecules corresponding to the candidate product molecules, and assemble the chemical reaction based on the candidate product molecules and the generated reactant molecules.

5. A storage medium, characterized in that: The storage medium stores computer instructions, which, when executed, execute the steps of the chemical reaction data mining method according to any one of claims 1 to 3.

6. A terminal, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer instructions executable on the processor, and the processor executes the steps of the chemical reaction data mining method according to any one of claims 1 to 3 when executing the computer instructions.