Method, device, equipment and storage medium for improving drugability of compound molecules

Abstract

The present application relates to a method, device, equipment and storage medium for improving the drugability of a compound molecule. The method: obtain a lead compound molecule, slice the lead compound molecule according to a preset slicing rule, obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecule, match the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replace the molecular fragments according to the substitution rules, and generate multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, each substitution rule is about the change direction of ADMET drugability, and multiple candidate compound molecules are screened according to the preset rules to obtain multiple target compound molecules. Since the substitution rules contained in the matching molecule pair database are about the change direction of ADMET drugability, it is possible to imitate the design ideas of pharmaceutical chemists and improve and optimize the drugability of compound molecules.

Description

Technical Field

[0001] The present application relates to the field of drug development technology, and in particular to a method, device, equipment and storage medium for improving the drugability of compound molecules. Background Art

[0002] Local quantitative structure-activity relationship (QSAR) reveals the influence of the molecular structure and physicochemical properties of a compound on a given property (such as biological activity). In the early stages of compound molecule involvement, the matched molecular pair (MMP) method is used as a QSAR optimization analysis scheme. The MMP method is used to establish a matched molecular pair database and modify some functional groups of the compound molecules to improve the activity of the compound molecules.

[0003] Although the MMP method can be used in the scenario of optimizing the activity of compound molecules, since the activity of compound molecules is essentially the result of physical interaction with target proteins and does not completely depend on the compound molecules themselves, it is impossible to establish a database of matching molecule pairs across target proteins. As a result, it is impossible to make good use of the MMP method in combination with the matching molecule database as an improved optimization solution for the activity of compound molecules. In other words, QSAR rules cannot be generalized in the application scenario of the activity of compound molecules and cannot be cross-used between different projects. Summary of the invention

[0004] In order to solve or partially solve the problems existing in the related art, the present application provides a method, device, equipment and storage medium for improving the drugability of compound molecules, which can imitate the design ideas of pharmaceutical chemists and improve and optimize the drugability of compound molecules.

[0005] The first aspect of the present application provides a method for improving the drugability of a compound molecule, comprising:

[0006] Obtain lead compound molecules;

[0007] Slicing and identifying the lead compound molecule to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecule;

[0008] Based on the chemical environment, a corresponding substitution rule in a matching molecule pair database is matched, and the molecular fragment is replaced according to the substitution rule to generate a plurality of candidate compound molecules, wherein the matching molecule pair database contains a plurality of substitution rules, and each substitution rule is about the change direction of ADMET drugability;

[0009] The plurality of candidate compound molecules are screened according to preset rules to obtain a plurality of target compound molecules.

[0010] Preferably, the molecular fragment comprises hydrogen atoms, functional groups or chemical skeletons;

[0011] The step of matching the corresponding substitution rules in the database of matching molecules based on the chemical environment, replacing the molecular fragments according to the substitution rules, and generating a plurality of candidate compound molecules includes:

[0012] Based on the chemical environment, a corresponding substitution rule in a matching molecule database is matched, and the hydrogen atom, the functional group or the chemical skeleton is replaced according to the substitution rule to generate a plurality of candidate compound molecules.

[0013] Preferably, the screening of the plurality of candidate compound molecules according to preset rules to obtain a plurality of target compound molecules comprises:

[0014] The plurality of candidate compound molecules are ranked based on the numerical values ​​of the ADMET drugability, and the plurality of candidate compound molecules are screened according to the ranking results to obtain the plurality of target compound molecules.

[0015] Preferably, the construction of the matching molecule pair database comprises:

[0016] Acquire multiple sample compound molecules;

[0017] Cleaning the plurality of sample compound molecules according to a pretreatment method to obtain a plurality of sample initial compound molecules;

[0018] Slicing a plurality of initial compound molecules of the sample;

[0019] Identifying all sample chemical environments and replaceable sample molecular fragment combinations corresponding to a plurality of sample initial compound molecules after slicing with different chemical radii;

[0020] Two sample initial compound molecules with the same sample chemical environment are paired, and the change direction of ADMET drugability is calculated based on the two paired sample initial compound molecules, and the substitution rules of the sample molecular fragments are established. This process is repeated until all the sample initial compound molecules are paired, and the matching molecule pair database is constructed.

[0021] Preferably, the step of washing the plurality of sample compound molecules according to the pretreatment method to obtain a plurality of sample initial compound molecules comprises:

[0022] Filter out the sample compound molecules whose ADMET drugability values ​​are empty;

[0023] selecting the plurality of retained sample compound molecules according to preset drug-like rules to obtain a plurality of pre-treated sample compound molecules;

[0024] The plurality of pre-processed sample compound molecules are represented in a typical SMILES manner, and the plurality of pre-processed sample compound molecules are deduplicated to obtain a plurality of sample initial compound molecules.

[0025] Preferably, the selecting of the plurality of retained sample compound molecules according to the preset drug-like rules to obtain a plurality of pre-treated sample compound molecules comprises:

[0026] The retained plurality of sample compound molecules are selected according to the five drug-like rules to obtain a plurality of pre-treated sample compound molecules.

[0027] Preferably, slicing the plurality of initial compound molecules of the sample comprises:

[0028] The plurality of sample initial compound molecules are sliced ​​in a manner of mainly cutting single bonds, cutting terminal functional groups and not exceeding a maximum number of slices.

[0029] Preferably, the no more than maximum number of slicing times is equal to 3.

[0030] The second aspect of the present application provides a device for improving the drugability of a compound molecule, comprising:

[0031] An acquisition module, used to acquire lead compound molecules;

[0032] A slicing and recognition module, used to slice and identify the lead compound molecules to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecules;

[0033] A matching substitution module, for matching the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replacing the molecular fragments according to the substitution rules, and generating a plurality of candidate compound molecules, wherein the matching molecule pair database contains a plurality of substitution rules, and each substitution rule is about the change direction of ADMET drugability;

[0034] The screening module is used to screen the plurality of candidate compound molecules according to preset rules to obtain a plurality of target compound molecules.

[0035] Preferably, the molecular fragment comprises hydrogen atoms, functional groups or chemical skeletons;

[0036] The matching and substitution module is used to match the corresponding substitution rules in the matching molecule database based on the chemical environment, replace the hydrogen atoms, the functional groups or the chemical skeleton according to the substitution rules, and generate multiple candidate compound molecules.

[0037] Preferably, the screening module is used to sort the multiple candidate compound molecules based on the numerical values ​​of the ADMET drugability, and complete the screening of the multiple candidate compound molecules according to the sorting results of the multiple candidate compound molecules to obtain the multiple target compound molecules.

[0038] A third aspect of the present application provides an electronic device, including:

[0039] Processor; and

[0040] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0041] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0042] The technical solution provided by this application may have the following beneficial effects:

[0043] The technical solution of the present application obtains a lead compound molecule, slices the lead compound molecule according to a preset slicing rule, obtains all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecule, matches the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replaces the molecular fragments according to the substitution rules, and generates multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, each substitution rule is about the change direction of ADMET drugability, and multiple candidate compound molecules are screened according to the preset rules to obtain multiple target compound molecules. Since the substitution rules contained in the matching molecule pair database are about the change direction of ADMET drugability, it is possible to imitate the design ideas of pharmaceutical experts and improve and optimize the drugability of compound molecules.

[0044] In addition to supporting the growth mode of hydrogen substitution and completing the directional generation of drugability of lead compound molecules, the technical solution of the present application can also support mutation modes of functional group replacement or chemical skeleton replacement, so that the lead compound molecules have the possibility of skeleton transition, making the technical solution of the present application highly synthetic.

[0045] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0047] Figure 1 It is a schematic flow chart of a method for improving the drugability of a compound molecule shown in an embodiment of the present application;

[0048] Figure 2 is a schematic flow chart of a method for improving the drugability of a compound molecule according to another embodiment of the present application;

[0049] Figure 3 It is a schematic diagram of the structure of a device for improving the drugability of compound molecules shown in the examples of the present application;

[0050] Figure 4 is a schematic structural diagram of a device for improving the drugability of a compound molecule shown in another embodiment of the present application;

[0051] Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0053] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0054] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0055] At present, in the relevant technology, since the activity of compound molecules is essentially the result of physical interaction with target proteins and does not completely depend on the compound molecules themselves, it is not possible to make good use of the MMP method combined with the matching molecule database as an improvement and optimization solution for the activity of compound molecules. However, the AMDET drugability of compound molecules is determined by the physical and chemical properties of the compound molecules themselves. Therefore, it is possible to establish a matching molecule pair database based on ADMET properties and use the MMP method as an improvement and optimization solution for the drugability of compound molecules.

[0056] In view of the above problems, the present application provides a method, device, equipment and storage medium for improving the drugability of compound molecules, which can imitate the design ideas of pharmaceutical chemists to improve and optimize the drugability of compound molecules. In order to facilitate the understanding of the technical solution of the present application, the technical solution of the present application is described in detail below in conjunction with the accompanying drawings.

[0057] Figure 1 A schematic flow chart of a method for improving the drugability of a compound molecule according to an embodiment of the present application is shown.

[0058] See also Figure 1 , a method for improving the drugability of a compound molecule, comprising the following steps:

[0059] Step S11, obtaining a lead compound molecule.

[0060] It should be noted that the lead compound molecule is the compound molecule that needs to be improved and optimized. The lead compound molecule is composed of a chemical skeleton and at least one functional group. The chemical skeleton is the core part of the lead compound molecule, and the functional group is the atom or atomic group that determines the chemical properties of the lead compound molecule. Common functional groups include hydroxyl, carboxyl, ether bond, aldehyde, carbonyl, etc.

[0061] Step S12: Slice and identify the lead compound molecules to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecules.

[0062] It should be noted that the slicing rules set in advance, for example, when slicing the lead compound molecules, the lead compound molecules are sliced ​​according to the slicing rules that mainly cut off the single bonds of the lead compound molecules, cut off the terminal functional groups of the lead compound molecules, and the lead compound molecules are cut into a maximum of three pieces. The sliced ​​lead compound molecules are identified with different chemical radii to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecules.

[0063] Step S13, matching the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replacing the molecular fragments according to the substitution rules, and generating multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, each substitution rule is about the change direction of ADMET drugability.

[0064] The construction of a matching molecule pair database includes: obtaining multiple sample compound molecules; cleaning the multiple sample compound molecules according to a pretreatment method to obtain multiple sample initial compound molecules; slicing the multiple sample initial compound molecules; identifying all sample chemical environments and sample molecular fragment combinations corresponding to the multiple sample initial compound molecules after slicing with different chemical radii; pairing two sample initial compound molecules with the same sample chemical environment, calculating the change direction of ADMET drugability based on the two paired sample initial compound molecules, establishing a substitution rule for sample molecular fragments, repeating this process until all sample initial compound molecules are paired, and constructing a matching molecule pair database.

[0065] After slicing and identifying the lead compound molecules, all chemical environments and replaceable molecular fragment combinations are obtained. Based on the chemical environment, the corresponding substitution rules in the matching molecule pair database are matched. When matching, matching is performed according to the chemical environment. For example, the combination of chemical environment A + replaceable molecular fragment A needs to be improved and optimized. The substitution rule corresponding to the chemical environment A is searched in the matching molecule pair database. According to the substitution rule, molecular fragment A is replaced with molecular fragment B to generate a candidate compound molecule. Since the substitution rules are all about the change direction of ADMET drugability, the ADMET drugability of the generated candidate compound molecules will change relative to the lead compound molecules. Repeat this step until all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecules are replaced, and multiple candidate compound molecules are generated.

[0066] Step S14: screening multiple candidate compound molecules according to preset rules to obtain multiple target compound molecules.

[0067] It should be noted that after obtaining multiple candidate compound molecules, in order to obtain compound molecules with excellent ADMET drugability, multiple candidate compound molecules are screened by setting preset rules to obtain multiple target compound molecules. The target compound molecules are compound molecules with excellent ADMET drugability.

[0068] The method of this embodiment obtains a lead compound molecule, slices the lead compound molecule according to a preset slicing rule, obtains all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecule, matches the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replaces the molecular fragments according to the substitution rules, and generates multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, each substitution rule is about the change direction of ADMET drugability, and multiple candidate compound molecules are screened according to the preset rules to obtain multiple target compound molecules. Since the substitution rules contained in the matching molecule pair database are about the change direction of ADMET drugability, it is possible to imitate the design ideas of pharmaceutical experts and improve and optimize the drugability of compound molecules.

[0069] Figure 2 Shown is a schematic flow chart of a method for improving the drugability of a compound molecule in another embodiment of the present application.

[0070] See also Figure 2 , a method for improving the drugability of a compound molecule, comprising the following steps:

[0071] Step S21, obtaining a lead compound molecule.

[0072] Lead compound molecules are compound molecules that need to be improved and optimized. Lead compound molecules are composed of a chemical skeleton and at least one functional group. The chemical skeleton is the core part of the lead compound molecule, and the functional group is the atom or atom group that determines the chemical properties of the lead compound molecule.

[0073] Step S22, slicing and identifying the lead compound molecules to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecules, wherein the molecular fragments may at least include hydrogen atoms, functional groups or chemical skeletons.

[0074] Pre-set slicing rules, for example, when slicing the lead compound molecule, the lead compound molecule is sliced ​​according to the slicing rules of mainly cutting off the single bonds of the lead compound molecule, cutting off the terminal functional groups of the lead compound molecule, and cutting the lead compound molecule into a maximum of three pieces, and the sliced ​​lead compound molecules are identified with different chemical radii to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecule.

[0075] The lead compound molecules after slicing have multiple chemical environments + replaceable molecular fragment combinations. Molecular fragments include hydrogen atoms, functional groups or chemical skeletons, that is, the lead compound molecules after slicing can obtain a combination of chemical environment + replaceable functional group or a combination of chemical environment + replaceable chemical skeleton after identification.

[0076] For example, after the same lead compound molecule is sliced ​​and identified, it may obtain chemical environment B + replaceable functional group B, chemical environment C + replaceable functional group C, chemical environment D + replaceable chemical skeleton D and chemical environment E + replaceable chemical skeleton E.

[0077] Step S23, matching the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replacing hydrogen atoms, functional groups or chemical skeletons according to the substitution rules, and generating multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, and each substitution rule is about the change direction of ADMET drugability.

[0078] The matching molecule pair database is a database pre-built based on the MMP method. Since the drugability of AMDET is determined by the physical and chemical properties of the compound molecule itself, the MMP method is used to establish the matching molecule pair database based on the ADMET properties. The substitution rules in the established matching molecule pair database can be universalized and used as a recommended database for generating new compound molecules for cross-use in different projects.

[0079] The construction of the database of matching molecular pairs includes:

[0080] A plurality of sample compound molecules are obtained. The sample compound molecules are the same as the lead compound molecules, except that the sample compound molecules are raw data for matching the molecular pair database.

[0081] According to the preprocessing method, multiple sample compound molecules are cleaned to obtain multiple sample initial compound molecules. After obtaining multiple sample compound molecules, data cleaning is required. On the one hand, it is to prevent some invalid sample compound molecules from being mixed into valid sample compound molecules for the construction of matching molecule pair databases, and on the other hand, it is to reduce the amount of database construction calculations by removing relevant useless sample compound molecules.

[0082] First, filter out the sample compound molecules with empty ADMET drugability values ​​(the sample compound molecules with empty values, i.e., unclear ADMET drugability values), and select the multiple sample compound molecules retained according to the preset drug-like rules, which can be drug-like five rules, drug-like four rules, or drug-like three rules. This embodiment uses the drug-like five rules with a relative molecular mass not exceeding 500, a hydrogen bond donor number not exceeding 5, a hydrogen bond acceptor number not exceeding 10, a lipid-water partition coefficient less than 5, and a number of rotatable bonds not exceeding 10 to select the multiple sample compound molecules retained, and obtain multiple pre-treated sample compound molecules. Finally, multiple pre-treated sample compound molecules are represented in a typical SMILES manner, and multiple pre-treated sample compound molecules are deduplicated to obtain multiple sample initial compound molecules.

[0083] The slicing of the multiple sample initial compound molecules is the same as the slicing rules set in advance when slicing the lead compound molecules, for example, the multiple sample initial compound molecules are sliced ​​in a manner of mainly cutting off single bonds, cutting off terminal functional groups, and not exceeding the maximum number of slicing times, wherein the maximum number of slicing times not exceeding can be set to be equal to 3. Of course, the maximum number of slicing times can also be flexibly set according to actual project needs, and this embodiment does not specifically limit it.

[0084] All sample chemical environments and replaceable sample molecular fragment combinations corresponding to multiple sample initial compound molecules after slicing are identified with different chemical radii. Sample molecular fragments are sample functional groups or sample chemical skeletons. The sample chemical environment has the same concept as the aforementioned chemical environment, and the word "sample" is added only for differentiation. The sample functional group has the same concept as the aforementioned functional group, and the word "sample" is added only for differentiation. The sample chemical skeleton has the same concept as the aforementioned chemical skeleton, and the word "sample" is added only for differentiation.

[0085] Two sample initial compound molecules with the same sample chemical environment are paired, and the change direction of ADMET drugability is calculated based on the two paired sample initial compound molecules. The substitution rules of sample molecular fragments are established, and this process is repeated until all sample initial compound molecules are paired, and a matching molecular pair database is constructed.

[0086] After slicing and identifying the sample initial compound molecules, all sample chemical environments + replaceable sample molecule fragment combinations corresponding to the sample initial compound molecules can be obtained. At this time, by pairing based on the same sample chemical environment, the pairing of two sample initial compound molecules can be achieved. For example, assuming that after slicing and identifying the sample initial compound molecule 1, the sample chemical environment F + replaceable functional group K combination is obtained, and after slicing and identifying the sample initial compound molecule 2, the sample chemical environment F + replaceable functional group P combination is obtained. Through pairing analysis, the chemical environment of the sample initial compound molecule 1 is the same as that of the sample initial compound molecule 2, and the sample initial compound molecule 1 and the sample initial compound molecule 2 can be used as a pair of matching molecular pairs. Based on this pair of matching molecular pairs, the change direction of ADMET drugability is calculated, and a substitution rule is established. Repeat the above process until all sample initial compound molecules are paired, and a matching molecular pair database is constructed.

[0087] Step S24, sorting the multiple candidate compound molecules based on the numerical values ​​of the ADMET drugability, and completing the screening of the multiple candidate compound molecules according to the sorting results of the multiple candidate compound molecules to obtain multiple target compound molecules.

[0088] It should be noted that after obtaining multiple candidate compound molecules, in order to obtain compound molecules with excellent ADMET drugability. Multiple candidate compound molecules are sorted based on the numerical value of ADMET drugability, and multiple candidate compound molecules are screened according to the sorting results of the multiple candidate compound molecules to obtain multiple target compound molecules. For example, the kinetic solubility in ADMET drugability is selected as the sorting criterion, and the candidate compound molecules are sorted according to the corresponding kinetic solubility size, and TOP K is taken, K>=100, that is, the candidate compound molecules ranked in the top 100 are taken as target compound molecules.

[0089] The method of this embodiment can imitate the design ideas of pharmaceutical experts and improve and optimize the drugability of compound molecules, because the substitution rules contained in the database of matching molecule pairs are about the change direction of ADMET drugability. In addition, in addition to supporting the growth mode of hydrogen substitution and completing the directional generation of drugability of lead compound molecules, the method of this embodiment can also support the mutation mode of functional group replacement or chemical skeleton replacement, so that the lead compound molecules have the possibility of skeleton transition, which has a high possibility of breaking through existing drug molecule patents and maintaining the high synthesizability of the designed molecules.

[0090] In order to better understand the technical solution of the present application, a specific embodiment is listed below to explain the technical solution of the present application in detail.

[0091] Embodiment 1

[0092] The kinetic solubility of the selected compound molecules in ADMET druggability is used as the prerequisite for building a database of matching molecule pairs.

[0093] Download the PubChem compound library from the relevant data website, and use two kinetic solubility sample compound molecule data sets from the PubChem compound library, including the two subsets PubChemAID1996 and AID1645848. In these two data subsets, remove the compound molecules whose kinetic solubility is empty in the experimental measurement and whose artificial markings question the accuracy of the experimental measurement of kinetic solubility. Select the retained sample compound molecules according to the drug-like five rules to obtain multiple pre-treated sample compound molecules.

[0094] Select the largest molecular fragment in the pre-treated sample compound molecule, and only select the pre-treated sample compound molecules containing hydrogen, carbon, nitrogen, oxygen, fluorine, sulfur, chlorine, bromine, and iodine elements, remove the chiral mark in the SMILES of the pre-treated sample compound molecule, and convert the molecular structure of the pre-treated sample compound molecule into a typical SMILES representation. And remove the repeated pre-treated sample compound molecules to ensure that all pre-treated sample compound molecules are unique, and one pre-treated sample compound molecule can correspond to one kinetic solubility, and obtain multiple sample initial compound molecules.

[0095] According to some pre-set slicing rules (such as mainly cutting single bonds, cutting terminal functional groups, and not exceeding the maximum number of slicing times, where the maximum number of slicing times is equal to 3), multiple sample initial compound molecules are identified with different chemical radii for all sample chemical environments and replaceable sample molecular fragment combinations corresponding to the multiple sample initial compound molecules after slicing. The sample molecular fragment is a sample functional group or a sample chemical skeleton. Two sample initial compound molecules with the same sample chemical environment are paired, and the change direction of ADMET drugability is calculated based on the two paired sample initial compound molecules, and the substitution rules of the sample molecular fragments are established. This process is repeated until all sample initial compound molecules are paired, and a matching molecular pair database for kinetic solubility is constructed.

[0096] After the establishment of the matching molecule pair database is completed, the lead compound molecule 1 is obtained, and the lead compound molecule 1 is sliced ​​and identified to obtain the combination of the chemical environment M corresponding to the lead compound molecule 1 + the replaceable molecular fragment M. Based on the chemical environment M, the same chemical environment is matched in the matching molecule pair database to obtain substitution rules 1, ..., substitution rules n.

[0097] According to substitution rules 1, ..., substitution rule n, replaceable molecular fragments M are replaced respectively to generate n candidate compound molecules (the value of n is determined by the number of substitution rules actually matched). When replacing, if the hydrogen atom is replaced, the generation mode is used to generate candidate compound molecules. If the functional group or chemical skeleton is replaced, the mutation mode is used to generate candidate compound molecules.

[0098] The n candidate compound molecules are sorted according to the numerical values ​​of the kinetic solubility (the sorting order is descending), and the top 30 candidate compound molecules are taken. These 30 candidate compound molecules are used as target compound molecules, that is, by replacing the molecular fragment M in the molecular fragment M according to substitution rules 1, ..., substitution rule n, respectively, a compound molecule with better kinetic solubility can be obtained.

[0099] Since the substitution rules contained in the database of matching molecular pairs are about the change direction of ADMET drugability, it is possible to imitate the design ideas of pharmaceutical experts and improve and optimize the drugability of compound molecules. In addition, in addition to supporting the growth mode of hydrogen atom replacement and completing the directional generation of drugability of lead compound molecules, the method of this embodiment can also support the mutation mode of functional group or chemical skeleton replacement, so that the lead compound molecules have the possibility of skeleton transition, making the method of this embodiment highly synthesizable.

[0100] Corresponding to the aforementioned application function method embodiments, the present application also provides a device for improving the drugability of compound molecules, an electronic device and corresponding embodiments.

[0101] Figure 3 It is a schematic structural diagram of a device 30 for improving the drugability of a compound molecule shown in an embodiment of the present application.

[0102] See also Figure 3 , a device 30 for improving the drugability of a compound molecule, comprising: an acquisition module 310, a slice recognition module 320, a matching substitution module 330 and a screening module 340.

[0103] The acquisition module 310 is used to acquire the lead compound molecule;

[0104] The slicing recognition module 320 is used to slice and recognize the lead compound molecules to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecules;

[0105] The matching substitution module 330 is used to match the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replace the molecular fragments according to the substitution rules, and generate multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, each substitution rule is about the change direction of ADMET drugability;

[0106] The screening module 340 is used to screen a plurality of candidate compound molecules according to preset rules to obtain a plurality of target compound molecules.

[0107] In the device of this embodiment, the acquisition module 310 acquires the lead compound molecule, the slicing identification module 320 slices the lead compound molecule according to the preset slicing rules, obtains all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecule, the matching substitution module 330 matches the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replaces the molecular fragments according to the substitution rules, and generates multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, each substitution rule is about the change direction of ADMET drugability, and the screening module 340 screens multiple candidate compound molecules according to the preset rules to obtain multiple target compound molecules. Since the substitution rules contained in the matching molecule pair database are about the change direction of ADMET drugability, it is possible to imitate the design ideas of pharmaceutical experts and improve and optimize the drugability of compound molecules.

[0108] Figure 4 It is a schematic structural diagram of a device 40 for improving the drugability of a compound molecule shown in another embodiment of the present application.

[0109] See also Figure 4 , a device 40 for improving the drugability of a compound molecule, comprising: an acquisition module 410, a slice recognition module 420, a matching substitution module 430 and a screening module 440.

[0110] Wherein, the acquisition module 410 can refer to Figure 3 The description in will not be repeated here.

[0111] The slicing recognition module 420 is used to slice and identify the lead compound molecules to obtain all chemical environments and replaceable molecular fragment combinations corresponding to the lead compound molecules, wherein the molecular fragments include hydrogen atoms, functional groups or chemical skeletons.

[0112] The matching substitution module 430 is used to match the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replace hydrogen atoms, functional groups or chemical skeletons according to the substitution rules, and generate multiple candidate compound molecules, wherein the matching molecule pair database contains multiple substitution rules, and each substitution rule is about the change direction of ADMET drugability.

[0113] The screening module 440 is used to sort multiple candidate compound molecules based on the numerical values ​​of ADMET drugability, and complete the screening of multiple candidate compound molecules based on the sorting results of the multiple candidate compound molecules to obtain multiple target compound molecules.

[0114] Regarding the device in the above embodiment, the specific manner in which each module and unit performs operations has been described in detail in the method embodiment corresponding to the device, and will not be elaborated again here.

[0115] See also Figure 5 , the electronic device 500 includes a processor 510 and a memory 520 .

[0116] The processor 510 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0117] The memory 520 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage. Among them, ROM can store static data or instructions required by the processor 510 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 520 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. The memory 520 stores executable codes, and when the executable codes are processed by the processor 510 , the processor 510 can execute part or all of the methods described above.

[0118] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0119] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0120] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for improving the drugability of a compound molecule, characterized in that: include: Obtain lead compound molecules; Slicing and identifying the lead compound molecule to obtain all chemical environments corresponding to the lead compound molecule and a combination of replaceable molecular fragments, including: slicing the lead compound molecule in a manner that mainly cuts off single bonds, cuts off terminal functional groups, and does not exceed a maximum number of slices, identifying the sliced ​​lead compound molecule with different chemical radii, and obtaining all chemical environments corresponding to the lead compound molecule and a combination of replaceable molecular fragments; Based on the chemical environment, a corresponding substitution rule in a matching molecule pair database is matched, and the molecular fragment is replaced according to the substitution rule to generate a plurality of candidate compound molecules, wherein the matching molecule pair database contains a plurality of substitution rules, and each substitution rule is about the change direction of ADMET drugability; Screening the plurality of candidate compound molecules according to preset rules to obtain a plurality of target compound molecules; Wherein, the construction of the matching molecule pair database includes: Acquire multiple sample compound molecules; Cleaning the plurality of sample compound molecules according to a pretreatment method to obtain a plurality of sample initial compound molecules; Slicing a plurality of initial compound molecules of the sample; Identifying all sample chemical environments and replaceable sample molecular fragment combinations corresponding to a plurality of sample initial compound molecules after slicing with different chemical radii; Two sample initial compound molecules with the same sample chemical environment are paired, and the change direction of ADMET drugability is calculated based on the two paired sample initial compound molecules, and the substitution rules of the sample molecular fragments are established. This process is repeated until all the sample initial compound molecules are paired, and the matching molecule pair database is constructed.

2. The method according to claim 1, characterized in that The molecular fragments include hydrogen atoms, functional groups or chemical skeletons; The step of matching the corresponding substitution rules in the database of matching molecules based on the chemical environment, replacing the molecular fragments according to the substitution rules, and generating a plurality of candidate compound molecules includes: Based on the chemical environment, a corresponding substitution rule in a matching molecule database is matched, and the hydrogen atom, the functional group or the chemical skeleton is replaced according to the substitution rule to generate a plurality of candidate compound molecules.

3. The method according to claim 1, characterized in that The method of screening the plurality of candidate compound molecules according to the preset rules to obtain a plurality of target compound molecules includes: The plurality of candidate compound molecules are ranked based on the numerical values ​​of the ADMET drugability, and the plurality of candidate compound molecules are screened according to the ranking results to obtain the plurality of target compound molecules.

4. The method according to any one of claims 1 to 3, characterized in that The step of washing the plurality of sample compound molecules according to the pretreatment method to obtain a plurality of sample initial compound molecules comprises: Filter out the sample compound molecules whose ADMET drugability values ​​are empty; selecting the plurality of retained sample compound molecules according to preset drug-like rules to obtain a plurality of pre-treated sample compound molecules; The plurality of pre-processed sample compound molecules are represented in a typical SMILES manner, and the plurality of pre-processed sample compound molecules are deduplicated to obtain a plurality of sample initial compound molecules.

5. The method according to claim 4, characterized in that The step of selecting the plurality of retained sample compound molecules according to the preset drug-like rules to obtain a plurality of pre-treated sample compound molecules comprises: The retained plurality of sample compound molecules are selected according to the five drug-like rules to obtain a plurality of pre-treated sample compound molecules.

6. The method according to any one of claims 1 to 3, characterized in that The slicing of the plurality of initial compound molecules of the sample comprises: The plurality of sample initial compound molecules are sliced ​​in a manner of mainly cutting single bonds, cutting terminal functional groups and not exceeding a maximum number of slices.

7. The method according to claim 6, characterized in that The maximum number of slicing times is equal to 3.

8. A device for improving the drugability of a compound molecule, characterized in that: include: An acquisition module, used to acquire lead compound molecules; A slicing recognition module is used to slice and identify the lead compound molecules to obtain all chemical environments corresponding to the lead compound molecules and replaceable molecular fragment combinations, including: slicing the lead compound molecules in a manner of mainly cutting off single bonds, cutting off terminal functional groups, and not exceeding a maximum number of slicing times, identifying the sliced ​​lead compound molecules with different chemical radii, and obtaining all chemical environments corresponding to the lead compound molecules and replaceable molecular fragment combinations; A matching substitution module, for matching the corresponding substitution rules in the matching molecule pair database based on the chemical environment, replacing the molecular fragments according to the substitution rules, and generating a plurality of candidate compound molecules, wherein the matching molecule pair database contains a plurality of substitution rules, and each substitution rule is about the change direction of ADMET drugability; A screening module, used to screen the plurality of candidate compound molecules according to preset rules to obtain a plurality of target compound molecules; Wherein, the construction of the matching molecule pair database includes: Acquire multiple sample compound molecules; Cleaning the plurality of sample compound molecules according to a pretreatment method to obtain a plurality of sample initial compound molecules; Slicing a plurality of initial compound molecules of the sample; Identifying all sample chemical environments and replaceable sample molecular fragment combinations corresponding to a plurality of sample initial compound molecules after slicing with different chemical radii; Two sample initial compound molecules with the same sample chemical environment are paired, and the change direction of ADMET drugability is calculated based on the two paired sample initial compound molecules, and the substitution rules of the sample molecular fragments are established. This process is repeated until all the sample initial compound molecules are paired, and the matching molecule pair database is constructed.

9. The device according to claim 8, characterized in that The molecular fragments include hydrogen atoms, functional groups or chemical skeletons; The matching and substitution module is used to match the corresponding substitution rules in the matching molecule database based on the chemical environment, replace the hydrogen atoms, the functional groups or the chemical skeleton according to the substitution rules, and generate multiple candidate compound molecules.

10. The device according to claim 8 or 9, characterized in that The screening module is used to sort the multiple candidate compound molecules based on the numerical values ​​of the ADMET drugability, and complete the screening of the multiple candidate compound molecules according to the sorting results of the multiple candidate compound molecules to obtain the multiple target compound molecules.

11. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 7.

12. A computer-readable storage medium, characterized in that: An executable code is stored thereon, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as claimed in any one of claims 1 to 7.

Images