Chemical space determination method and device

Abstract

The invention provides a chemical space determination method and device, and the method comprises the steps: obtaining a target file which comprises one or more chemical molecular structural formulas; identifying the target file through an identification model to obtain the type to which each chemical molecular structural formula belongs; under the condition that the type of the chemical molecular structural formula is a first type, attribute information and restriction information of substituent groups in the chemical molecular structural formula are obtained through a recognition model, and the first type represents that the chemical molecular structural formula comprises the substituent groups; generating a target program through a target model based on the attribute information and the restriction information; and determining a chemical space corresponding to the target file based on the target program. Compared with the prior art, the chemical space corresponding to the target file can be determined without manual participation, the efficiency and the automation degree are high, meanwhile, the situation that omission exists when possible structures of substituent groups are extracted and enumerated manually is avoided, and the accuracy of the determined chemical space is improved.

Description

Technical Field

[0001] The present application relates to the technical field of chemical informatics, and in particular to a method and device for determining a chemical space. Background Art

[0002] Chemical space refers to the collection of all potential molecules contained in the general chemical structure formula. The chemical space covered by chemical literature or patents represents the collection of all functional molecules. Accurately identifying the chemical space of literature and patents can determine whether a molecule is within the scope of the patent on the one hand, and on the other hand, it can assist in the study of structure-activity relationships and the design of better molecules. However, the general structural formula usually contains many arbitrary substitutions on the rings and some free restrictive descriptions, which cannot be enumerated using simple rules and permutation and combination methods. Usually, to identify the chemical space described by the general structural formula, it is necessary to manually read the possible structures of all substituents in the general structural formula from the file. These substituents may also have nested relationships or other associations. Therefore, the substituents need to be arranged and combined.

[0003] The current solution is to manually obtain the possible structure of each substituent, then use chemical informatics methods to arrange and combine the substituents, enumerate all possible substituents, and finally assemble the complete molecule to determine the corresponding chemical space. However, this method requires a lot of manual work, and has low efficiency and automation. In addition, for some more complex situations, such as substituents at any position on the ring, at least one nitrogen and at most two sulfurs in the substituent, and other substituents nested in the substituent, there will be omissions when manually extracting and enumerating the possible structures of the substituents, which leads to inaccurate chemical space. Summary of the invention

[0004] In view of this, an object of the embodiments of the present application is to provide a method and device for determining a chemical space, so as to solve the problems of low efficiency, automation and accuracy in determining the chemical space in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for determining a chemical space, which includes:

[0006] Acquire a target file, wherein the target file includes one or more chemical molecular structure formulas;

[0007] Identify the target file through a recognition model to obtain the type to which each chemical molecule structure formula belongs;

[0008] In the case where the type to which the chemical molecular structure belongs is the first type, obtaining attribute information of substituents in the chemical molecular structure and restriction information of the substituents through the recognition model, wherein the first type indicates that the chemical molecular structure includes substituents;

[0009] Based on the attribute information and the restriction information, generating a target program through a target model;

[0010] Based on the target program, a chemical space corresponding to the target file is determined.

[0011] In a possible implementation, the obtaining of the property information of the substituents in the chemical molecule structure and the restriction information of the substituents by the recognition model includes:

[0012] Using the recognition model, the target file is divided into image information and text information;

[0013] Identify the image information and the text information to obtain the attribute information of the substituent;

[0014] The text information is identified to obtain restriction information of the substituent.

[0015] In a possible implementation manner, the identifying the image information and the text information to obtain the property information of the substituent includes:

[0016] Identify the image information to obtain label information and coordinate information of the chemical molecule structure formula;

[0017] Based on the label information and the coordinate information, determining text sub-information corresponding to the chemical molecule structure formula from the text information;

[0018] Based on the image information and the text sub-information, attribute information of the substituents of each chemical molecule structural formula is determined, the attribute information including the number of substituents and the serial number of each substituent.

[0019] In a possible implementation, identifying the text information to obtain restriction information of the substituent includes:

[0020] Identifying the text information to determine the substituents belonging to the chemical molecule structure formula;

[0021] Descriptive information for each of the substituents is extracted.

[0022] In a possible implementation, determining the chemical space corresponding to the target file based on the target program includes:

[0023] Executing the target program to obtain a first molecular entity corresponding to the chemical molecular structure of the first type;

[0024] Determining a chemical space corresponding to the target file based on the first molecular entity and the second molecular entity;

[0025] The second molecular entity is a chemical molecular structure formula belonging to a second type, and the second type characterizes that the chemical molecular structure formula is a molecular entity.

[0026] In a possible implementation manner, the determination method further includes:

[0027] determining all third molecular entities in the target file;

[0028] Based on the target algorithm, determining whether all third molecular entities are included in the chemical space;

[0029] If not, the recognition model and / or the target model are adjusted until all third molecular entities are included in the chemical space.

[0030] In a second aspect, the embodiment of the present application further provides a device for determining a chemical space, which includes:

[0031] An acquisition module, configured to acquire a target file, wherein the target file includes one or more chemical molecular structure formulas;

[0032] An identification module configured to identify the target file through a recognition model to obtain the type to which each chemical molecule structure belongs;

[0033] an obtaining module configured to obtain, by using the recognition model, attribute information of a substituent in the chemical molecular structure and restriction information of the substituent when the type to which the chemical molecular structure belongs is a first type, wherein the first type indicates that the chemical molecular structure includes a substituent;

[0034] A generating module configured to generate a target program through a target model based on the attribute information and the restriction information;

[0035] A determination module is configured to determine the chemical space corresponding to the target file based on the target program.

[0036] In a possible implementation manner, the determining device further includes an adjustment module, which is configured to:

[0037] determining all third molecular entities in the target file;

[0038] Based on the target algorithm, determining whether all third molecular entities are included in the chemical space;

[0039] If not, the recognition model and / or the target model are adjusted until all third molecular entities are included in the chemical space.

[0040] In a third aspect, an embodiment of the present application further provides a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the method for determining the chemical space as described in any one of the above are executed.

[0041] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through a bus, and when the machine-readable instructions are executed by the processor, the steps of the method for determining the chemical space as described in any one of the above are performed.

[0042] Compared with the prior art of manually determining the chemical space, the present application obtains the attribute information of the substituents in the chemical molecular structure and the restriction information of the substituents through the recognition model, and based on the attribute information and the restriction information, determines the chemical space corresponding to the target file through the target model. The chemical space corresponding to the target file can be determined without manual participation, and the efficiency and degree of automation are high. At the same time, it avoids omissions when manually extracting and enumerating the possible structures of the substituents, thereby improving the accuracy of the determined chemical space.

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present application or 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 recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0045] Figure 1 A flow chart showing a method for determining a chemical space provided in the present application is shown;

[0046] Figure 2 A schematic diagram showing the general structural formula provided by the present application;

[0047] Figure 3 A schematic diagram of a molecular fragment provided by the present application is shown;

[0048] Figure 4 Schematic diagrams of molecular entities provided in the present application are shown;

[0049] Figure 5A flow chart showing the method for determining the chemical space provided in the present application for identifying the image information and text information to obtain the attribute information of the substituent;

[0050] Figure 6 A flowchart showing the identification of text information and obtaining restriction information of substituents in the method for determining the chemical space provided by the present application is shown;

[0051] Figure 7 A flow chart showing the accuracy of the determination method in the chemical space determination method provided in the present application is shown;

[0052] Figure 8 A schematic diagram of the structure of a device for determining a chemical space provided in the present application is shown;

[0053] Fig. 9 A schematic structural diagram of an electronic device provided in the present application is shown. DETAILED DESCRIPTION

[0054] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0055] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0056] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0057] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0058] It should also be understood that, although the present application has been described with reference to some specific examples, those skilled in the art will be able to implement many other equivalent forms of the present application that have the features described in the claims and are therefore within the scope of protection defined thereby.

[0059] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0060] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0061] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0062] In the first aspect, in order to facilitate the understanding of the present application, a method for determining a chemical space provided by the present application is first introduced in detail. Figure 1 As shown, a method for determining a chemical space provided in an embodiment of the present application includes specific steps S101-S105.

[0063] S101, obtaining a target file, wherein the target file includes one or more chemical molecular structure formulas.

[0064] In a specific implementation, the target file may be a chemical document, a special document, a journal, etc. When obtaining the target file, if the target file is an electronic file, the electronic file can be directly obtained; if it is a paper file, the target file is scanned by a scanning device or an image acquisition device is used to acquire an image of the target file, etc., to obtain the electronic file of the target file. Of course, the target file can remain a paper file, and its corresponding chemical space can also be determined.

[0065] The target file includes one or more chemical molecular structure formulas.

[0066] S102, identifying the target file through a recognition model to obtain the type to which each chemical molecule structure formula belongs.

[0067] Here, the recognition model is constructed in advance, and the constructed recognition model is trained through a large number of data samples to obtain a trained recognition model. The recognition model uses an optical character recognition (OCR) algorithm, and OCR can recognize electronic files or paper files (for example, the recognition model is set on a scanning device or an image acquisition device).

[0068] The target file is identified by the recognition model to obtain the type of each chemical molecular structure. Here, the chemical molecular structure usually exists in the target file in the form of a picture. Therefore, the picture OCR algorithm in the recognition model is used to identify the pictures in the target file one by one, screen out the pictures including the chemical molecular structure, and further determine the type of each chemical molecular structure. Compared with manual recognition, the recognition model has higher recognition efficiency and accuracy, which effectively avoids the omissions existing in manual recognition.

[0069] In a specific implementation, it is determined whether the chemical molecular structure formula includes a substituent to determine the type to which the chemical molecular structure formula belongs. Optionally, if the chemical molecular structure formula includes a substituent, the type to which the chemical molecular structure formula belongs is determined to be the first type, for example Figure 2 A schematic diagram showing the general structural formula and Figure 3 A schematic diagram of the molecular fragments shown, consisting of Figure 2 and Figure 3 It can be seen that Figure 2 The general structural formula and Figure 3 The molecular fragments in include substituents, that is, Figure 2 The general structural formula and Figure 3 The types of molecular fragments in are all of the first type. If the chemical molecular structure does not include substituents, for example Figure 4 Schematic diagram of the molecular entity shown, Figure 4 The chemical molecular structure formula in is a molecular entity which does not include a substituent. In this case, the type to which the chemical molecular structure formula belongs is determined to be the second type. It is worth noting that the substituents included in the chemical molecular structure formula of the first type may be one or more.

[0070] S103, when the type to which the chemical molecular structure belongs is the first type, obtaining attribute information of substituents and restriction information of substituents in the chemical molecular structure through a recognition model, the first type indicating that the chemical molecular structure includes substituents.

[0071] When the chemical molecular structure is identified and determined to be of the first type, that is, the chemical molecular structure includes substituents, attribute information of the substituents and restriction information of the substituents in the chemical molecular structure are obtained through the identification model.

[0072] The attribute information of the substituent includes the optional groups, quantity and number of each substituent, and the restriction information of the substituent includes the description information for each substituent and the description information for the relationship between two or more substituents.

[0073] Optionally, considering that the target file may include both image information and text information, based on this, when the attribute information of the substituents in the chemical molecule structure and the restriction information of the substituents are obtained through the recognition model, the target file is divided into image information and text information through the recognition model, and the image information includes the image, and the text information includes the text content. Afterwards, the image information and the text information are identified to obtain the attribute information of the substituents, and the text information is identified to obtain the restriction information of the substituents. The embodiment of the present application identifies the image information and the text information respectively, which can improve the accuracy of the identification of the image information and the text information, that is, improve the accuracy of the identification of the target file.

[0074] S104: Generate a target program through a target model based on the attribute information and the restriction information.

[0075] After obtaining the attribute information of the substituents and the restriction information of the substituents in the first type of chemical molecular structure, a target program is generated through a target model based on the attribute information and the restriction information.

[0076] Optionally, the target model is a large language model under the framework of an artificial intelligence agent (AI Agent), and the large language model under the AI ​​Agent framework can automatically generate code and execute the program corresponding to the code. In an embodiment of the present application, the attribute information and restriction information of the substituents in all chemical molecular structural formulas are input into the target model, and the target model is programmed based on the attribute information and restriction information to automatically generate the target code, and then generate the corresponding target program. Here, the target model can automatically generate the corresponding target program based on the attribute information and restriction information, without the need to manually write code, and the requirements for generating the target program are relatively low, and for different attribute information and restriction information, different target programs are generated, which improves the pertinence based on the target file, and then can improve the accuracy of the chemical space corresponding to the subsequent determination of the target file.

[0077] Among them, the target program can realize automatic enumeration of possible structures of substituents in chemical molecular structural formulas, and the enumerated structures meet the restriction conditions corresponding to the restriction information, that is, the possible structures of substituents can be obtained without human participation, with a high degree of automation. At the same time, the enumeration efficiency is improved, and compared with manual work, the enumeration results obtained through the target model are more accurate, which prevents omissions during enumeration.

[0078] S105, determining the chemical space corresponding to the target file based on the target program.

[0079] After obtaining the target program, the target model executes the target program to determine the chemical space corresponding to the target file. Compared with the prior art that manually determines the chemical space, the present application obtains the attribute information of the substituents in the chemical molecular structure and the restriction information of the substituents through the recognition model, and based on the attribute information and the restriction information, determines the chemical space corresponding to the target file through the target model, and can determine the chemical space corresponding to the target file without manual participation, with high efficiency and automation. At the same time, it avoids the omission of manual extraction and enumeration of possible structures of substituents, and improves the accuracy of the determined chemical space.

[0080] As one example, when determining the chemical space corresponding to the target file based on the target program, the target program is executed to obtain the first molecular entity corresponding to the first type of chemical molecular structure, that is, for each chemical molecular structure of the first type, the target model executes the target program, and can calculate the possible structure of each substituent in the chemical molecular structure based on the attribute information and restriction information corresponding to the chemical molecular structure. For example Figure 2 The general structural formula shown in FIG. includes R 1 , R 2 , R 5 , R 6 , R 7 , R 8 , R 9 , R 10 and R 11 There are 9 substituents in total. After executing the target program through the target model, the structural combinations formed by the possible structures of the above 9 substituents can be obtained, and a complete first molecular entity can be obtained using each structural combination.

[0081] As one example, the target model calculates all possible structural combinations based on the number of substituents and the numbers of the substituents. For example, each structural combination is calculated according to R 1 , R 2 , R 5 , R 6 , R 7 , R 8 , R 9 , R 10 and R 11 Then, the target model deletes the structural combinations that do not meet the restriction conditions corresponding to the restriction information in all structural combinations based on the restriction information of all substituents, and then replaces the corresponding substituents with the structures in each structural combination to obtain the first molecular entity. Of course, for each chemical molecular structure formula belonging to the first type, the number of first molecular entities is the number of structural combinations that meet the restriction conditions.

[0082] It is worth noting that the recognition model and the target model can be respectively set as a model block in the same large model, so that the target model can directly obtain the recognition result obtained by the recognition model, and the recognition result includes the type to which each chemical molecule structure in the target file belongs, the attribute information of the substituent in the chemical molecule structure of the first type, and the restriction information of the substituent, etc. Of course, the recognition model and the target model can also be set as two independent models, and the recognition model and the target model can communicate to realize data transmission, so that the recognition model transmits the recognition result it recognizes to the target model. The embodiment of the present application does not specifically limit this.

[0083] Based on any of the above methods, the target model can obtain the second molecular entity identified by the recognition model, that is, the chemical molecular structure of the second type. Then, the target model determines the chemical space corresponding to the target file based on the first molecular entity and the second molecular entity.

[0084] Optionally, Figure 5 A flow chart of a method for identifying image information and text information to obtain property information of a substituent is shown, wherein specific steps include S501-S503.

[0085] S501, identifying the image information to obtain label information and coordinate information of the chemical molecule structure formula.

[0086] S502: Determine text sub-information corresponding to the chemical molecule structure formula from the text information based on the tag information and the coordinate information.

[0087] S503, based on the image information and the text sub-information, determining the attribute information of the substituents of each chemical molecule structure formula, the attribute information including the number of the substituents and the serial number of each substituent.

[0088] In a specific implementation, based on the fact that the target file can include both image information and text information, a recognition model is set to include an image sub-recognition model and a text sub-recognition model, wherein the image sub-recognition model includes an OCR algorithm for images, and the text sub-recognition model includes an OCR algorithm and / or a PDF parsing algorithm for text.

[0089] Based on this, the image information is identified through the image sub-recognition model to obtain the label information and coordinate information of the chemical molecular structure formula, wherein the label information of the chemical molecular structure formula includes the name and logo of the chemical molecular structure formula, and the label information of the chemical molecular structure formula can be text information in the picture corresponding to the chemical molecular structure formula, and the label information of the chemical molecular structure formula is usually marked in the picture corresponding to the chemical molecular structure formula, and the distance between the label information and the chemical molecular structure formula is less than a predetermined value. When the distance between the chemical molecular structure formula and the label information is less than a predetermined value, it indicates that the chemical molecular structure formula corresponds to the label information one by one. The coordinate information of the chemical molecular structure formula includes the coordinate range of the chemical molecular structure formula in the pixel coordinate system of the corresponding picture, the coordinate range of each structure in the chemical molecular structure formula, etc.

[0090] Furthermore, based on the tag information and the coordinate information, the text sub-information corresponding to the chemical molecular structure formula is determined from the text information. Here, the text information usually includes a description of the image information, and therefore, the text information includes text such as the name and logo of the chemical molecular structure formula. Thus, the text sub-recognition model is used to select the text block containing the name and logo of the chemical molecular structure formula as the target text block. At the same time, the image sub-recognition model is used to calculate the distance between each text block in the text information and the chemical molecular structure formula for the target file, and the text block with a distance less than a threshold is used as the target text block. Afterwards, the set of target text blocks is determined as the text sub-information corresponding to the chemical molecular structure formula.

[0091] After obtaining the text sub-information of each chemical molecular structure, the attribute information of the substituents of each chemical molecular structure is determined based on the image information and the text sub-information. The attribute information includes the number of substituents and the number of each substituent, such as Figure 3 In the chemical molecular structure shown, the attribute information of the substituents includes that the number of substituents is 2, and the numbers of the substituents are R 3 and R 4 Of course, the property information may also include the position of the substituent, the relative position between two or more substituents, and the like.

[0092] As one example, Figure 6 A flow chart of a method for identifying text information and obtaining restriction information of substituents is shown, wherein specific steps include S601 and S602.

[0093] S601, identifying the text information and determining the substituents belonging to the chemical molecule structure formula.

[0094] S602: extracting description information for each substituent.

[0095] In a specific implementation, the text information in the target file may contain description information for substituents, which may be all substituents included in the image information or some substituents included in the image information. Based on this, the text information is identified through the text sub-recognition model to determine the substituents belonging to the same chemical molecular structure.

[0096] At the same time, the descriptive information of the substituents for the same chemical molecular structure formula in the text information is extracted, for example, the substituent R in the chemical molecular structure formula 1 3 =[-CH2-,N,S,-C=OCC],R 4 =[-CH3,N],R 6 , R 7 , R 8 , R 9 and R 10 At least three of them are heteroatoms, etc. The restriction information is composed of the description information of the substituents, and the restriction information of all substituents is the restriction information of their corresponding chemical molecular structure. It is worth noting that the restriction information forms the restriction conditions for the substituents or chemical molecular structure.

[0097] As one example, Figure 7 A flow chart of a method for verifying the accuracy of a method for determining a chemical space is shown, wherein specific steps include S701-S703.

[0098] S701, determining all third molecular entities in the target file.

[0099] S702, based on the target algorithm, determining whether the chemical space includes all third molecular entities.

[0100] S703: If not, adjust the recognition model and / or the target model until all third molecular entities are included in the chemical space.

[0101] In a specific implementation, all the instances in the target file are used to determine all the third molecular entities in the target file, that is, the chemical molecular structural formula whose structure clearly does not include a substituent. Afterwards, it is determined based on the target algorithm whether all the third molecular entities are included in the chemical space, that is, whether there is a first molecular entity or a second molecular entity that is the same as the third molecular entity among all the first molecular entities and the second molecular entities included in the chemical space. Optionally, the target algorithm includes a maximum common substructure (MCS).

[0102] If so, then all third molecular entities are included in the characterization chemical space, that is, the accuracy of the above-mentioned chemical space determination method is high, and the accuracy of the chemical space determined is also high. If not, then all third molecular entities are not included in the characterization chemical space, that is, the structure of the substituents enumerated by the above-mentioned chemical space determination method or the molecular entity is omitted. At this time, the recognition model and / or the target model are adjusted until all third molecular entities are included in the chemical space. Among them, the adjustment of the recognition model and / or the target model in the embodiment of the present application is not elaborated in detail, and those skilled in the art can easily obtain and implement the method and steps for adjusting the recognition model and / or the target model.

[0103] The embodiment of the present application verifies the accuracy of the above determination method, thereby ensuring the accuracy of the chemical space determined by the above determination method, improving the credibility of the chemical space determined by the above determination method and the reliability of the above determination method.

[0104] Based on the same inventive concept, the second aspect of the present application also provides a device for determining a chemical space. Since the principle of solving the problem by the device in the present application is similar to the method for determining the chemical space mentioned above in the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0105] See also Figure 8 As shown, the chemical space determination device includes:

[0106] An acquisition module 801 is configured to acquire a target file, wherein the target file includes one or more chemical molecular structure formulas;

[0107] An identification module 802 is configured to identify the target file through a recognition model to obtain the type to which each chemical molecule structure belongs;

[0108] an obtaining module 803, which is configured to obtain, by using the recognition model, attribute information of substituents in the chemical molecular structure and restriction information of the substituents when the type to which the chemical molecular structure belongs is a first type, wherein the first type indicates that the chemical molecular structure includes substituents;

[0109] A generating module 804, configured to generate a target program through a target model based on the attribute information and the restriction information;

[0110] The determination module 805 is configured to determine the chemical space corresponding to the target file based on the target program.

[0111] In another embodiment, the determining device further includes an adjustment module 806, which is configured to:

[0112] determining all third molecular entities in the target file;

[0113] Based on the target algorithm, determining whether all third molecular entities are included in the chemical space;

[0114] If not, the recognition model and / or the target model are adjusted until all third molecular entities are included in the chemical space.

[0115] In another embodiment, the obtaining module 803 is specifically configured as follows:

[0116] Using the recognition model, the target file is divided into image information and text information;

[0117] Identify the image information and the text information to obtain the attribute information of the substituent;

[0118] The text information is identified to obtain restriction information of the substituent.

[0119] In yet another embodiment, the obtaining module 803 is further configured to:

[0120] Identify the image information to obtain label information and coordinate information of the chemical molecule structure formula;

[0121] Based on the label information and the coordinate information, determining text sub-information corresponding to the chemical molecule structure formula from the text information;

[0122] Based on the image information and the text sub-information, attribute information of the substituents of each chemical molecule structural formula is determined, the attribute information including the number of substituents and the serial number of each substituent.

[0123] In yet another embodiment, the obtaining module 803 is further configured to:

[0124] Identifying the text information to determine the substituents belonging to the chemical molecule structure formula;

[0125] Descriptive information for each of the substituents is extracted.

[0126] In yet another embodiment, the determination module 805 is specifically configured as follows:

[0127] Executing the target program to obtain a first molecular entity corresponding to the chemical molecular structure of the first type;

[0128] Determining a chemical space corresponding to the target file based on the first molecular entity and the second molecular entity;

[0129] The second molecular entity is a chemical molecular structure formula belonging to a second type, and the second type characterizes that the chemical molecular structure formula is a molecular entity.

[0130] Compared with the prior art of manually determining the chemical space, the present application obtains the attribute information of the substituents in the chemical molecular structure and the restriction information of the substituents through the recognition model, and based on the attribute information and the restriction information, determines the chemical space corresponding to the target file through the target model. The chemical space corresponding to the target file can be determined without manual participation, and the efficiency and degree of automation are high. At the same time, it avoids omissions when manually extracting and enumerating the possible structures of the substituents, thereby improving the accuracy of the determined chemical space.

[0131] The third aspect of the present application further provides a storage medium, which is a computer-readable medium and stores a computer program. When the computer program is executed by a processor, the method provided in any embodiment of the present application is implemented, including the following steps:

[0132] S11, obtaining a target file, wherein the target file includes one or more chemical molecular structure formulas;

[0133] S12, identifying the target file through a recognition model to obtain the type to which each chemical molecule structure formula belongs;

[0134] S13, when the type to which the chemical molecular structure belongs is the first type, obtaining attribute information of substituents in the chemical molecular structure and restriction information of the substituents through the recognition model, wherein the first type indicates that the chemical molecular structure includes substituents;

[0135] S14, generating a target program through a target model based on the attribute information and the restriction information;

[0136] S15, determining the chemical space corresponding to the target file based on the target program.

[0137] Compared with the prior art of manually determining the chemical space, the present application obtains the attribute information of the substituents in the chemical molecular structure and the restriction information of the substituents through the recognition model, and based on the attribute information and the restriction information, determines the chemical space corresponding to the target file through the target model. The chemical space corresponding to the target file can be determined without manual participation, and the efficiency and degree of automation are high. At the same time, it avoids omissions when manually extracting and enumerating the possible structures of the substituents, thereby improving the accuracy of the determined chemical space.

[0138] It should be noted that the storage medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any storage medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0139] The fourth aspect of the present application also provides an electronic device, such as Fig. 9 As shown, the electronic device at least includes a memory 901 and a processor 902. The memory 901 stores a computer program. The processor 902 implements the method provided by any embodiment of the present application when executing the computer program on the memory 901. Exemplarily, the method executed by the electronic device computer program is as follows:

[0140] S21, obtaining a target file, wherein the target file includes one or more chemical molecular structure formulas;

[0141] S22, identifying the target file through a recognition model to obtain the type to which each chemical molecule structure formula belongs;

[0142] S23, when the type to which the chemical molecular structure belongs is the first type, obtaining attribute information of substituents in the chemical molecular structure and restriction information of the substituents through the recognition model, wherein the first type indicates that the chemical molecular structure includes substituents;

[0143] S24, generating a target program through a target model based on the attribute information and the restriction information;

[0144] S25, determining the chemical space corresponding to the target file based on the target program.

[0145] Compared with the prior art of manually determining the chemical space, the present application obtains the attribute information of the substituents in the chemical molecular structure and the restriction information of the substituents through the recognition model, and based on the attribute information and the restriction information, determines the chemical space corresponding to the target file through the target model. The chemical space corresponding to the target file can be determined without manual participation, and the efficiency and degree of automation are high. At the same time, it avoids omissions when manually extracting and enumerating the possible structures of the substituents, thereby improving the accuracy of the determined chemical space.

[0146] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0147] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other.

[0148] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0149] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

[0150] The above describes in detail several embodiments of the present application, but the present application is not limited to these specific embodiments. Technical personnel in this field can make various variations and modifications to the embodiments based on the concept of the present application, and these variations and modifications should all fall within the scope of protection claimed by the present application.

Claims

1. A method for determining a chemical space, characterized in that: include: Acquire a target file, wherein the target file includes one or more chemical molecular structure formulas; Identify the target file through a recognition model to obtain the type to which each chemical molecule structure formula belongs; In the case where the type to which the chemical molecular structure belongs is the first type, obtaining attribute information of substituents in the chemical molecular structure and restriction information of the substituents through the recognition model, wherein the first type indicates that the chemical molecular structure includes substituents; Based on the attribute information and the restriction information, generating a target program through a target model; Based on the target program, a chemical space corresponding to the target file is determined.

2. The determination method according to claim 1, characterized in that: The obtaining of the property information of the substituents in the chemical molecular structure and the restriction information of the substituents through the recognition model includes: Using the recognition model, the target file is divided into image information and text information; Identify the image information and the text information to obtain the attribute information of the substituent; The text information is identified to obtain restriction information of the substituent.

3. The determination method according to claim 2, characterized in that: The image information and the text information are identified to obtain the property information of the substituent, including: Identify the image information to obtain label information and coordinate information of the chemical molecule structure formula; Based on the label information and the coordinate information, determining text sub-information corresponding to the chemical molecule structure formula from the text information; Based on the image information and the text sub-information, attribute information of the substituents of each chemical molecule structural formula is determined, the attribute information including the number of substituents and the serial number of each substituent.

4. The determination method according to claim 2, characterized in that: The identifying of the text information to obtain the restriction information of the substituent includes: Identifying the text information to determine the substituents belonging to the chemical molecule structure formula; Descriptive information for each of the substituents is extracted.

5. The determination method according to claim 1, characterized in that: The step of determining the chemical space corresponding to the target file based on the target program includes: Executing the target program to obtain a first molecular entity corresponding to the chemical molecular structure of the first type; Determining a chemical space corresponding to the target file based on the first molecular entity and the second molecular entity; The second molecular entity is a chemical molecular structure formula belonging to a second type, and the second type characterizes that the chemical molecular structure formula is a molecular entity.

6. The determination method according to claim 1, characterized in that: Also includes: determining all third molecular entities in the target file; Based on the target algorithm, determining whether all third molecular entities are included in the chemical space; If not, the recognition model and / or the target model are adjusted until all third molecular entities are included in the chemical space.

7. A device for determining a chemical space, characterized in that: include: An acquisition module, configured to acquire a target file, wherein the target file includes one or more chemical molecular structure formulas; An identification module configured to identify the target file through a recognition model to obtain the type to which each chemical molecule structure belongs; an obtaining module configured to obtain, by using the recognition model, attribute information of a substituent in the chemical molecular structure and restriction information of the substituent when the type to which the chemical molecular structure belongs is a first type, wherein the first type indicates that the chemical molecular structure includes a substituent; A generating module configured to generate a target program through a target model based on the attribute information and the restriction information; A determination module is configured to determine the chemical space corresponding to the target file based on the target program.

8. The determination device according to claim 7, characterized in that: Also included is the tuning module, which is configured as: determining all third molecular entities in the target file; Based on the target algorithm, determining whether all third molecular entities are included in the chemical space; If not, the recognition model and / or the target model are adjusted until all third molecular entities are included in the chemical space.

9. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for determining the chemical space as claimed in any one of claims 1 to 6.

10. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via a bus, and when the machine-readable instructions are executed by the processor, the steps of the method for determining the chemical space as described in any one of claims 1 to 6 are performed.

Images