Molecule generation method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a molecule generation method and device, electronic equipment and storage medium, and relates to the fields of artificial intelligence such as biological computing and deep learning. The method can include: obtaining a first molecule to be processed, and obtaining a synthesis route of the first molecule as an original synthesis route; modifying the original synthesis route to obtain a target synthesis route; and generating a second molecule required according to the target synthesis route. The scheme disclosed in the present disclosure can improve the generation efficiency of molecules and the quality of generated molecules.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to a molecule generation method and device, an electronic device and a storage medium in the fields of biological computing and deep learning. BACKGROUND

[0002] Molecule structure editing is a common method for generating new molecules. Existing research and products often directly edit the structure of molecules to obtain new molecules, but this approach is prone to structural conflicts, i.e., generating molecules that cannot be synthesized or do not actually exist. SUMMARY

[0003] The present disclosure provides a molecule generation method, device, electronic device and storage medium.

[0004] A molecule generation method comprises:

[0005] obtaining a first molecule to be processed, and obtaining a synthesis route of the first molecule as an original synthesis route;

[0006] modifying the original synthesis route to obtain a target synthesis route;

[0007] generating a second molecule required according to the target synthesis route.

[0008] A molecule generation device comprises a route obtaining module, a route modifying module and a molecule generation module.

[0009] The route obtaining module is configured to obtain a first molecule to be processed, and obtain a synthesis route of the first molecule as an original synthesis route;

[0010] The route modifying module is configured to modify the original synthesis route to obtain a target synthesis route;

[0011] The molecule generation module is configured to generate a second molecule required according to the target synthesis route.

[0012] An electronic device comprises:

[0013] at least one processor; and

[0014] a memory connected to the at least one processor in communication; wherein

[0015] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method as described above.

[0016] A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method as described above.

[0017] A computer program product comprising computer programs / instructions which, when executed by a processor, implement the method as described above.

[0018] It should be understood that the contents described in this part are not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0020] Figure 1 Flow chart of the first embodiment of the molecule generation method described in the present disclosure;

[0021] Figure 2 First schematic diagram of the first molecule, original synthetic route, target synthetic route and second molecule described in the present disclosure;

[0022] Figure 3 Second schematic diagram of the first molecule, original synthetic route, target synthetic route and second molecule described in the present disclosure;

[0023] Figure 4 Third schematic diagram of the first molecule, original synthetic route, target synthetic route and second molecule described in the present disclosure;

[0024] Figure 5 Flow chart of the second embodiment of the molecule generation method described in the present disclosure;

[0025] Figure 6 Schematic diagram of the component structure of the molecule generation device embodiment 600 described in the present disclosure;

[0026] Figure 7 A schematic block diagram of an electronic device 700 that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0027] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to assist in understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, descriptions of well-known functions and structures are omitted in the following description.

[0028] In addition, it should be understood that the term "and / or" herein merely describes an associated relationship with the associated objects, which means that there can be three relationships, for example, A and / or B can represent the existence of A alone, the existence of A and B together, and the existence of B alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0029] Figure 1 A flowchart of a first embodiment of a method for generating molecules according to the present disclosure is shown in FIG. 1. As shown in FIG. 1, the method includes the following specific implementation. Figure 1

[0030] In step 101, a first molecule to be processed is obtained, and a synthesis route of the first molecule is obtained as an original synthesis route.

[0031] In step 102, the original synthesis route is modified to obtain a target synthesis route.

[0032] In step 103, a second molecule required is generated according to the target synthesis route.

[0033] By using the above method embodiment, a new molecule can be generated by modifying the synthesis route, thereby bypassing the structural conflict risk caused by directly editing the original molecule structure, and improving the generation efficiency of the molecule and the quality of the generated molecule.

[0034] Generally, the first molecule can be any molecule. An effective standard for determining whether a molecule structure can exist or can be synthesized is to determine whether its synthesis route exists and is feasible. The synthesis route refers to starting from analyzing the chemical structure of the target molecule, comprehensively using the knowledge of organic chemical reaction methods and reaction mechanisms according to the characteristics of the connection between each part of the target molecule, selecting appropriate chemical bonds to cut, thereby converting the target molecule into some smaller intermediates, and then cutting the intermediates into smaller intermediates as new target molecules, and so on, until the starting material that can be easily obtained is found.

[0035] Correspondingly, for the first molecule, its synthesis route can be obtained first. For ease of distinction, the synthesis route of the first molecule can be referred to as the original synthesis route. In some embodiments of the present disclosure, the first molecule can be used as the input of a pre-trained first model, so as to obtain the original synthesis route output by the first model.

[0036] How to train the first model is not limited. For example, training samples can be constructed first, each training sample can include a molecule and a corresponding synthesis route, and then the constructed training samples can be used to train the first model, and the trained first model can be used for actual synthesis route generation. ​

[0037] Correspondingly, by means of the first model, the required original synthesis route can be efficiently and accurately obtained for the first molecule, thereby laying a good foundation for subsequent processing.

[0038] For the original synthesis route, modification can be performed to obtain a target synthesis route. In actual application, a pre-set modification rule can be obtained, which can be formulated by an expert, and then the original synthesis route can be modified according to the modification rule.

[0039] In some embodiments of the present disclosure, modifying the original synthesis route can include one or any combination of the following: deleting part of the sub-synthesis routes in the original synthesis route, replacing part of the sub-synthesis routes in the original synthesis route with new sub-synthesis routes, and adding new sub-synthesis routes to the original synthesis route.

[0040] That is to say, the modification in the scheme of the present disclosure mainly includes three modification methods, which are deletion, replacement and addition. By means of the three modification methods, various modification requirements of different users can be met, and the controllability of the generated new molecules can be improved, etc.

[0041] The modified original synthesis route can be used as a target synthesis route, and a required second molecule can be generated according to the target synthesis route.

[0042] Figure 2 A first schematic diagram of the first molecule, the original synthesis route, the target synthesis route and the second molecule according to the present disclosure is shown in FIG. 1. Figure 2 As shown, part of the sub-synthesis routes in the original synthesis route can be deleted, as shown in the dashed box, by performing the deletion operation, the target synthesis route can be obtained, and then the second molecule shown in FIG. 2 can be generated according to the target synthesis route. The modification corresponds to the highlighted part in the first molecule and the second molecule. Figure 2

[0043] A third schematic diagram of the first molecule, the original synthesis route, the target synthesis route and the second molecule according to the present disclosure is shown in FIG. 3. Figure 3 As shown, new sub-synthesis routes can be added to the original synthesis route, as shown in the dashed box, by performing the addition operation, the target synthesis route can be obtained, and then the second molecule shown in FIG. 4 can be generated according to the target synthesis route. The modification corresponds to the highlighted part in the first molecule and the second molecule. Figure 3 Figure 3 A third schematic diagram of the first molecule, the original synthesis route, the target synthesis route and the second molecule according to the present disclosure is shown in FIG. 3.

[0044] As shown, new sub-synthesis routes can be added to the original synthesis route, as shown in the dashed box, by performing the addition operation, the target synthesis route can be obtained, and then the second molecule shown in FIG. 4 can be generated according to the target synthesis route. The modification corresponds to the highlighted part in the first molecule and the second molecule. Figure 4 Figure 4 ​As shown, part of the original synthesis route can be replaced by a new sub-synthesis route, as shown in the dashed box, by performing the replacement operation, the target synthesis route can be obtained, and then the second molecule can be generated according to the target synthesis route Figure 4 The second molecule shown in the middle is modified according to the first molecule and the bolded part of the second molecule.

[0045] In some embodiments of the present disclosure, the target synthesis route is a tree structure, which includes nodes and connection relationships between nodes. Accordingly, the way of generating the second molecule according to the target synthesis route can include: according to the modification, updating the content of the relevant nodes in the tree structure in a bottom-up order, and taking the updated root node as the second molecule.

[0046] Both the original synthesis route and the target synthesis route are tree structures. As shown, Figures 2 to 4 Each circle in the figure can represent a node, the root node represents the molecule corresponding to the tree structure, and the other nodes represent intermediates and the like.

[0047] For the target synthesis route, the content (such as molecular structure) of the relevant nodes in the tree structure of the target synthesis route can be updated in a bottom-up order according to the modification compared with the original synthesis route, and the updated root node can be taken as the second molecule. For example, Figure 4 As shown in the target synthesis route, when the replacement is performed, the content of each node in the upper layer of the replaced node (dashed box) needs to be updated accordingly. The update can be performed in a bottom-up order, and after the update is completed, the root node can be taken as the generated second node.

[0048] Through the above processing, the second molecule can be generated based on the target synthesis route, thereby improving the synthesizability and effectiveness of the new molecule generated after the modification.

[0049] In some embodiments of the present disclosure, the modification of the original synthesis route can also include: verifying the rationality of the original synthesis route, and in response to determining that the verification passes, modifying the original synthesis route, and / or generating the second molecule according to the target synthesis route can also include: verifying the rationality of the target synthesis route, and in response to determining that the verification passes, generating the second molecule according to the target synthesis route.

[0050] That is, after obtaining the original synthesis route, the rationality of the original synthesis route can be checked. If it is determined that the check passes, the original synthesis route can be modified, otherwise, error processing or re-generating the original synthesis route can be performed, and the specific manner is not limited. Similarly, after obtaining the target synthesis route, the rationality of the target synthesis route can be checked. If it is determined that the check passes, the second molecule can be generated according to the target synthesis route, otherwise, error processing can be performed, and the specific manner is also not limited.

[0051] By checking, it can be determined that the obtained original synthesis route and target synthesis route are reasonable and effective synthesis routes, thereby improving the quality of the obtained original synthesis route and target synthesis route, and further improving the quality of the generated molecule.

[0052] In some embodiments of the present disclosure, the way of checking the rationality of the original synthesis route can include: taking the original synthesis route as the input of the second model trained in advance to obtain the output first rationality score, and determining that the check passes in response to determining that the first rationality score is greater than a predetermined threshold. Similarly, the way of checking the rationality of the target synthesis route can include: taking the target synthesis route as the input of the second model to obtain the output second rationality score, and determining that the check passes in response to determining that the second rationality score is greater than the threshold. The specific value of the threshold can be determined according to actual needs.

[0053] How to train the second model is not limited. For example, training samples can be constructed first, each training sample can include a synthesis route and a corresponding rationality score, then the constructed training samples can be used to train the second model, and then the trained second model can be used for actual rationality score generation.

[0054] Alternatively, in some embodiments of the present disclosure, the way of checking the rationality of the original synthesis route can also include: determining that the check passes in response to determining that the original synthesis route meets a predetermined rationality evaluation rule, and the way of checking the rationality of the target synthesis route can also include: determining that the check passes in response to determining that the target synthesis route meets the rationality evaluation rule.

[0055] That is, the rationality of the original synthetic route and the target synthetic route can be checked by means of the second model, or the rationality of the original synthetic route and the target synthetic route can be directly checked by using the rationality evaluation rule. Which way to use can be determined according to actual needs, which is very flexible and convenient. In addition, what the rationality evaluation rule specifically includes can also be determined according to actual needs. Taking the original synthetic route as an example, if it is determined that the structure and the included content thereof meet the rationality evaluation rule, it is determined that the rationality check of the original synthetic route is passed. In addition, if necessary, the rationality evaluation rule can be updated at any time.

[0056] In combination with the above introduction, Figure 5 The flowchart of the second embodiment of the molecule generation method of the present disclosure is shown in FIG. 5. As shown in FIG. 5, the following specific implementation modes are included. Figure 5

[0057] In step 501, a first molecule to be processed is obtained, and a synthetic route of the first molecule is obtained as an original synthetic route.

[0058] For example, the first molecule can be taken as an input of a first model trained in advance to obtain an output original synthetic route.

[0059] In step 502, the rationality of the original synthetic route is checked, and it is determined whether the check is passed. If yes, step 503 is performed, otherwise, the flow is ended.

[0060] In this embodiment, it is assumed that the check is not passed and the flow is ended.

[0061] The original synthetic route can be taken as an input of a second model to obtain an output first rationality score. If it is determined that the first rationality score is greater than a predetermined threshold, it is determined that the check is passed. Alternatively, if it is determined that the original synthetic route meets a predetermined rationality evaluation rule, it is determined that the check is passed.

[0062] In step 503, the original synthetic route is modified to obtain a target synthetic route.

[0063] The modification can include one or any combination of the following: deleting part of the sub-synthetic routes in the original synthetic route, replacing part of the sub-synthetic routes in the original synthetic route with new sub-synthetic routes, and adding new sub-synthetic routes to the original synthetic route.

[0064] In step 504, the rationality of the target synthetic route is checked, and it is determined whether the check is passed. If yes, step 505 is performed, otherwise, the flow is ended.

[0065] In this embodiment, it is assumed that the check is not passed and the flow is ended. ​

[0066] Wherein, the target synthesis route can be taken as the input of the second model, and the output second rationality score is obtained, if it is determined that the second rationality score is greater than a predetermined threshold, it can be determined that the verification is passed, or if it is determined that the target synthesis route meets the predetermined rationality evaluation rule, it can be determined that the verification is passed.

[0067] In step 505, according to the modification, the content of the relevant nodes in the tree structure of the target synthesis route is updated in a bottom-up order, and the updated root node is taken as the second molecule, and then the process ends.

[0068] It should be noted that for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present disclosure is not limited by the order of the described actions, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present disclosure. In addition, the parts not described in detail in a certain embodiment can refer to the related description in other embodiments.

[0069] The above is the introduction of the method embodiment, and the scheme of the present disclosure will be further described through the device embodiment.

[0070] Figure 6 The constituent structure schematic diagram of the molecule generation device embodiment 600 of the present disclosure is shown. As shown in the figure, it can include: a route acquisition module 601, a route modification module 602, and a molecule generation module 603. Figure 6

[0071] The route acquisition module 601 is used to acquire the first molecule to be processed, and acquire the synthesis route of the first molecule as the original synthesis route.

[0072] The route modification module 602 is used to modify the original synthesis route to obtain the target synthesis route.

[0073] The molecule generation module 603 is used to generate the required second molecule according to the target synthesis route.

[0074] The scheme described by the above device embodiment can generate a new molecule by modifying the synthesis route, thereby bypassing the structural conflict risk brought by directly editing on the original molecule structure, and further improving the generation efficiency of the molecule and improving the quality of the generated molecule, etc.

[0075] In some embodiments of the present disclosure, the route acquisition module 601 can take the first molecule as the input of the first model trained in advance, so as to obtain the output original synthesis route.​

[0076] Afterwards, the route modification module 602 can modify the original synthetic route to obtain a target synthetic route. A pre-set modification rule can be obtained, which can be formulated by an expert, and the original synthetic route can be modified according to the modification rule.

[0077] In some embodiments of the present disclosure, the modification of the original synthetic route by the route modification module 602 can include one or any combination of the following: deleting part of the sub-synthetic routes in the original synthetic route, replacing part of the sub-synthetic routes in the original synthetic route with new sub-synthetic routes, and adding new sub-synthetic routes to the original synthetic route.

[0078] The modified original synthetic route can be used as the target synthetic route, and the molecule generation module 603 can generate the required second molecule according to the target synthetic route.

[0079] In some embodiments of the present disclosure, the target synthetic route can be a tree structure, which includes nodes and connection relationships between the nodes. Accordingly, the way in which the molecule generation module 603 generates the second molecule according to the target synthetic route can include: updating the content of the relevant nodes in the tree structure in a bottom-up order according to the modification, and taking the updated root node as the second molecule.

[0080] In addition, in some embodiments of the present disclosure, the modification of the original synthetic route by the route modification module 602 can also include: verifying the rationality of the original synthetic route, and in response to determining that the verification is passed, modifying the original synthetic route, and / or the generation of the second molecule by the molecule generation module 603 according to the target synthetic route can also include: verifying the rationality of the target synthetic route, and in response to determining that the verification is passed, generating the second molecule according to the target synthetic route.

[0081] That is, after obtaining the original synthetic route, the rationality of the original synthetic route can also be verified, and if it is determined that the verification is passed, the original synthetic route can be modified, otherwise, error processing or re-generation of the original synthetic route can be performed, and the specific manner is not limited. Similarly, after obtaining the target synthetic route, the rationality of the target synthetic route can also be verified, and if it is determined that the verification is passed, the second molecule can be generated according to the target synthetic route, otherwise, error processing can be performed, and the specific manner is also not limited.

[0082] In some embodiments of the present disclosure, the route modification module 602 may, in a manner of checking the rationality of the original synthetic route, input the original synthetic route into the pre-trained second model to obtain an output first rationality score, and in response to determining that the first rationality score is greater than a predetermined threshold, determine that the checking is passed. The molecule generation module 603 may, in a manner of checking the rationality of the target synthetic route, input the target synthetic route into the second model to obtain an output second rationality score, and in response to determining that the second rationality score is greater than the threshold, determine that the checking is passed.

[0083] Alternatively, in some embodiments of the present disclosure, the route modification module 602 may, in a manner of checking the rationality of the original synthetic route, further include, in response to determining that the original synthetic route meets a predetermined rationality evaluation rule, determining that the checking is passed. The molecule generation module 603 may, in a manner of checking the rationality of the target synthetic route, further include, in response to determining that the target synthetic route meets the rationality evaluation rule, determining that the checking is passed.

[0084] That is, the rationality of the original synthetic route and the target synthetic route can be checked by means of the second model, or the rationality of the original synthetic route and the target synthetic route can also be checked directly by using the rationality evaluation rule. The specific way to be adopted can be determined according to actual needs, which is very flexible and convenient. In addition, the specific content included in the rationality evaluation rule can also be determined according to actual needs. Taking the original synthetic route as an example, if it is determined that the structure and the content included therein meet the rationality evaluation rule, then it is determined that the rationality checking of the original synthetic route is passed. In addition, if necessary, the rationality evaluation rule can also be updated at any time.

[0085] Figure 6 The specific working process of the device embodiment can be referred to the related description in the foregoing method embodiment, and will not be described here.

[0086] The scheme of the present disclosure can be applied to the field of artificial intelligence, and particularly relates to the fields of biological computing and deep learning. Artificial intelligence is a discipline that studies enabling computers to simulate some thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.) of humans. It has both hardware-level technologies and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, and big data processing. Artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, knowledge graph technology, and several other directions.

[0087] In addition, the collection, storage, use, processing, transmission, provision and disclosure of user personal information in the technical solutions of the present disclosure comply with relevant laws and regulations and do not violate public order and good customs.

[0088] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0089] Figure 7 A schematic block diagram of an electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, servers, blades, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0090] As shown in Figure 7 The device 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded into a random access memory (RAM) 703 from a storage unit 708. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0091] Various components in the device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, etc., an output unit 707, such as various types of displays, speakers, etc., a storage unit 708, such as a magnetic disk, an optical disk, etc., and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunications networks.

[0092] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphic processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, and the like. The computing unit 701 performs various methods and processes described above, such as the methods described in the present disclosure. For example, in some embodiments, the methods described in the present disclosure can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the methods described in the present disclosure can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the methods described in the present disclosure by any other suitable means, such as by means of firmware.

[0093] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0094] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0095] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory, read-only memory, erasable programmable read-only memory (EPROM), flash memory, optical fibers, compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0096] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0097] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0098] The computer system can include clients and servers. This relationship can be. The servers are typically remote from the clients with the interactions between them occurring over a communication network. The relationship between a client and a server is one of client-server. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0099] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in series, or executed in different orders, as long as the desired results of the technical solutions of the present disclosure are achieved, and the present disclosure is not limited herein.

[0100] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A method for generating a molecule, comprising: obtaining a first molecule to be processed, and obtaining a synthesis route of the first molecule as an original synthesis route; verifying rationality of the original synthesis route, including: determining whether a structure and included content of the original synthesis route conform to a rationality evaluation rule, or taking the original synthesis route as an input of a second pre-trained model to obtain an output first rationality score; in response to determining that the verification passes, obtaining a pre-set modification rule, and modifying the original synthesis route according to the modification rule to obtain a target synthesis route, the modification including one or any combination of the following: deletion, replacement, addition; generating a second molecule required according to the target synthesis route.

2. The method of claim 1, wherein, The obtaining of the synthesis route of the first molecule as the original synthesis route includes: taking the first molecule as an input of a first pre-trained model to obtain the output original synthesis route.

3. The method of claim 1, wherein, The modification of the original synthesis route includes one or any combination of the following: deleting part of the sub-synthesis routes in the original synthesis route; replacing part of the sub-synthesis routes in the original synthesis route with new sub-synthesis routes; adding new sub-synthesis routes to the original synthesis route.

4. The method of claim 1, wherein: the generating of the second molecule required according to the target synthesis route includes: verifying rationality of the target synthesis route, and in response to determining that the verification passes, generating the second molecule according to the target synthesis route.

5. The method of claim 4, wherein: the verifying of the rationality of the target synthesis route includes: determining whether a structure and included content of the target synthesis route conform to the rationality evaluation rule, or taking the target synthesis route as an input of the second model to obtain an output second rationality score.

6. The method of claim 5, wherein: the response to determining that the verification passes includes: for the original synthesis route, in response to determining that the structure and included content of the original synthesis route both conform to the rationality evaluation rule, determining that the verification passes, or in response to determining that the first rationality score is greater than a predetermined threshold, determining that the verification passes; for the target synthesis route, in response to determining that the structure and included content of the target synthesis route both conform to the rationality evaluation rule, determining that the verification passes, or in response to determining that the second rationality score is greater than the threshold, determining that the verification passes.

7. The method of any one of claims 1-6, wherein: the target synthesis route is a tree structure including nodes and connection relationships between the nodes; the generating of the second molecule required according to the target synthesis route includes: according to the modification, updating content of related nodes in the tree structure in a bottom-up order, and taking a root node after the updating as the second molecule.

8. A molecular generator device comprising: a route obtaining module, a route modifying module, and a molecule generating module; The route obtaining module is configured to obtain a first molecule to be processed, and obtain a synthesis route of the first molecule as an original synthesis route. The route modifying module is configured to check rationality of the original synthesis route, including: determining whether a structure and included content of the original synthesis route conform to a rationality evaluation rule, or taking the original synthesis route as an input of a second pre-trained model to obtain an output first rationality score; in response to determining that the check passes, obtaining a pre-set modification rule, and modifying the original synthesis route according to the modification rule to obtain a target synthesis route, the modification including one or any combination of the following: deletion, replacement, addition. The molecule generating module is configured to generate a second molecule required according to the target synthesis route.

9. The apparatus of claim 8, wherein, The route obtaining module takes the first molecule as an input of a first pre-trained model to obtain the output original synthesis route.

10. The apparatus of claim 8, wherein, The modification of the original synthesis route by the route modifying module includes one or any combination of the following: deleting part of a sub-synthesis route in the original synthesis route, replacing part of a sub-synthesis route in the original synthesis route with a new sub-synthesis route, and adding a new sub-synthesis route to the original synthesis route.

11. The apparatus of claim 8, wherein, The molecule generating module is further configured to check rationality of the target synthesis route, and in response to determining that the check passes, generate the second molecule according to the target synthesis route.

12. The apparatus of claim 11, wherein, The molecule generating module determines whether a structure and included content of the target synthesis route conform to the rationality evaluation rule, or takes the target synthesis route as an input of the second model to obtain an output second rationality score.

13. The apparatus of claim 12, wherein, The route modifying module determines that the check passes in response to determining that the structure and included content of the original synthesis route both conform to the rationality evaluation rule, or in response to determining that the first rationality score is greater than a predetermined threshold value; The molecule generating module determines that the check passes in response to determining that the structure and included content of the target synthesis route both conform to the rationality evaluation rule, or in response to determining that the second rationality score is greater than the threshold value.

14. The apparatus of any one of claims 8-13, wherein, The target synthesis route is a tree structure including nodes and connection relationships between the nodes; The molecule generating module updates content of related nodes in the tree structure in a bottom-up order according to the modification, and takes a root node after the update as the second molecule.

15. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are for causing a computer to perform the method of any one of claims 1-7.

17. A computer program product comprising computer programs / instructions which, when executed by a processor, implement the method of any one of claims 1-7.

Images