A method, device, medium and program product for predicting antigen epitope information

Abstract

The object of the present application is to provide a method, device, medium and program product for predicting antigen epitope information. The method includes: determining antigen surface atom information and antibody surface atom information respectively based on the antigen information to be docked and the antibody information to be docked; determining corresponding antigen block information and antibody block information respectively based on the antigen surface atom information and the antibody surface atom information; and determining corresponding antigen epitope information by using a corresponding deep learning network based on the antigen block information and the antibody block information. The present application focuses on the surface information in the process of antigen-antibody binding, and predicts antigen epitopes by learning the surface information in antigen-antibody binding, thereby improving the prediction efficiency and accuracy.

Description

Technical Field

[0001] This application relates to the field of bioinformatics technology, and particularly to a technology for predicting antigen epitope information. Background Art

[0002] Accurately predicting the binding configuration of antigens and antibodies is very helpful for the research and development of immune drugs. Although the structures of antigens and antibodies alone can now be predicted with high precision, determining the three-dimensional structure of the antigen-antibody complex remains a challenge. And determining the specific regions on the antigen that can be recognized and bound by antibodies (i.e., antigen epitopes) is very helpful for subsequent prediction of antigen-antibody binding configuration and antibody function prediction. Traditional epitope prediction methods rely on empirical scoring functions and rigid body simulations for prediction. The prediction of empirical scoring functions is limited by the size and quality of the known antigen epitope datasets, and rigid body simulations ignore the conformational changes of proteins from the unbound to the bound state, and the prediction accuracy is often limited. Summary of the Invention

[0003] An object of this application is to provide a method and device for predicting antigen epitope information.

[0004] According to one aspect of this application, a method for predicting antigen epitope information is provided. The method includes:

[0005] Based on the antigen information to be docked and the antibody information to be docked, determine the antigen surface atom information and the antibody surface atom information respectively;

[0006] Based on the antigen surface atom information and the antibody surface atom information, determine the corresponding antigen block information and antibody block information respectively;

[0007] Based on the antigen block information and the antibody block information, use the corresponding deep learning network to determine the corresponding antigen epitope information.

[0008] According to one aspect of this application, a computer device for predicting antigen epitope information is provided, including a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of any of the above methods.

[0009] According to one aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored. The computer program, when executed by a processor, implements the steps of any of the above methods.

[0010] According to one aspect of the present application, there is provided a computer program product including a computer program, characterized in that when the computer program is executed by a processor, it implements the steps of any of the above-mentioned methods.

[0011] According to one aspect of the present application, there is provided a device for predicting antigen epitope information, the device comprising:

[0012] a first module configured to respectively determine antigen surface atom information and antibody surface atom information based on the antigen information to be docked and the antibody information to be docked;

[0013] a second module configured to respectively determine corresponding antigen block information and antibody block information based on the antigen surface atom information and the antibody surface atom information;

[0014] a third module configured to determine corresponding antigen epitope information based on the antigen block information and the antibody block information by using a corresponding deep learning network.

[0015] Compared with the prior art, the present application respectively determines antigen surface atom information and antibody surface atom information based on the antigen information to be docked and the antibody information to be docked; respectively determines corresponding antigen block information and antibody block information based on the antigen surface atom information and the antibody surface atom information; and determines corresponding antigen epitope information based on the antigen block information and the antibody block information by using a corresponding deep learning network. The present application focuses on the surface information in the process of antigen-antibody binding, and predicts the antigen epitope by learning the surface information in antigen-antibody binding, thereby improving the prediction efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0017] Figure 1 showing a flowchart of a method for predicting antigen epitope information according to an embodiment of the present application;

[0018] Figure 2 showing a flowchart of a method for determining antigen / antibody block information according to an embodiment of the present application;

[0019] Figure 3 showing a flowchart of a method for predicting antigen epitope information according to an embodiment of the present application;

[0020] Figure 4 showing a flowchart of a method for predicting antigen epitope information according to an embodiment of the present application;

[0021] Figure 5The structural diagram of a device for predicting antigen epitope information according to an embodiment of the present application is shown;

[0022] Figure 6 An exemplary system that can be used to implement the various embodiments described in the present application is shown.

[0023] The same or similar reference numerals in the drawings represent the same or similar components. Detailed implementation manners

[0024] The present application will be further described in detail below with reference to the drawings.

[0025] In a typical configuration of the present application, the terminal, the devices of the service network, and the trusted party all include one or more processors (for example, a Central Processing Unit (CPU)), an input / output interface, a network interface, and a memory.

[0026] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of, for example, read only memory (ROM) or flash memory. The memory is an example of a computer-readable medium.

[0027] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for information storage. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, Phase-Change Memory (PCM), Programmable Random Access Memory (PRAM), Static Random-Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read-Only Memory (ROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), flash memory or other memory technologies, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device.

[0028] The devices referred to in this application include, but are not limited to, user devices, network devices, or devices formed by integrating user devices and network devices through a network. The user devices include, but are not limited to, any mobile electronic product that can perform human-computer interaction with users (such as human-computer interaction through a touchpad), such as smart phones, tablets, etc. The mobile electronic products can adopt any operating system, such as Android operating system, iOS operating system, etc. Among them, the network devices include an electronic device that can automatically perform numerical calculations and information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application specific integrated circuits (ASICs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc. The network devices include, but are not limited to, computers, network hosts, single network servers, multiple network server sets, or clouds composed of multiple servers; here, the cloud is composed of a large number of computers or network servers based on cloud computing. Among them, cloud computing is a type of distributed computing, consisting of a virtual supercomputer formed by a group of loosely coupled computer sets. The network includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, VPN network, wireless ad hoc network (Ad Hoc network), etc. Preferably, the device can also be a program running on the user device, network device, or a device formed by integrating user devices and network devices, network devices, touch terminals, or network devices and touch terminals through a network.

[0029] Of course, those skilled in the art should understand that the above devices are only examples. Other existing or future devices that can be applied to this application should also be included within the protection scope of this application and are hereby incorporated by reference.

[0030] In the description of this application, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0031] Figure 1The flowchart of a method for predicting antigen epitope information according to an embodiment of the present application is shown. The method includes step S11, step S12, and step S13. In step S11, device 1 determines antigen surface atom information and antibody surface atom information respectively based on the antigen information to be docked and the antibody information to be docked; in step S12, device 1 determines corresponding antigen block information and antibody block information respectively based on the antigen surface atom information and the antibody surface atom information; in step S13, device 1 determines corresponding antigen epitope information by using the corresponding deep learning network based on the antigen block information and the antibody block information.

[0032] In step S11, device 1 determines antigen surface atom information and antibody surface atom information respectively based on the antigen information to be docked and the antibody information to be docked. In some embodiments, the device 1 includes, but is not limited to, a user device or a network device with information processing or computing capabilities, such as a tablet computer, a computer, or a server. In some embodiments, the antigen information to be docked includes, but is not limited to, the sequence information and structural information of the antigen that has not bound to an antibody (for example, the three-dimensional coordinate information of atoms in the antigen to be docked). The antibody information to be docked includes, but is not limited to, the sequence information and structural information of the antibody that has not bound to an antigen (for example, the three-dimensional coordinate information of atoms in the antibody to be docked). In some embodiments, device 1 determines the atoms located on the surfaces of the antigen to be docked and the antibody to be docked respectively, and determines the corresponding antigen surface atom information and antibody surface atom information for these antigen surface atoms and antibody surface atoms. The antigen surface atom information includes, but is not limited to, residue features and pairwise features corresponding to the antigen surface atoms, where the residue features include, but are not limited to, the element type, atomic coordinates, centrality encoding information, and / or backbone torsion angle information of the antigen surface atoms, and the pairwise features include, but are not limited to, the relative coordinate relationship between antigen surface atom pairs. The antibody surface atom information also includes, but is not limited to, residue features and pairwise features corresponding to the antibody surface atoms. The residue features and pairwise features are similar to those in the antigen surface atom information, so they will not be elaborated here and are included herein by reference.

[0033] In some embodiments, step S11 includes: The device 1 determines the exposed area corresponding to each atom in the antigen and the antibody respectively based on the antigen information to be docked and the antibody information to be docked; Based on the exposed area corresponding to each atom in the antigen and the antibody, the antigen surface atom information and the antibody surface atom information are determined respectively. For example, atoms of different element types have different atomic radii. The atomic radius of each atom in the antigen can be determined based on the antigen information to be docked. Furthermore, based on the atomic radius of each atom in the antigen and the three-dimensional coordinate information of each atom, the surface area of each atom in the antigen that is not covered by other atoms is determined. This surface area not covered by other atoms is used as the exposed area corresponding to the atom. Atoms in the antigen with an exposed area greater than a preset area threshold are determined as antigen surface atoms, and the corresponding antigen surface atom information is determined. The method for determining the antibody surface atom information is the same as the method for determining the antigen surface atom information described above, so it will not be repeated here and is included herein by reference. The area threshold is preset based on actual needs. For example, this area threshold can be set to Atoms with an exposed area greater than are determined as surface atoms. Here, those skilled in the art should understand that the setting of the above area threshold is only an example, and other existing or future possible area thresholds that can be applied to this application should also be included within the protection scope of this application and are included herein by reference.

[0034] In step S12, the device 1 determines the corresponding antigen patch information and antibody patch information respectively based on the antigen surface atom information and the antibody surface atom information. In some embodiments, the device 1 can cluster the antigen surface atom information and the antibody surface atom information respectively. The adjacent antigen surface atoms are clustered to obtain an antigen patch, and the adjacent antibody surface atoms are clustered to obtain an antibody patch. And the corresponding antigen patch information and antibody patch information are obtained. The antigen patch information includes the antigen surface atom information corresponding to each antigen surface atom in the antigen patch. The antibody patch information includes the antibody surface atom information corresponding to each antibody surface atom in the antibody patch. In some embodiments, the aforementioned clustering can be performed separately based on different chains of the antigen and the antibody. For example, based on the surface atoms of the antigen chain, the heavy chain and / or light chain of the antibody respectively, the patch information of each chain is clustered respectively.

[0035] Refer to Figure 2 the flowchart shown. In some embodiments, step S12 includes: Step S121, the device 1 determines the integration information corresponding to each surface atom of the antigen and the antibody respectively based on the antigen surface atom information and the antibody surface atom information; Step S122, the device 1 determines the corresponding antigen patch information and antibody patch information respectively based on the integration information corresponding to each surface atom of the antigen and the antibody.

[0036] In some embodiments, in order to have richer information for epitope prediction in subsequent steps and improve the accuracy of antigen epitope prediction, the atomic information of multiple antigen atoms near each antigen surface atom of the antigen can be integrated, and the atomic information of multiple antibody atoms near each antibody surface atom of the antibody can be integrated, so as to obtain the integrated information corresponding to each surface atom. Then, based on these integrated information, antigen block information and antibody block information are obtained by clustering.

[0037] In some embodiments, based on the antigen information and the corresponding antigen surface atom information, multiple antigen atoms closest to the surface atoms of the antigen can be selected to determine the integrated information corresponding to the surface atom. The integrated information includes, but is not limited to, physical and chemical characteristics such as the antigen surface atom information, the interaction characteristics, spatial structure, and chemical properties between the antigen surface atom and the multiple closest antigen atoms. The determination method of the integrated information corresponding to each surface atom of the antibody is the same as that of the integrated information corresponding to each surface atom of the aforementioned antigen, so it will not be elaborated here and is included herein by reference. In some embodiments, the number of atoms adjacent to the surface atoms of the antigen / antibody selected can be set according to actual needs. For example, the number can be set to 16 or other values.

[0038] In some embodiments, step S121 includes: Device 1 determines multiple atomic information corresponding to each surface atom of the antigen and the antibody respectively based on the antigen surface atom information and the antibody surface atom information; combining the multiple atomic information corresponding to each surface atom of the antigen and the antibody, the integrated information corresponding to each surface atom of the antigen and the antibody is determined respectively.

[0039] In some embodiments, Device 1 can use a vector field to calculate the distance between an antigen surface atom and other atoms of the antigen. In some embodiments, the distance calculated using the vector field is based on the antigen surface, rather than the Euclidean distance. In some embodiments, based on the distance between the antigen surface atom and other atoms of the antigen, a preset number of antigen atoms closest in distance to each antigen surface atom are selected, and the corresponding atomic information of these antigen atoms is determined. These antigen atoms can be atoms located on the antigen surface or atoms located inside the antigen, which is not limited herein. The atomic information includes, but is not limited to, the residue characteristics and pairwise characteristics corresponding to the antigen atom. The determination method of the multiple atomic information corresponding to each surface atom of the antibody is the same as that of the multiple atomic information corresponding to each surface atom of the aforementioned antigen, so it will not be elaborated here and is included herein by reference.

[0040] In some embodiments, the device 1 can perform information integration on the basis of multiple atomic information corresponding to each surface atom of the antigen and the corresponding antigen surface atomic information by using a Geometric Aggregation Network, so as to obtain the integrated information corresponding to each surface atom of the antigen. The Geometric Aggregation Network includes a Multi Layer Perceptron (MLP). The integrated information includes, but is not limited to, the antigen surface atomic information, the interaction characteristics, spatial structure, chemical properties and other physical and chemical characteristics between the antigen surface atom and multiple antigen atoms with the closest distance. The determination method of the integrated information corresponding to each surface atom of the antibody is the same as that of the integrated information corresponding to each surface atom of the aforementioned antigen, so it will not be elaborated here and is included herein by reference.

[0041] In some embodiments, the step S122 includes: the device 1 respectively samples based on the integrated information corresponding to each surface atom of the antigen and the antibody to obtain the integrated information corresponding to the surface atoms of the sampled antigen and antibody; and respectively performs clustering processing on the integrated information corresponding to the surface atoms of the sampled antigen and antibody to obtain the corresponding antigen block information and antibody block information.

[0042] In some embodiments, in order to improve the calculation efficiency, the integrated information corresponding to each surface atom of the antigen and the antibody can be sampled first. Here, the farthest point sampling method can be used to sample each surface atom of the antigen / antibody to obtain the integrated information corresponding to the sampled surface atoms. Those skilled in the art should understand that the above sampling method is only an example, and other existing or future possible sampling methods applicable to the present application should also be included in the protection scope of the present application and are included herein by reference.

[0043] In some embodiments, the device 1 can cluster the integrated information corresponding to the surface atoms of antigens with relatively close distances by combining a corresponding clustering algorithm to obtain the corresponding antigen block information. The antigen block information includes the integrated information corresponding to each surface atom within the antigen block. The calculation method of the antibody block information is the same as that of the aforementioned antigen block information, so it will not be elaborated here and is included herein by reference. Here, the distance is similar to the atomic distance calculated by the vector field mentioned above, and it also refers to the distance based on the surface of the antigen / antibody. The clustering algorithm includes, but is not limited to, the K-Nearest Neighbors algorithm.

[0044] In some embodiments, for the convenience of subsequent calculation and processing, step S122 further includes performing Morton encoding on the antigen block information and the antibody block information respectively, thereby converting the antigen block information and the antibody block information from high-dimensional space data into one-dimensional sequences, enabling some machine learning models for one-dimensional sequences to conveniently process the antigen / antibody block information and reducing the limitations on the models used in epitope prediction.

[0045] In step S13, device 1 determines corresponding antigen epitope information based on the antigen block information and the antibody block information by using a corresponding deep learning network. In some embodiments, the deep learning network includes an encoder and a decoder. The encoder can encode the input antigen block information and antibody block information into a vector of a fixed size. The vector can capture key features such as the atomic composition and structure on the surfaces of the antigen and the antibody, as well as the relationship between the antigen block information and the antibody block information (e.g., the strength of the interaction between different blocks). The decoder predicts the antigen epitope information based on the vector. The deep learning network can be pre-trained and deployed on device 1, or can be trained by device 1. The antigen epitope information includes, but is not limited to, antigen epitope sequence information, un-docked antigen epitope coordinate information, and / or docked antigen epitope coordinate information.

[0046] In some embodiments, step S13 includes: device 1 determines corresponding antigen block integration information and antibody block integration information respectively based on the antigen block information and the antibody block information by using a quasi-geodesic convolutional network; and determines corresponding antigen epitope information based on the antigen block integration information and the antibody block integration information by using a corresponding deep learning network.

[0047] In some embodiments, to improve the accuracy of antigen epitope prediction, the antigen block information can also be integrated. For each antigen block information, a quasi-geodesic convolutions network is used to integrate it with other antigen block information adjacent based on surface distance to obtain antigen block integration information. The antigen block integration information includes, but is not limited to, this antigen block information and other antigen block information adjacent based on surface distance. In some embodiments, for each antigen block information, weight information corresponding to other antigen block information can be determined based on the surface distance between this antigen block information and other antigen block information. Then, in combination with the weight information, the antigen block integration information corresponding to this antigen block information is determined. The weight information is negatively correlated with the surface distance. If the surface distance between this antigen block information and other antigen block information is smaller, then this other antigen block information is more important to this antigen block information, and the corresponding weight information is larger. The method for determining the antibody block integration information is the same as that for determining the aforementioned antigen block integration information, so it will not be elaborated here and is included herein by reference.

[0048] Reference Figure 3 Referring to the flowchart shown, in some embodiments, the method further includes: Step S14, the device 1 trains and obtains a corresponding deep learning network based on the antigen sample information, antibody sample information, and the corresponding antigen-antibody binding information under an encoder-decoder architecture. In some embodiments, the antigen sample information includes, but is not limited to, the sequence information and structural information of the undocked sample antigen (for example, the three-dimensional atomic coordinate information in the sample antigen). The antibody sample information includes, but is not limited to, the sequence information and structural information of the undocked sample antibody (for example, the three-dimensional atomic coordinate information in the sample antibody). The antigen-antibody binding information includes, but is not limited to, the sequence information and structural information of the complex after docking of the sample antigen and the sample antibody, and epitope information such as the epitope coordinates and epitope sequences corresponding to the sample antigen.

[0049] In some embodiments, before performing Steps S11 - S13, the device 1 first trains and obtains the deep learning network based on the corresponding sample data. Since only the surfaces of the antigen and antibody are involved in docking, in order to improve the efficiency and accuracy of epitope prediction, the antigen sample information and the antibody sample information can be processed in the same or similar manner as Steps S11 and S12 described above to obtain the corresponding sample antigen block information / sample antigen block integration information and sample antibody block information / sample antibody block integration information, so as to focus on the surface information of the antigen and antibody during the training of the deep learning network. The sample antigen block information / sample antigen block integration information and the sample antibody block information / sample antibody block integration information are input into the deep learning network to obtain the corresponding epitope prediction results. Based on the corresponding loss function, the difference between the epitope prediction result and the antigen-antibody binding information is calculated, and based on this, the parameters of the deep learning network are updated through backpropagation, and finally the corresponding deep learning network is obtained.

[0050] Reference Figure 4 Referring to the flowchart shown, in some embodiments, the method further includes: Step S15, the device 1 determines the antigen-antibody complex structure information based on the antigen epitope information. For example, the antigen epitope information includes the epitope coordinate information after docking. The device 1 then combines the coordinate information of other atoms in the antigen information to be docked and the antibody information to be docked to obtain the coordinate information of each atom in the antigen-antibody complex, that is, the antigen-antibody complex structure information.

[0051] Figure 5Shows a structural diagram of a device for predicting antigen epitope information according to an embodiment of the present application. The device 1 includes a module 11, a module 12, and a module 13. The module 11 determines antigen surface atom information and antibody surface atom information respectively based on the antigen information to be docked and the antibody information to be docked; the module 12 determines corresponding antigen block information and antibody block information respectively based on the antigen surface atom information and the antibody surface atom information; the module 13 determines corresponding antigen epitope information by using a corresponding deep learning network based on the antigen block information and the antibody block information. Herein, the Figure 5 The specific implementation manners corresponding to the shown module 11, module 12, and module 13 are the same as or similar to the specific embodiments of the foregoing steps S11, S12, and S13 respectively, and thus will not be described in detail again and are included herein by reference.

[0052] In some embodiments, the module 12 includes a unit 121 and a unit 122. The unit 121 determines integrated information corresponding to each surface atom of the antigen and the antibody respectively based on the antigen surface atom information and the antibody surface atom information; the unit 122 determines corresponding antigen block information and antibody block information respectively based on the integrated information corresponding to each surface atom of the antigen and the antibody. Herein, the specific implementation manners of the unit 121 and the unit 122 are the same as or similar to the specific embodiments of the foregoing steps S121 and S122 respectively, and thus will not be described in detail again and are included herein by reference.

[0053] In some embodiments, the device 1 further includes a module 14 (not shown). The module 14 trains and obtains a corresponding deep learning network under an encoder-decoder architecture based on antigen sample information, antibody sample information, and corresponding antigen-antibody binding information. Herein, the specific implementation manner corresponding to the module 14 is the same as or similar to the specific embodiment of the foregoing step S14, and thus will not be described in detail again and are included herein by reference.

[0054] In some embodiments, the device 1 further includes a module 15 (not shown). The module 15 determines antigen-antibody complex structure information based on the antigen epitope information. Herein, the specific implementation manner corresponding to the module 15 is the same as or similar to the specific embodiment of the foregoing step S15, and thus will not be described in detail again and are included herein by reference.

[0055] Figure 6 Shows an exemplary system that can be used to implement the various embodiments described in the present application.

[0056] Such as Figure 6As shown, in some embodiments, system 300 can function as any one of the devices in the respective embodiments. In some embodiments, system 300 may include one or more computer-readable media having instructions (e.g., system memory or NVM / storage device 320) and one or more processors (e.g., (one or more) processors 305) coupled to the one or more computer-readable media and configured to execute the instructions to implement modules to perform the actions described in this application.

[0057] For one embodiment, system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of (one or more) processors 305 and / or any suitable device or component communicating with system control module 310.

[0058] System control module 310 may include a memory controller module 330 to provide an interface to system memory 315. Memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0059] System memory 315 may be used, for example, to load and store data and / or instructions for system 300. For one embodiment, system memory 315 may include any suitable volatile memory, e.g., suitable DRAM. In some embodiments, system memory 315 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0060] For one embodiment, system control module 310 may include one or more input / output (I / O) controllers to provide an interface to NVM / storage device 320 and (one or more) communication interfaces 325.

[0061] For example, NVM / storage device 320 may be used to store data and / or instructions. NVM / storage device 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (one or more) non-volatile storage devices (e.g., one or more hard disk drives (HDDs), one or more optical disc (CD) drives, and / or one or more digital versatile disc (DVD) drives).

[0062] NVM / storage device 320 may include storage resources physically as part of the device on which system 300 is installed, or it may be accessed by the device without being part of the device. For example, NVM / storage device 320 may be accessed via (one or more) communication interfaces 325 over a network.

[0063] One or more communication interfaces 325 may provide an interface for system 300 to communicate via one or more networks and / or with any other suitable devices. System 300 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols.

[0064] For one embodiment, at least one of (one or more) processors 305 may be logically encapsulated with one or more controllers of system control module 310 (e.g., memory controller module 330). For one embodiment, at least one of (one or more) processors 305 may be logically encapsulated with one or more controllers of system control module 310 to form a system-in-package (SiP). For one embodiment, at least one of (one or more) processors 305 may be logically integrated with one or more controllers of system control module 310 on the same die. For one embodiment, at least one of (one or more) processors 305 may be logically integrated with one or more controllers of system control module 310 on the same die to form a system-on-chip (SoC).

[0065] In various embodiments, system 300 may be, but is not limited to: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, system 300 may have more or fewer components and / or a different architecture. For example, in some embodiments, system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touchscreen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and speakers.

[0066] In addition to the methods and devices introduced in the above embodiments, the present application also provides a computer-readable storage medium storing computer code, which when executed, performs the method as described in any of the previous items.

[0067] The present application also provides a computer program product, which when executed by a computer device, performs the method as described in any of the previous items.

[0068] The present application also provides a computer device, which includes:

[0069] One or more processors;

[0070] A memory for storing one or more computer programs;

[0071] When the one or more computer programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any of the preceding items.

[0072] It should be noted that the present application can be implemented in software and / or a combination of software and hardware. For example, it can be implemented using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the steps or functions described above. Similarly, the software program (including related data structures) of the present application can be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive, or a floppy disk and the like. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to execute each step or function.

[0073] In addition, a part of the present application can be applied as a computer program product, such as computer program instructions, which when executed by a computer, through the operation of the computer, can call or provide the method and / or technical solution according to the present application. Those skilled in the art should be able to understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0074] The communication medium includes a medium through which a communication signal containing, for example, computer-readable instructions, data structures, program modules, or other data is transmitted from one system to another system. The communication medium can include a guided transmission medium (such as cables and wires (e.g., optical fibers, coaxial, etc.)) and a wireless (unguided transmission) medium that can propagate energy waves, such as sound, electromagnetic, RF, microwave, and infrared. The computer-readable instructions, data structures, program modules, or other data can be embodied as, for example, a modulated data signal in a wireless medium (such as a carrier wave or a similar mechanism embodied as part of spread spectrum technology). The term "modulated data signal" refers to a signal whose one or more characteristics are changed or set in a manner that encodes information in the signal. The modulation can be analog, digital, or a hybrid modulation technique.

[0075] By way of example and not limitation, a computer-readable storage medium may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. For example, computer-readable storage media includes, but is not limited to, volatile memory such as random access memory (RAM, DRAM, SRAM); and non-volatile memory such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, tapes, CDs, DVDs); or other media now known or later developed that can store computer-readable information / data for use by a computer system.

[0076] Here, an embodiment according to the present application includes a device that includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to operate based on the methods and / or technical solutions according to the foregoing multiple embodiments of the present application.

[0077] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic characteristics of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be construed as limiting the claims involved. In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the apparatus claims can also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are used to denote names and do not denote any particular order.

Claims

1. A method for predicting antigen epitope information, wherein: The method comprises: Based on the information of the antigen to be docked and the information of the antibody to be docked, respectively determining the surface atomic information of the antigen and the surface atomic information of the antibody; Based on the antigen surface atom information and the antibody surface atom information, respectively determine the corresponding antigen block information and antibody block information, wherein the corresponding antigen block information and antibody block information based on the antigen surface atom information and the antibody surface atom information include: based on the antigen surface atom information and the antibody surface atom information, respectively determine the integrated information corresponding to each surface atom of the antigen and the antibody, wherein the integrated information includes the antigen / antibody surface atom information and the physical and chemical characteristics between the antigen / antibody surface atom and multiple antigen / antibody atoms that are closest to each other; based on the integrated information corresponding to each surface atom of the antigen and the antibody, respectively determine the corresponding antigen block information and antibody block information, wherein the antigen block corresponding to the antigen block information and the antibody block corresponding to the antibody block information are obtained by clustering the antigen surface atoms and the antibody surface atoms, respectively; Based on the antigen block information and the antibody block information, the corresponding antigen epitope information is determined using a corresponding deep learning network.

2. The method according to claim 1, wherein: The step of determining the antigen surface atom information and the antibody surface atom information based on the antigen information to be docked and the antibody information to be docked comprises: Based on the information of the antigen to be docked and the information of the antibody to be docked, the exposed area corresponding to each atom in the antigen and the antibody is determined respectively; Based on the exposed area corresponding to each atom in the antigen and antibody, the surface atomic information of the antigen and the surface atomic information of the antibody are determined respectively.

3. The method according to claim 1, wherein: The step of determining the integrated information corresponding to each surface atom of the antigen and the antibody based on the surface atom information of the antigen and the surface atom information of the antibody comprises: Based on the antigen surface atomic information and the antibody surface atomic information, respectively determine multiple atomic information corresponding to each surface atom of the antigen and the antibody; The integrated information corresponding to each surface atom of the antigen and antibody is determined by combining multiple atomic information corresponding to each surface atom of the antigen and antibody.

4. The method according to claim 1 or 3, wherein: The step of determining corresponding antigen block information and antibody block information based on the integrated information corresponding to each surface atom of the antigen and the antibody comprises: Based on the integration information corresponding to each surface atom of the antigen and antibody, sampling is performed respectively to obtain the integration information corresponding to the surface atoms of the sampled antigen and antibody; The integrated information corresponding to the surface atoms of the sampled antigens and antibodies is clustered to obtain corresponding antigen block information and antibody block information.

5. The method according to claim 4, wherein: The step of determining corresponding antigen block information and antibody block information based on the integrated information corresponding to each surface atom of the antigen and antibody also includes: The antigen block information and the antibody block information are Morton encoded respectively.

6. The method according to claim 1, wherein: The determining of corresponding antigen epitope information based on the antigen block information and the antibody block information by using a corresponding deep learning network includes: Based on the antigen block information and the antibody block information, using a quasi-geodesic convolutional network, respectively determining corresponding antigen block integration information and antibody block integration information; Based on the antigen block integration information and the antibody block integration information, the corresponding antigen epitope information is determined using a corresponding deep learning network.

7. The method according to claim 1, wherein: The method further comprises: Based on the antigen sample information, antibody sample information and the corresponding antigen-antibody binding information, the corresponding deep learning network is trained under the encoder-decoder architecture.

8. The method according to claim 1, wherein: The method further comprises: Based on the antigen epitope information, the antigen-antibody complex structure information is determined.

9. A computer device for predicting antigen epitope information, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images