A method and device for determining antigen-antibody docking information

Abstract

The purpose of this application is to provide a method and device for determining antigen-antibody docking information, the method comprising: based on antigen information and antibody information, using a deep learning network to obtain corresponding antigen-antibody docking information, wherein the antigen information includes antigen sequence information and antigen structure information, the antibody information includes antibody sequence information and antibody structure information, the deep learning network includes an encoder-decoder architecture, and the antigen-antibody docking information includes antigen-antibody complex structure information. The deep learning network predicts the binding structure of unbound antigens and antibodies, not only predicts the structure of antigen-antibody binding, but also predicts the transition of the antigen and antibody's own structure from the unbound to the bound state. Using the encoder-decoder architecture for binding structure prediction effectively improves computational efficiency and prediction accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of bioinformatics, and in particular to a technology for determining antigen-antibody docking information. Background Art

[0002] Antibodies play a vital role in the immune system by binding to foreign substances, activating complement, and promoting phagocytosis of phagocytes. Accurately predicting the binding configuration of antigens and antibodies is very helpful for the development of immunological 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. Antigen-antibody docking refers to a method of predicting the structure of the antigen-antibody complex based on the non-binding structures of the antigen and antibody alone. Traditional docking methods rely on empirical scoring functions and rigid body simulations to predict the binding posture of antigens and antibodies. They often cannot effectively adapt to conformational flexibility and cannot guarantee prediction accuracy. Summary of the invention

[0003] One object of the present application is to provide a method and device for determining antigen-antibody docking information.

[0004] According to one aspect of the present application, a method for determining antigen-antibody docking information is provided, the method comprising:

[0005] Based on the antigen information and the antibody information, a deep learning network is used to obtain corresponding antigen-antibody docking information, wherein the antigen information includes antigen sequence information and antigen structure information, the antibody information includes antibody sequence information and antibody structure information, the deep learning network includes an encoder-decoder architecture, and the antigen-antibody docking information includes antigen-antibody complex structure information.

[0006] According to one aspect of the present application, a computer device for determining antigen-antibody docking information is provided, comprising a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0007] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0008] According to one aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0009] According to one aspect of the present application, a device for determining antigen-antibody docking information is provided, the device comprising:

[0010] The first module is used to obtain corresponding antigen-antibody docking information based on antigen information and antibody information using a deep learning network, wherein the antigen information includes antigen sequence information and antigen structure information, the antibody information includes antibody sequence information and antibody structure information, the deep learning network includes an encoder-decoder architecture, and the antigen-antibody docking information includes antigen-antibody complex structure information.

[0011] Compared with the prior art, the present application is based on antigen information and antibody information, and uses a deep learning network to obtain corresponding antigen-antibody docking information, wherein the antigen information includes antigen sequence information and antigen structure information, the antibody information includes antibody sequence information and antibody structure information, the deep learning network includes an encoder-decoder architecture, and the antigen-antibody docking information includes antigen-antibody complex structure information. The deep learning network predicts the binding structure of unbound antigens and antibodies, and not only predicts the structure of antigen-antibody binding, but also predicts the transformation of the structure of antigens and antibodies from unbound to bound states. Using an encoder-decoder architecture for binding structure prediction effectively improves computational efficiency and prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0013] Figure 1 A flow chart of a method for determining antigen-antibody docking information according to one embodiment of the present application is shown;

[0014] Figure 2 A flow chart of a method for determining antigen-antibody docking information according to one embodiment of the present application is shown;

[0015] Figure 3 A flow chart of a method for determining antigen-antibody docking information according to one embodiment of the present application is shown;

[0016] Figure 4 A flow chart of a method for determining antigen-antibody docking information according to one embodiment of the present application is shown;

[0017] Figure 5 A structural diagram of a device for determining antigen-antibody docking information according to an embodiment of the present application is shown;

[0018] Figure 6 An exemplary system is shown that can be used to implement the various embodiments described in this application.

[0019] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0020] The present application is described in further detail below in conjunction with the accompanying drawings.

[0021] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (eg, a central processing unit (CPU)), an input / output interface, a network interface and a memory.

[0022] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory. Memory is an example of a computer-readable medium.

[0023] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, modules of programs 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 technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0024] 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 products that can interact with users (for example, interact with users through a touchpad), such as smart phones, tablet computers, etc. The mobile electronic products can use any operating system, such as Android operating system, iOS operating system, etc. Among them, the network device includes an electronic device that can automatically perform numerical calculations and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), digital signal processors (Digital Signal Processor, DSP), embedded devices, etc. The network devices include but are not limited to computers, network hosts, single network servers, multiple network server sets or multiple servers. The cloud is composed of a large number of computers or network servers based on cloud computing (Cloud Computing), wherein cloud computing is a type of distributed computing, a virtual supercomputer composed of a group of loosely coupled computer sets. The network includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless self-organizing network (Ad Hoc network), etc. Preferably, the device may also be a program running on the user device, the network device, or a device formed by integrating the user device and the network device, the network device, the touch terminal, or the network device and the touch terminal through a network.

[0025] Of course, those skilled in the art should understand that the above-mentioned devices are only examples, and other existing or future devices that are applicable to the present application should also be included in the scope of protection of the present application and are included here by reference.

[0026] In the description of the present application, “plurality” means two or more, unless otherwise clearly and specifically defined.

[0027] Figure 1A flow chart of a method for determining antigen-antibody docking information according to an embodiment of the present application is shown, the method comprising: step S1. In step S1, device 1 obtains corresponding antigen-antibody docking information based on antigen information and antibody information using a deep learning network, wherein the antigen information comprises antigen sequence information and antigen structure information, the antibody information comprises antibody sequence information and antibody structure information, the deep learning network comprises an encoder-decoder architecture, and the antigen-antibody docking information comprises antigen-antibody complex structure information.

[0028] In some embodiments, the device 1 includes but is not limited to a user device or a network device having information processing or computing capabilities, such as a tablet computer, a computer, or a server. The method described in the present application is applied to the device 1 .

[0029] In some embodiments, the deep learning network is obtained by training based on antigen sample information, antibody sample information and corresponding antigen-antibody complex sample information. The antigen sample information includes but is not limited to the antigen sample sequence information and antigen sample structure information corresponding to the unbound antigen sample. The antibody sample information includes but is not limited to the antibody sample sequence information and antibody sample structure information corresponding to the unbound antibody sample. The antigen-antibody complex sample information includes but is not limited to the structural information after the unbound antigen sample is combined with the unbound antibody sample (for example, the three-dimensional coordinate information / relative position information of the atoms in the amino acid after the unbound antigen sample is combined with the unbound antibody sample). The antigen-antibody complex sample information also includes the change information corresponding to the respective structures of the antigen sample and the antibody sample from the unbound state to the bound state (especially the complementary determining region of the antibody sample). In some embodiments, the antigen sample information, the antibody sample information and the antigen-antibody complex sample information can be obtained from the corresponding literature or protein database. In some embodiments, the deep learning network training is performed under the encoder-decoder architecture. The encoder is used to predict the connection between the antigen sample and the antibody sample, and then the decoder outputs the corresponding antigen-antibody complex information. Then, the loss calculation is performed based on the difference between the output antigen-antibody complex information and the corresponding antigen-antibody complex sample information. Then, according to the gradient calculated by the loss function, the network weights of the encoder and decoder are updated through back propagation. After several iterative trainings, the deep learning network is finally obtained.

[0030] In some embodiments, the antigen sequence information includes but is not limited to the amino acid residue sequence of the antigen, and the antigen structure information includes but is not limited to the three-dimensional coordinate information of each atom of each amino acid corresponding to the unbound antigen, the distance between different atoms, the angle formed by different atoms, and the distance information between different amino acids. The antibody information is similar to the antigen information. The antibody sequence information includes but is not limited to the amino acid residue sequence of the antibody, and the antibody structure information includes but is not limited to the three-dimensional coordinate information of each atom of each amino acid corresponding to the unbound antibody, the distance between different atoms, the angle formed by different atoms, and the distance information between different amino acids. In some embodiments, the device 1 inputs the antigen information and the antibody information into the deep learning network obtained by the aforementioned training, and then obtains the corresponding antigen-antibody docking information. The antigen-antibody docking information includes the antigen-antibody complex structure information, and the antigen-antibody complex structure information includes the relative position information between the bound antigen and antibody. In some embodiments, the antigen-antibody docking information also includes antibody structure change information and antigen structure change information. For example, the change information corresponding to the respective structures of the antigen and / or antibody from the unbound state to the bound state (for example, the change of the atomic three-dimensional coordinates before and after binding).

[0031] In some embodiments, reference Figure 2 As shown in the flow chart, step S1 includes: step S11, based on the antigen information and the antibody information, determining the antigen-antibody complex encoding information through an encoder, wherein the encoder is constructed based on a self-attention mechanism; step S12, converting the antigen-antibody complex encoding information into corresponding antigen-antibody docking information through a decoder.

[0032] For example, the encoder part in the deep learning network captures the connection between the antigen amino acids and the antibody amino acids (for example, the relative position between the two) based on the input antigen information and antibody information, updates the antigen structure and the antibody structure, and obtains the corresponding antigen-antibody complex encoding information. The antigen-antibody complex encoding information includes but is not limited to the distance information and angle information between the amino acid atoms in the antigen and the amino acid atoms in the antibody. The decoder part in the deep learning network can predict the antigen-antibody docking information based on the antigen-antibody complex encoding information.

[0033] In some embodiments, the encoder in the deep learning network introduces a self-attention mechanism to help determine the correlation between antigen information and antibody information, thereby facilitating information integration. In some embodiments, in order to better integrate information, the encoder may also introduce a triplet attention mechanism for information processing.

[0034] In some embodiments, reference Figure 3 As shown in the flow chart, step S11 includes: step S111, device 1 uses a protein language model to determine the antigen embedding information corresponding to the antigen information and the antibody embedding information corresponding to the antibody information; step S112, based on the antigen embedding information and the antibody embedding information, determine the antigen-antibody complex encoding information through an encoder.

[0035] For example, before using a deep learning network to obtain antigen-antibody docking information, device 1 obtains the embedding information corresponding to the antigen information and the antibody information through a protein language model (PLM) to capture the corresponding characteristic information and attribute information of the antigen and antibody (for example, antigen and antibody structural composition, biochemical characteristics and evolutionary information, etc.), and converts the antigen information and the antibody information into the same expression form to facilitate subsequent docking prediction processing and improve computational efficiency.

[0036] In some embodiments, determining the antigen-antibody complex encoding information through an encoder based on the antigen embedding information and the antibody embedding information includes: determining the corresponding antibody complementary determining region encoding information based on the antibody embedding information; determining the antigen-antibody complex encoding information based on the antibody complementary determining region encoding information and the antigen embedding information.

[0037] The variable region of an antibody is mainly composed of a framework region (FR) and a complementarity determining region (CDR). The complementarity determining region of an antibody is responsible for complementary binding to a specific epitope of an antigen. The framework region of an antibody does not directly participate in antigen-antibody docking, but provides a stable structural support for the complementarity determining region, so that the complementarity determining region can be correctly positioned and interact with the epitope of the antigen. Here, the encoder part of the deep learning network uses a self-attention mechanism to determine the complementary determining region encoding information of the antibody to be docked based on the antibody embedding information, thereby using the antibody complementary determining region encoding information and the antigen embedding information to determine the antigen-antibody complex encoding information.

[0038] In some embodiments, the antibody embedding information includes antibody framework region information and antibody complementary determining region information; determining the corresponding antibody complementary determining region encoding information based on the antibody embedding information includes: updating the antibody complementary determining region information based on the antibody framework region information, and determining the corresponding antibody complementary determining region encoding information.

[0039] Since the antibody framework region provides structural support for the complementary determining region, it has a certain influence on the three-dimensional structure of the complementary determining region. In order to accurately predict the antigen-antibody docking structure, the antibody framework region information can be used to update the antibody complementary determining region information. Figure 4 As shown in the flowchart, the antibody embedding information input into the deep learning network is divided into antibody framework region information and antibody complementary determining region information. First, based on the antibody framework region information, the self-attention mechanism is used to determine the key information of the framework region that is more important / affecting the antibody complementary determining region. Then the key information of the framework region is passed to the antibody complementary determining region, and the antibody complementary determining region information is updated to obtain the antibody complementary determining region encoding information. Here, the encoder is also integrated with a message passing neural network (MPNNs). The key information of the framework region can be transmitted and the antibody complementary determining region information can be updated through the information transmission network.

[0040] In some embodiments, the determination of the corresponding antibody complementary determining region encoding information based on the antibody embedding information further includes: determining the antibody framework region information and the antibody complementary determining region information corresponding to the antibody embedding information. In some embodiments, the framework region and complementary determining region of the antibody can be identified by sequence alignment, and then the antibody framework region information and the antibody complementary determining region information can be determined. For example, device 1 can identify the framework region and complementary determining region of the antibody before the antibody embedding information is input into the deep learning network. The antibody embedding information is distinguished based on the framework region and complementary determining region of the antibody identified by sequence alignment, and the corresponding antibody framework region information and the antibody complementary determining region information are determined. The antibody embedding information, which is distinguished into the antibody framework region information and the antibody complementary determining region information, is then input into the deep learning network.

[0041] In some embodiments, the encoder includes multiple sub-network layers; the step of determining the antigen-antibody complex encoding information through the encoder based on the antigen information and the antibody information includes: a. determining the intermediate antigen-antibody complex encoding information corresponding to the current sub-network layer based on the antigen information, the antibody information and the intermediate antigen-antibody complex encoding information determined in the previous sub-network layer; and repeating step a until the last sub-network layer outputs the corresponding antigen-antibody complex encoding information.

[0042] For example, refer to Figure 4As shown in the flowchart, the encoder includes multiple sub-network layers with the same architecture. In each sub-network layer, the current intermediate antigen-antibody complex encoding information is determined based on the antigen information, antibody information, and the intermediate antigen-antibody complex encoding information determined in the previous sub-network layer (if it is the first sub-network layer, the intermediate antigen-antibody complex encoding information is not involved in the calculation), and the current intermediate antigen-antibody complex encoding information is determined (if it is the last sub-network layer, the current intermediate antigen-antibody complex encoding information is output as the antigen-antibody complex encoding information). Thus, the association between the antigen amino acids and antibody amino acids learned in the previous layer (i.e., the intermediate antigen-antibody complex encoding information) is passed to the current layer, and learning continues on this basis, which helps to capture information at different levels of antigen and antibody information. In the current sub-network layer, the intermediate antigen-antibody complex encoding information is processed in combination with the antigen information and the antibody information, so that when an error occurs in the processing of a certain layer, the original input can still be seen. In each layer of sub-network, the processing of antigen information and antibody information is the same or similar to the above steps: before inputting the encoder, the protein language model is used to determine the antigen embedding information corresponding to the antigen information and the antibody embedding information corresponding to the antibody information; after inputting the encoder, in each layer of sub-network, the corresponding antibody complementary determining region encoding information is determined based on the antibody embedding information; based on the antibody complementary determining region encoding information, the antigen embedding information and the intermediate antigen-antibody complex encoding information determined in the previous sub-network layer, the antigen-antibody complex encoding information is determined. Therefore, it will not be repeated here, and it is included here by reference.

[0043] Figure 5 A device structure diagram for determining antigen-antibody docking information according to an embodiment of the present application is shown, wherein the device 1 includes a first module 1. The first module 1 uses a deep learning network to obtain corresponding antigen-antibody docking information based on antigen information and antibody information, wherein the antigen information includes antigen sequence information and antigen structure information, the antibody information includes antibody sequence information and antibody structure information, the deep learning network includes an encoder-decoder architecture, and the antigen-antibody docking information includes antigen-antibody complex structure information. Here, the Figure 3 The specific implementations corresponding to the first module 1 shown are respectively the same as or similar to the specific embodiments of the aforementioned step S1 , and therefore will not be described in detail and are included herein by reference.

[0044] In some embodiments, the first module 1 includes a one-to-one unit 11 and a one-to-two unit 12. The one-to-one unit 11 determines the antigen-antibody complex encoding information through an encoder based on the antigen information and the antibody information, wherein the encoder is constructed based on the self-attention mechanism; the one-to-two unit 12 converts the antigen-antibody complex encoding information into corresponding antigen-antibody docking information through a decoder. Here, the specific implementation methods of the one-to-one unit 11 and the one-to-two unit 12 are respectively the same or similar to the specific embodiments of the aforementioned step S11 and step S12, so they are not repeated here and are included here by reference.

[0045] Figure 6 An exemplary system that can be used to implement the various embodiments described in this application is shown; Figure 6 In some embodiments shown, the system 300 can be used as any of the devices in the various described embodiments. In some embodiments, the system 300 may include one or more computer-readable media (e.g., system memory or NVM / storage device 320) with instructions 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 instructions to implement modules to perform the actions described in this application.

[0046] For one embodiment, system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of processor(s) 305 and / or any suitable device or component in communication with system control module 310 .

[0047] The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. The memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0048] The system memory 315 may be used, for example, to load and store data and / or instructions for the system 300. For one embodiment, the system memory 315 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the system memory 315 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0049] For one embodiment, system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to NVM / storage device 320 and communication interface(s) 325 .

[0050] 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 non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0051] NVM / storage device 320 may include storage resources that are physically part of the device on which system 300 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 320 may be accessed over a network via communication interface(s) 325.

[0052] Communication interface(s) 325 may provide an interface for system 300 to communicate over 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 in accordance with any of one or more wireless network standards and / or protocols.

[0053] For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 (e.g., the memory controller module 330). For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310 to form a system on chip (SoC).

[0054] In various embodiments, the 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 computer, a netbook, etc.). In various embodiments, the system 300 may have more or fewer components and / or a different architecture. For example, in some embodiments, the system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and a speaker.

[0055] In addition to the methods and devices described in the above embodiments, the present application also provides a computer-readable storage medium, which stores computer code. When the computer code is executed, the method described in any of the preceding items is executed.

[0056] The present application also provides a computer program product. When the computer program product is executed by a computer device, the method described in any of the preceding items is executed.

[0057] The present application also provides a computer device, the computer device comprising:

[0058] one or more processors;

[0059] a memory for storing one or more computer programs;

[0060] 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.

[0061] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, 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 of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. 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 perform each step or function.

[0062] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes but is not limited to source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes but is 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.

[0063] Communication media include media by which communication signals containing, for example, computer readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media may include guided transmission media such as cables and wires (e.g., fiber optic, coaxial, etc.) and wireless (unguided transmission) media that can propagate energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied as a modulated data signal in, for example, a wireless medium such as a carrier wave or similar mechanism such as 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 such a manner as to encode information in the signal. Modulation may be analog, digital, or a hybrid modulation technique.

[0064] By way of example and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are 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, magnetic tapes, CDs, DVDs); or other media now known or later developed that can store computer-readable information / data for use with a computer system.

[0065] Here, according to one embodiment of the present application, a device is included, which 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 run the methods and / or technical solutions based on the aforementioned multiple embodiments of the present application.

[0066] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for determining antigen-antibody docking information, wherein: The method comprises: Based on the antigen information and the antibody information, using a deep learning network, obtaining corresponding antigen-antibody docking information, wherein the antigen information includes antigen sequence information and antigen structure information, the antibody information includes antibody sequence information and antibody structure information, the deep learning network includes an encoder-decoder architecture, and the antigen-antibody docking information includes antigen-antibody complex structure information; Wherein, based on the antigen information and the antibody information, using a deep learning network to obtain corresponding antigen-antibody docking information includes: Based on the antigen information and the antibody information, the antigen-antibody complex encoding information is determined by the encoder, wherein the encoder is constructed based on the self-attention mechanism, and the antigen-antibody complex encoding information is determined by the encoder based on the antigen information and the antibody information, including: using a protein language model to determine the antigen embedding information corresponding to the antigen information and the antibody embedding information corresponding to the antibody information; based on the antigen embedding information and the antibody embedding information, the antigen-antibody complex encoding information is determined by the encoder; wherein, based on the antigen embedding information and the antibody embedding information, the antigen-antibody complex encoding information is determined by the encoder, including: based on the antibody embedding information, the corresponding antibody complementary determining region encoding information is determined, wherein the antibody complementary determining region encoding information is to be used for docking; based on the antibody complementary determining region encoding information and the antigen embedding information, the antigen-antibody complex encoding information is determined; The antigen-antibody complex encoding information is converted into corresponding antigen-antibody docking information by a decoder.

2. The method according to claim 1, wherein: The antibody embedding information includes antibody framework region information and antibody complementary determining region information; Determining the corresponding antibody complementary determining region encoding information based on the antibody embedding information includes: Based on the antibody framework region information, the antibody complementary determining region information is updated, and corresponding antibody complementary determining region encoding information is determined.

3. The method according to claim 2, wherein: The determining of the corresponding antibody complementary determining region encoding information based on the antibody embedding information further comprises: The antibody framework region information and the antibody complementary determining region information corresponding to the antibody embedding information are determined.

4. The method according to any one of claims 1 to 3, wherein: The encoder comprises a plurality of sub-network layers; Determining the antigen-antibody complex encoding information by the encoder based on the antigen information and the antibody information includes: a. Determine the intermediate antigen-antibody complex encoding information corresponding to the current sub-network layer based on the antigen information, the antibody information and the intermediate antigen-antibody complex encoding information determined in the previous sub-network layer; Repeat step a until the last sub-network layer outputs the corresponding antigen-antibody complex encoding information.

5. A computer device for determining antigen-antibody docking 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 4.

6. 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 as claimed in any one of claims 1 to 4 are implemented.

7. 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 4 are implemented.

Images