Method and equipment for constructing protein sequence prediction model

Abstract

The invention aims to provide a method and equipment for constructing a protein sequence prediction model, and the method comprises the steps: determining surface point cloud information and sample protein sequence information corresponding to corresponding sample protein based on sample protein information, the sample protein information comprises protein sequence information and protein structure information, and sequence information belonging to the surface of a sample protein in the sample protein sequence information is masked; based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, a corresponding protein sequence prediction model is obtained through training, and the protein sequence prediction model comprises a structure encoder, a sequence encoder and a corresponding decoder. According to the method, the information of the protein surface is introduced in the construction of the protein sequence prediction model for sequence prediction, so that the model prediction accuracy can be effectively improved, and the surface precision of the predicted protein sequence is improved.

Description

Technical Field

[0001] The present application relates to the technical field of bioinformatics, and in particular to a technology for constructing a protein sequence prediction model. Background Art

[0002] Proteins regulate various physiological responses through interactions with other proteins or small molecules on their surfaces. Accurately designing amino acids on the surface of proteins is very helpful in regulating protein functions. Currently, protein sequences can be predicted relatively accurately based on the protein skeleton, but because the designed sequence is based on the skeleton, the accuracy of predicting the surface amino acids that actually affect the protein is limited, and it cannot be used to design protein sequences most effectively. Summary of the invention

[0003] One object of the present application is to provide a method and device for constructing a protein sequence prediction model.

[0004] According to one aspect of the present application, a method for constructing a protein sequence prediction model is provided, the method comprising:

[0005] Based on the sample protein information, determining the surface point cloud information and the sample protein sequence information corresponding to the corresponding sample protein, wherein the sample protein information includes protein sequence information and protein structure information, and the sequence information belonging to the sample protein surface in the sample protein sequence information is masked;

[0006] Based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, a corresponding protein sequence prediction model is trained and obtained, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder.

[0007] According to one aspect of the present application, a computer device for constructing a protein sequence prediction model is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0008] 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.

[0009] 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.

[0010] According to one aspect of the present application, a device for constructing a protein sequence prediction model is provided, the device comprising:

[0011] A module, for determining surface point cloud information and sample protein sequence information corresponding to the corresponding sample protein based on the sample protein information, wherein the sample protein information includes protein sequence information and protein structure information, and sequence information belonging to the sample protein surface in the sample protein sequence information is masked;

[0012] The first and second modules are used to train and obtain a corresponding protein sequence prediction model based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder.

[0013] Compared with the prior art, the present application determines the surface point cloud information and sample protein sequence information corresponding to the corresponding sample protein based on the sample protein information, wherein the sample protein information includes protein sequence information and protein structure information, and the sequence information belonging to the sample protein surface in the sample protein sequence information is masked; based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, the corresponding protein sequence prediction model is trained and obtained, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder. The present application introduces protein surface information for sequence prediction in the construction of a protein sequence prediction model, which can effectively improve the model prediction accuracy and improve the surface accuracy of the predicted protein sequence. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] 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:

[0015] Figure 1 A flow chart of a method for constructing a protein sequence prediction model according to one embodiment of the present application is shown;

[0016] Figure 2 A flowchart of a method for training a protein sequence prediction model according to one embodiment of the present application is shown;

[0017] Figure 3 A schematic diagram showing the angles of two points in surface point cloud information according to an embodiment of the present application is shown;

[0018] Figure 4 A flow chart of a method for constructing a protein sequence prediction model according to one embodiment of the present application is shown;

[0019] Figure 5A structural diagram of a device for constructing a protein sequence prediction model according to one embodiment of the present application is shown;

[0020] Figure 6 A structural diagram of a device for constructing a protein sequence prediction model according to one embodiment of the present application is shown;

[0021] Figure 7 An exemplary system is shown that can be used to implement the various embodiments described in this application.

[0022] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0023] The present application is described in further detail below in conjunction with the accompanying drawings.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] In the description of the present application, “plurality” means two or more, unless otherwise clearly and specifically defined.

[0030] Figure 1A flow chart of a method for constructing a protein sequence prediction model according to an embodiment of the present application is shown, and the method includes step S11 and step S12. In step S11, device 1 determines the surface point cloud information and sample protein sequence information corresponding to the corresponding sample protein based on the sample protein information, wherein the sample protein information includes protein sequence information and protein structure information, and the sequence information belonging to the surface of the sample protein in the sample protein sequence information is masked; in step S12, device 1 trains and obtains the corresponding protein sequence prediction model based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder.

[0031] In step S11, device 1 determines the surface point cloud information and sample protein sequence information corresponding to the corresponding sample protein based on the sample protein information, wherein the sample protein information includes protein sequence information and protein structure information, and the sequence information belonging to the surface of the sample protein in the sample protein sequence information is masked. In some embodiments, the device 1 includes but is not limited to user devices and network devices with information processing or computing capabilities, such as tablet computers, computers, and servers. In some embodiments, the sample protein information can be obtained from corresponding literature or protein databases. The sample protein information includes protein sequence information and protein structure information corresponding to the sample protein, that is, the information of the sample protein is completely known. The protein structure information includes three-dimensional coordinate information of atoms in the sample protein. Device 1 processes the sample protein information, distinguishes the surface and interior of the sample protein, extracts the surface point cloud information corresponding to the sample protein, and masks the surface amino acid sequence information for subsequent model training.

[0032] In some embodiments, step S11 includes: based on the protein structure information, device 1 uses a preset virtual sphere to perform surface sampling to determine the surface point cloud information corresponding to the sample protein and the amino acid information located on the surface of the sample protein; based on the amino acid information on the surface of the sample protein and the protein sequence information, determine the sample protein sequence information. For example, device 1 can set a radius of A virtual sphere is used to roll around the sample protein atoms and record the points touched by the virtual sphere. These points constitute a point cloud on the surface of the sample protein. Device 1 can determine the physical and chemical characteristic information such as electrical properties and polarity corresponding to these points based on the physical and chemical characteristics corresponding to the atoms closest to these points. The surface point cloud information corresponding to the sample protein includes the position information corresponding to each point in the sample protein surface point cloud (for example, the coordinate information of the point or the normal vector information of the point toward the outside of the protein surface, etc.) and the corresponding physical and chemical characteristic information. Device 1 can determine the amino acids to which these atoms belong based on the atoms closest to these points, and determine these amino acids as the amino acids on the surface of the sample protein. Furthermore, based on the amino acid information on the surface of the sample protein, the amino acids belonging to the surface of the sample protein in the protein sequence information can be masked to obtain the sample protein sequence information. In some embodiments, the device 1 can use protein structure processing / visualization tools such as PyMol (https: / / pymol.org / ) or PyGAMer (https: / / gamer.readthedocs.io / en / latest / tutorials / notebooks / meshingprotein.html) to perform surface sampling and generate point clouds.

[0033] In step S12, the device 1 trains and obtains the corresponding protein sequence prediction model based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder. In some embodiments, the structure encoder is used to encode the surface point cloud information corresponding to the sample protein, and the sequence encoder is used to encode the sample protein sequence information. These encoded information are input into the decoder to predict the masked surface amino acid sequence information. The protein sequence prediction model is optimized in combination with the prediction results and the known actual sequence information, so as to obtain a model that can be combined with protein surface information to predict protein sequences, so that the design of protein surface amino acid sequences is more accurate. The protein sequence prediction model described in this scheme is mainly aimed at the situation where the protein on one side is known and the protein on the other side is designed in the design task of protein-protein interaction. In this design task, the protein surface shape required for the protein interacting on the other side and the corresponding surface physicochemical characteristics, the correspondence between the surface point cloud and the surface amino acids, and other information can be inferred based on the known protein information. Or a task that requires a large-scale modification of a known protein. For example, there is a protein that can bind tightly to receptor A but not to receptor B. In order to make the protein bind to receptor B, it is necessary to redesign the surface amino acids of a certain area of ​​the protein based on the known approximate binding configuration of the two. In this task, the internal amino acid sequence information is known, and the corresponding surface shape, physicochemical characteristics, correspondence between surface point cloud and surface amino acids and other information can be inferred based on the original conditions of receptor B and the protein. Therefore, in the case of unknown types of amino acids on the surface of proteins, the surface information of these proteins can be provided to the model as known information to make a more accurate prediction of the amino acid sequence, so that the predicted protein can better interact with other proteins or small molecules. Here, those skilled in the art should understand that the above-mentioned model application scenarios are only examples, and other existing or future protein design tasks that have the same or similar needs and can provide the same or similar model input information, if applicable to this application, should also be included in the scope of protection of this application, and are included here by reference.

[0034] In some embodiments, reference Figure 2The protein sequence prediction model training flow chart shown in the figure, the step S12 includes: step S121, device 1 determines the corresponding sample protein surface coding information based on the surface point cloud information corresponding to the sample protein using the structure encoder; step S122, device 1 determines the corresponding sample protein sequence coding information based on the sample protein sequence information using the sequence encoder; step S123, device 1 determines the protein sequence prediction information corresponding to the sample protein based on the sample protein surface coding information and the sample protein sequence coding information using the decoder; step S124, device 1 optimizes the protein sequence prediction model based on the protein sequence prediction information and the protein sequence information. Here, the execution order of step S121 and step S122 is not limited, and the two can be executed simultaneously or successively.

[0035] In some embodiments, the structure encoder includes a graph neural network. Device 1 uses the graph neural network to capture feature information of each point and its neighboring points in the surface point cloud information corresponding to the sample protein, and based on the feature information of each point and its neighboring points, updates and integrates the point in the surface point cloud information corresponding to the sample protein to obtain the corresponding sample protein surface encoding information.

[0036] In some embodiments, the step S121 includes: step S1211, device 1 determines the surface feature information corresponding to the surface point cloud information corresponding to the sample protein using the structure encoder based on the surface point cloud information corresponding to the sample protein, wherein the surface feature information includes feature information corresponding to each point in the surface point cloud information corresponding to the sample protein; step S1212, device 1 determines the corresponding sample protein surface coding information based on the surface feature information through information integration, wherein the sample protein surface coding information includes feature information corresponding to each amino acid on the surface of the sample protein.

[0037] In some embodiments, the process of using the structure encoder to determine the surface feature information corresponding to the surface point cloud information corresponding to the sample protein is: for any point i and the neighboring point j of the point i in the surface point cloud information corresponding to the sample protein, the information transmitted between the point i and j can be determined based on the pre-constructed feature information. Based on the information transmitted between the point i and j, the feature information of the point i is updated. In some embodiments, in order to improve the prediction accuracy, the attention mechanism can also be used to weight the information transmitted between the point i and j, so that the information with stronger association and more important information with the point i has a higher weight, and then the feature information of the point i is updated in combination with the weighted information. In some embodiments, as described in the above embodiments, in the protein sequence design / modification task targeted by this scheme, although the specific type information of the surface amino acids of the protein is unknown, the surface shape composed of these surface amino acids and the corresponding surface physicochemical characteristics and other information can still be obtained. Therefore, even if the type of amino acid is unknown, the surface amino acid to which the point in the point cloud belongs can be determined according to the principle of the closest distance. The neighboring point j and the point i belong to the same surface amino acid, or the surface amino acid to which the neighboring point j belongs is one of the multiple surface amino acids closest to the surface amino acid to which the point i belongs. The number of the closest surface amino acids can be set based on actual task requirements, and preferably, the number can be set to 7.

[0038] In some embodiments, the feature information corresponding to each point in the surface point cloud information corresponding to the sample protein includes at least one of the following: the physicochemical feature information corresponding to each point; the curvature feature corresponding to each point; the directional feature between each point and any neighboring point. In some embodiments, the curvature feature corresponding to each point includes a pseudocurvature vector, which provides a feature about rotation invariance. In some embodiments, the directional feature between each point and any neighboring point includes a directional vector between the point and the neighboring point, and angle feature information determined based on the position information corresponding to the point and the neighboring point.

[0039] In some embodiments, a corresponding covariance matrix can be constructed based on the surface amino acid to which any point i in the surface point cloud information belongs and the multiple surface amino acids closest to the surface amino acid.

[0040]

[0041] Among them, N (i) is the surface amino acid to which point i belongs and the set of multiple surface amino acids closest to the surface amino acid, is the center of gravity of the surface amino acid to which point i belongs and the set of multiple surface amino acids closest to the surface amino acid, x j N(i) The position information corresponding to the midpoint j. Calculate the eigenvalues ​​of the covariance matrix Based on this eigenvalue, the corresponding pseudo-curvature vector (ψ1, ψ2, ψ3) is obtained, where

[0042]

[0043] In some embodiments, reference Figure 3 The angle diagram shown is based on the surface point cloud information of point i and its neighboring point j, as well as the normal vector information n of these two points toward the outside of the protein surface. i ,n j , determine the normal vector n corresponding to point i i The angle information between the two points and the normal vector n corresponding to point j j The angle information between the two points and the normal vector n i With the normal vector n j Angle information and other angle feature information

[0044]

[0045] Based on the above feature information, the information transmitted between point i and its neighboring point j can be determined

[0046]

[0047] In some embodiments, the attention mechanism can also be used to perform weighted calculation on the information transmitted between the point i and the neighboring point j.

[0048]

[0049] Then, the feature information of point i is updated by combining the above transmitted information to obtain the surface feature information corresponding to the surface point cloud information of the corresponding sample protein.

[0050]

[0051] Among them, f m 、f h 、f x Refers to three different multilayer perceptrons (MLPs). Refers to the physical and chemical characteristics of point i in the l-th layer network, Refers to the direction vector from point i to point j in the l-th layer of the network.

[0052] In some embodiments, since the atoms on the surface of the protein are relatively flexible, their frequent and tiny movements will give a lot of noise to the protein surface determined by the sampling of the virtual sphere surface. In order to reduce the noise of the surface point cloud information corresponding to the sample protein and improve the prediction accuracy, before step S1211, the step S121 also includes: device 1 smoothes the surface point cloud information corresponding to the sample protein. The surface point cloud information corresponding to the sample protein after smoothing is input into the structure encoder for processing. In some embodiments, the smoothing process can use Gaussian Kernel Smoothing, or Nearest Neighbor Smoothing, etc. Here, those skilled in the art should understand that the above-mentioned smoothing process is only an example, and other existing or future possible smoothing processes, if applicable to the present application, should also be included in the scope of protection of the present application, and are included here by reference.

[0053] In some embodiments, after the feature information corresponding to each point in the surface point cloud information corresponding to the sample protein is updated by the structure encoder, the feature information corresponding to each point in the updated surface point cloud information corresponding to the sample protein is also integrated into the corresponding surface amino acid. Among them, the feature information corresponding to the surface amino acid of the sample protein includes the feature information corresponding to one or more points in the surface point cloud information corresponding to the sample protein, and the surface amino acid is closest to the one or more points compared to other surface amino acids. Here, as described in the above embodiments, the specific type information of the amino acids on the surface of the protein is unknown. However, for the surface amino acid, it not only has its own feature information, but also has the feature information of the amino acids around it, so that in the subsequent sequence design, these feature information can be combined for more comprehensive consideration to obtain better design accuracy.

[0054] In some embodiments, the step S1212 includes: the device 1 determines the surface amino acid to which each point in the surface point cloud information corresponding to the sample protein belongs; based on the surface amino acid to which each point in the surface point cloud information corresponding to the sample protein belongs and the surface feature information, determines the feature information corresponding to each amino acid on the surface of the sample protein. For example, determine the atom closest to the point in the surface point cloud information corresponding to the sample protein. Based on the surface amino acid to which the atom belongs, determine the surface amino acid to which the point belongs. Then integrate the feature information corresponding to the point into the feature information of the surface amino acid.

[0055] In some embodiments, the sequence encoder includes a protein language model, preferably a protein language model with a multi-layer self-attention mechanism. The sequence encoder encodes the sample protein sequence information without surface amino acid sequence information to obtain an embedded representation of the input sample protein sequence information to capture the contextual relationship of the amino acids in the sequence.

[0056] In some embodiments, the device 1 can use the protein language model as a decoder, and predict the amino acid type information on the masked sample protein surface based on the sample protein surface coding information and the sample protein sequence coding information, and generate corresponding protein sequence prediction information. Here, the decoder can not only predict the surface amino acid type based on the internal amino acid information, but also combine the sample protein surface coding information, that is, the feature information corresponding to the surface amino acid to be predicted. Since there is more information available, the prediction accuracy will be higher. After obtaining the protein sequence prediction information, the corresponding loss function (for example, the cross entropy loss function or the Focal Loss loss function suitable for the protein sequence design task) is used to calculate the loss between the protein sequence prediction information and the actual protein sequence information corresponding to the sample protein. The gradient of the loss function with respect to the model parameters is calculated by the back propagation algorithm. The protein sequence prediction model parameters are updated using the corresponding optimization algorithm (for example, gradient descent or Adam, RMSprop optimizer, etc.). The device 1 can repeat the above steps S121-S124 until the performance of the model is no longer improved or reaches the predetermined training round, thereby obtaining the final protein sequence prediction model.

[0057] In some embodiments, reference Figure 4As shown in the flowchart, the method further includes: step S13, based on one or more target protein information corresponding to the target protein, using the protein sequence prediction model, determining the corresponding target protein sequence information, wherein the target protein information includes the target protein surface information and the target protein sequence association information. In some embodiments, the protein sequence prediction model can be trained and directly applied by device 1, or the protein sequence prediction model can be deployed in other devices to perform protein sequence modification / design. In some embodiments, for the protein modification / design task described in the above embodiments, for the target protein to be predicted, the sequence length / length range of its surface amino acids can be estimated to obtain one or more target protein information. For example, for the task of modifying an existing protein, the corresponding sequence length / length range can be determined based on the length of its original surface amino acid sequence (for example, a certain amount of increase or decrease is performed on the basis of the original length). For the task of protein design, the surface amino acid sequence length can be estimated based on the protein on one side that is known. The target protein surface information includes the inferred surface point cloud information of the target protein. The target protein sequence association information includes the internal amino acid sequence information of the target protein and the length information of the surface amino acid sequence. The length information of the surface amino acid sequence corresponding to different target protein information is different. The most suitable target protein sequence information can be determined based on the prediction results of the protein sequence prediction model for the target protein information. Here, the process of predicting the target protein sequence using the protein sequence prediction model based on the target protein information is similar to the aforementioned steps S121-S123, so it will not be repeated here and is included here by reference.

[0058] In some embodiments, step S13 further comprises determining one or more target protein information corresponding to the target protein using a generative simulation method. For example, for a protein design task, a diffusion model-based model such as RFDiffusion (https: / / github.com / RosettaCommons / RFdiffusion, an open source protein structure generation method) can be used to predict the length of the amino acid sequence on the surface of the target protein, and then combined with the estimated length / length range (for example, a certain amount of increase or decrease based on the estimated length) to determine the target protein information corresponding to different surface amino acid sequence lengths.

[0059] In some embodiments, step S13 includes determining the candidate target protein sequence information corresponding to each target protein information using the protein sequence prediction model based on one or more target protein information corresponding to the target protein; and determining the corresponding target protein sequence information based on the candidate target protein sequence information. In some embodiments, the protein sequence prediction model also outputs confidence information corresponding to the predicted candidate target protein sequence information. Based on the confidence information, a sequence that meets the conditions (for example, one or more candidate target protein sequence information with the largest confidence information or greater than the corresponding threshold) can be selected from the candidate target protein sequence information as the target protein sequence information. In some embodiments, perplexity can be used as an evaluation indicator of the prediction result of the protein sequence prediction model to obtain confidence information about the predicted candidate target protein sequence information.

[0060] Figure 5 A device structure diagram for constructing a protein sequence prediction model according to an embodiment of the present application is shown, wherein the device 1 includes a first module 11 and a second module 12. The first module 11 determines the surface point cloud information and the sample protein sequence information corresponding to the corresponding sample protein based on the sample protein information, wherein the sample protein information includes protein sequence information and protein structure information, and the sequence information belonging to the surface of the sample protein in the sample protein sequence information is masked; the first module 12 trains and obtains the corresponding protein sequence prediction model based on the surface point cloud information and the sample protein sequence information corresponding to the sample protein, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder. Here, the Figure 5 The specific implementations corresponding to the illustrated one-one module 11 and one-two module 12 are respectively the same as or similar to the specific embodiments of the aforementioned step S11 and step S12, and therefore will not be described in detail and are included herein by reference.

[0061] In some embodiments, the one-two module 12 includes a one-two-one unit 121, a one-two-two unit 122, a one-two-three unit 123 and a one-two-four unit 124. The one-two-one unit 121 determines the corresponding surface coding information of the sample protein by using the structure encoder based on the surface point cloud information corresponding to the sample protein; the one-two-two unit 122 determines the corresponding sequence coding information of the sample protein by using the sequence encoder based on the sample protein sequence information; the one-two-three unit 123 determines the protein sequence prediction information corresponding to the sample protein by using the decoder based on the sample protein surface coding information and the sample protein sequence coding information; the one-two-four unit 124 optimizes the protein sequence prediction model based on the protein sequence prediction information and the protein sequence information. Here, the specific implementations of the 121 unit 121, the 122 unit 122, the 123 unit 123 and the 124 unit 124 are respectively the same as or similar to the specific implementations of the aforementioned step S121, step S122, step S123 and step S124, so they are not repeated here and are included here by reference.

[0062] In some embodiments, the one-two-one unit 121 includes a one-two-one-one subunit 1211 and a one-two-one-two subunit 1212. The one-two-one-one subunit 1211 determines the surface feature information corresponding to the surface point cloud information corresponding to the sample protein by using the structure encoder based on the surface point cloud information corresponding to the sample protein, wherein the surface feature information includes the feature information corresponding to each point in the surface point cloud information corresponding to the sample protein; the one-two-one-two subunit 1212 determines the corresponding sample protein surface encoding information by information integration based on the surface feature information, wherein the sample protein surface encoding information includes the feature information corresponding to each amino acid on the surface of the sample protein. Here, the specific implementations of the one-two-one-one subunit 1211 and the one-two-one-two subunit 1212 are respectively the same or similar to the specific embodiments of the aforementioned step S1211 and step S1212, so they are not repeated here and are included here by reference.

[0063] In some embodiments, reference Figure 6 As shown in the device structure diagram, the device 1 also includes a three-module 13. The three-module 13 determines the corresponding target protein sequence information based on one or more target protein information corresponding to the target protein using the protein sequence prediction model, wherein the target protein information includes target protein surface information and target protein sequence association information. Here, the specific implementation method corresponding to the three-module 13 is the same or similar to the specific embodiment of the aforementioned step S13, so it will not be repeated and is included here by reference.

[0064] Figure 7An exemplary system that can be used to implement the various embodiments described in this application is shown. Figure 7 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.

[0065] 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 .

[0066] 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.

[0067] 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).

[0068] 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 .

[0069] 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).

[0070] 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.

[0071] 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.

[0072] 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).

[0073] 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.

[0074] 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.

[0075] 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.

[0076] The present application also provides a computer device, the computer device comprising:

[0077] one or more processors;

[0078] a memory for storing one or more computer programs;

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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 by a computer system.

[0084] Here, according to an 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.

[0085] 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 constructing a protein sequence prediction model, wherein: The method comprises: Based on the sample protein information, determining the surface point cloud information and the sample protein sequence information corresponding to the corresponding sample protein, wherein the sample protein information includes protein sequence information and protein structure information, and the sequence information belonging to the sample protein surface in the sample protein sequence information is masked; Based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, a corresponding protein sequence prediction model is trained and obtained, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder.

2. The method according to claim 1, wherein: The method of determining the surface point cloud information and the sample protein sequence information corresponding to the corresponding sample protein based on the sample protein information, wherein the sample protein information includes protein sequence information and protein structure information, and the sequence information belonging to the sample protein surface in the sample protein sequence information is masked includes: Based on the protein structure information, a preset virtual sphere is used to perform surface sampling to determine the surface point cloud information corresponding to the sample protein and the amino acid information located on the surface of the sample protein; The sample protein sequence information is determined based on the amino acid information on the surface of the sample protein and the protein sequence information.

3. The method according to claim 1 or 2, wherein: Based on the surface point cloud information corresponding to the sample protein and the sample protein sequence information, a corresponding protein sequence prediction model is trained and obtained, wherein the protein sequence prediction model includes a structure encoder, a sequence encoder and a corresponding decoder including: Based on the surface point cloud information corresponding to the sample protein, using the structure encoder, determining the corresponding sample protein surface encoding information; Based on the sample protein sequence information, using the sequence encoder, determining corresponding sample protein sequence encoding information; Based on the sample protein surface coding information and the sample protein sequence coding information, using the decoder, determining the protein sequence prediction information corresponding to the sample protein; Based on the protein sequence prediction information and the protein sequence information, the protein sequence prediction model is optimized.

4. The method according to claim 3, wherein: The determining of the corresponding sample protein surface coding information based on the surface point cloud information corresponding to the sample protein by using the structure encoder comprises: Based on the surface point cloud information corresponding to the sample protein, using the structure encoder, determining the surface feature information corresponding to the surface point cloud information corresponding to the sample protein, wherein the surface feature information includes feature information corresponding to each point in the surface point cloud information corresponding to the sample protein; Based on the surface characteristic information, corresponding sample protein surface coding information is determined through information integration, wherein the sample protein surface coding information includes characteristic information corresponding to each amino acid on the surface of the sample protein.

5. The method according to claim 4, wherein: Before determining the surface feature information corresponding to the surface point cloud information corresponding to the sample protein by using the structure encoder based on the surface point cloud information corresponding to the sample protein, wherein the surface feature information includes feature information corresponding to each point in the surface point cloud information corresponding to the sample protein, determining the corresponding sample protein surface encoding information by using the structure encoder based on the surface point cloud information corresponding to the sample protein further includes: The surface point cloud information corresponding to the sample protein is smoothed.

6. The method according to claim 4 or 5, wherein: The characteristic information corresponding to each point in the surface point cloud information corresponding to the sample protein includes at least any one of the following: the physical and chemical characteristic information corresponding to each point; the bending characteristic corresponding to each point; and the directional characteristic between each point and any adjacent point.

7. The method according to any one of claims 4 to 6, wherein: Based on the surface feature information, the corresponding sample protein surface coding information is determined by information integration, wherein the sample protein surface coding information includes feature information corresponding to each amino acid on the surface of the sample protein, including: Determine the surface amino acid to which each point in the surface point cloud information corresponding to the sample protein belongs; Based on the surface amino acid to which each point in the surface point cloud information corresponding to the sample protein belongs and the surface characteristic information, characteristic information corresponding to each amino acid on the surface of the sample protein is determined.

8. The method according to any one of claims 1 to 7, wherein: The method further comprises: Based on one or more target protein information corresponding to the target protein, the corresponding target protein sequence information is determined using the protein sequence prediction model, wherein the target protein information includes target protein surface information and target protein sequence association information.

9. The method according to claim 8, wherein: Based on the one or more target protein information corresponding to the target protein, the corresponding target protein sequence information is determined using the protein sequence prediction model, wherein the target protein information includes target protein surface information and target protein sequence association information and further includes: Using a generative simulation method, one or more target protein information corresponding to the target protein is determined.

10. The method according to claim 8 or 9, wherein: The one or more target protein information corresponding to the target protein is determined by using the protein sequence prediction model, wherein the target protein information includes target protein surface information and target protein sequence association information including: Based on one or more target protein information corresponding to the target protein, using the protein sequence prediction model, determining candidate target protein sequence information corresponding to each target protein information; Based on the candidate target protein sequence information, the corresponding target protein sequence information is determined.

11. A computer device for constructing a protein sequence prediction model, 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 10.

12. 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 10 are implemented.

13. 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 10 are implemented.

Images