Data prediction method for stable mutation site of envelope virus surface antigen

Abstract

The invention discloses a data prediction method for a stable mutation site of an envelope virus surface antigen. The method comprises the following steps: acquiring protein sequence data corresponding to antigen protein of a target virus; according to the protein sequence data, predicting each site which is kept in an unstable state in the mutation process of the target virus from each site on the protein sequence as a first candidate site, predicting each site in a pocket region from each site on the protein sequence as a second candidate site, and predicting each site in a pocket region from each site on the protein sequence as a third candidate site; determining each site capable of being combined with an antibody acting on the antigen protein of the target virus from each site on the protein sequence as a third candidate site; and determining a target site on the protein sequence according to the first candidate site, the second candidate site and the third candidate site, and executing a task. According to the scheme, the key mutation site data which does not influence the immunogenicity of the antigen protein and can ensure the stability of the antigen can be accurately predicted.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method for predicting data on stable mutation sites of enveloped virus surface antigens. Background Art

[0002] In nature, enveloped viruses such as influenza virus and respiratory syncytial virus (RSV) are the main pathogens that cause major respiratory diseases in humans. The surfaces of these viruses are covered with glycoprotein spikes, which play a key role in the infection process of the virus and are also the main targets of vaccines and therapeutic antibodies. However, the conformation of the protein on the surface of the virus will continue to change during the life cycle of the virus. Different conformational states have significant differences in the antigenicity and immunogenicity of the vaccine, making the conformational diversity and variability of viral surface proteins a huge challenge for vaccine development.

[0003] Studies have shown that antigen proteins in a specific effective conformational state play a vital role in improving the immunogenicity and protective effect of the vaccine while reducing potential risks. By maintaining the antigen protein in a specific conformational state, the immune effect of antibodies on viruses in different conformational states can be improved, allowing the human body to produce an effective immune response to viruses in different conformational states.

[0004] Currently, the antigen conformation is usually stabilized by introducing site-specific mutations, that is, by introducing mutations at key sites of the antigen protein to keep the antigen protein in a stable state. However, if site-specific mutations are to be introduced, it is necessary to find sites on the antigen protein that are suitable for introducing mutations. This requires a large amount of screening and experiments on the sites on the antigen protein. The whole process is not only inefficient, but the screening method lacks an effective basis and has poor accuracy, making it difficult to ensure that the antigen protein can remain in an effective conformational state. Summary of the invention

[0005] The present specification provides a data prediction method for stable mutation sites of enveloped virus surface antigens to partially solve the above-mentioned problems existing in the prior art.

[0006] This manual adopts the following technical solutions: This specification provides a method for predicting data on stable mutation sites of enveloped virus surface antigens, including: In response to a prediction instruction from a user, determining a target virus corresponding to a prediction task to be performed by the user; Obtaining protein sequence data corresponding to the antigenic protein of the target virus; According to the protein sequence data, predicting each site that remains in a non-stable state during the mutation of the target virus in each site on the protein sequence corresponding to the protein sequence data as a first candidate site, predicting each site located in a pocket region in each site on the protein sequence as a second candidate site, and determining each site that can bind to an antibody that acts on an antigen protein of the target virus in each site on the protein sequence as a third candidate site; A target site on the protein sequence is determined according to the first candidate site, the second candidate site and the third candidate site, so as to perform a task according to the target site.

[0007] Optionally, based on the protein sequence data, predicting each site that remains in a non-stable state in the process of mutation of the target virus in each site on the protein sequence corresponding to the protein sequence data as a first candidate site specifically includes: Determine, according to the protein sequence data, an evolutionary constraint value corresponding to each site on the protein sequence, wherein the evolutionary constraint value is used to characterize the stability of the site on the protein sequence during the virus mutation process; According to the evolutionary constraint value, the first candidate site is determined in each site on the protein sequence.

[0008] Optionally, predicting each site located in the pocket region in each site on the protein sequence as a second candidate site specifically includes: Receiving a molecular dynamics simulation instruction, and constructing a simulation environment according to the molecular dynamics simulation instruction, and parsing the protein sequence data to obtain protein structure data corresponding to the antigen protein; According to the protein structure data, a molecular dynamics simulation is performed on the protein sequence in the simulation environment to predict each site in the pocket region of each site on the protein sequence as a second candidate site.

[0009] Optionally, each site on the protein sequence that can bind to an antibody that acts on the antigen protein of the target virus is determined as a third candidate site, specifically including: Acquiring complex structure data corresponding to the complex formed by the protein sequence and the antibody; The third candidate site is determined in each site on the protein sequence according to the complex structure data.

[0010] Optionally, determining the target site on the protein sequence according to the first candidate site, the second candidate site and the third candidate site specifically includes: Determine a site common to each of the first candidate sites, each of the second candidate sites, and each of the third candidate sites as a common site; Based on the consensus site, a target site on the protein sequence is determined.

[0011] Optionally, determining the target site on the protein sequence according to the first candidate site, the second candidate site and the third candidate site specifically includes: According to the protein sequence data, determining the evolutionary constraint value and the first fitness value corresponding to each site on the protein sequence, and obtaining the complex structure data corresponding to the complex formed by the protein sequence and the antibody, and determining the second fitness value corresponding to each site on the protein sequence according to the complex structure data, wherein the evolutionary constraint value is used to characterize the stability of the site on the protein sequence during the virus mutation process, the first fitness value is used to characterize the probability that the site on the protein sequence is located in the pocket area during the movement of the antigen protein, and the second fitness value is used to characterize the affinity between the site and the antibody; For each site on the protein sequence, determining a mutation priority corresponding to the site according to an evolutionary constraint value, a first fitness value, and a second fitness value corresponding to the site; According to the mutation priority corresponding to each site, the target site is determined in each site on the protein sequence.

[0012] Optionally, according to the target site, performing a task specifically includes: Parsing the protein sequence data to obtain protein structure data corresponding to the antigen protein; Determining disulfide bond mutation sites and cavity filling sites in each target site based on the protein sequence data and the protein structure data; Several combinations of disulfide bond mutation sites and cavity filling sites are determined in each disulfide bond mutation site and each cavity filling site, and the protein sequence data is processed based on at least some of the combinations of disulfide bond mutation sites and cavity filling sites to perform a task based on the processed protein sequence data.

[0013] This specification provides a data prediction device for stable mutation sites of enveloped virus surface antigens, comprising: A response module, used to respond to a prediction instruction of a user and determine a target virus corresponding to a prediction task to be performed by the user; An acquisition module, used to acquire protein sequence data corresponding to the antigen protein of the target virus; A prediction module is used to predict, based on the protein sequence data, each site that remains in a non-stable state during the mutation of the target virus in each site on the protein sequence corresponding to the protein sequence data as a first candidate site, predict each site located in a pocket region in each site on the protein sequence as a second candidate site, and determine each site on the protein sequence that can bind to an antibody that acts on an antigen protein of the target virus as a third candidate site; An execution module is used to determine a target site on the protein sequence according to the first candidate site, the second candidate site and the third candidate site, so as to execute a task according to the target site.

[0014] The present specification provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned data prediction method for stable mutation sites on the surface antigen of an enveloped virus.

[0015] The present specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the above-mentioned data prediction method for stable mutation sites of enveloped virus surface antigens is implemented.

[0016] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects: In a data prediction method for stable mutation sites of enveloped virus surface antigens provided in the present specification, protein sequence data corresponding to the antigenic protein of the target virus is obtained; based on the protein sequence data, each site on the protein sequence corresponding to the protein sequence data that remains in an unstable state during the mutation of the target virus is predicted as the first candidate site, each site on the protein sequence is predicted to be located in the pocket area as the second candidate site, and each site on the protein sequence that can bind to antibodies acting on the antigenic protein of the target virus is determined as the third candidate site; based on the first candidate site, the second candidate site and the third candidate site, the target site on the protein sequence is determined and the task is performed.

[0017] It can be seen from the above method that, on the one hand, this scheme predicts each site that remains in an unstable state during the mutation of the target virus, so that the determined target site can be in the non-conserved region of the target virus during the mutation process, further ensuring that the natural conformation and immunogenicity of the antigen protein are not affected. On the other hand, in each site on the protein sequence, each site located in the pocket area and each site that can bind to the antibody of the antigen protein of the target virus are predicted, thereby accurately determining the site suitable for introducing mutations, while ensuring that the immunogenicity of the antigen protein is not affected, while improving the stability of the antigen protein. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings: Figure 1 A schematic diagram of a data prediction method for stable mutation sites on the surface antigen of enveloped viruses provided in this specification; Figure 2 A schematic diagram of a target site determination process provided in this specification; Figure 3 A schematic diagram of a data prediction device for stable mutation sites of enveloped virus surface antigens provided in this specification; Figure 4 A method corresponding to the Figure 1 Schematic diagram of electronic equipment. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0020] The surface proteins of type I enveloped viruses usually exist in multiple conformational states, which play different roles in the life cycle of the virus. For example, the hemagglutinin (HA) protein of influenza virus has pre-fusion and post-fusion conformations, the spike protein of SARS-CoV-2 has open and closed states, and the F protein of RSV has pre-fusion (pre-F) and post-fusion (post-F) conformations. These different conformations have a crucial impact on the effectiveness of vaccines.

[0021] Taking RSV as an example, the pre-F and post-F conformations of its F protein have significant differences in antigenicity and immunogenicity. Studies have shown that antibodies against the pre-F conformation can neutralize the virus more effectively, while antibodies against the post-F conformation may lead to lower protective effects. This discovery has a profound impact on the development of RSV vaccines.

[0022] Therefore, in the development of type I enveloped virus vaccines, maintaining the surface protein in a specific effective conformation is crucial to improving the immunogenicity and protective effect of the vaccine while reducing potential risks. To this end, researchers have developed a variety of strategies to stabilize specific conformations, including introducing site-specific mutations, using molecular clamps, optimizing protein sequences, and other methods.

[0023] Taking RSV as an example, by introducing specific mutations at key sites of the F protein, researchers successfully stabilized the pre-F conformation, which greatly improved the immunogenicity and protective effect of vaccine candidates based on this conformation. Similar strategies have also been applied to the development of other viral vaccines, such as stabilizing the prefusion conformation of the SARS-CoV-2 spike protein.

[0024] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0025] Figure 1 A schematic flow chart of a method for predicting stable mutation sites of enveloped virus surface antigens provided in this specification, comprising the following steps: S101: In response to a prediction instruction of a user, determining a target virus corresponding to a prediction task to be performed by the user; S102: Obtaining protein sequence data corresponding to the antigen protein of the target virus.

[0026] Virus protein conformational change refers to the process in which the spatial structure of its protein molecules is rearranged under specific conditions. For antigenic proteins on the surface of viruses, conformational changes may affect their ability to bind to host cell receptors, the stability of virus particles, and the recognition ability of the immune system, thereby directly affecting the infection efficiency and pathogenicity of the virus.

[0027] In practical applications, there may be many factors that lead to conformational changes in viral proteins. For example, changes in environmental conditions such as temperature, pH value, and ionic strength may cause conformational changes in viral surface antigen proteins. In addition, the antigen proteins on the surface of the virus will also undergo conformational changes when they recognize and bind to receptors on the surface of host cells. In addition, there may be some regulatory mechanisms inside the virus, such as enzyme catalysis, molecular chaperone assistance, etc., which can also lead to conformational changes in viral surface antigen proteins.

[0028] Generally, the introduction of site-specific mutations can effectively stabilize the antigen conformation. Site-specific mutations refer to purposeful changes at specific positions in the protein sequence, usually achieved by replacing, inserting or deleting one or more amino acid residues. Such mutations can affect the structure, function, stability and interaction of proteins with other molecules.

[0029] In practical applications, the evolutionarily conserved regions of proteins are usually crucial to maintaining their structural functions. Introducing mutations may destroy the natural conformation, so non-conserved regions are more suitable for introducing artificial mutations. In addition, the interaction characteristics between antibodies and proteins can reveal potential epitope regions, the stability of which is crucial to the effectiveness of vaccines. In addition, dynamic pocket regions on the surface of proteins are often associated with molecular motion, so these regions can serve as key regions for protein conformational changes.

[0030] Based on this, this specification provides a data prediction method for stable mutation sites of enveloped virus surface antigens, combining evolutionary constraints, antibody-protein interaction characteristics and dynamic pocket information to determine from multiple dimensions the key mutation sites that do not affect the natural conformation and immunogenicity but can change the conformational flexibility, and then optimize the antigen protein based on these key mutation points to carry out subsequent vaccine development tasks.

[0031] In the present specification, the execution entity for implementing a data prediction method for stable mutation sites on the surface antigen of an enveloped virus can be a designated device such as a server, or a terminal device such as a laptop computer or a desktop computer. For the sake of ease of description, the following will only take the server as an example of the execution entity to illustrate a data prediction method for stable mutation sites on the surface antigen of an enveloped virus provided in this specification.

[0032] Among them, the user can input a prediction instruction for the mutation site on the terminal device, and after receiving the prediction instruction, the server can respond to the prediction instruction and determine the target virus corresponding to the prediction task to be performed by the user.

[0033] The server can obtain protein sequence data corresponding to the antigenic protein of the target virus. In this specification, the target virus may be an enveloped virus such as influenza virus, respiratory syncytial virus RSV, etc. Of course, it can also be other types of viruses, and this specification does not make specific limitations on this.

[0034] After obtaining the protein sequence data, the server can parse the protein sequence data to obtain the protein structure data corresponding to the protein sequence of the target virus.

[0035] It should be pointed out that the data format of the above protein sequence data can be an image or text or other data format that can be recognized by a computer. In other words, the protein sequence data can be recorded in the acquired image, and the server can identify the protein sequence data through image recognition. Of course, it can also be structured text data.

[0036] S103: Based on the protein sequence data, predict each site that remains in a non-stable state during the mutation of the target virus at each site on the protein sequence corresponding to the protein sequence data as a first candidate site, predict each site located in a pocket region at each site on the protein sequence as a second candidate site, and determine each site that can bind to an antibody that acts on the antigen protein of the target virus at each site on the protein sequence as a third candidate site.

[0037] The server can determine the sites of the antigen protein in the evolutionarily non-conserved region based on the protein sequence data of the antigen protein. These sites remain stable during the mutation of the target virus, so these sites can be used as the first candidate sites.

[0038] In one embodiment provided in the present specification, the server can input the protein sequence of the antigen protein into a pre-trained evaluation model to determine the evolutionary constraint value corresponding to each site on the protein sequence through the evaluation model, and then determine the first candidate site in each site on the protein sequence based on the evolutionary constraint value corresponding to each site.

[0039] Among them, the above-mentioned evolutionary constraint value is used to characterize the stability of the site on the protein sequence during the virus mutation process. The smaller the evolutionary constraint value, the more stable the site during the virus mutation process. The server can use the site with an evolutionary constraint value greater than a preset threshold (i.e., an unstable site) as the first site. The preset threshold can be set according to actual conditions, and this manual does not make specific restrictions on this.

[0040] In practical applications, the above evaluation model can be a deep learning model based on the variational auto-encoder (VAE) architecture.

[0041] In another embodiment provided in the present specification, the server may perform a multiple sequence alignment of the protein sequence of the target virus with homologous protein sequences of other related virus strains, thereby determining, based on the alignment results, sites with significant differences between the protein sequence of the target virus and other homologous protein sequences as first candidate sites.

[0042] Of course, the server can also determine the first candidate site on the protein sequence of the target virus by other means. For example, the server can simulate the mutation process of the target virus, and then find a site with a mutation frequency higher than a preset threshold according to the simulation results as the first candidate site.

[0043] The server can also determine each site located in the pocket region in each site on the protein sequence as a second candidate site.

[0044] Among them, the protein pocket region refers to the concave area formed on the surface or inside the protein. These areas are usually able to specifically bind to other molecules (such as ligands, substrates, inhibitors, etc.), thereby participating in various physiological and pathological processes of the organism.

[0045] In one embodiment provided in this specification, the server can perform molecular dynamics simulation on the protein sequence based on the protein structure data to determine each site in the pocket region that may be formed by the protein sequence as the second candidate site.

[0046] Specifically, the server can receive the molecular dynamics simulation instructions sent by the user on the client, and build a simulation environment that matches the mutation environment of the target virus according to the molecular dynamics simulation instructions, and then perform molecular dynamics simulation on the protein sequence in the simulation environment according to the protein structure data, so as to predict each site located in the dynamic pocket area in each site on the protein sequence as the second candidate site.

[0047] In another embodiment provided in the present specification, the server can construct graph data based on protein structure data, taking atoms or residues in the protein as nodes of a graph, and defining edges between nodes according to spatial distances, chemical bonds, interactions between residues, etc., and then input the graph data into a pre-trained graph neural network model to predict the pocket area that may be formed in the protein at a specific time point and the changing trend of the pocket area over time through the graph neural network model, and then determine each site in the dynamic pocket area as the second candidate site based on the prediction results.

[0048] Furthermore, for each second candidate site, the server can determine the first fitness value corresponding to each second candidate site according to the protein structure data in the above process, and the first fitness value is used to characterize the probability that the site on the protein sequence is located in the pocket area during the molecular movement of the protein sequence. The greater the probability that the site is located in the pocket area during the dynamic behavior of the protein, the higher the first fitness value, and vice versa.

[0049] At the same time, the server can identify each site on the protein sequence that can bind to the antibody as the third candidate site.

[0050] Specifically, the server may obtain the complex structure data corresponding to the complex formed by the above protein sequence and the antibody, and then determine, based on the complex structure data, a site in each site on the protein sequence that can interact with the antibody as the third candidate site.

[0051] Among them, the server can input the complex structure data into the pre-trained affinity prediction model, and extract the physical and chemical interaction characteristics of the antibody and the antigen protein through the affinity prediction model, and then determine the second fitness value corresponding to each site on the protein sequence of the antigen protein according to the physical and chemical interaction characteristics. The second fitness value is used to characterize the affinity between the site on the protein sequence of the antigen protein and the antibody. The higher the affinity, the higher the second fitness value, and vice versa. Afterwards, the affinity prediction model can use the site with a second fitness value higher than a preset threshold as the third candidate site. The preset threshold can be set according to actual conditions, and this specification does not specifically limit this.

[0052] S104: Determine a target site on the protein sequence according to the first candidate site, the second candidate site, and the third candidate site, so as to perform a task according to the target site.

[0053] After determining the first candidate site, the second candidate site, and the third candidate site, the server may determine each target site on the protein sequence according to these sites.

[0054] In one embodiment provided in the present specification, the server may use the common sites among the first candidate sites, the second candidate sites and the third candidate sites (i.e., the sites in the intersection of the first candidate sites, the second candidate sites and the third candidate sites) as common candidate sites, and then the server may use these common sites as target sites on the protein sequence.

[0055] In another embodiment provided in this specification, for each site on the protein sequence, the server can determine the mutation priority corresponding to the site according to the evolutionary constraint value, the first fitness value and the second fitness value corresponding to the site, and then determine the target site in each site on the protein sequence according to the mutation priority corresponding to each site. (For details on the determination process of the evolutionary constraint value, the first fitness value and the second fitness value, please refer to step S103).

[0056] For example, the server may use each site with a mutation priority greater than a preset priority as a target site. The size of the preset priority may be set according to actual conditions, and this specification does not make any specific limitation on this.

[0057] In practical applications, there are many ways to determine the above mutation priority. For example, the server can use the product of the evolution constraint value, the first fitness value and the second fitness value as the score of the mutation priority. For another example, the server can use the average of the evolution constraint value, the first fitness value and the second fitness value as the score of the mutation priority. Of course, the server can also set a weight for the evolution constraint value, the first fitness value and the second fitness value respectively, and then determine the score of the mutation priority by weighted summation.

[0058] It should be noted that in the process of calculating the mutation priority score, the server can normalize the evolution constraint value, the first adaptation value and the second adaptation value respectively in an existing manner so that these values ​​are at the same calculation level, and then determine the mutation priority based on these normalized values.

[0059] Furthermore, the server can combine the above two methods of determining target sites to determine the target site at each site of the protein sequence, that is, the site common to each first candidate site, each second candidate site, and each third candidate site is used as a common candidate site, and then the mutation priority corresponding to each common candidate site is determined, and then the common candidate site with a mutation priority higher than the preset priority is used as the target site. For ease of understanding, this specification provides a schematic diagram of the process of determining the target site, such as Figure 2 shown.

[0060] Figure 2 A schematic diagram of a target site determination process provided in this specification.

[0061] Among them, after the server obtains the protein sequence of the target virus, it can determine the first candidate site located in the unstable region (non-conserved region) during the virus mutation process, the second candidate site located in the dynamic pocket region, and the third candidate site located in the complex interaction region, thereby determining the target site based on the first candidate site, the second candidate site and the third candidate site.

[0062] After determining the target site, the server can optimize the protein sequence according to the target site to perform the task according to the processed original protein sequence.

[0063] Specifically, the server can determine the disulfide bond mutation sites and cavity filling sites contained in each target site based on the protein sequence data and the protein structure data, and then determine several combinations of disulfide bond mutation sites and cavity filling sites in each disulfide bond mutation site and each cavity filling site, and use each pair of combinations as the minimum optimization unit in the protein sequence, and then select at least some of the minimum optimization units therefrom, and introduce specific mutations in the sites contained in these minimum optimization units to achieve optimization of the protein sequence.

[0064] For each selected minimum optimization unit, the optimization process can be to introduce a mutation factor into the disulfide bond mutation site therein, so that the original chemical bond at the site mutates into a disulfide bond, and to introduce a filling factor (such as amino acids or other molecules) into the cavity at the cavity filling site to fill the cavity.

[0065] Furthermore, the server may divide the protein sequence of the antigen protein into three regions: upper, middle and lower regions, and determine a number of minimum optimization units in each region for optimization.

[0066] In addition, the server can use molecular dynamics simulation and structural stability prediction tools to evaluate the effects of designed mutations on protein structural stability. Based on the stability evaluation results, the optimal mutation combination scheme is screened out.

[0067] After completing the optimization of the antigen protein, the server can perform the task of vaccine design for the target virus based on the optimized antigen protein sequence.

[0068] It can be seen from the above methods that this scheme innovatively integrates protein evolution constraints, antibody-protein interaction characteristics and dynamic pocket information, providing a multi-dimensional and systematic method for optimizing the stability of vaccine antigens. The concept of the minimum optimization unit is introduced, and the precise regulation of protein conformation is achieved through the combination of disulfide bonds and cavity filling. Fixed positions are designed in the key areas of protein conformation to effectively lock the protein conformation while maintaining immunogenicity. The range of candidate mutation sites is significantly narrowed, greatly reducing the workload of subsequent experimental verification. In addition, this method can be widely used in the stability design of various enveloped virus vaccine antigens (such as influenza, RSV, etc.), and has significant universality.

[0069] The above is one or more embodiments of this specification. A data prediction method for stable mutation sites of enveloped virus surface antigens. Based on the same idea, this specification also provides a corresponding data prediction device for stable mutation sites of enveloped virus surface antigens, such as Figure 3 shown.

[0070] Figure 3 A schematic diagram of a data prediction device for stable mutation sites of enveloped virus surface antigens provided in this specification, comprising: A response module 301 is used to respond to a prediction instruction of a user and determine a target virus corresponding to a prediction task to be performed by the user; An acquisition module 302 is used to acquire protein sequence data corresponding to the antigen protein of the target virus; A prediction module 303 is used to predict, based on the protein sequence data, each site on the protein sequence corresponding to the protein sequence data that remains in a non-stable state during the mutation of the target virus as a first candidate site, predict each site in the pocket region of each site on the protein sequence as a second candidate site, and determine each site on the protein sequence that can bind to an antibody that acts on the antigen protein of the target virus as a third candidate site; The execution module 304 is used to determine the target site on the protein sequence according to the first candidate site, the second candidate site and the third candidate site, so as to execute a task according to the target site.

[0071] Optionally, the prediction module 303 is specifically used to determine, based on the protein sequence data, an evolutionary constraint value corresponding to each site on the protein sequence, wherein the evolutionary constraint value is used to characterize the stability of the site on the protein sequence during the viral mutation process; and based on the evolutionary constraint value, determine the first candidate site in each site on the protein sequence.

[0072] Optionally, the prediction module 303 is specifically used to receive molecular dynamics simulation instructions, and according to the molecular dynamics simulation instructions, construct a simulation environment, and parse the protein sequence data to obtain protein structure data corresponding to the antigen protein; according to the protein structure data, perform molecular dynamics simulation on the protein sequence in the simulation environment to predict each site located in the pocket area in each site on the protein sequence as the second candidate site.

[0073] Optionally, the prediction module 303 is specifically used to obtain complex structure data corresponding to the complex formed by the protein sequence and the antibody; and determine the third candidate site in each site on the protein sequence according to the complex structure data.

[0074] Optionally, the execution module 304 is specifically used to determine a site common to each of the first candidate sites, each of the second candidate sites, and each of the third candidate sites as a common site; and determine a target site on the protein sequence based on the common site.

[0075] Optionally, the execution module 304 is specifically used to determine the evolutionary constraint value and the first fitness value corresponding to each site on the protein sequence according to the protein sequence data, and to obtain the complex structure data corresponding to the complex formed by the protein sequence and the antibody, and to determine the second fitness value corresponding to each site on the protein sequence according to the complex structure data, wherein the evolutionary constraint value is used to characterize the stability of the site on the protein sequence during the virus mutation process, the first fitness value is used to characterize the probability that the site on the protein sequence is located in the pocket area during the movement of the antigen protein, and the second fitness value is used to characterize the affinity between the site and the antibody; for each site on the protein sequence, the mutation priority corresponding to the site is determined according to the evolutionary constraint value, the first fitness value and the second fitness value corresponding to the site; according to the mutation priority corresponding to each site, the target site is determined in each site on the protein sequence.

[0076] Optionally, the execution module 304 is specifically used to parse the protein sequence data to obtain protein structure data corresponding to the antigen protein; determine disulfide bond mutation sites and cavity filling sites in each target site based on the protein sequence data and the protein structure data; determine a combination of several disulfide bond mutation sites and cavity filling sites in each disulfide bond mutation site and each cavity filling site, and process the protein sequence data based on at least some of the combinations of disulfide bond mutation sites and cavity filling sites to execute the task based on the processed protein sequence data.

[0077] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A data prediction method for stable mutation sites of enveloped virus surface antigens is provided.

[0078] This manual also provides Figure 4 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 4 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The data prediction method for the stable mutation site of the surface antigen of the enveloped virus. Of course, in addition to the software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0079] For the improvement of a technology, it can be clearly distinguished whether it is a hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or a software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0080] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0081] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0082] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0083] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0084] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0087] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0088] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0089] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (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 disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic 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. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0090] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0091] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0093] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0094] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A data prediction method for stable mutation sites of enveloped virus surface antigens, characterized in that: include: In response to a prediction instruction from a user, determining a target virus corresponding to a prediction task to be performed by the user; Obtaining protein sequence data corresponding to the antigenic protein of the target virus; According to the protein sequence data, predicting each site that remains in a non-stable state during the mutation of the target virus in each site on the protein sequence corresponding to the protein sequence data as a first candidate site, predicting each site located in a pocket region in each site on the protein sequence as a second candidate site, and determining each site that can bind to an antibody that acts on an antigen protein of the target virus in each site on the protein sequence as a third candidate site; A target site on the protein sequence is determined according to the first candidate site, the second candidate site and the third candidate site, so as to perform a task according to the target site.

2. The method according to claim 1, characterized in that According to the protein sequence data, predicting each site that remains in an unstable state during the mutation of the target virus in each site on the protein sequence corresponding to the protein sequence data as a first candidate site specifically includes: Determine, according to the protein sequence data, an evolutionary constraint value corresponding to each site on the protein sequence, wherein the evolutionary constraint value is used to characterize the stability of the site on the protein sequence during the virus mutation process; According to the evolutionary constraint value, the first candidate site is determined in each site on the protein sequence.

3. The method according to claim 1, characterized in that Predicting each site in the pocket region of each site on the protein sequence as a second candidate site specifically includes: Receiving a molecular dynamics simulation instruction, and constructing a simulation environment according to the molecular dynamics simulation instruction, and parsing the protein sequence data to obtain protein structure data corresponding to the antigen protein; According to the protein structure data, a molecular dynamics simulation is performed on the protein sequence in the simulation environment to predict each site in the pocket region of each site on the protein sequence as a second candidate site.

4. The method according to claim 1, characterized in that In each site on the protein sequence, each site that can bind to the antibody acting on the antigen protein of the target virus is determined as the third candidate site, specifically including: Acquiring complex structure data corresponding to the complex formed by the protein sequence and the antibody; The third candidate site is determined in each site on the protein sequence according to the complex structure data.

5. The method according to claim 1, characterized in that Determining a target site on the protein sequence according to the first candidate site, the second candidate site, and the third candidate site specifically includes: Determine a site common to each of the first candidate sites, each of the second candidate sites, and each of the third candidate sites as a common site; Based on the consensus site, a target site on the protein sequence is determined.

6. The method according to claim 1, characterized in that Determining a target site on the protein sequence according to the first candidate site, the second candidate site, and the third candidate site specifically includes: According to the protein sequence data, determining the evolutionary constraint value and the first fitness value corresponding to each site on the protein sequence, and obtaining the complex structure data corresponding to the complex formed by the protein sequence and the antibody, and determining the second fitness value corresponding to each site on the protein sequence according to the complex structure data, wherein the evolutionary constraint value is used to characterize the stability of the site on the protein sequence during the virus mutation process, the first fitness value is used to characterize the probability that the site on the protein sequence is located in the pocket area during the movement of the antigen protein, and the second fitness value is used to characterize the affinity between the site and the antibody; For each site on the protein sequence, determining a mutation priority corresponding to the site according to an evolutionary constraint value, a first fitness value, and a second fitness value corresponding to the site; According to the mutation priority corresponding to each site, the target site is determined in each site on the protein sequence.

7. The method according to claim 1, characterized in that According to the target site, tasks are performed, including: Parsing the protein sequence data to obtain protein structure data corresponding to the antigen protein; Determining disulfide bond mutation sites and cavity filling sites in each target site based on the protein sequence data and the protein structure data; Several combinations of disulfide bond mutation sites and cavity filling sites are determined in each disulfide bond mutation site and each cavity filling site, and the protein sequence data is processed based on at least some of the combinations of disulfide bond mutation sites and cavity filling sites to perform a task based on the processed protein sequence data.

8. A data prediction device for stable mutation sites of enveloped virus surface antigens, characterized in that: include: A response module, used to respond to a prediction instruction of a user and determine a target virus corresponding to a prediction task to be performed by the user; An acquisition module, used to acquire protein sequence data corresponding to the antigen protein of the target virus; A prediction module is used to predict, based on the protein sequence data, each site that remains in a non-stable state during the mutation of the target virus in each site on the protein sequence corresponding to the protein sequence data as a first candidate site, predict each site located in a pocket region in each site on the protein sequence as a second candidate site, and determine each site on the protein sequence that can bind to an antibody that acts on an antigen protein of the target virus as a third candidate site; An execution module is used to determine a target site on the protein sequence according to the first candidate site, the second candidate site and the third candidate site, so as to execute a task according to the target site.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images