Three-dimensional reconstruction method and system for viruses based on three-dimensional gaussian blurring

Abstract

The embodiment of the application discloses a virus three-dimensional reconstruction method and system based on three-dimensional Gaussian splash, and the method comprises the following steps: acquiring three-dimensional point cloud data of a target virus; performing molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, identifying a high-energy interaction region, and acquiring binding energy data of the target virus and host molecules in the interaction process; tracking the conformational change of the virus structure to obtain conformational change data; performing three-dimensional Gaussian splash processing on the point cloud data to generate an in-situ visual three-dimensional model of the target virus; and in the Gaussian splash processing, the shape, direction and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and the conformational change data. The application realizes efficient generation of a virus three-dimensional model according to the characteristics of the virus.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of biomedical imaging and computer vision, and particularly relates to a virus three-dimensional reconstruction method and system based on three-dimensional Gaussian splatting. BACKGROUND

[0002] With the deepening of virology research, the interaction mechanism between viruses and host molecules (such as receptors and antibodies) has become a key to drug design and vaccine development. Traditional virus three-dimensional reconstruction methods mainly rely on cryo-electron microscopy (Cryo-EM) or X-ray crystallography to generate static high-resolution structures, but it is difficult to capture the dynamic conformational changes and energy distribution of viruses during the interaction process. Three-dimensional Gaussian splatting, as a point cloud rendering technology, converts point cloud points into ellipsoid Gaussian kernels, achieving efficient and high-fidelity three-dimensional reconstruction. However, existing Gaussian splatting techniques are mainly used for reconstruction of buildings or objects, and are not optimized for the characteristics of viruses, making it difficult to meet the needs of virology research.

[0003] Therefore, there is an urgent need for a virus three-dimensional reconstruction method that combines Gaussian splatting to efficiently generate dynamic three-dimensional models of viruses based on their characteristics. SUMMARY

[0004] The present application provides a virus three-dimensional reconstruction method based on three-dimensional Gaussian splatting, which efficiently generates dynamic three-dimensional models of viruses based on their characteristics.

[0005] The present application provides the following solutions:

[0006] According to a first aspect, a virus three-dimensional reconstruction method based on three-dimensional Gaussian splatting is provided, the method comprising: obtaining three-dimensional point cloud data of a target virus, the point cloud data including spatial coordinates, geometric features, and biological attributes; performing molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, calculating the binding site energy distribution of the target virus and host molecules, identifying high-energy interaction regions, and obtaining binding energy data of the target virus and host molecules during the interaction process; and tracking the conformational changes of the virus structure through time series atomic coordinate analysis to obtain conformational change data; performing three-dimensional Gaussian splatting processing on the point cloud data to generate an in-situ visual three-dimensional model of the target virus; wherein in the Gaussian splatting processing, the shape, direction, and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and conformational change data.

[0007] According to an implementable manner in the embodiments of the present application, in the Gaussian splash processing, dynamically adjusting the shape, direction and weight of the Gaussian kernel according to the binding energy data and the conformation change data comprises: converting each point in the point cloud data into a Gaussian kernel respectively, the parameters of the Gaussian kernel including Gaussian distribution representation, color representation and opacity representation corresponding to the point in the point cloud data; wherein the Gaussian distribution representation includes shape information and direction information of the Gaussian kernel; adjusting the shape information of the Gaussian kernel corresponding to each point in the point cloud according to the binding energy distribution data; adjusting the direction information in the Gaussian distribution representation according to the conformation change data, so that the shape of the Gaussian kernel is along the normal vector direction of the interaction region; dynamically adjusting the weight of each Gaussian kernel according to the biological attribute of the interaction region of the target virus and the host molecule.

[0008] According to an implementable manner in the embodiments of the present application, dynamically adjusting the weight of each Gaussian kernel according to the biological attribute of the interaction region of the target virus and the host molecule comprises: obtaining the biological attribute of the high-energy interaction region, the biological attribute including binding affinity and immunogenicity; using a quantitative mapping function to calculate the weight of each Gaussian kernel according to the binding affinity and the immunogenicity, wherein on the basis of assigning higher weight to the interaction region with high binding affinity, the weight of the interaction region with high immunogenicity is further increased.

[0009] According to an implementable manner in the embodiments of the present application, the method further comprises: pre-calculating a plurality of key states of the target virus and the host molecule in the interaction process based on the coarse-grained molecular dynamics model, the key states including binding energy and conformation change data at different infection times; in the Gaussian splash processing, dynamically adjusting the shape, direction and weight of the Gaussian kernel according to the binding energy data and the conformation change data comprises: using an interpolation algorithm to generate point cloud data and kernel parameters with smooth transition between the key states, forming a pseudo-real-time demonstration effect; based on the pseudo-real-time data, dynamically adjusting the shape, direction and weight of the Gaussian kernel to generate a continuous three-dimensional rendering model.

[0010] According to an implementable manner in the embodiments of the present application, the method further comprises: modifying the parameters of the point cloud region with significant conformation change and energy distribution based on the shape, direction and weight of the Gaussian kernel of the previous infection state; and / or using a predictive optimization algorithm based on Kalman filtering to predict the conformation change and energy distribution of the next infection state, and pre-adjust the parameters of the Gaussian kernel.

[0011] According to an implementable manner in the embodiments of the present application, the three-dimensional Gaussian splash processing is performed on the point cloud data to generate the in-situ visual three-dimensional model of the target virus, including: retaining key Gaussian kernels, deleting other Gaussian kernels, and generating a continuous three-dimensional rendering model by using the key Gaussian kernels; wherein the method for determining the importance degree includes: calculating the binding energy values of the point cloud points corresponding to each Gaussian kernel according to the binding energy data, obtaining a first Gaussian kernel set with an absolute binding energy value higher than a first preset threshold; evaluating the conformational change amplitudes of each point cloud point according to the conformational change data, obtaining a second Gaussian kernel set with a conformational change higher than a second preset threshold; obtaining a third Gaussian kernel set with high immunogenicity or high hydrophobicity according to the biological attributes; calculating the union set of the first Gaussian kernel set, the second Gaussian kernel set and the third Gaussian kernel set, and obtaining the key Gaussian kernels.

[0012] According to an implementable manner in the embodiments of the present application, when the method performs three-dimensional Gaussian splash processing on the point cloud data to generate a continuous visual three-dimensional real scene model of the target virus, it further includes: adjusting the color representation and opacity representation of the Gaussian kernel corresponding to the functional region of the target virus based on the biological attributes of the point cloud data; wherein the biological attributes include immunogenicity or hydrophobicity; the functional region includes an immunodominant epitope or a structural stability region; the color representation is mapped to a specific color channel according to the immunogenicity, and the opacity representation is dynamically adjusted according to the hydrophobicity value.

[0013] According to a second aspect, a virus three-dimensional reconstruction system based on three-dimensional Gaussian splash is provided, characterized in that the system includes: a point cloud data acquisition unit configured to acquire three-dimensional point cloud data including a target virus, the point cloud data including spatial coordinates, geometric features and biological attributes; a dynamics simulation unit configured to perform molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, calculate the binding site energy distribution of the target virus and host molecules, identify high-energy interaction regions, obtain the binding energy data of the target virus and host molecules in the interaction process; and track the conformational change of the virus structure by time series atomic coordinate analysis, and obtain conformational change data; a three-dimensional reconstruction unit configured to perform three-dimensional Gaussian splash processing on the point cloud data to generate an in-situ visual three-dimensional model of the target virus; wherein in the Gaussian splash processing, the shape, direction and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and conformational change data.

[0014] According to a third aspect, a computer readable storage medium is provided, which stores a computer program, the program being executed by a processor to implement the steps of the method of any one of the above first aspect.

[0015] According to a fourth aspect, there is provided an electronic device comprising: one or more processors; and a memory associated with the one or more processors, the memory for storing program instructions that, when read and executed by the one or more processors, perform the steps of the method of any one of the first aspect.

[0016] According to the specific embodiments provided in the present application, the present application discloses the following technical effects:

[0017] The present application realizes the visual modeling effect more in line with the real behavior of biological molecules by introducing binding energy data and conformation change data in three-dimensional Gaussian splash processing, dynamically adjusting the shape, direction and weight of the Gaussian kernel, not only improving the continuity and authenticity of virus three-dimensional structure reconstruction, but also enhancing the expression ability of key interaction regions, highlighting the high-energy binding region and its conformation change characteristics, so that the model can more accurately reflect the action mechanism of virus and host at the spatial level. It has higher expression accuracy and practical value in displaying biological properties and molecular dynamic information, and is helpful for in-depth research on virus structure and visualization analysis of interaction mechanism.

[0018] Of course, implementing any product of the present application does not necessarily require all the advantages described above to be achieved at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0020] Figure 1 is a system architecture diagram applicable to the embodiments of the present application;

[0021] Figure 2 is a flowchart of the virus three-dimensional reconstruction method based on three-dimensional Gaussian splash provided by the embodiments of the present application;

[0022] Figure 3 is a structural block diagram of the virus three-dimensional reconstruction system based on three-dimensional Gaussian splash provided by the embodiments of the present application;

[0023] Figure 4 is a schematic block diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0024] With reference to the drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art belong to the scope of protection of the present application.

[0025] The terms used in the embodiments of the present application are merely for the purpose of describing the specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0026] It should be understood that the term "and / or" used herein is merely to describe the association relationship of the associated objects, and means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0027] Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted as "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0028] Currently, there are some three-dimensional reconstruction techniques for viruses, which mainly rely on cryo-electron microscopy (Cryo-EM) or X-ray crystallography to generate static high-resolution structures, but it is difficult to capture the dynamic conformational changes and energy distribution of viruses during interaction.

[0029] Therefore, the present application provides a new idea. In order to facilitate the understanding of the present application, first, the system architecture based on the present application is described. Figure 1 An exemplary system architecture to which embodiments of the present application can be applied is shown, as shown in Figure 1 The system architecture can include a user device and a three-dimensional reconstruction system located at a server end.

[0030] The user can input stereoscopic data and point cloud data through a user device, which sends the data to a three-dimensional reconstruction system on a server side. The three-dimensional reconstruction system can use the method provided in the embodiments of the present application to perform three-dimensional reconstruction on a target virus sample to obtain an in-situ three-dimensional model. The server side can send the three-dimensional real scene model to a user terminal, which uses the three-dimensional real scene model to perform rendering to obtain a two-dimensional image, a three-dimensional image, etc.

[0031] The user device can include, but is not limited to, a smart mobile terminal, a smart home device, a wearable device, a PC (Personal Computer), etc. The smart mobile device can include a mobile phone, a tablet computer, a notebook computer, a PDA (Personal Digital Assistant), an Internet car, etc. The smart home device can include a smart television, a smart refrigerator, etc. The wearable device can include a smart watch, smart glasses, etc.

[0032] The three-dimensional reconstruction system can be set as an independent server, a server group, or a cloud server. The cloud server, also known as a cloud computing server or a cloud host, is a host product in a cloud computing service system, which solves the defects of large management difficulty and weak service scalability in traditional physical hosts and VPS (Virtual Private Server) services. In addition to the architecture shown in the figure, the three-dimensional reconstruction system can also be set in a computer terminal with strong computing power. Figure 1

[0033] It should be understood that the user device and the three-dimensional reconstruction system in the figure are only illustrative. According to the implementation needs, there can be any number of user devices and three-dimensional reconstruction systems. Figure 1

[0034] Figure 2 A three-dimensional reconstruction method of a virus based on three-dimensional Gaussian splash provided in the embodiments of the present application is shown in the figure. The method can be executed by a three-dimensional reconstruction system of a virus based on three-dimensional Gaussian splash in the system shown in the figure. As shown in the figure, the method can include the following steps: Figure 1 Figure 2

[0035] Step 201: Obtain three-dimensional point cloud data of a target virus, which includes spatial coordinates, geometric features, and biological attributes.

[0036] ​​​​Step 202: Based on the coarse-grained molecular dynamics model, the binding site energy distribution of the target virus and host molecules is calculated, the high-energy interaction region is identified, and the binding energy data of the target virus and host molecules in the interaction process is obtained; and through time series atomic coordinate analysis, the conformational change of the virus structure is tracked, and conformational change data is obtained.

[0037] Step 203: Perform three-dimensional Gaussian splash processing on the point cloud data to generate an in-situ visual three-dimensional model of the target virus; wherein in the Gaussian splash processing, the shape, direction and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and conformational change data.

[0038] From the above process, it can be seen that by introducing the binding energy data and conformational change data in the three-dimensional Gaussian splash processing and dynamically adjusting the shape, direction and weight of the Gaussian kernel, a visual modeling effect more consistent with the behavior of real biological molecules is achieved. Not only does it improve the continuity and authenticity of virus three-dimensional structure reconstruction, but also enhances the expression ability of key interaction regions, highlighting the high-energy binding region and its conformational change characteristics, making the model more accurately reflect the virus-host interaction mechanism in the spatial level. In terms of displaying biological properties and molecular dynamic information, it has higher expression accuracy and practical value, which helps in-depth research of virus structure and visualization analysis of interaction mechanism.

[0039] The steps in the above process and the effects that can be further produced will be described in detail below with respect to the embodiments. It should be noted that the "first", "second" and the like in the present disclosure do not have the limitations of size, order and quantity, and are only used to distinguish in name, for example, "first preset threshold" and "second preset threshold" are used to distinguish two thresholds.

[0040] First, the above step 201, i.e., "obtaining three-dimensional point cloud data including a target virus, the point cloud data including spatial coordinates, geometric features and biological properties", will be described in detail with respect to the embodiments.

[0041] Point cloud data is a discrete three-dimensional representation, composed of a large number of points, each carrying multidimensional information, used to describe the surface structure and characteristics of the target virus. Point cloud data not only contains the geometric shape of the virus, but also integrates biological information, ensuring that subsequent rendering can reflect both the physical structure and biological function of the virus. For example, for the spike protein of the new coronavirus, point cloud data can represent its surface morphology and functional characteristics, providing comprehensive data support for dynamic visualization.

[0042] The content of the point cloud data includes three parts: spatial coordinates, geometric features, and biological attributes. Spatial coordinates refer to the position of each point cloud point in three-dimensional space (x, y, z) in nanometers (nm), accurately describing the geometric position of the virus surface. Geometric features can include information such as normal vectors and curvatures, where normal vectors represent the surface direction of the point cloud point for direction adjustment of the Gaussian kernel; curvature reflects surface shape changes to assist in rendering details. Biological attributes cover functional characteristics such as immunogenicity and hydrophobicity, for example, the immunogenicity score of the RBD binding site may be 0.7, and the hydrophobicity value is 0.5. These attributes provide the basis for the visualization of interaction regions and functional regions.

[0043] Point cloud data can be obtained in various ways, for example, using a cryogenic electron microscope (Cryo-EM), X-ray crystallography, an atomic force microscope, a scanning electron microscope, a transmission electron microscope scan, auxiliary three-dimensional laser scanning or structured light scanning, to collect three-dimensional point cloud data of the target virus surface.

[0044] The following describes the step 202, i.e., "performing molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, calculating the binding site energy distribution of the target virus and host molecules, identifying high-energy interaction regions, obtaining binding energy data of the target virus and host molecules during the interaction process; and tracking conformational changes in the virus structure through time series atomic coordinate analysis to obtain conformational change data", in detail in conjunction with an embodiment.

[0045] The present application uses molecular dynamics simulation technology to generate dynamic data of the target virus and host molecules during the interaction process. Molecular dynamics simulation solves the motion equation of the molecular system through numerical methods, simulates the dynamic behavior of atoms or molecules, and outputs time series data for analyzing the structural changes and interaction characteristics of the virus. The present application combines a coarse-grained model to calculate the binding site energy distribution of the virus and host molecules, identify high-energy interaction regions, and track conformational changes, providing binding energy data and conformational change data for dynamic rendering of the three-dimensional model. For example, for the interaction between the spike protein of the new coronavirus and the ACE2 receptor, the simulation can reveal the energy distribution of the binding site and the conformational dynamics, providing a basis for the study of the infection mechanism.

[0046] The coarse-grained molecular dynamics model is the core technical means of the present application. Compared with full-atom molecular dynamics simulation, the coarse-grained model simplifies multiple atoms into a "bead" or pseudo-atom, reducing the system degrees of freedom and thus significantly reducing the computational load. The present patent uses a coarse-grained model to simulate the target virus, which can be implemented using a simulation platform. For example, the spike protein of the new coronavirus, the system includes about 3000 residues of viral protein, 600 residues of host molecules, and surrounding water molecules and ions.

[0047] Binding site energy distribution and interaction region identification are important outputs of molecular dynamics simulations. This feature calculates binding site energy distribution of virus and host molecules through coarse-grained models, identifies high-energy interaction regions, and obtains binding energy data. Binding sites refer to regions where the virus surface directly contacts host molecules, such as the binding interface between the receptor binding domain of the spike protein and the ACE2 receptor. Binding energy is calculated using the molecular mechanics-Poisson-Boltzmann surface area method, with typical values ranging from -10 to -15 kilocalories per mole. High-energy interaction regions typically refer to regions with higher absolute binding energy values, such as the binding site of the receptor binding domain, which can reach -15 kilocalories per mole, much higher than the -5 kilocalories per mole of non-interacting regions. These data are used for subsequent Gaussian kernel adjustment to highlight the rendering effect of the interaction regions.

[0048] Time series atomic coordinate analysis is used to track conformational changes in virus structures, generating conformational change data. Molecular dynamics simulations output trajectory files containing atomic coordinates for each frame, and time series atomic coordinate analysis processes these coordinates to quantify dynamic changes in virus structures. For example, the conformational change of the receptor binding domain of the spike protein from closed to open can be calculated using the root mean square deviation, with a typical value of 2 angstroms. The analysis process includes extracting coordinates, calculating normal vectors, and updating point cloud data. Normal vectors are generated from coordinates using principal component analysis or curvature analysis, reflecting surface geometry changes, such as the receptor binding domain normal vector changing from [0, 0, 1] to [0.7, 0.7, 0]. Conformational change data drives point cloud updates, generating dynamic point clouds of approximately 100,000 points per frame, providing geometric input for Gaussian splashing.

[0049] The following embodiments describe the step 203 in detail, which is "performing three-dimensional Gaussian splashing on the point cloud data to generate an in-situ visualized three-dimensional model of the target virus; wherein, in the Gaussian splashing process, the shape, direction, and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and conformational change data."

[0050] This application uses three-dimensional Gaussian splashing technology to convert discrete point cloud data into continuous three-dimensional models, dynamically displaying the structure and interaction characteristics of the target virus. Three-dimensional Gaussian splashing is an advanced point cloud rendering method that assigns an ellipsoidal Gaussian kernel to each point cloud point to generate smooth surface effects, suitable for efficient and high-fidelity three-dimensional reconstruction. This application uses binding energy data and conformational change data to dynamically adjust Gaussian kernel parameters, ensuring that the model accurately reflects dynamic changes in virus interaction regions such as the receptor binding domain of the spike protein, such as the conformational transition from closed to open, and the visual prominence of high-energy binding sites, thereby supporting virology research and drug design.

[0051] The technical feature plays a crucial role in the patent. It integrates point cloud data, binding energy data, and conformational change data into a dynamic three-dimensional model, achieving high-fidelity visualization of virus interaction characteristics. In Gaussian blur, each point cloud point is represented as a three-dimensional Gaussian kernel, and the three-dimensional model is essentially composed of a series of Gaussian kernels that can be mapped to a specific viewing angle during subsequent rendering of the in-situ three-dimensional model, generating an image. These Gaussian kernels are represented by Gaussian distribution, color, and opacity, which are usually encoded as vector representations, so a series of Gaussian kernels are actually encoded as Gaussian distribution matrix, color matrix, and opacity matrix, respectively. After these matrices are initialized, they are continuously optimized through a series of training iterations, and the resulting Gaussian kernels constitute the in-situ three-dimensional model.

[0052] To meet the needs of virus three-dimensional reconstruction, the application proposes a dynamic adjustment mechanism to dynamically adjust the shape, direction, and weight of the Gaussian kernel based on binding energy data and conformational change data. For example, in areas where the virus surface has strong binding energy or significant conformational changes with host molecules, sharper and more concentrated Gaussian kernels (i.e., more elongated shape and higher weight) can be used to highlight these functional areas in the visualization model; while in stable or less changing areas, less flat and lower weight Gaussian kernels can be used to reduce visual interference.

[0053] As an implementable way, the application converts each point in the point cloud data into a Gaussian kernel, and the parameters of the Gaussian kernel include Gaussian distribution representation, color representation, and opacity representation corresponding to the points in the point cloud; wherein the Gaussian distribution representation includes shape information and direction information of the Gaussian kernel; the shape information of the Gaussian kernel corresponding to each point in the point cloud is adjusted according to the binding energy distribution data; the direction information in the Gaussian distribution representation is adjusted according to the conformational change data, so that the shape of the Gaussian kernel is along the normal vector direction of the interaction region; the weight of each Gaussian kernel is dynamically adjusted according to the biological properties of the interaction region between the target virus and the host molecule.

[0054] Specifically, the Gaussian kernel parameters include Gaussian distribution representation, color representation, and opacity representation, providing multi-dimensional control for rendering. The Gaussian distribution representation defines the geometric properties of the Gaussian kernel, including shape information and direction information. The shape information is determined by the eigenvalues of the covariance matrix, controlling the size of the kernel. The direction information is determined by the eigenvectors of the covariance matrix, reflecting the orientation of the Gaussian kernel, which is usually aligned with the normal vector of the point cloud point.

[0055] First, the three-dimensional point cloud data of the target virus is obtained, and each point is assigned with initial Gaussian distribution, color and opacity parameters. Then, molecular dynamics simulation is performed to obtain the binding energy distribution and conformational change data. In the high-energy binding region, the shape of the Gaussian kernel corresponding to the point is adjusted to be more elongated or more concentrated. Taking the binding region of the spike protein of the new coronavirus and the human ACE2 receptor as an example, in this high-energy binding region, a point A in the point cloud is located at a key contact site between the RBD (receptor binding domain) and ACE2. After molecular dynamics simulation, the binding energy value of this point is significantly higher than that of the surrounding area, indicating that it plays an important role in the virus infection process. To enhance the visual prominence and structural expression of this point in the three-dimensional model, the Gaussian kernel corresponding to this point can be adjusted to a more concentrated or more elongated form. For example, by default, the covariance matrix of the Gaussian kernel is the unit matrix, indicating that the Gaussian kernel is uniformly expanded in each direction, i.e., the Gaussian kernel is in a spherical distribution with a standard deviation of 1.0. After adjustment, the Gaussian kernel of point A can be set to have a smaller standard deviation along the surface normal direction (e.g., the z-axis), such as a standard deviation of 0.5, while being slightly stretched in the transverse direction (e.g., the x-axis and y-axis), such as x-axis standard deviation = y-axis standard deviation = 0.8, so as to form an ellipsoid that is more concentrated along the vertical direction of the contact surface.

[0056] According to the conformational change analysis results, the displacement direction or surface normal vector of each point during the simulation process is extracted, and the direction of the Gaussian kernel is set to better conform to the actual conformational trend of the interaction region. Continuing with the above example, in the receptor binding domain of the spike protein of the new coronavirus, a point C in the point cloud is located at an amino acid residue position at the top of the RBD. During the conformational transition from "descending" to "ascending", this point has an average displacement of 0.8 nanometers along the z-axis direction, showing a clear vertical opening trend, with a displacement unit vector of (0, 0, 1). To express this conformational trend in the three-dimensional Gaussian splash model, we adjust the Gaussian kernel of point C from the default spherical distribution to an ellipsoid stretched along the z-axis direction. For example, the Gaussian kernel originally has a standard deviation of 1 in each direction, and the principal axis direction is by default along the z-axis. Simulation analysis results show that the displacement direction of this point is 45 degrees inclined to the xy-plane direction (0.7, 0.7, 0), so the principal axis direction is rotated to the (0.7, 0.7, 0) direction through a rotation matrix to complete the direction adjustment.

[0057] Finally, according to the biological attributes such as the importance of the functional region in the virus life cycle, the weight of each Gaussian kernel is dynamically adjusted, thereby completing a more accurate three-dimensional visualization reconstruction in terms of spatial morphology and biological significance.

[0058] Preferably, the dynamic adjustment of the weight of each Gaussian kernel in the present application can be realized by the following way: obtaining the biological properties of the high-energy interaction region, including binding affinity and immunogenicity; using a quantitative mapping function to calculate the weight of each Gaussian kernel according to the binding affinity and immunogenicity, wherein the interaction region with high binding affinity is assigned a higher weight, and the interaction region with high immunogenicity further enhances the weight.

[0059] Specifically, the weight of the Gaussian kernel determines its opacity, controlling the visual intensity of the interaction region in rendering, such as high weight region presenting higher brightness or contrast. This feature calculates the weight by obtaining the biological properties of the high-energy interaction region, using binding affinity and immunogenicity, preferentially highlighting the region with high binding affinity, and further enhancing the weight based on high immunogenicity. For example, for the receptor binding domain of the spike protein of the new coronavirus, its high binding affinity and immunogenicity make this region display in deep red high light in the model, with a frame rate of 35 frames per second, supporting the analysis of infection mechanism. The biological properties include binding affinity and immunogenicity, which are the core input of weight calculation. The binding affinity reflects the interaction strength between the virus and the host molecule, which is obtained by calculating the binding energy through molecular dynamics simulation, such as the binding site energy of the receptor binding domain and the ACE2 receptor is-15 kilocalorie per mole, normalized to 0.9. Immunogenicity represents the ability of the interaction region to be recognized by the immune system, which is predicted by tools such as IEDB, with a typical score of 0 to 1, such as the epitope score of the receptor binding domain is 0.7. These properties are extracted from the high-energy interaction region, focusing on the region with absolute binding energy higher than 10 kilocalorie per mole, ensuring that the weight adjustment is concentrated on the key interaction sites, such as the receptor binding domain rather than the non-interaction region.

[0060] The quantization mapping function is the mathematical basis of weight adjustment, which is used to convert biological attributes into Gaussian kernel weights. The application adopts a linear mapping function, which assigns higher weights to interaction regions with high affinity and further enhances the weights of interaction regions with high immunogenicity. That is, the application first assigns higher weights to interaction regions with high binding affinity, and then further enhances the weights of interaction regions with high immunogenicity, with binding affinity as the dominant factor of weight. Specifically, the weight calculation formula can be weight equal to the normalized value of binding affinity multiplied by a coefficient of 0.6 plus the immunogenicity score multiplied by a coefficient of 0.4, wherein the weight contribution of binding affinity is greater, accounting for 60%, and immunogenicity is an auxiliary factor, accounting for 40%. For example, the receptor binding domain binding affinity is normalized to 0.9, and the immunogenicity score is 0.7, the weight calculation is 0.6 multiplied by 0.9 plus 0.4 multiplied by 0.7, equal to 0.82, corresponding to opacity 0.82. If the immunogenicity is low, such as 0.3, the weight decreases to 0.66, indicating that binding affinity is the dominant factor and immunogenicity only further enhances the weight on the basis of high binding affinity.

[0061] In order to save computing resources and improve the efficiency of three-dimensional reconstruction, the application pre-calculates a plurality of key states of the virus and the host molecules in the interaction process when performing molecular dynamics simulation on the target virus based on the coarse-grained molecular dynamics model. The key states include binding energy and conformational change data of different infection states. The application efficiently obtains the dynamic data of the interaction between the virus and the host molecules by pre-calculating the key states, and provides input for subsequent pseudo-real-time rendering. The key state refers to the representative time point data in the interaction process of the virus and the host molecules, including binding energy and conformational change data.

[0062] The application can also use a Kalman filter-based predictive optimization algorithm to predict the conformational change and energy distribution of the next infection state and pre-adjust the parameters of the Gaussian kernel. Kalman filtering is a recursive estimation method that combines historical observation data and system dynamic models to predict future states and optimize estimates. Kalman filtering treats trajectory data from molecular dynamics simulations as a time series, with state variables including point cloud coordinates, normal vectors, and binding energies. The filter predicts the conformational change of the next infection state through a state transition model, such as the root mean square deviation trend, and corrects the prediction through an observation model, incorporating the actual data from the current frame. The prediction mechanism specifically targets the prediction of conformational changes and energy distribution. Conformational changes are quantified by changes in point cloud coordinates and normal vectors, such as a change from closed to open in the receptor binding domain, an increase in root mean square deviation from 1 angstrom to 2 angstroms, and a change in normal vector from the initial direction to the new direction. Kalman filtering predicts the point cloud position and direction of the next frame based on the coordinate and normal vector sequences of the previous frames. Energy distribution prediction incorporates energy change trends, such as an increase in receptor binding domain binding site energy from -10 kilocalories per mole to -15 kilocalories per mole, and the filter estimates the energy value of the next frame. Parameter pre-adjustment optimizes Gaussian kernel parameters in advance based on predicted data. Kernel parameters include eigenvalues and eigenvectors of the covariance matrix, weights, and colors. Predicted conformational changes adjust kernel directions, such as normal vector predictions to new directions, eigenvector alignment in advance, and kernel shape stretching along the surface.

[0063] Preferably, when generating in-situ visual three-dimensional models through three-bit Gaussian splash processing, the application can only render key Gaussian kernels, thereby saving computational resources. Specifically, the key Gaussian kernels are retained, and the other Gaussian kernels are deleted, and a continuous three-dimensional rendering model is generated using the key Gaussian kernels; wherein the method for determining the importance includes: calculating the binding energy values of the point cloud points corresponding to each Gaussian kernel according to the binding energy data, obtaining a first Gaussian kernel set with an absolute binding energy value higher than a first preset threshold; evaluating the conformational change amplitude of each point cloud point according to the conformational change data, obtaining a second Gaussian kernel set with a conformational change higher than a second preset threshold; obtaining a third Gaussian kernel set with high immunogenicity or high hydrophilic-hydrophobicity according to the biological properties; calculating the union of the first Gaussian kernel set, the second Gaussian kernel set, and the third Gaussian kernel set, and obtaining the key Gaussian kernels.

[0064] The key Gaussian kernel screening is based on the importance judgment and is divided into three standards to generate three kernel sets and take the union. The energy standard is combined with the energy data to calculate the binding energy value of each point cloud point, and the kernel with an absolute value higher than a first preset threshold, such as 10 kilocalories per mole, is screened to form a first Gaussian kernel set. For example, the energy of the binding site of the receptor binding domain is -15 kilocalories per mole, which is much higher than the threshold, and the kernel is included in the first set, reflecting the interaction strength. The conformation change standard evaluates the conformation change amplitude of the point cloud point, which is quantified by the root mean square deviation, and the kernel higher than a second preset threshold, such as 1 angstrom, is screened to form a second Gaussian kernel set. For example, the root mean square deviation of the receptor binding domain from closed to open is 2 angstroms, and the kernel is included in the second set, reflecting the dynamic geometry. The biological attribute standard screens the kernel with high immunogenicity, such as a score of 0.7, or high hydrophobicity, such as a value of 0.5, to form a third Gaussian kernel set, highlighting the epitope region. Finally, the union of the three sets is taken to obtain the key Gaussian kernel, ensuring that all important regions are covered.

[0065] In the three-dimensional Gaussian splash processing of the point cloud data, the color and opacity of the functional region Gaussian kernel can be adjusted based on immunogenicity and hydrophobicity to optimize the visualization of the functional region of the virus three-dimensional model. Including: based on the biological attributes of the point cloud data, adjusting the color representation and opacity representation of the functional region corresponding Gaussian kernel of the target virus; wherein the biological attributes include immunogenicity or hydrophobicity; the functional region includes an immunogenic epitope or a structural stability region; the color representation is mapped to a specific color channel according to the immunogenicity, and the opacity representation is dynamically adjusted according to the hydrophobicity value.

[0066] Specifically, the functional region refers to the region on the virus surface with specific biological significance, including the immunogenic epitope and the structural stability region. The immunogenic epitope is the region on the virus surface recognized by the antibody, and its high immunogenicity makes it need to be highlighted in the model. The structural stability region maintains the integrity of the virus structure, and its high hydrophobicity is usually related to stability. The color representation is mapped to a specific color channel according to the immunogenicity, for example, the epitope region with an immunogenicity score higher than 0.7 is mapped to green, with RGB value 0, 255, 0, and the region with a score lower than 0.3 is mapped to gray, with RGB value 128, 128, 128. The opacity representation is dynamically adjusted according to the hydrophobicity value, for example, the structural stability region with a hydrophobicity value higher than 0.5 is assigned an opacity of 0.8, and the hydrophilic region with a value lower than -0.5 is assigned an opacity of 0.4. The mapping function is realized by linear or exponential form, for example, the opacity is equal to 0.5 plus 0.3 multiplied by the hydrophobicity value.

[0067] The above method provided by the embodiments of the present application can be applied to various application scenarios, including but not limited to: infection mechanism research, dynamically visualizing the interaction region of a virus and a host molecule, such as the binding process of the receptor binding domain of the spike protein of the new coronavirus and the ACE2 receptor, revealing the conformational change and the binding energy distribution; drug design, highlighting high-energy binding sites to support the optimization of target sites of neutralizing antibodies or small molecule drugs; vaccine development, rendering immunogenic epitopes using immunogenicity mapping to analyze epitope exposure dynamics to assist immunogen design; virus structure analysis, displaying structural stability regions such as the hydrophilic and hydrophobic properties of the capsid to evaluate the stability of the virus. These scenarios provide powerful tools for antiviral research by efficiently and pseudo-real-time rendering of three-dimensional models, improving analysis accuracy and interaction.

[0068] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in an order different than the order in the embodiments and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or possible.

[0069] According to another aspect, embodiments of a virus three-dimensional reconstruction system based on three-dimensional Gaussian splash are provided. Figure 3 A schematic block diagram of the virus three-dimensional reconstruction system based on three-dimensional Gaussian splash according to one embodiment is shown. As shown, Figure 3 The system 300 includes:

[0070] A point cloud data acquisition unit 301 configured to acquire three-dimensional point cloud data of a target virus, the point cloud data including spatial coordinates, geometric features, and biological attributes.

[0071] A dynamics simulation unit 302 configured to perform molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, calculate the binding site energy distribution of the target virus and host molecules, identify high-energy interaction regions, acquire binding energy data of the target virus and host molecules during the interaction process; and track the conformational changes of the virus structure through time series atomic coordinate analysis to obtain conformational change data.

[0072] A three-dimensional reconstruction unit 303 configured to perform three-dimensional Gaussian splash processing on the point cloud data to generate an in-situ visualized three-dimensional model of the target virus; wherein in the Gaussian splash processing, the shape, direction, and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and conformational change data.

[0073] As an implementable manner, the three-dimensional reconstruction unit 303 can be configured to convert each point in the point cloud data into a Gaussian kernel in the Gaussian splash processing, wherein the parameters of the Gaussian kernel include a Gaussian distribution representation, a color representation, and an opacity representation corresponding to the point in the point cloud data; the Gaussian distribution representation includes shape information and direction information of the Gaussian kernel; the shape information of the Gaussian kernel corresponding to each point in the point cloud is adjusted according to the binding energy distribution data; the direction information in the Gaussian distribution representation is adjusted according to the conformational change data, so that the shape of the Gaussian kernel is along the normal vector direction of the interaction region; and the weight of each Gaussian kernel is dynamically adjusted according to the biological attributes of the interaction region between the target virus and the host molecule.

[0074] As an implementable manner, the three-dimensional reconstruction unit 303 can be configured to obtain the biological attributes of the high-energy interaction region, wherein the biological attributes include binding affinity and immunogenicity; and calculate the weight of each Gaussian kernel according to the binding affinity and the immunogenicity by using a quantitative mapping function, wherein the weight of the interaction region with high immunogenicity is further increased on the basis of assigning higher weight to the interaction region with high binding affinity.

[0075] As an implementable manner, the dynamics simulation unit 302 can be configured to pre-calculate a plurality of key states of the target virus and the host molecule in the interaction process, wherein the key states include binding energy and conformational change data of different infection states, when performing molecular dynamics simulation on the target virus based on the coarse-grained molecular dynamics model. The three-dimensional reconstruction unit 303 can be configured to: in the Gaussian splash processing, dynamically adjust the shape, direction, and weight of the Gaussian kernel according to the binding energy data and the conformational change data, wherein the Gaussian kernel is generated by using an interpolation algorithm to generate smooth transition point cloud data and kernel parameters between the key states, forming a pseudo-real-time demonstration effect; and dynamically adjust the shape, direction, and weight of the Gaussian kernel based on the pseudo-real-time data to generate a continuous three-dimensional rendering model.

[0076] As an implementable manner, the dynamics simulation unit 302 can be configured to modify the parameters of the point cloud region with significant conformational change and energy distribution based on the shape, direction, and weight of the Gaussian kernel of the previous infection state; and / or use a Kalman filter-based predictive optimization algorithm to predict the conformational change and energy distribution of the next state, and pre-adjust the parameters of the Gaussian kernel.

[0077] As an implementable manner, the three-dimensional reconstruction unit 303 can be configured to retain key Gaussian kernels, delete other Gaussian kernels, and generate a continuous three-dimensional rendering model using the key Gaussian kernels when dynamically adjusting the weights of the Gaussian kernels according to the biological attributes of the interaction region of the target virus and the host molecules. The method for determining the importance includes: calculating the binding energy values of the point cloud points corresponding to each Gaussian kernel according to the binding energy data, obtaining a first Gaussian kernel set with an absolute binding energy value higher than a first preset threshold; evaluating the conformational change amplitude of each point cloud point according to the conformational change data, obtaining a second Gaussian kernel set with a conformational change higher than a second preset threshold; obtaining a third Gaussian kernel set with high immunogenicity or high hydrophobicity according to the biological attributes; calculating the union of the first Gaussian kernel set, the second Gaussian kernel set, and the third Gaussian kernel set, and obtaining the key Gaussian kernels.

[0078] As an implementable manner, the three-dimensional reconstruction unit 303 can be configured to adjust the color representation and opacity representation of the Gaussian kernel corresponding to the functional region of the target virus based on the biological attributes of the point cloud data when dynamically adjusting the weights of the Gaussian kernels according to the biological attributes of the interaction region of the target virus and the host molecules. The biological attributes include immunogenicity or hydrophobicity. The functional region includes an immunogenic epitope or a structural stability region. The color representation is mapped to a specific color channel according to the immunogenicity, and the opacity representation is dynamically adjusted according to the hydrophobicity value.

[0079] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, it is described more simply, and the relevant parts can be referred to the part of the method embodiment. The above-described system embodiment is only illustrative, and the units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0080] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0081] In addition, the embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the method in any one of the preceding method embodiments.

[0082] And an electronic device, comprising: one or more processors; and a memory associated with the one or more processors, the memory being configured to store program instructions that, when executed by the one or more processors, perform the steps of the method in any one of the preceding method embodiments.

[0083] The present application also provides a computer program product, comprising a computer program which, when executed by a processor, realizes the steps of the method in any one of the preceding method embodiments.

[0084] Among them, Figure 4 An exemplary architecture of an electronic device is shown, which can specifically include a processor 410, a video display adapter 411, a disk drive 412, an input / output interface 413, a network interface 414, and a memory 420. The processor 410, video display adapter 411, disk drive 412, input / output interface 413, network interface 414, and memory 420 can be connected by a communication bus 430.

[0085] Among them, the processor 410 can be implemented by a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., for executing related programs to realize the technical solutions provided by the present application.

[0086] The memory 420 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 420 can store an operating system 421 for controlling the operation of the electronic device 400, a basic input / output system (BIOS) 422 for controlling the low-level operation of the electronic device 400. In addition, a web browser 423, a data storage management system 424, and a virus three-dimensional reconstruction system based on three-dimensional Gaussian splashing 425, etc. can also be stored. The virus three-dimensional reconstruction system based on three-dimensional Gaussian splashing 425 described above can be an application program for specifically implementing the operations of the foregoing steps in the embodiments of the present application. In summary, when the technical solutions provided in the present application are implemented by software or firmware, the relevant program codes are stored in the memory 420 and executed by the processor 410.

[0087] The input / output interface 413 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0088] The network interface 414 is configured to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0089] The bus 430 includes a path for transmitting information between various components (such as the processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, and the memory 420) of the device.

[0090] It should be noted that although the above device only shows the processor 410, the video display adapter 411, the disk drive 412, the input / output interface 413, the network interface 414, the memory 420, the bus 430, etc., in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only contain the components necessary to implement the solutions of the present application, and does not necessarily contain all the components shown in the figure.

[0091] Those skilled in the art can clearly understand the application by the description of the above embodiments that the application can be implemented by means of software plus necessary universal hardware platforms. Based on such an understanding, the technical solutions of the application can be embodied in the form of a computer program product, which can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and include a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the application.

[0092] The technical solutions provided by the application are described in detail above, and the principles and implementation manners of the application are described by using specific examples. The above description of the embodiments is only used to help understand the methods and core ideas of the application. Meanwhile, for those skilled in the art, the specific implementation manners and application ranges can be changed according to the ideas of the application. In conclusion, the content of the specification should not be understood as a limitation of the application.

Claims

1. A method for three-dimensional reconstruction of viruses based on three-dimensional Gaussian blurring, characterized in that, The method comprises: acquiring three-dimensional point cloud data of a target virus, the point cloud data comprising spatial coordinates, geometric features and biological attributes; performing molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, calculating binding site energy distribution of the target virus and host molecules, identifying high-energy interaction regions, and obtaining binding energy data of the target virus and host molecules during interaction; and tracking conformational changes of the virus structure through time series atomic coordinate analysis to obtain conformational change data; performing three-dimensional Gaussian splatting processing on the point cloud data to generate an in-situ visual three-dimensional model of the target virus; wherein, in the Gaussian splatting processing, the shape, direction and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and conformational change data.

2. The method of claim 1, wherein, The dynamic adjustment of the shape, direction and weight of the Gaussian kernel in the Gaussian splatting processing comprises: converting each point in the point cloud data into a Gaussian kernel, the parameters of the Gaussian kernel including Gaussian distribution representation, color representation and opacity representation corresponding to the point in the point cloud data; wherein, the Gaussian distribution representation includes shape information and direction information of the Gaussian kernel; adjusting the shape information of the Gaussian kernel corresponding to each point in the point cloud according to the binding energy distribution data; adjusting the direction information in the Gaussian distribution representation according to the conformational change data, so that the shape of the Gaussian kernel is along the normal vector direction of the interaction region; dynamically adjusting the weight of each Gaussian kernel according to the biological attributes of the interaction region between the target virus and the host molecules.

3. The method of claim 2, wherein, The dynamic adjustment of the weight of each Gaussian kernel according to the biological attributes of the interaction region between the target virus and the host molecules comprises: obtaining the biological attributes of the high-energy interaction region, including binding affinity and immunogenicity; using a quantitative mapping function to calculate the weight of each Gaussian kernel according to the binding affinity and immunogenicity, wherein, on the basis of assigning higher weights to interaction regions with high binding affinity, the weights of interaction regions with high immunogenicity are further increased.

4. The method of claim 1, wherein, The method further comprises: pre-calculating a plurality of key states of the target virus and host molecules during the interaction process when performing molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, the key states including binding energy and conformational change data at different infection times; The dynamic adjustment of the shape, direction and weight of the Gaussian kernel in the Gaussian splatting processing comprises: using an interpolation algorithm to generate smooth transition point cloud data and kernel parameters between the key states to form a pseudo-real-time demonstration effect; dynamically adjusting the shape, direction and weight of the Gaussian kernel based on the pseudo-real-time data to generate a continuous three-dimensional rendering model.

5. The method of claim 4, wherein, The method further comprises: modifying the parameters of the point cloud region with significant conformational changes and energy distribution based on the shape, direction and weight of the Gaussian kernel of the previous infection state; and / or; The predictive optimization algorithm based on Kalman filtering is used to predict the conformational change and energy distribution of the next infection state, and the parameters of the Gaussian kernel are pre-adjusted.

6. The method of claim 3, wherein, The three-dimensional Gaussian splash processing is performed on the point cloud data to generate an in-situ visual three-dimensional model of the target virus, including: Reserve the key Gaussian kernel, delete other Gaussian kernels, and generate a three-dimensional rendering model using the key Gaussian kernel; The method for determining the importance degree includes: According to the binding energy data, the binding energy values of the point cloud points corresponding to each Gaussian kernel are calculated to obtain a first Gaussian kernel set with an absolute binding energy value higher than a first preset threshold; According to the conformational change data, the conformational change amplitudes of each point cloud point are evaluated to obtain a second Gaussian kernel set with a conformational change higher than a second preset threshold; According to the biological properties, a third Gaussian kernel set with high immunogenicity or high hydrophobicity is obtained; The union of the first Gaussian kernel set, the second Gaussian kernel set, and the third Gaussian kernel set is calculated to obtain the key Gaussian kernel.

7. The method of claim 1, wherein, When the three-dimensional Gaussian splash processing is performed on the point cloud data to generate an in-situ visual three-dimensional model of the target virus, the method further includes: Based on the biological properties of the point cloud data, the color representation and opacity representation of the Gaussian kernel corresponding to the functional region of the target virus are adjusted; wherein the biological properties include immunogenicity or hydrophobicity; the functional region includes an immunodominant epitope or a structural stability region; The color representation is mapped to a specific color channel according to the immunogenicity, and the opacity representation is dynamically adjusted according to the hydrophobicity value.

8. A three-dimensional reconstruction system for viruses based on three-dimensional Gaussian blurring, characterized in that, The system includes: A point cloud data acquisition unit configured to acquire three-dimensional point cloud data including a target virus, the point cloud data including spatial coordinates, geometric features, and biological properties; A dynamics simulation unit configured to perform molecular dynamics simulation on the target virus based on a coarse-grained molecular dynamics model, calculate the binding site energy distribution of the target virus and host molecules, identify high-energy interaction regions, and obtain binding energy data of the target virus and host molecules during interaction; and track the conformational change of the virus structure through time series atomic coordinate analysis to obtain conformational change data; A three-dimensional reconstruction unit configured to perform three-dimensional Gaussian splash processing on the point cloud data to generate an in-situ visual three-dimensional model of the target virus; wherein in the Gaussian splash processing, the shape, direction, and weight of the Gaussian kernel are dynamically adjusted according to the binding energy data and conformational change data.

9. An electronic device, comprising: It includes: One or more processors; And a memory associated with the one or more processors, the memory is used to store program instructions, the program instructions are read and executed by the one or more processors to perform the steps of the method of any one of claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images