A method, device and storage medium for constructing a digital cell model

Abstract

The application provides a digital cell model construction method and device, equipment and a storage medium, and relates to the technical field of bio-artificial intelligence. The digital cell model construction method comprises the following steps: compiling a cell language through an intelligent processing module, and obtaining recompiled data; generating a digital cell model based on the recompiled data; fine-tuning the digital cell model; obtaining simulation results through the fine-tuned digital cell model, and verifying the simulation results. According to the embodiment of the application, the real cell dynamics can be simulated preliminarily, and the dynamic changes of molecules in the cell and the interaction thereof can be accurately reflected.

Description

Technical Field

[0001] This application relates to the field of bioartificial intelligence technology, and more specifically, to a method, apparatus, device, and storage medium for constructing a digital cell model. Background Technology

[0002] With the application of multi-omics technologies in cell biology, biological data is experiencing explosive growth, driving the development of biological artificial intelligence systems. Currently, with the improvement of computing power, artificial intelligence models can utilize massive datasets and parameters to demonstrate high accuracy in predicting biomolecular structures and interactions, and can even simulate the early evolutionary processes of macromolecules, providing compelling evidence for realizing integrated digital cells based on extensive quantitative molecular data and interaction networks.

[0003] The inventors of this application have discovered that current artificial intelligence model technologies mainly suffer from the following defects:

[0004] 1) Data processing bottleneck: Current methods mainly rely on manual processing of multimodal data or simple processing of single data types. With the advancement of observation techniques, the amount and complexity of data are growing exponentially, making manual processing impractical.

[0005] 2) Insufficient data integration: Existing databases are usually simple aggregations of single data types, lacking organic connections between different data types, making it difficult to uncover deep relationships between data.

[0006] 3) Model limitations: Current cell models are mainly based on simple cellular systems (such as JCVI-syn3A and mycoplasma) or focus only on a single data layer (such as gene expression). These models cannot simulate the real state of more complex cells and lack multi-level integrated networks.

[0007] 4) Mechanized simulation: Current methods lack deep integration with artificial intelligence and cannot capture the true dynamics of complex cellular systems.

[0008] 5) Insufficient interpretability: Existing AI-assisted prediction models often fail to provide biologically reasonable explanations for their results, and there is a lack of biological evidence at the algorithm level. Summary of the Invention

[0009] According to one aspect of this application, a method for constructing a digital cell model is provided, comprising: compiling cell language through an intelligent processing module and obtaining recompiled data; generating a digital cell model based on the recompiled data; fine-tuning the digital cell model; obtaining simulation results through the fine-tuned digital cell model and verifying the simulation results.

[0010] According to some embodiments, before compiling the cell language through the intelligent processing module and obtaining the recompiled data, the method further includes: acquiring multiple preset intelligent models; fine-tuning the multiple preset intelligent models using preset multimodal biological data; and constructing an intelligent processing module based on the fine-tuned multiple preset intelligent models.

[0011] According to some embodiments, cell language compilation is performed through an intelligent processing module to obtain recompiled data, including: identifying multiple data types and biological information contained in multimodal biological data through the intelligent processing module; performing cell language compilation on the multimodal biological data based on the biological information to obtain recompiled data through the intelligent processing module; performing dimensionality reduction processing on the recompiled data based on multiple data types through the intelligent processing module; and constructing the relationships between different types of data in the recompiled data.

[0012] According to some embodiments, based on biological information, multimodal biological data is compiled into cell language using an intelligent processing module to obtain recompiled data, including: compiling multimodal biological data into cell language using an intelligent processing module to obtain a unified token for the multimodal biological data; and constructing a mapping relationship between the unified token and the tokens corresponding to different data types in the multimodal biological data.

[0013] According to some embodiments, a digital cell model is generated based on recompiled data, including: acquiring cellular component structure information and spatiotemporal information from multimodal biological data; and constructing a digital cell model based on the recompiled data that has undergone dimensionality reduction, combined with the cellular component structure information and spatiotemporal information, using a preset modeling method.

[0014] According to some embodiments, fine-tuning a digital cell model includes: acquiring biological information and cell characteristics of a preset cell; decoding the digital cell model based on the mapping relationship and the biological information of the preset cell; and fine-tuning the decoded digital cell model according to the cell characteristics so that the digital cell model can simulate the preset cell.

[0015] According to some embodiments, simulation results are obtained through a finely tuned digital cell model, and the simulation results are verified, including: inputting the pre-set signal mediators and the recompiled data corresponding to the pre-set cells into the digital cell model to obtain simulation results; comparing and verifying the simulation results with experimental data and generating verification results; and feeding the verification results back to the intelligent processing module.

[0016] According to one aspect of this application, a digital cell model construction apparatus is provided, comprising: a data compilation module for compiling cell language through an intelligent processing module and obtaining recompiled data; a model construction module for generating a digital cell model based on the recompiled data; a model training module for fine-tuning the digital cell model; and a simulation verification module for obtaining simulation results through the fine-tuned digital cell model and verifying the simulation results.

[0017] According to one aspect of this application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to perform the method as described above.

[0018] According to one aspect of this application, a computer-readable storage medium is provided that stores a computer program or instructions thereon, which, when executed by a processor, implement the method as described above.

[0019] According to the embodiments of this application, automated data integration and standardization can be achieved, improving data processing efficiency; effective connections between data layers can be realized; by constructing a digital cell model that integrates multiple biological data types, the digital cell model exhibits higher accuracy and stability in predicting cell behavior and responses, which helps to reveal complex cell dynamics and their biological mechanisms; the constructed digital cell model is easy to expand and maintain, can adapt to future technological developments and changes in data types, and has long-term applicability and performance stability.

[0020] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application.

[0022] Figure 1 A flowchart illustrating a method for constructing an intelligent processing module according to an example embodiment of this application is shown.

[0023] Figure 2 A flowchart illustrating a method for constructing a digital cell model according to an example embodiment of this application is shown.

[0024] Figure 3 A block diagram of an apparatus for constructing a digital cell model according to an example embodiment of this application is shown.

[0025] Figure 4 A block diagram of an electronic device according to an example embodiment of this application is shown. Detailed Implementation

[0026] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this application will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0027] The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of these specific details, or other methods, components, materials, apparatus, or operations may be employed. In these cases, well-known structures, methods, apparatuses, implementations, materials, or operations will not be shown or described in detail.

[0028] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0029] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0030] This application provides a method, apparatus, device, and storage medium for constructing a digital cell model, which can construct a digital cell model integrating multiple biological data types, and can initially simulate real cell dynamics, more accurately reflect the dynamic changes and interactions of molecules within the cell, thereby promoting the prediction and understanding of biological mechanisms.

[0031] The following will describe in detail, with reference to the accompanying drawings, a method, apparatus, device, and storage medium for constructing a digital cell model according to embodiments of this application.

[0032] Figure 1 A flowchart illustrating a method for constructing an intelligent processing module according to an example embodiment of this application is shown.

[0033] like Figure 1 As shown, in step S100, the construction device acquires multiple preset intelligent models.

[0034] For example, in step S100, the construction device acquires multiple preset intelligent models according to the application scenario.

[0035] The device acquires multiple preset intelligent models that match the application scenario to build an intelligent processing module and configures computing resources (such as GPUs) for it.

[0036] According to some embodiments, the preset intelligent model includes a large artificial intelligence model based on a general artificial intelligence framework (such as GPT, Llama, etc.).

[0037] In step S110, the construction device fine-tunes multiple preset intelligent models using preset multimodal biological data.

[0038] For example, in step S110, the construction device acquires preset multimodal biological data and uses it to fine-tune multiple preset intelligent models.

[0039] The device is constructed to acquire pre-defined multimodal biological data.

[0040] According to some embodiments, multimodal biological data includes various types of biological data, including multiple sequencing data (such as genome, epigenome, transcriptome, proteome and metabolome), biological macromolecular structure data, spatiotemporal information and cell phenotype information.

[0041] According to some embodiments, the construction device also sets data preprocessing code for preset multimodal biological data to guide the intelligent processing module to perform data preprocessing on the multimodal biological data. This data preprocessing includes data cleaning and dimensionality reduction.

[0042] Based on multimodal biological data, the device fine-tunes and trains multiple preset intelligent models through a pre-defined multimodal data processing pipeline to learn how to identify and process multimodal biological data.

[0043] In step S120, the construction device constructs an intelligent processing module based on multiple pre-set intelligent models that have been fine-tuned.

[0044] For example, in step S120, after model fine-tuning training, the construction device constructs an intelligent processing module using multiple pre-set intelligent models that have been fine-tuned.

[0045] According to some embodiments, the construction device can identify and process multimodal biological data of different types through an intelligent processing module, and reduce all data to a unified dimension that can be directly correlated during the data processing process.

[0046] Figure 2 A flowchart illustrating a method for constructing a digital cell model according to an example embodiment of this application is shown.

[0047] like Figure 2 As shown, in step S200, the construction device compiles the cell language through the intelligent processing module and obtains recompiled data.

[0048] For example, in step S200, the construction device processes the multimodal biological data through the intelligent processing module to compile the multimodal biological data into cell language and generate recompiled data.

[0049] The device identifies multiple data types and biological information contained in multimodal biological data through a pre-built intelligent processing module.

[0050] According to some embodiments, the construction device can automatically design corresponding algorithms through an intelligent processing module to obtain multiple data types and biological information in multimodal biological data.

[0051] The device preprocesses multimodal biological data through an intelligent processing module, and compiles the multimodal biological data into cell language according to the biological information contained in the multimodal biological data and the current application scenario to obtain recompiled data.

[0052] According to some embodiments, the construction device automatically compiles the multimodal biological data into cell language according to the current application scenario through an intelligent processing module based on the biological information contained in the multimodal biological data, and obtains a unified token for the multimodal biological data.

[0053] According to some embodiments, the construction device constructs a mapping relationship between a unified token for multimodal biological data and the tokens corresponding to different data types in the multimodal biological data through an intelligent processing module.

[0054] According to some embodiments, the recompiled data includes a unified token for multimodal biological data, and a mapping between the unified token and the tokens corresponding to different data types. The recompiled data retains the biological information in the multimodal biological data and is easy to combine in multiple modalities.

[0055] Based on the multiple data types in multimodal biological data, the construction device uses an intelligent processing module to perform dimensionality reduction on the recompiled data, so that biological data of multiple data types can be unified into a dimension that can be correlated with each other.

[0056] According to some embodiments, the construction device forms an intelligent database based on the recompiled data that has undergone dimensionality reduction processing, and performs feature extraction, feature alignment and feature fusion of the recompiled data through the intelligent database.

[0057] Based on the biological information in the recompiled data, the device can be constructed to obtain the connections between different types of data in the recompiled data in the intelligent database.

[0058] In step S210, a digital cell model is generated by the construction device based on the recompiled data.

[0059] For example, in step S210, the construction device recompiles the data to construct a digital cell model using a preset modeling method.

[0060] The device is constructed by first acquiring the cellular component structural information and spatiotemporal information contained in the multimodal biological data.

[0061] The construction device combines the recompiled data that has already undergone dimensionality reduction with the cellular component structure information and spatiotemporal information, and constructs a digital cell model using a preset modeling method.

[0062] According to some embodiments, the preset modeling method includes deep learning algorithms (such as deep neural networks, convolutional neural networks, etc.) to adapt to the data structure of recompiled data in the intelligent database.

[0063] In step S220, the construction device fine-tunes the digital cell model.

[0064] For example, in step S220, the construction device fine-tunes the digital cell model by using preset cell characteristics.

[0065] The device is constructed to obtain biological information and cellular characteristics of a preset cell.

[0066] Based on the mapping relationship between the unified token of multimodal biological data and the tokens corresponding to different data types in multimodal biological data, a device is constructed to decode the digital cell model in order to realize the translation function between the biological information of the preset cell and the digital cell model.

[0067] The construction device fine-tunes the decoded digital cell model based on the cell characteristics of the preset cells, so that the digital cell model can simulate the preset cells.

[0068] For example, if the preset cells are immune cells, the construction device acquires the cellular characteristics of immune cells, including cell surface proteins, intracellular signaling proteins, effector proteins and genes, epigenetic features, signaling pathways, transcription factors, and other information. The construction device provides these cellular characteristics of immune cells to a digital cell model for fine-tuning and training. The more information provided and the more accurate it is (e.g., mass cytometry values ​​of multiple cell surface receptors and their surface antigens, and the expression levels of genes reflecting immune cell characteristics within the cell), the more accurately the digital cell model can simulate immune cells.

[0069] In step S230, the construction device obtains simulation results through the finely tuned digital cell model and verifies the simulation results.

[0070] For example, in step S230, based on the recompiled data corresponding to the preset cells and the preset signal mediators, the construction device obtains the simulation results of the preset cells through the finely tuned digital cell model and verifies the simulation results.

[0071] The device inputs the pre-defined signal mediators and the recompiled data corresponding to the pre-defined cells into the digital cell model to simulate the pre-defined cells and obtain the simulation results.

[0072] According to some embodiments, signal mediators include cytokines, receptor ligands, etc., for binding to receptors on cells, causing a cascade-amplified reaction within the cell to produce phenotypic changes. The signal mediators can be selected based on a predetermined cell type.

[0073] According to some embodiments, the simulation of preset cells includes real cell simulation, cell development and evolution, and molecular mechanism mining.

[0074] The device compares and verifies the simulation results generated by the digital cell model with the experimental data, and generates verification results to determine the consistency between the simulation results and the experimental data.

[0075] According to some embodiments, the validation results include predictions of cell behavior and explanations of biological mechanisms.

[0076] According to some embodiments, the construction device feeds back the verification results to the intelligent processing module for iterative optimization of the intelligent processing module.

[0077] According to embodiments of this application, multiple biological data types can be integrated through the constructed digital cell model, enabling the digital cell model to exhibit higher accuracy and stability in predicting cell behavior and responses.

[0078] Figure 3 A block diagram of an apparatus for constructing a digital cell model according to an example embodiment of this application is shown.

[0079] like Figure 3 As shown, the construction device 300 includes a data compilation module 310, a model construction module 320, a model training module 330, and a simulation verification module 340.

[0080] The data compilation module 310 identifies multiple data types and biological information contained in multimodal biological data through the already constructed intelligent processing module.

[0081] The data compilation module 310 performs data preprocessing on the multimodal biological data through the intelligent processing module, and compiles the multimodal biological data into cell language according to the current application scenario based on the biological information contained in the multimodal biological data to obtain recompiled data.

[0082] Based on the multiple data types in the multimodal biological data, the data compilation module 310 performs dimensionality reduction processing on the recompiled data through the intelligent processing module, so that the biological data of multiple data types can be unified into a dimension that can be correlated with each other.

[0083] Based on the biological information in the recompiled data, the data compilation module 310 obtains the relationships between different types of data in the recompiled data.

[0084] The model building module 320 acquires the cellular component structure information and spatiotemporal information contained in the multimodal biological data.

[0085] The model building module 320 combines the recompiled data that has already undergone dimensionality reduction with the cell component structure information and spatiotemporal information, and constructs a digital cell model using a preset modeling method.

[0086] The model training module 330 acquires the biological information and cell characteristics of preset cells.

[0087] Based on the mapping relationship between the unified token of multimodal biological data and the tokens corresponding to different data types in multimodal biological data, the model training module 330 decodes the digital cell model to realize the translation function between the biological information of the preset cell and the digital cell model.

[0088] The model training module 330 fine-tunes the decoded digital cell model based on the cell characteristics of the preset cells, so that the digital cell model can simulate the preset cells.

[0089] The simulation verification module 340 inputs the preset signal mediating factors and the recompiled data corresponding to the preset cells into the digital cell model to simulate the preset cells and obtain the simulation results.

[0090] The simulation verification module 340 compares and verifies the simulation results generated by the digital cell model with the experimental data, and generates verification results to determine the consistency between the simulation results and the experimental data.

[0091] Figure 4 A block diagram of an electronic device according to an example embodiment of this application is shown.

[0092] like Figure 4 As shown, the electronic device 600 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0093] like Figure 4 As shown, the electronic device 600 is manifested in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc. The storage unit stores program code, which can be executed by the processing unit 610, causing the processing unit 610 to perform the methods described in this specification according to the various exemplary embodiments of this application. For example, the processing unit 610 can perform, for example... Figure 2 The method shown.

[0094] Storage unit 620 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include a read-only memory (ROM) 6203.

[0095] Storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0096] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0097] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0098] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. The technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0099] Software products may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0100] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0101] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0102] The aforementioned computer-readable medium carries one or more programs, which, when executed by a device, cause the computer-readable medium to perform the aforementioned functions.

[0103] Those skilled in the art will understand that the above modules can be distributed in the device as described in the embodiments, or they can be modified accordingly and located in one or more devices that are unique to this embodiment. The modules in the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0104] The embodiments of this application have been described in detail above. These descriptions are solely for the purpose of helping to understand the method and core ideas of this application. Furthermore, any changes or modifications made by those skilled in the art based on the ideas of this application, its specific implementation methods, and its application scope, are all within the scope of protection of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for constructing a digital cell model, characterized in that, include: The cell language is compiled through the intelligent processing module, and recompiled data is obtained. Based on the recompiled data, a digital cell model is generated; The digital cell model was fine-tuned; Simulation results were obtained using a finely tuned digital cell model, and the simulation results were then validated. The method further includes, before compiling the cell language through the intelligent processing module and obtaining the recompiled data: Acquire multiple preset intelligent models; The multiple preset intelligent models are fine-tuned using preset multimodal biological data; The intelligent processing module is constructed based on multiple pre-set intelligent models that have been fine-tuned; The process involves using an intelligent processing module to compile the cell language and obtain recompiled data, including: The intelligent processing module identifies multiple data types and biological information contained in the multimodal biological data. Based on the biological information, the intelligent processing module performs cell language compilation on the multimodal biological data to obtain the recompiled data; Based on the multiple data types, the intelligent processing module performs dimensionality reduction processing on the recompiled data. Construct the relationships between different types of data in the recompiled data; Specifically, based on the biological information, the intelligent processing module performs cell language compilation on the multimodal biological data to obtain the recompiled data, including: The intelligent processing module compiles the multimodal biological data into cell language to obtain a unified token for the multimodal biological data. Construct a mapping relationship between the unified token and the tokens corresponding to different data types in the multimodal biological data; The process of generating a digital cell model based on the recompiled data includes: Obtain cellular component structural information and spatiotemporal information from the multimodal biological data; Based on the recompiled data that has undergone dimensionality reduction, combined with the cell component structure information and the spatiotemporal information, the digital cell model is constructed using a preset modeling method.

2. The method according to claim 1, characterized in that, Fine-tuning the digital cell model includes: Acquire biological information and cellular characteristics of preset cells; Based on the mapping relationship and the biological information of the preset cells, the digital cell model is decoded; The decoded digital cell model is fine-tuned based on the cell characteristics so that the digital cell model can simulate the preset cell.

3. The method according to claim 2, characterized in that, Simulation results are obtained using a finely tuned digital cell model, and the simulation results are validated, including: The preset signal mediating factors and the recompiled data corresponding to the preset cells are input into the digital cell model to obtain the simulation results; The simulation results are compared and verified with the experimental data, and verification results are generated. The verification result is fed back to the intelligent processing module.

4. A device for constructing a digital cell model, characterized in that, include: The data compilation module is used to compile the cell language through the intelligent processing module and obtain recompiled data; A model building module is used to generate a digital cell model based on the recompiled data; The model training module is used to fine-tune the digital cell model; The simulation verification module is used to obtain simulation results through a finely tuned digital cell model and to verify the simulation results. The data compilation module is further used for, The intelligent processing module identifies multiple data types and biological information contained in the preset multimodal biological data; Based on the biological information, the intelligent processing module performs cell language compilation on the multimodal biological data to obtain the recompiled data; Based on the multiple data types, the intelligent processing module performs dimensionality reduction processing on the recompiled data. Construct the relationships between different types of data in the recompiled data; The data compilation module is also used for, The intelligent processing module compiles the multimodal biological data into cell language to obtain a unified token for the multimodal biological data. Construct a mapping relationship between the unified token and the tokens corresponding to different data types in the multimodal biological data; The model building module is also used for, Obtain cellular component structural information and spatiotemporal information from the multimodal biological data; Based on the recompiled data that has undergone dimensionality reduction, combined with the cell component structure information and the spatiotemporal information, the digital cell model is constructed using a preset modeling method.

5. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-3.

6. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the method as described in any one of claims 1-3.

Images