Microbial fermentation experiment intelligent design method and system based on large language model

Abstract

The invention belongs to the technical field of bioengineering and artificial intelligence crossing, and particularly discloses a microbial fermentation experiment intelligent design method and system based on a large language model (LLM). According to the invention, a historical database can be automatically retrieved and an experiment resource state can be inquired according to an experiment purpose input by a user intention, an experiment scheme is generated through large language model reasoning, and a task structure which can be identified by an experiment system is synchronized to a digital system so as to support confirmation, optimization and execution of tasks.

Description

Technical Field

[0001] This invention belongs to the interdisciplinary field of bioengineering and artificial intelligence, specifically relating to an intelligent design system and method for microbial fermentation experiments based on large language model (LLM), used for the automatic generation and execution of experimental schemes. Background Technology

[0002] In microbial fermentation experiments, the experimental design process is complex, requiring consideration of multiple variables (such as strain, culture medium, process parameters, fermenter model, etc.), and often relies on expert experience, resulting in low efficiency, poor repeatability, and difficulty in standardization.

[0003] While existing digital systems have data recording capabilities, they lack the ability to design autonomous experiments and decompose intelligent tasks.

[0004] In recent years, open-source large language models have demonstrated excellent performance in knowledge reasoning and text generation, but they have not yet been widely used in the design of structured scientific research experiments. Currently, there is a lack of an intelligent design system that can transform user intent into standardized experimental plans and interface with fermentation platforms and scheduling systems. Summary of the Invention

[0005] To address the problems existing in the prior art, the purpose of this invention is to provide an intelligent design method and system for microbial fermentation experiments based on a large language model.

[0006] To achieve the objectives of this invention, the technical solution is as follows.

[0007] In a first aspect, the present invention provides an intelligent design method for microbial fermentation experiments based on a large language model, comprising: S1, the natural language instructions input by the user are structured and parsed into experimental objectives and constraints through a large language model; S2, based on the parsed experimental objectives and constraints, automatically retrieves the user's historical experimental database, integrates historical information that meets the preset similarity as enhancement conditions, and outputs prompts containing the enhancement conditions; S3, obtain available resource information via API based on prompts containing enhanced conditions; S4 encapsulates the experimental objectives and constraints parsed from S1, the prompts containing enhancement conditions output from S2, and the available resource information obtained from S3 into an integrated prompt. It then performs instruction reasoning through a large language model and outputs the optimal experimental design scheme based on the direction of maximizing the objective. S5 sends the optimal experimental design to the user and provides a visual interface for the user to confirm or modify the experimental design. S6 converts the user-confirmed or modified experimental design into a task structure that the experimental system can recognize, and sends it to the experimental system to complete the execution of the experimental design.

[0008] Furthermore, the user's historical experiment database mentioned in S2 contains various information recorded in the user's historical experiments, including but not limited to experimental objectives, strain information, culture medium information, process parameters, product information, SOP steps, and abnormal situations.

[0009] Furthermore, the similarity described in S2 can be measured using a multi-dimensional nested scoring method. This includes keyword semantic matching, embedded vector semantic matching, and multi-field weighted matching. By extracting key information from the user's experimental goals and constraints, and combining it with the structured fields of historical experiments, a comprehensive similarity score is calculated. A threshold is then set to filter out historical experimental records that meet the conditions for use in enhancing prompt word construction.

[0010] Alternatively, the similarity described in S2 can also be measured by a weighted scoring method that combines domain-specific weighting factors. These weighting factors can be determined based on the analysis results of historical experimental data or the model training results, and are used to reflect the relative importance of different experimental information fields to the final experimental design scheme.

[0011] Furthermore, in S2, historical information that meets the preset similarity is generated and fused as an enhancement condition through multidimensional clustering statistics, parameter induction fusion, and natural language prompts.

[0012] Specifically, the multidimensional clustering statistics involves performing multidimensional clustering statistics on the structured fields (such as strains, process parameters, culture media, etc.) in the selected historical experimental records, and extracting the options with higher frequency of occurrence as recommended values. Specifically, parameter induction and fusion involves: extracting reference ranges for continuous parameter fields through interval analysis, and sorting and filtering candidate information by combining actual performance indicators from historical experiments (such as yield and recovery rate); Specifically, the natural language prompt generation involves converting the above content into enhanced prompt words in natural language form, which are then input into the large language model along with the current experimental objective.

[0013] Furthermore, the available resource information mentioned in S3 includes, but is not limited to, equipment information, microbial information, and material information. For example, a list of currently available fermenters (model, capacity, status), available strain inventory (number, purity, past yield), and culture medium inventory (components, batch number, cost).

[0014] Furthermore, if there are multiple indicators in the objective (such as "increase yield + reduce time"), the optimal experimental design scheme is output through the Pareto optimal solution set.

[0015] The Pareto optimal solution set is calculated using the Pareto optimality rule, which is as follows: For each candidate experimental scheme, multiple optimization metrics (such as yield, time, cost, purity, etc.) are constructed into a multi-dimensional vector. Any two schemes are compared one by one. If scheme A is superior to scheme B in at least one metric and not inferior to scheme B in any other metric, then A dominates B. The dominated scheme is eliminated, and the remaining solutions constitute the Pareto optimal solution set. If multiple solutions exist within the set, the system can normalize and weight each metric according to user-defined or preset metric weights, and combine this with additional constraints such as resource availability and execution risk to select the final recommended optimal experimental design scheme from the set.

[0016] Furthermore, the experimental design scheme includes, but is not limited to, material selection, process parameters, equipment selection, and schedule arrangement.

[0017] Secondly, the present invention provides an intelligent design system for microbial fermentation experiments based on a large language model, comprising: The intent parsing module is used to parse the natural language instructions input by the user into experimental objectives and constraints through a large language model. The knowledge enhancement module is used to automatically retrieve the user's historical experiment database based on the parsed experimental objectives and constraints, and integrate historical information that meets the preset similarity with the enhancement conditions to output prompt words containing the enhancement conditions; The resource scheduling module is used to obtain available resource information via API based on prompts containing enhanced conditions; The experiment design module is used to encapsulate the parsed experimental objectives and constraints, prompts containing enhancement conditions, and available resource information into an integrated prompt. It then uses a large language model to perform instruction reasoning and outputs the optimal experimental design scheme based on the direction of maximizing the objective. The human-machine collaboration module is used to send the optimal experimental design scheme to the user and provide a visual interface for the user to confirm or modify the experimental design scheme. The task execution module is used to convert the experimental design scheme confirmed or modified by the user into a task structure that can be recognized by the experimental system, and send it to the experimental system to complete the execution of the experimental design scheme.

[0018] Thirdly, the present invention provides a computer-readable storage medium including a stored program, wherein, when the program is running, it controls the device where the computer-readable storage medium is located to execute the intelligent design method for microbial fermentation experiments based on a large language model as described in the first aspect.

[0019] Fourthly, the present invention provides an electronic device, including a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the intelligent design method for microbial fermentation experiments based on a large language model as described in the first aspect.

[0020] Compared with the prior art, the advantages and positive effects of the present invention are as follows: 1. High automation: The entire process from intent to experiment execution is automated, greatly improving the efficiency of experiment design; 2. Knowledge Enhancement: Combining RAG technology with private historical data ensures that the design solutions are based on solid evidence; 3. Resource awareness: By combining real-time resource status, the feasibility of the solution and scheduling efficiency are improved; 4. Structured output: It can generate standardized experimental task structures, which facilitates system integration; 5. Human-machine collaboration mechanism: Retain the expert optimization interface to ensure the safety and controllability of experiments.

[0021] In summary, this invention provides an intelligent design system for microbial fermentation experiments. Based on the experimental objectives input by the user, it can automatically retrieve historical databases (or private knowledge bases), query the status of experimental resources, generate experimental plans through large language models, and synchronize them to a digital system with a task structure recognizable by the experimental system to support task confirmation, optimization, and execution. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the system module connections of the present invention.

[0025] Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0026] To better understand the above-mentioned objectives, features, and advantages of the present invention, the solutions of the present invention will be further described below. It should be noted that, unless otherwise specified, the embodiments of the present invention and the features thereof can be combined with each other.

[0027] Many specific details are set forth in the following description in order to provide a full understanding of the invention, but the invention may also be practiced in other ways different from those described herein; obviously, the embodiments in the specification are only some embodiments of the invention, and not all embodiments.

[0028] The preferred embodiments of the present invention will now be described in detail with reference to specific examples. It should be understood that the following examples are given for illustrative purposes only and are not intended to limit the scope of the invention. Those skilled in the art can make various modifications and substitutions to the present invention without departing from its spirit and essence.

[0029] Example 1

[0030] See Figure 1 As shown, this embodiment provides an intelligent design system for microbial fermentation experiments based on a large language model, including: The intent parsing module is used to parse the natural language instructions input by the user into experimental objectives and constraints through a large language model. The knowledge enhancement module is used to automatically retrieve the user's historical experiment database based on the parsed experimental objectives and constraints, and integrate historical information that meets the preset similarity with the enhancement conditions to output prompt words containing the enhancement conditions; The resource scheduling module is used to obtain available resource information via API based on prompts containing enhanced conditions; The experiment design module is used to encapsulate the parsed experimental objectives and constraints, prompts containing enhancement conditions, and available resource information into an integrated prompt. It then uses a large language model to perform instruction reasoning and outputs the optimal experimental design scheme based on the direction of maximizing the objective. The human-machine collaboration module is used to send the optimal experimental design scheme to the user and provide a visual interface for the user to confirm or modify the experimental design scheme. The task execution module is used to convert the experimental design scheme confirmed or modified by the user into a task structure that can be recognized by the experimental system, and send it to the experimental system to complete the execution of the experimental design scheme.

[0031] Example 2

[0032] This embodiment provides an intelligent design method for microbial fermentation experiments based on a large language model, such as... Figure 2 As shown, the specific steps are as follows.

[0033] S1 parses the natural language instructions input by the user into experimental objectives and constraints using a large language model.

[0034] Specifically: Users can input their experimental intentions in natural language through a graphical or command-line interface, such as "I want to use Bacillus subtilis to ferment and produce glutamic acid, the higher the yield the better, and the time should preferably not exceed 48 hours".

[0035] The system uses a large language model to perform structured understanding of the input sentence and extracts: Experimental objective: To produce glutamic acid Strains preferred: Bacillus subtilis Optimization metric: Maximizing yield Time constraint: No more than 48 hours The final output is structured content for downstream modules to use:

[0036] S2, based on the parsed experimental objectives and constraints, automatically retrieves the user's historical experimental database, integrates historical information that meets the preset similarity as enhancement conditions, and outputs prompts containing the enhancement conditions.

[0037] Specifically: S21, the system automatically retrieves the user's historical experimental database records from the local or cloud-based database based on the experimental objectives and constraints parsed from S1. S22, compared with the current input, BERT vector embedding and multi-field weighting mechanism are used to score the similarity of strains, target products and process parameters in the historical experimental database records; S23, filter historical experimental records with a similarity higher than 0.75; S24, Information fusion generation enhancement conditions: If a certain strain or culture medium is used in most experiments, it is recommended as a candidate. The temperature, pH, and ventilation rates of multiple high-performance experiments were merged into ranges (e.g., 30℃–34℃). Select experimental characteristics that perform well based on historical yields; S25 outputs a prompt containing enhanced conditions for downstream modules to use, such as "Based on historical experiments, it is recommended to use Bacillus subtilis ATCC6051, cultured in the range of 30℃–34℃, with an optimal glutamic acid yield of 56%–62%".

[0038] S3 retrieves available resource information via API based on prompts containing enhanced conditions.

[0039] Specifically: Based on the prompts containing enhanced conditions output by S2, the system calls the experimental resource platform (LIMS / MES) via API to retrieve the following resource statuses and obtain available resource information: Current available strain inventory (number, batch, purity, remaining quantity); Optional culture medium components and costs; List of available fermenters (model, capacity, current status); Available sensors and control devices can be configured; Output format as follows:

[0040] S4 encapsulates the experimental objective and constraints parsed from S1, the prompt words containing enhancement conditions output by S2, and the available resource information obtained by S3 into an integrated prompt word. It then performs instruction reasoning through a large language model and outputs the optimal experimental design scheme based on the direction of maximizing the objective.

[0041] Specifically: S41, encapsulate the following content as an "integrated prompt word" and input it into the LLM: The experimental objectives and constraints derived from S1; S2 outputs prompts containing enhanced conditions; Available resource information obtained by S3; S42 uses a large language model for instruction reasoning and, based on the goal maximization direction, outputs a complete optimal experimental design scheme, including: Recommendations for strain selection (and reasons); Culture medium type and component ratio; Recommended process parameters (temperature, pH, time, etc.); Recommended equipment and schedule; Recommended experimental procedures (or simplified SOPs).

[0042] For example, "It is recommended to use strain ATCC6051, select M9 culture medium, control the temperature at 32℃, the aeration rate at 1.2 vvm, the fermentation time at 48h, and the equipment at FQ-500L. The expected glutamic acid yield is 60%."

[0043] S5 sends the optimal experimental design to the user and provides a visual interface for the user to confirm or modify the experimental design.

[0044] Specifically: The system will display the design scheme in the form of tables / flowcharts; Users can modify parameters or switch candidate schemes; Provide risk warnings for sensitive items (such as pH / strain); The changes will be fed back to the system for updating the task schedule.

[0045] S6 converts the user-confirmed or modified experimental design into a task structure that the experimental system can recognize, and sends it to the experimental system to complete the execution of the experimental design.

[0046] Specifically: The user clicks "Confirm Execution"; The system encodes the design scheme into a structured task JSON; Automatically sent to the underlying experimental system (such as MES / LabOS); The experimental platform automatically schedules, executes, and records data.

[0047] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for intelligent design of microbial fermentation experiments based on a large language model, characterized in that, Includes the following steps: S1, the natural language instructions input by the user are structured and parsed into experimental objectives and constraints through a large language model; S2, based on the parsed experimental objectives and constraints, automatically retrieves the user's historical experimental database, integrates historical information that meets the preset similarity as enhancement conditions, and outputs prompts containing the enhancement conditions; S3, obtain available resource information via API based on prompts containing enhanced conditions; S4 encapsulates the experimental objectives and constraints parsed from S1, the prompts containing enhancement conditions output from S2, and the available resource information obtained from S3 into an integrated prompt. It then performs instruction reasoning through a large language model and outputs the optimal experimental design scheme based on the direction of maximizing the objective. S5 sends the optimal experimental design to the user and provides a visual interface for the user to confirm or modify the experimental design. S6 converts the user-confirmed or modified experimental design into a task structure that the experimental system can recognize, and sends it to the experimental system to complete the execution of the experimental design.

2. The intelligent design method for microbial fermentation experiments according to claim 1, characterized in that, The user's historical experiment database mentioned in S2 contains various information recorded in the user's historical experiments, including but not limited to experimental objectives, strain information, culture medium information, process parameters, product information, SOP steps, and abnormal situations.

3. The intelligent design method for microbial fermentation experiments according to claim 1, characterized in that, The similarity described in S2 is measured using a multi-dimensional nested scoring system.

4. The intelligent design method for microbial fermentation experiments according to claim 1, characterized in that, In S2, historical information that meets the preset similarity is fused into enhancement conditions through multidimensional clustering statistics, parameter induction fusion, and natural language prompt template generation.

5. The intelligent design method for microbial fermentation experiments according to claim 1, characterized in that, The available resource information mentioned in S3 includes, but is not limited to, equipment information, microbial information, and material information.

6. The intelligent design method for microbial fermentation experiments according to claim 1, characterized in that, If there are multiple indicators in the objective in S4, the optimal experimental design scheme is output through the Pareto optimal solution set.

7. The intelligent design method for microbial fermentation experiments according to claim 1, characterized in that, The experimental design scheme includes, but is not limited to, material selection, process parameters, equipment selection, and schedule arrangement.

8. A smart design system for microbial fermentation experiments based on a large language model, characterized in that, include: The intent parsing module is used to parse the natural language instructions input by the user into experimental objectives and constraints through a large language model. The knowledge enhancement module is used to automatically retrieve the user's historical experiment database based on the parsed experimental objectives and constraints, and integrate historical information that meets the preset similarity with the enhancement conditions to output prompt words containing the enhancement conditions; The resource scheduling module is used to obtain available resource information via API based on prompts containing enhanced conditions; The experiment design module is used to encapsulate the parsed experimental objectives and constraints, prompts containing enhancement conditions, and available resource information into an integrated prompt. It then uses a large language model to perform instruction reasoning and outputs the optimal experimental design scheme based on the direction of maximizing the objective. The human-machine collaboration module is used to send the optimal experimental design scheme to the user and provide a visual interface for the user to confirm or modify the experimental design scheme. The task execution module is used to convert the experimental design scheme confirmed or modified by the user into a task structure that can be recognized by the experimental system, and send it to the experimental system to complete the execution of the experimental design scheme.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is running, it controls the device containing the computer-readable storage medium to execute the intelligent design method for microbial fermentation experiments as described in any one of claims 1-7.

10. An electronic device, characterized in that, It includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the intelligent design method for microbial fermentation experiments according to any one of claims 1-7.

Images