An intelligent optimization method and system for animal-derived epidermal growth factor

Abstract

This application relates to the technical field of growth factor monitoring systems, and specifically discloses an intelligent optimization method and system for animal-derived epidermal growth factor. The method mainly includes: determining a target strain that highly expresses epidermal growth factor, where the strain is a genetically engineered strain containing animal-derived epidermal growth factor; determining the culture conditions of the target strain; monitoring the physiological indicators of the target strain; determining the current growth stage of the target strain based on the physiological indicators; and optimizing the culture conditions of the target strain according to the current growth stage of the target strain. This application effectively solves the problem in the prior art that using fixed culture conditions to culture genetically engineered strains is difficult to meet the specific requirements of the strains at different growth stages, thereby restricting the yield and expression efficiency of epidermal factors. By identifying and utilizing the growth cycle of the strains and dynamically adjusting the culture conditions, the specific requirements of the strains at different growth stages are met, thereby significantly improving the yield and expression efficiency of epidermal factors.

Description

Technical Field

[0001] The present application relates to the technical field of growth factor monitoring, and in particular to an intelligent optimization method and system for animal-derived epidermal growth factor. Background Art

[0002] Animal-derived epidermal growth factor (EGF) is an important bioactive polypeptide, widely present in mammals. It plays a key role in regulating physiological processes such as cell proliferation, differentiation, and tissue repair. EGF promotes the growth and division of epidermal cells, accelerates wound healing, and improves skin quality. Therefore, it has broad application prospects in medical cosmetology, skin repair, and biopharmaceuticals.

[0003] Currently, fixed culture conditions are usually used to cultivate genetically engineered bacteria in order to obtain higher EGF expression levels. However, the bacteria will go through different growth stages during the growth process, and each stage has different requirements for culture conditions such as nutrition, temperature, and pH. Fixed culture conditions are difficult to meet the specific needs of bacteria in different growth stages, thereby limiting the production and expression efficiency of epidermal growth factor. Summary of the Invention

[0004] The present application provides an intelligent optimization method and system for animal-derived epidermal growth factor, which effectively solves the problem in the prior art that fixed culture conditions are used to cultivate genetically engineered strains, making it difficult to meet the specific needs of the strains at different growth stages, thereby limiting the production and expression efficiency of the epidermal factor. By identifying and utilizing the growth cycle of the strains and dynamically adjusting the culture conditions, the specific needs of the strains at different growth stages are met, thereby significantly improving the production and expression efficiency of the epidermal factor.

[0005] In a first aspect, the present application provides an intelligent optimization method for animal-derived epidermal growth factor, comprising: determining a target bacterial species that efficiently expresses epidermal growth factor; wherein the bacterial species is a genetically engineered bacterial species containing animal-derived epidermal growth factor; determining the culture conditions of the target bacterial species; monitoring the physiological indicators of the target bacterial species; determining the current growth stage of the target bacterial species based on the physiological indicators; and optimizing the culture conditions of the target bacterial species based on the current growth stage of the target bacterial species.

[0006] Further, monitor the physiological indicators of the target strain, including: obtaining a fluorescence image of the target strain at a specified time; quantifying and recording the fluorescence intensity in the specified fluorescence image, and calculating the change in fluorescence intensity; evaluating the growth amount of the target strain according to the change in fluorescence intensity; constructing a growth curve with the specified time and fluorescence intensity; calculating the slope of the growth curve between two adjacent specified times in sequence; when the current slope is less than the preset value, mark the time corresponding to the current slope as the initial stage of the stationary phase.

[0007] Further, optimize the culture conditions of the target strain according to the current growth stage of the target strain, including:

[0008] Before the growth stage of the target strain reaches the initial stage of the stationary phase: monitor the changes in culture conditions caused by the reproduction of the strain, quantitatively evaluate the degree of influence of the changes in culture conditions on the growth amount of the target strain, and judge whether to optimize the culture conditions according to the degree of influence.

[0009] After the growth stage of the target strain reaches the initial stage of the stationary phase: regularly optimize the culture conditions to an environment suitable for the expression of epidermal factors.

[0010] Further, monitor the changes in culture conditions caused by the reproduction of the strain, and quantitatively evaluate the degree of influence of the changes in culture conditions on the growth amount of the target strain, including: monitoring the change characteristics, where the change characteristics include: pH value, dissolved oxygen content, and the degree of overlap between strains; using the entropy weight method to assign weights to each change characteristic; defining fuzzy sets for each change characteristic, and defining membership functions for each fuzzy set; inputting the monitored pH value, dissolved oxygen content, and the degree of overlap between strains into the membership function to obtain the fuzzy values of each change characteristic; determining the fuzzy output of the growth amount of the target strain according to the predefined fuzzy rules and the input fuzzy values; using the weighted average method, considering the output weights and membership degrees of each fuzzy set, to convert the fuzzy output into a specific value; performing a multiplication operation on each output membership degree value and the specific value, adding up all the multiplication results, and dividing the obtained sum by the sum of all membership degree values to obtain the dynamic influence factor of the change in culture conditions on the growth amount of the target strain.

[0011] Further, monitor the degree of overlap between strains, including: regularly obtaining an image of the target strain, calculating the total area of the strains in the image, and marking it as the area before segmentation; using an image segmentation algorithm to segment the strains in the image to obtain each strain, and calculating the total area of all strains, and marking it as the area after segmentation; obtaining the overlapping area according to the area before segmentation and the area after segmentation, and marking the quotient of the overlapping area divided by the total area after segmentation as the degree of overlap between strains.

[0012] Further, based on the degree of influence of changes in culture conditions on the growth of the target strain, it is determined whether to optimize the culture conditions, including: determining whether the dynamic influence factor is greater than a preset threshold. If so, the genetic algorithm is used to optimize the culture conditions into an environment suitable for the growth of the strain.

[0013] Further, using the genetic algorithm to optimize the culture conditions into an environment suitable for the growth of the strain includes: obtaining environmental parameters, where the environmental parameters include: temperature, pH value, overlap degree between strains, and dissolved oxygen content; generating an initial population, where the initial population contains individuals with different environmental parameters; based on the growth amount, designing a fitness function for evaluating the quality of each individual and calculating the fitness value of each individual; using roulette wheel selection to select individuals with higher fitness to enter the next generation of reproduction; performing a crossover operation on the selected parental individuals to generate a new individual combination; performing a mutation operation on the new individuals to randomly adjust some parameters; through multiple iterations of the genetic algorithm, gradually optimizing the growth amount and maximizing the value of the fitness function; stopping the iteration when the change in population fitness tends to be stable and outputting the final environmental parameters suitable for the growth of the strain.

[0014] Further, regularly optimizing the culture conditions into an environment suitable for the expression of epidermal growth factor includes: obtaining the key features affecting the expression amount, where the key features include: temperature, metabolite amount, pH value, and dissolved oxygen content; determining the initial values of the key features suitable for the expression of epidermal growth factor; monitoring the change amount of each key feature and the growth amount of epidermal growth factor at a specified time; assigning weight coefficients to each key feature, and marking the sum of the product of the change amount of each key feature and its respective weight coefficient as the change index; calculating the linear correlation between the change index and the growth amount; determining whether the linear correlation is greater than a preset critical value. If so, adjusting the values of the key features to the initial values.

[0015] Further, monitoring the change amount of each key feature and the growth amount of epidermal growth factor at a specified time includes: determining the initial value of the time interval; at the end of each time interval, recording the change amount of the key feature and the growth amount of epidermal growth factor, and updating the time interval to the old value; changing the old value to the new value, specifically: calculating the ratio of the growth amount monitored at the end of the current time interval to the growth amount monitored at the end of the previous time interval, and marking the product of the ratio and the old value as the new value.

[0016] On the other hand, the present application also provides an intelligent optimization system for animal-derived epidermal growth factor, including: a target strain determination module, a culture condition and physiological index module, a growth stage determination module, and a culture condition optimization module.

[0017] The target strain determination module is used to determine the target strain that highly expresses epidermal growth factor; wherein, the strain is a genetic engineering strain containing animal-derived epidermal growth factor.

[0018] The culture condition and physiological index module is used to determine the culture conditions of the target strain; monitor the physiological indexes of the target strain.

[0019] The growth stage determination module is used to determine the current growth stage of the target strain according to the physiological indexes.

[0020] The culture condition optimization module is used to optimize the culture conditions of the target strain according to the current growth stage of the target strain.

[0021] The technical solution provided by this application has at least the following technical effects or advantages:

[0022] By monitoring the physiological indexes of the target strain, this application can accurately judge the current growth stage of the target strain according to the monitored physiological indexes, and optimize the culture conditions accordingly to meet the specific needs of the strain at different growth stages, solving the problem in the prior art that a fixed culture condition is used to culture genetically engineered strains, which is difficult to meet the specific needs of the strain at different growth stages, thus restricting the yield and expression efficiency of epidermal growth factor. It significantly improves the yield and expression efficiency of epidermal growth factor, provides strong support for the efficient culture of genetically engineered strains, and has remarkable superiority and wide practicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flowchart of the intelligent optimization method for animal-derived epidermal growth factor in Embodiment 1 of this application;

[0024] Figure 2 It is a schematic diagram of the modules of the intelligent optimization system for animal-derived epidermal growth factor in Embodiment 2 of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] This application solves the problem in the prior art that a fixed culture condition is used to culture genetically engineered strains, which is difficult to meet the specific needs of the strain at different growth stages, thus restricting the yield and expression efficiency of epidermal growth factor. This application dynamically adjusts the culture conditions by identifying and utilizing the growth cycle of the strain, meeting the specific needs of the strain at different growth stages, and thus significantly improving the yield and expression efficiency of epidermal growth factor.

[0026] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the drawings in the specification and specific embodiments.

[0027] Embodiment 1: As Figure 1 shown, this embodiment provides an intelligent optimization method for animal-derived epidermal growth factor, including:

[0028] S100. Determine the target strain that highly expresses epidermal growth factor; wherein, the strain is a genetically engineered strain containing animal-derived epidermal growth factor gene.

[0029] S200. Determine the culture conditions of the target strain; monitor the physiological indexes of the target strain.

[0030] S300. Determine the current growth stage of the target strain according to the physiological indexes.

[0031] S400. Optimize the culture conditions of the target strain according to the current growth stage of the target strain.

[0032] In S100 - S400, by determining the target strain that highly expresses EGF, then determining the culture conditions of the target strain, and monitoring its physiological indexes, according to the monitored physiological indexes, the current growth stage of the target strain can be accurately judged, and the culture conditions can be optimized accordingly to meet the specific requirements of the strain at different growth stages, thereby improving the yield and purity of EGF.

[0033] After determining the target strain that highly expresses epidermal growth factor, in order to achieve precise control of its growth process, we need to monitor the physiological indexes of the target strain. Specifically, in S200, monitor the physiological indexes of the target strain, including:

[0034] S210. Obtain the fluorescence image of the target strain at a specified time.

[0035] S220. Quantify and record the fluorescence intensity in the specified fluorescence image, and calculate the change amount of fluorescence intensity.

[0036] S230. Evaluate the growth amount of the target strain according to the change amount of fluorescence intensity.

[0037] S240. Construct a growth curve with the specified time and fluorescence intensity.

[0038] S250. Calculate the slope of the growth curve between two adjacent specified times in sequence.

[0039] S260. When the current slope is less than the preset value, mark the time corresponding to the current slope as the initial stage of the stationary phase.

[0040] Specific fluorescent dyes are used to label the bacterial strains, enabling them to emit visible light under fluorescence excitation. The fluorescence images can intuitively reflect the growth status and distribution of the bacterial strains. By acquiring the fluorescence images and performing quantitative processing on them, the numerical values of the fluorescence intensity in the images are measured and recorded. The fluorescence intensity is positively correlated with the growth amount of the bacterial strains. Therefore, the growth situation of the bacterial strains can be inferred from the change in fluorescence intensity. By calculating the change amount of fluorescence intensity at adjacent time points, the growth rate of the bacterial strains can be more accurately reflected. By comparing the change amounts of fluorescence intensity at different time points, the growth amount of the target bacterial strains can be evaluated. An increase in fluorescence intensity means an increase in the number of bacterial strains or an enhancement of growth activity, while the opposite may indicate that the growth of the bacterial strains is inhibited or they have entered the decline phase.

[0041] To more intuitively display the growth process of the target bacterial strains, the specified time and the corresponding fluorescence intensity data can be plotted into a growth curve. The growth curve can clearly reflect the growth status of the bacterial strains at different time points, providing a basis for subsequent analysis and judgment. To further quantify the growth rate of the bacterial strains, the slopes of the growth curve between adjacent two specified times are calculated in sequence. The magnitude of the slope reflects the growth speed of the bacterial strains during this time period. The larger the slope, the faster the growth speed. The stationary phase is an important stage in the growth process of the bacterial strains. At this time, the number of bacterial strains is relatively stable, the growth speed slows down, but they begin to express a large amount of epidermal growth factor. By setting a preset slope value as the judgment criterion, when the current slope of the growth curve reaches or approaches this preset value, the bacterial strains have entered the initial stage of the stationary phase.

[0042] The following is a specific example to illustrate how to apply the above method in actual operation to monitor the physiological indicators of the target bacterial strains and determine the initial stage of their stationary phase:

[0043] Suppose an Escherichia coli genetically engineered to efficiently express animal-derived epidermal growth factor is used as the target bacterial strain. To distinguish Escherichia coli from the background, we use a fluorescent dye specific to Escherichia coli for labeling. A monitoring cycle of every two hours is set, and fluorescence imaging of Escherichia coli in the culture is performed using a fluorescence microscope at specified times (such as the 0th hour, the 2nd hour, the 4th hour, etc.).

[0044] Quantitative analysis is performed on the acquired fluorescence images using image processing software, and the fluorescence intensity values in the fluorescence images at each time point are measured and recorded. For example, at the 0th hour, we measured the fluorescence intensity to be 100 units; at the 2nd hour, the fluorescence intensity increased to 150 units; and so on. By calculating the difference in fluorescence intensity at adjacent time points, we can obtain the change amount of fluorescence intensity. For example, the change amount from the 0th hour to the 2nd hour is 50 units.

[0045] As the monitoring time progressed, it was observed that the fluorescence intensity continued to increase, indicating that the number of Escherichia coli was constantly increasing. By comparing the change in fluorescence intensity at different time points, the growth rate of Escherichia coli could be evaluated.

[0046] The fluorescence intensity values at each time point were plotted to form a growth curve. The horizontal axis represented time (hours), and the vertical axis represented fluorescence intensity (units). The growth curve could visually display the growth state of Escherichia coli at different time points. The slope of the growth curve between two adjacent time points was calculated to quantify the growth rate of Escherichia coli. For example, the slope of the growth curve from hour 0 to hour 2 was 25 units / hour (change of 50 units divided by the time interval of 2 hours); the slope from hour 2 to hour 4 was less than 25 units / hour, indicating that the growth rate began to slow down.

[0047] A preset slope value, such as 10 units / hour, was set as the criterion for judging the early stage of the stationary phase. When the slope of the growth curve first dropped below this preset value, it was considered that Escherichia coli had entered the early stage of the stationary phase.

[0048] After determining the current growth stage of the target strain, we need to optimize its culture conditions based on this information to ensure that the strain can grow efficiently and express the target product. Specifically, in 300, according to the current growth stage of the target strain, the culture conditions of the target strain were optimized, including:

[0049] S310: Before the growth stage of the target strain reaches the early stage of the stationary phase: Monitor the changes in culture conditions caused by the reproduction of the strain, quantitatively evaluate the degree of influence of the changes in culture conditions on the growth amount of the target strain, and judge whether to optimize the culture conditions according to the degree of influence.

[0050] S320: After the growth stage of the target strain reaches the early stage of the stationary phase: Regularly optimize the culture conditions to an environment suitable for the expression of epidermal growth factor.

[0051] During the growth process of the target strain, its reproductive activities will cause changes in culture conditions, such as a decrease in pH value, consumption of nutrients, and accumulation of metabolites. Regularly monitoring these changes in culture conditions to ensure that they are maintained within an appropriate range can effectively avoid adverse effects on the growth of the strain.

[0052] When the growth stage of the target strain reaches the early stage of the stationary phase, its growth rate begins to slow down, but it begins to express a large amount of epidermal growth factor. At this time, regularly optimize the culture conditions to create an environment more suitable for the expression of epidermal growth factor.

[0053] To evaluate the impact of changes in culture conditions on the growth of the target strain, a fuzzy logic-based method was adopted. Specifically, in S310, the changes in culture conditions caused by the reproduction of the strain were monitored, and the degree of influence of the changes in culture conditions on the growth of the target strain was quantitatively evaluated, including:

[0054] Sa311. Monitor the change characteristics, where the change characteristics include: pH value, dissolved oxygen content, and the overlap degree between strains.

[0055] Sa312. Use the entropy weight method to assign weights to each change characteristic.

[0056] Sa313. Define fuzzy sets for each change characteristic and define membership functions for each fuzzy set.

[0057] Sa314. Input the monitored pH value, dissolved oxygen content, and the overlap degree between strains into the membership function to obtain the fuzzy values of each change characteristic.

[0058] Sa315. Determine the fuzzy output of the growth of the target strain according to the predefined fuzzy rules and the input fuzzy values;

[0059] Sa316. Use the weighted average method, considering the output weights of each fuzzy set and their membership degrees, to convert the fuzzy output into a specific numerical value.

[0060] Sa317. Perform a product operation on the membership degree value of each output and the specific numerical value, accumulate all the product results, and divide the obtained accumulated value by the sum of the accumulated values of all membership degree values to obtain the dynamic influence factor of the change in culture conditions on the growth of the target strain.

[0061] First, it is necessary to monitor the change characteristics that have an important impact on the growth of the target strain. The pH value, dissolved oxygen content, and the overlap degree between strains can be selected as the monitoring objects. Among them, the pH value reflects the acidity and alkalinity of the culture solution and has a direct impact on the growth and metabolism of the strain; the dissolved oxygen content determines whether the strain can obtain sufficient oxygen for respiration; the overlap degree between strains reflects the distribution density of the strains in the culture space and may affect their growth rate and product expression.

[0062] Use the entropy weight method to assign weights to each change characteristic to reflect its importance in the evaluation. The entropy value of each change characteristic is: , where, represents the entropy value, represents the standardized value of the i-th sample on the j-th characteristic, , n represents the number of samples; the weight of each change characteristic is: ; where, m represents the number of change characteristics.

[0063] Define fuzzy sets for each variable feature, such as "low", "medium", "high", etc., and define membership functions for each fuzzy set.

[0064] Input the overlaps between the monitored pH value, dissolved oxygen content, and bacterial species into their respective membership functions, and calculate the fuzzy values of each variable feature, i.e., the degrees of belonging to each fuzzy set.

[0065] According to the predefined fuzzy rules (such as "if the pH value is low and the dissolved oxygen content is high, then the growth amount is medium", etc.) and the input fuzzy values, use the fuzzy inference mechanism to determine the fuzzy output of the growth amount of the target bacterial species.

[0066] Use the weighted average method to convert the fuzzy output into a specific numerical value. The specific formula is: , where Y represents the specific numerical value of the fuzzy output, represents the output weight of the j-th fuzzy set, represents the membership degree of the j-th fuzzy set.

[0067] To obtain the dynamic influence factor of the change in culture conditions on the growth amount of the target bacterial species, perform a multiplication operation on the membership degree value and the specific numerical value of each output, and sum up all the multiplication results. Then, divide the obtained sum value by the sum of all membership degree values. The specific formula is: , where IF represents the dynamic influence factor, represents the specific numerical value of the j-th output.

[0068] The dynamic influence factor of the change in culture conditions on the growth amount of the target bacterial species reflects the comprehensive influence degree of the change in culture conditions on the growth amount of the target bacterial species, and can be used to guide the optimization of culture conditions to increase the growth amount and product expression amount of the target bacterial species.

[0069] In Sa311, monitor the overlap between bacterial species, including:

[0070] Sa3111. Regularly obtain images of the target bacterial species, calculate the total area of the bacterial species in the image, and mark it as the area before segmentation.

[0071] Sa3112. Use an image segmentation algorithm to segment the bacterial species in the image to obtain each bacterial species, and calculate the total area of all bacterial species, which is marked as the area after segmentation.

[0072] Sa3113. Obtain the overlapping area based on the area before segmentation and the area after segmentation, and mark the quotient of dividing the overlapping area by the total area after segmentation as the overlap between bacterial species.

[0073] Regularly capture images of the target bacterial species using a microscope to ensure that the images can accurately reflect the morphology and distribution of the bacterial species. Calculate the total area of the bacterial species in the captured images and label this area as the "area before segmentation". Apply an image segmentation algorithm to process the captured images, individually identify and separate each bacterial species in the images, calculate the total area of all the segmented bacterial species, and label this area as the "area after segmentation". Then calculate the overlap degree. The formula for calculating the overlap degree is: , where OR represents the overlap degree between bacterial species, Ab represents the total area of the bacterial species before segmentation, and Aa represents the total area of all the bacterial species after segmentation; thus, it is possible to evaluate the mutual influence and space occupation of bacterial species during the growth process.

[0074] In S310, based on the degree of influence of changes in culture conditions on the growth amount of the target bacterial species, determine whether to optimize the culture conditions, including: determining whether the dynamic influence factor is greater than a preset threshold. If so, use a genetic algorithm to optimize the culture conditions into an environment suitable for the growth of the bacterial species.

[0075] Using a genetic algorithm to optimize the culture conditions into an environment suitable for the growth of the bacterial species includes:

[0076] Sb311. Obtain environmental parameters, where the environmental parameters include: temperature, pH value, overlap degree between bacterial species, dissolved oxygen content.

[0077] Sb312. Generate an initial population, where the initial population contains individuals with different environmental parameters.

[0078] Sb313. Based on the growth amount, design a fitness function for evaluating the quality of each individual and calculate the fitness value of each individual.

[0079] Sb314. Use roulette wheel selection to select individuals with higher fitness to enter the next generation of reproduction.

[0080] Sb315. Perform a crossover operation on the selected parental individuals to generate new individual combinations.

[0081] Sb316. Perform a mutation operation on the new individuals to randomly adjust some parameters.

[0082] Sb317. Through multiple iterations, the genetic algorithm gradually optimizes the growth amount and maximizes the value of the fitness function; when the change in population fitness tends to be stable, stop the iteration and output the final environmental parameters suitable for the growth of the bacterial species.

[0083] Obtain the key environmental parameters affecting the growth of bacterial strains through sensors, including temperature, pH value, overlap degree between bacterial strains, dissolved oxygen content, etc. Randomly generate a group of individuals containing different combinations of environmental parameters to form an initial population. Each individual represents a possible environmental parameter setting. Design a fitness function based on the growth amount of bacterial strains (such as biomass, growth rate, etc.) to evaluate the quality of each individual. The fitness function formula can be: Growth, where Growth represents the monitored growth amount; Use the roulette wheel selection method, and the selection probability of an individual is proportional to its fitness value.

[0084] The crossover operation generates new individual combinations by exchanging the environmental parameters of parental individuals, such as single-point crossover and two-point crossover; The mutation operation increases the diversity of the population by randomly adjusting some parameter values of individuals, and the mutation probability can be determined according to the complexity of the problem and computing resources.

[0085] Through multiple iterations, gradually optimize the growth amount and maximize the value of the fitness function. In each iteration, perform selection, crossover, and mutation operations to generate a new population. When the change in population fitness tends to be stable, that is, the average fitness change of the population for consecutive generations is less than a certain value, stop the iteration and output the final environmental parameter combination suitable for the growth of bacterial strains.

[0086] In the initial stage of bacterial strain growth, the bacterial strains need to adapt to the new environment, and cell division is relatively slow. At this time, a relatively high temperature may be required to stimulate the metabolic activities of the bacterial strains and accelerate their growth rate. A relatively high temperature can increase the activity of enzymes inside cells, promote the absorption of nutrients and the synthesis of metabolites, thereby helping the bacterial strains quickly adapt to the environment and enter the rapid growth stage. As the growth amount of the bacterial strains increases, their metabolic activities will also gradually increase. In the vigorous growth period, the bacterial strains need more nutrients and oxygen to support their growth and metabolism, but at the same time, a large amount of metabolic waste and heat will be generated, and the temperature needs to be appropriately reduced to maintain the metabolic balance inside the bacterial strains and ensure the healthy growth of the bacterial strains.

[0087] During the growth process of bacterial strains, as reproduction proceeds, the culture conditions will constantly change, including key factors such as pH value, dissolved oxygen content, and overlap degree between bacterial strains. The changes in these factors will have a significant impact on the target bacterial strains in the growth stage. By comprehensively considering the changes in these culture conditions and real-time evaluating their specific impacts on the growth of bacterial strains, when this impact reaches a certain amount, the genetic algorithm can quickly respond and comprehensively optimize the culture conditions from multiple aspects such as temperature, pH value, overlap degree between bacterial strains, dissolved oxygen content, etc. to ensure that the environment is suitable for the growth requirements of bacterial strains.

[0088] In S320, regularly optimize the culture conditions to an environment suitable for the expression of epidermal growth factor, including:

[0089] S321. Obtain the key features that affect the expression level, where the key features include: temperature, metabolite amount, pH value, dissolved oxygen amount.

[0090] S322. Determine the initial values of the key features suitable for epidermal growth factor expression.

[0091] S323. Monitor the change amounts of each key feature and the growth amount of epidermal growth factor at a specified time.

[0092] S324. Assign a weight coefficient to each key feature, and mark the sum of the product of the change amount of each key feature and its respective weight coefficient as the change index.

[0093] S325. Calculate the linear correlation between the change index and the growth amount.

[0094] S326. Determine whether the linear correlation is greater than a preset critical value. If so, adjust the value of the key feature to the initial value.

[0095] First, it is necessary to identify and obtain the key features that have a significant impact on the expression level of epidermal growth factor, including temperature, metabolite amount, pH value, and dissolved oxygen amount. Through experiments or literature review, a set of initial values of the key features suitable for the current epidermal growth factor expression can be determined. During the cultivation process, the change amounts of each key feature and the growth amount of epidermal growth factor are regularly monitored by sensors.

[0096] To evaluate the influence degree of each key feature on the expression of epidermal growth factor, a weight coefficient can be assigned to each feature according to the relative importance of the feature or experimental data, and the change index is calculated. The formula is: , where represents the change index, , , , respectively represent the change amounts of temperature, metabolite amount, pH value, and dissolved oxygen amount, , , , respectively represent the weight coefficients of these change amounts.

[0097] By calculating the linear correlation between the change index and the growth amount of epidermal growth factor, such as using the Pearson correlation coefficient to achieve, the formula is: , where n represents the number of observations, and respectively represent the change index and the growth amount of epidermal growth factor in the i-th observation, and respectively represent their average values.

[0098] The calculated Peel correlation coefficient is compared with the preset critical value. If the Peel correlation coefficient is greater than the critical value, it is considered that there is a strong linear correlation between the change index and the growth amount of the epidermal factor. At this time, the value of the key feature should be adjusted, specifically reset to the initial value, to optimize the expression environment of the epidermal factor.

[0099] In S323, the change amount of each key feature and the growth amount of the epidermal factor are monitored at a specified time, including:

[0100] S3231. Determine the initial value of the time interval.

[0101] S3232. At the end of each time interval, record the change in key features and the increase in skin factor, and update the time interval to the old value.

[0102] S3233. Change the old value to the new value, specifically: calculate the ratio of the growth amount monitored at the end of the current time interval to the growth amount monitored at the end of the previous time interval, and mark the product of the ratio and the old value as the new value.

[0103] A reasonable initial time interval value is determined based on the growth characteristics of the epidermal factor, the stability of the culture environment, and the experimental requirements. For example, monitoring is performed once an hour. At the end of each time interval, the key characteristic values (temperature, metabolite content, pH value, dissolved oxygen content) and the amount of epidermal factor at the current moment need to be recorded, and their changes relative to the end of the previous time interval are calculated. At the same time, the current time interval is updated to the old value. , so as to be used in the next cycle. Calculate the ratio r of the epidermal factor growth monitored at the end of the current time interval to the epidermal factor growth monitored at the end of the previous time interval: ,in, Represents the increase in epidermal factor at the end of the previous time interval, Represents the increase in the epidermal factor at the end of the current time interval, and then multiply this ratio by the old value to get the new time interval , .

[0104] For example, if the skin factor increased by 10 mg / L in the previous time interval (from the 2nd hour to the 3rd hour), and the skin factor increased by 5 mg / L in the current time interval (from the 3rd hour to the 4th hour), the ratio r is 2, and the new time interval is obtained. =2.

[0105] During the stationary and decline phases of the bacterial strain, the expression level of the epidermal growth factor first remains unchanged and then gradually decreases. According to the time intervals of the optimized culture conditions based on the expression level of the epidermal growth factor, the unnecessary monitoring frequency can be significantly reduced, saving experimental resources and time, while still being able to effectively capture the key change points and improving the experimental efficiency and accuracy.

[0106] Example 2: As Figure 2 shown, this example provides an intelligent optimization system for animal-derived epidermal growth factor, including: a target bacterial strain determination module, a culture condition and physiological index module, a growth stage determination module, and a culture condition optimization module.

[0107] The target bacterial strain determination module is used to determine the target bacterial strain that highly expresses epidermal growth factor; wherein, the bacterial strain is a genetically engineered bacterial strain containing animal-derived epidermal growth factor.

[0108] The culture condition and physiological index module is used to determine the culture conditions of the target bacterial strain; monitor the physiological indexes of the target bacterial strain.

[0109] The growth stage determination module is used to determine the current growth stage of the target bacterial strain according to the physiological indexes.

[0110] The culture condition optimization module is used to optimize the culture conditions of the target bacterial strain according to the current growth stage of the target bacterial strain.

[0111] This example has all the advantages of the intelligent optimization method of animal-derived epidermal growth factor in Example 1, and can automatically implement the steps of the intelligent identity authentication and access control method for the cloud computing platform.

[0112] This example provides a device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the intelligent optimization method of animal-derived epidermal growth factor in Example 1 when executing the computer program.

[0113] This example provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and run by a processor, the steps of the intelligent optimization method of animal-derived epidermal growth factor in Example 1 are executed.

[0114] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing steps of functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to cover the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

Claims

1. An intelligent optimization method for animal-derived epidermal growth factor, characterized in that Including: Determine the target strain that highly expresses epidermal growth factor; wherein, the strain is a genetically engineered strain containing animal-derived epidermal growth factor; Determine the culture conditions of the target strain; monitor the physiological indicators of the target strain, including: Obtain the fluorescence image of the target strain at a specified time; Quantify and record the fluorescence intensity in the fluorescence image, and calculate the change amount of the fluorescence intensity; Evaluate the growth amount of the target strain according to the change amount of the fluorescence intensity; Construct a growth curve with the specified time and fluorescence intensity; Calculate the slope of the growth curve between two adjacent specified times in sequence; When the current slope is less than the preset value, mark the time corresponding to the current slope as the initial stage of the stationary phase; determine the current growth stage of the target strain according to the physiological indicators; According to the current growth stage of the target strain, optimize the culture conditions of the target strain, including: Before the growth stage of the target strain reaches the initial stage of the stationary phase: monitor the changes in the culture conditions caused by the reproduction of the strain, and quantitatively evaluate the influence degree of the changes in the culture conditions on the growth amount of the target strain, including: Monitor the change characteristics, and the change characteristics include: pH value, dissolved oxygen content, and overlap degree between strains; Use the entropy weight method to assign weights to each change characteristic; Define fuzzy sets for each change characteristic, and define membership functions for each fuzzy set; Input the monitored pH value, dissolved oxygen content, and overlap degree between strains into the membership function to obtain the fuzzy values of each change characteristic; According to the predefined fuzzy rules and the input fuzzy values, determine the fuzzy output of the growth amount of the target strain; Use the weighted average method, considering the output weights and membership degrees of each fuzzy set, to convert the fuzzy output into a specific value; Perform a multiplication operation on the membership degree value of each output and the specific value, accumulate all the multiplication results, and divide the obtained accumulated value by the sum of all membership degree values to obtain the dynamic influence factor of the change in the culture conditions on the growth amount of the target strain; According to the influence degree, judge whether to optimize the culture conditions, including: Judge whether the dynamic influence factor is greater than the preset threshold. If so, use the genetic algorithm to optimize the culture conditions into an environment suitable for the growth of the strain, including: Obtain the environmental parameters, and the environmental parameters include: temperature, pH value, overlap degree between strains, and dissolved oxygen content; Generate an initial population, and the initial population contains individuals with different environmental parameters; Based on the growth amount, design a fitness function for the pros and cons of each individual, and calculate the fitness value of each individual; Use roulette wheel selection to select individuals with higher fitness to enter the next generation of reproduction; Perform a crossover operation on the selected parental individuals to generate a new individual combination; Perform a mutation operation on the new individuals to randomly adjust some parameters; The genetic algorithm gradually optimizes the growth amount through multiple iterations to maximize the value of the fitness function; stop the iteration when the change in population fitness tends to be stable, and output the final environmental parameters suitable for the growth of the strain; After the growth stage of the target strain reaches the initial stage of the stationary phase: regularly optimize the culture conditions into an environment suitable for the expression of epidermal factor.

2. The method according to claim 1, characterized in that, Monitor the overlap degree between strains, including: Regularly obtain the image of the target strain, calculate the total area of the strains in the image, and mark it as the area before segmentation; Use an image segmentation algorithm to segment the bacterial strains in the image to obtain each bacterial strain, and calculate the total area of all bacterial strains, which is marked as the area after segmentation; Obtain the overlapping area based on the area before segmentation and the area after segmentation, and mark the quotient of dividing the overlapping area by the total area after segmentation as the overlapping degree between bacterial strains.

3. The method according to claim 1, wherein Regularly optimize the culture conditions to an environment suitable for epidermal growth factor expression, including: Obtain the key features affecting the expression level, and the key features include: temperature, metabolite amount, pH value, dissolved oxygen content; Determine the initial values of the key features suitable for epidermal growth factor expression; Monitor the change amount of each key feature and the growth amount of epidermal growth factor at a specified time; Assign a weight coefficient to each key feature, and mark the sum of the product of the change amount of each key feature and its respective weight coefficient as the change index; Calculate the linear correlation between the change index and the growth amount; Judge whether the linear correlation is greater than a preset critical value. If so, adjust the value of the key feature to the initial value.

4. The method according to claim 3, characterized in that, Monitor the change amount of each key feature and the growth amount of epidermal growth factor at a specified time, including: Determine the initial value of the time interval; At the end of each time interval, record the change amount of the key feature and the growth amount of epidermal growth factor, and update the time interval to the old value; Change the old value to the new value. Specifically, calculate the ratio of the growth amount monitored at the end of the current time interval to the growth amount monitored at the end of the previous time interval, and mark the product of the ratio and the old value as the new value.

5. An intelligent optimization system for animal-derived epidermal growth factor, characterized in that, Including: Target bacterial strain determination module: It is used to determine the target bacterial strain that highly expresses epidermal growth factor; wherein, the bacterial strain is a genetically engineered bacterial strain containing animal-derived epidermal growth factor; Culture condition and physiological index module: It is used to determine the culture conditions of the target bacterial strain; monitor the physiological indexes of the target bacterial strain; obtain the fluorescence image of the target bacterial strain at a specified time; Quantify and record the fluorescence intensity in the fluorescence image, and calculate the change amount of the fluorescence intensity; Evaluate the growth amount of the target bacterial strain according to the change amount of the fluorescence intensity; Construct a growth curve with the specified time and fluorescence intensity; Calculate the slope of the growth curve between two adjacent specified times in sequence; When the current slope is less than the preset value, mark the time corresponding to the current slope as the initial stage of the stationary phase; Before the growth stage of the target bacterial strain reaches the initial stage of the stationary phase: Monitor the changes in culture conditions caused by bacterial strain reproduction, quantitatively evaluate the influence degree of the changes in culture conditions on the growth amount of the target bacterial strain, and monitor the change characteristics, and the change characteristics include: pH value, dissolved oxygen content, overlapping degree between bacterial strains; Use the entropy weight method to assign weights to each change characteristic; Define a fuzzy set for each change characteristic, and define a membership function for each fuzzy set; Input the monitored pH value, dissolved oxygen content, and overlapping degree between bacterial strains into the membership function to obtain the fuzzy value of each change characteristic; Determine the fuzzy output of the growth amount of the target bacterial strain according to the predefined fuzzy rules and the input fuzzy values; Use the weighted average method, considering the output weights of each fuzzy set and their membership degrees, to convert the fuzzy output into a specific value; Perform a multiplication operation on each output membership degree value and the specific numerical value, accumulate all the product results, divide the obtained accumulated value by the accumulated sum of all membership degree values, and obtain the dynamic influence factor of the change in culture conditions on the growth amount of the target strain; Judge whether to optimize the culture conditions according to the degree of influence; After the growth stage of the target strain reaches the initial stage of the stationary phase: regularly optimize the culture conditions to an environment suitable for the expression of epidermal factors; Growth stage determination module: It is used to determine the current growth stage of the target strain according to the physiological index; Culture condition optimization module: It is used to optimize the culture conditions of the target strain according to the current growth stage of the target strain; Before the growth stage of the target strain reaches the initial stage of the stationary phase: monitor the change in culture conditions caused by the reproduction of the strain, quantitatively evaluate the degree of influence of the change in culture conditions on the growth amount of the target strain, judge whether to optimize the culture conditions according to the degree of influence; judge whether the dynamic influence factor is greater than a preset threshold, if so, use the genetic algorithm to optimize the culture conditions to an environment suitable for the growth of the strain; obtain environmental parameters, the environmental parameters include: temperature, pH value, overlap degree between strains, dissolved oxygen; generate an initial population, the initial population contains individuals with different environmental parameters; Based on the growth amount, design a fitness function for the pros and cons of each individual, and calculate the fitness value of each individual; use roulette wheel selection to select individuals with higher fitness to enter the next generation of reproduction; Perform a crossover operation on the selected parental individuals to generate a new individual combination; Perform a mutation operation on the new individuals and randomly adjust some parameters; The genetic algorithm gradually optimizes the growth amount through multiple iterations to maximize the value of the fitness function; stop the iteration when the change in population fitness tends to be stable, and output the final environmental parameters suitable for the growth of the strain.

Images