High-throughput reaction screening system and method based on computer control and data processing

Abstract

The invention relates to the field of data processing, in particular to a high-throughput reaction screening system and method based on computer control and data processing. The method comprises the following steps: executing a parallel chemical reaction experiment, obtaining experiment parameters and experiment reaction results, and carrying out standardization processing to obtain standardized parameter values and standardized experiment reaction results; calculating the relative weight of the experimental parameters by analyzing the correlation between the experimental parameters and the experimental reaction results; and based on the relative weights of the standardized parameter values and the experimental parameters, selecting an optimal parameter vector through a high-throughput reaction parameter screening algorithm for guiding a subsequent experiment. The problems that in a chemical reaction screening method, experimental parameter importance is difficult to quantify, fitness is evaluated only based on a reaction result, and a suboptimal solution may be mistakenly selected are solved; in the optimization process, the population diversity is possibly reduced due to insufficient variation, or the optimal solution cannot be converged due to excessive variation, so that the optimization effect of the chemical experiment condition is influenced.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and particularly to a high-throughput reaction screening system and method based on computer control and data processing. Background Art

[0002] High-throughput reaction screening technology is a key tool in the fields of modern chemistry, materials science, and drug research and development. With the rapid development of computer technology, big data processing, automation control, and artificial intelligence, high-throughput reaction screening systems have evolved from traditional manual experiments to highly automated, intelligent, and data-driven directions; traditional chemical reaction screening methods usually rely on experimental personnel to manually prepare reagents, record data, and analyze results, which have problems such as long time consumption, poor repeatability, and low efficiency, and are difficult to meet the needs of modern chemical research and industrial production.

[0003] The introduction of computer control and data processing technologies provides a new development direction for high-throughput screening. By precisely controlling experimental equipment through a computer, automated reaction operations are realized. At the same time, combined with efficient data acquisition, storage, and analysis technologies, high-throughput screening can not only perform large-scale chemical experiments in a short time but also optimize experimental parameters through intelligent algorithms, improving screening efficiency and accuracy. In the future, with the continuous development of technologies such as artificial intelligence, microfluidics, and cloud computing, high-throughput reaction screening systems will further improve screening efficiency and provide more powerful support for scientific research and industrial production. Summary of the Invention

[0004] The present invention provides a high-throughput reaction screening system and method based on computer control and data processing to solve the problems that it is difficult to quantify the importance of experimental parameters; it is difficult to efficiently screen out the best experimental conditions when processing multiple groups of experimental data; in the optimization of experimental parameters, only the fitness is evaluated based on the reaction results, ignoring the influence of parameter weights and deviations, which may lead to the misselection of suboptimal solutions or the underestimation of changes in key parameters; during the optimization process, the population diversity may decrease due to insufficient mutation or it may not converge to the optimal solution due to excessive mutation, affecting the optimization effect of chemical experimental conditions.

[0005] The high-throughput reaction screening system and method based on computer control and data processing of the present invention specifically include the following technical solutions:

[0006] A high-throughput reaction screening method based on computer control and data processing includes the following steps:

[0007] S1. Perform parallel chemical reaction experiments to obtain experimental parameters and experimental reaction results; perform standardization processing on the experimental parameters and experimental reaction results to obtain standardized parameter values and standardized experimental reaction results, and calculate the relative weights of the experimental parameters by analyzing the correlation between the experimental parameters and the experimental reaction results;

[0008] S2. Based on the relative weights of the standardized parameter values and the experimental parameters, through the high-throughput reaction parameter screening algorithm, select the optimal parameter vector and perform anti-normalization processing to obtain the actual parameter values for guiding subsequent experiments.

[0009] Preferably, the S1 specifically includes:

[0010] Based on the standardized experimental reaction results, calculate the deviation of the experimental reaction results; by calculating the product of the standardized parameter values and the deviation of the experimental reaction results and performing normalization processing, obtain the relative weights of the experimental parameters.

[0011] Preferably, the S2 specifically includes:

[0012] The high-throughput reaction parameter screening algorithm combines the genetic algorithm and weighted fitness evaluation, and gradually iteratively optimizes the experimental parameters by simulating the biological evolution process to obtain the optimal parameter vector.

[0013] Preferably, the S2 specifically includes:

[0014] In the implementation process of the high-throughput reaction parameter screening algorithm, use the standardized experimental parameter data set as the initial population; for each experimental parameter, calculate the absolute deviation value between the standardized parameter value and the average value of the standardized parameters; based on the absolute deviation value, introduce an exponential function, and combine the predicted reaction results of the individual and the relative weights of the experimental parameters to calculate the fitness of the individual.

[0015] The predicted reaction result of the individual is calculated according to the linear regression model, and the true standardized experimental reaction results are used to calculate the fitness of the individual during initialization.

[0016] Preferably, the S2 specifically includes:

[0017] Pair up the individuals in the current population and perform crossover operations to obtain the crossed individuals; calculate the fitness of the crossed individuals to obtain the fitness of the crossed individuals.

[0018] Preferably, the S2 specifically includes:

[0019] Introduce an adaptive mutation mechanism and perform mutation operations on the crossed individuals to obtain the mutated individuals.

[0020] Preferably, the S2 specifically includes:

[0021] In the implementation process of the adaptive mutation mechanism, based on the relative weights of the experimental parameters, the current iteration progress, and the dispersion degree of the population, calculate the mutation probability, and the specific formula is as follows:

[0022]

[0023] Among them, represents the mutation probability of the th experimental parameter; represents the relative weight of the th experimental parameter; represents the sine function; represents pi; represents the total number of iterations; represents the iteration progress ratio; represents the number of groups of parallel chemical reaction experiments; represents the th generation of the population, the th individual, and the th normalized parameter value; represents the initial mean value of the th normalized parameter; represents the normalized dispersion degree of the population; represents the th parameter in the group of parallel chemical reaction experiments and the standard deviation; represents the number of parameters in each group of experimental data; represents the global regulation mutation probability coefficient.

[0024] Preferably, the S2 specifically includes:

[0025] When the mutation probability is greater than the preset probability mutation threshold, it indicates that the experimental parameter has mutated. By adding a random perturbation to the current normalized parameter value, the mutated experimental parameter is calculated to obtain the mutated individual; the fitness of the mutated individual is re-evaluated to obtain the fitness of the mutated individual.

[0026] Preferably, the S2 specifically includes:

[0027] Compare the fitness of the original individual, the crossed individual, and the mutated individual, and select the individual with the highest fitness as the individual of the next generation; repeat the processes of crossing, mutation, selection, and update until the predetermined number of iterations is reached. In the last generation of the population, traverse all individuals, select the individual with the highest fitness as the elite individual, and use the parameter vector of the elite individual as the optimal parameter vector.

[0028] A high-throughput reaction screening system based on computer control and data processing includes the following parts:

[0029] A reaction device, a data acquisition module, a data processing module, an optimization screening module, and a control module;

[0030] Reaction device: As the physical hardware part, it is used to perform parallel chemical reaction experiments and generate experimental data; the experimental data includes experimental parameters and corresponding experimental reaction results; the experimental data is output to the data acquisition module and receives the control signal from the control module to execute chemical reactions;

[0031] Data acquisition module: Obtain the experimental data from the reaction device and output it to the data processing module;

[0032] Data processing module: Perform standardization processing on the experimental data from the data acquisition module to obtain standardized parameter values and standardized experimental reaction results, and calculate the relative weights of the experimental parameters; output the standardized parameter values, standardized experimental reaction results, and relative weights of the experimental parameters to the optimization and screening module;

[0033] Optimization and screening module: Based on the standardized parameter values, standardized experimental reaction results, and relative weights of the experimental parameters from the data processing module, through the high-throughput reaction parameter screening algorithm, select the optimal parameter vector and perform inverse standardization processing to convert it into actual parameter values; output the actual parameter values to the control module;

[0034] Control module: Receive the actual parameter values from the optimization and screening module, generate control signals to guide subsequent experiments; output the control signals to the reaction device.

[0035] The beneficial effects of the technical solution of the present invention are:

[0036] 1. Through standardization processing, the dimension difference is eliminated, the data processing efficiency and accuracy are improved, and the comparability and consistency of the data are enhanced.

[0037] 2. By calculating the relative weights of the experimental parameters, the influence degree of the experimental parameters on the experimental reaction results is quantified, the accurate identification of the key influencing factors of the chemical reaction is realized, the experimental cost is reduced, and the experimental efficiency is improved.

[0038] 3. Using the high-throughput reaction parameter screening algorithm to take the standardized experimental parameter dataset as the initial population, combined with the genetic algorithm, through crossover, mutation and selection operations, simulating the biological evolution process, gradually optimizing the parameter combination, automatically screening out the best experimental conditions that can maximize the experimental reaction results (such as yield), avoiding the waste of resources in a large number of invalid experiments in the traditional trial-and-error method, reducing manual intervention, and improving the scientificity and efficiency of experimental design.

[0039] 4. Through the global optimization ability of the genetic algorithm, combined with the relative weights of the experimental parameters, the optimization efficiency and the reliability of the results are improved.

[0040] 5. The adaptive mutation mechanism balances exploration and convergence, enhances the robustness and applicability of the high-throughput reaction parameter screening algorithm, and is applicable to different chemical reaction scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural diagram of a high-throughput reaction screening system based on computer control and data processing according to the present invention;

[0042] Figure 2 It is a flowchart of a high-throughput reaction screening method based on computer control and data processing according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0045] The following specifically describes the specific solutions of the high-throughput reaction screening system and method based on computer control and data processing provided by the present invention with reference to the accompanying drawings.

[0046] Referring to the attached Figure 1 , which shows a structural diagram of a high-throughput reaction screening system based on computer control and data processing provided by an embodiment of the present invention. The system includes the following parts:

[0047] A reaction device, a data acquisition module, a data processing module, an optimization and screening module, and a control module;

[0048] Reaction device: As the physical hardware part, it is used to perform parallel chemical reaction experiments. Through multiple parallel reaction units (such as microreactors or multi-channel reactors), multiple groups of parallel chemical reaction experiments are simultaneously carried out under different parameter conditions (such as temperature, pressure, concentration, etc.) to generate experimental data; the experimental data includes experimental parameters and corresponding experimental reaction results; the experimental data is output to the data acquisition module and receives control signals from the control module to perform chemical reactions;

[0049] Data acquisition module: Obtain experimental data from the reaction device and output it to the data processing module;

[0050] Data processing module: Standardize the experimental data from the data acquisition module to obtain standardized parameter values, standardized experimental reaction results, and calculate the relative weights of the experimental parameters; output the standardized parameter values, standardized experimental reaction results, and the relative weights of the experimental parameters to the optimization and screening module;

[0051] Optimization and screening module: Based on the standardized parameter values, standardized experimental reaction results, and the relative weights of the experimental parameters from the data processing module, use the high-throughput reaction parameter screening algorithm to select the optimal parameter vector from multiple groups of chemical reaction experimental data and perform inverse standardization processing to convert it into actual parameter values; output the actual parameter values to the control module;

[0052] Control module: Receive the actual parameter values from the optimization and screening module, generate control signals to guide subsequent experiments; output the control signals to the reaction device.

[0053] Refer to the appendix Figure 2 , which shows the flowchart of the high-throughput reaction screening method based on computer control and data processing provided by an embodiment of the present invention. The method includes the following steps:

[0054] S1. Perform parallel chemical reaction experiments to obtain experimental parameters and experimental reaction results; standardize the experimental parameters and experimental reaction results to obtain standardized parameter values and standardized experimental reaction results, and calculate the relative weights of the experimental parameters by analyzing the correlation between the experimental parameters and the experimental reaction results;

[0055] Execute through the reaction device groups of parallel chemical reaction experiments to generate experimental data; obtain the parameters (such as temperature, pressure, concentration, etc.) of each group of experimental data and the corresponding experimental reaction results. The experimental parameters are denoted as the vector , represents the th parameter value of the

[0056] To eliminate the difference in parameter dimensions, standardize each group of experimental parameters and experimental reaction results to obtain standardized parameter values and standardized experimental reaction results; taking the experimental parameters as an example, the standardization processing formula is as follows:

[0057]

[0058] Among them, represents the th standardized parameter value of the th group of experiments; represents the Indicates the average value of the th parameter in the group of experiments, and the calculation formula is: Indicates the average value of the th parameter in the group of experiments, and the calculation formula is:

[0059] To quickly identify key parameters, reduce invalid experiments, and improve efficiency, by analyzing the correlation between experimental parameters and experimental reaction results, the influence degree of each experimental parameter on the experimental reaction results is quantified, thereby generating a set of weight values;

[0060] For each experimental parameter, each group of experimental data will be traversed. Based on the standardized experimental reaction results, the experimental reaction result deviation will be calculated; the product of the standardized parameter value and the experimental reaction result deviation will be calculated to reflect the correlation between the change of the experimental parameter and the change of the experimental reaction result. If the experimental reaction result also significantly deviates from the average value when the experimental parameter increases, it indicates that the experimental parameter has a greater impact on the experimental reaction result; to ensure the stability of the calculation, the absolute value of the above product will be taken to avoid the situation of positive and negative cancellation; the sum of the absolute values of the products of all experimental groups will be obtained to get the total contribution of the experimental parameter, reflecting the overall influence degree of the experimental parameter on the experimental reaction results;

[0061] To convert the influence degree of each experimental parameter into a relative weight, normalization processing is required. Calculate the sum of the absolute values of the products of all standardized parameter values and experimental reaction result deviations, that is, add up the total contributions of each experimental parameter to get a global total value. Divide the total contribution of each experimental parameter by the global total value to get a proportional value between 0 and 1 as the relative weight of the experimental parameter, indicating the relative importance of the experimental parameter to the experimental reaction results. The greater the relative weight, the more significant the influence of the experimental parameter on the experimental reaction results, and vice versa, the influence is smaller; the calculation formula for the relative weight is:

[0062]

[0063] Among them, Indicates the relative weight of the th experimental parameter, used to quantify the influence degree of each experimental parameter on the experimental reaction results; Indicates the average value of the standardized experimental reaction results of all groups, and the calculation formula is: Indicates the experimental reaction result deviation; Indicates the product of the standardized parameter value and the experimental reaction result deviation, used to reflect the th group of experiments and the The contribution of each experimental parameter to the deviation of the experimental reaction result from the mean; Indicates the group of standardized experimental reaction results; Indicates double summation, calculating the sum of the absolute values of the products of the standardized parameter values and the experimental reaction result deviations for all experimental parameters in all experiments, for normalization processing;

[0064] S2. Based on the standardized parameter values and the relative weights of the experimental parameters, through the high-throughput reaction parameter screening algorithm, select the optimal parameter vector and perform inverse normalization processing to obtain the actual parameter values for guiding subsequent experiments;

[0065] Based on the relative weights of the standardized parameters and the experimental parameters, screen out the best experimental conditions from multiple groups of parallel chemical reaction experimental data through the high-throughput reaction parameter screening algorithm;

[0066] The high-throughput reaction parameter screening algorithm combines the genetic algorithm and weighted fitness evaluation, and through simulating the biological evolution process, gradually iteratively optimizes the experimental parameters, and finally outputs the optimal parameter vector that can maximize the experimental reaction result;

[0067] Use the standardized experimental parameter dataset as the initial population , each individual in the initial population is a parameter vector representing a set of experimental conditions, and the individual will be gradually optimized through subsequent evolution processes. To facilitate tracking the changes in each round of iteration, the population of each generation will be marked with different versions. Starting from the first generation, each generation is denoted as: , Indicates the current iteration number, Indicates the total number of iterations, which can be specifically set according to the specific implementation scenario and is not limited here;

[0068] Evaluate the quality of each individual by calculating the fitness of each individual. The calculation of the fitness not only considers the experimental reaction result but also introduces additional weighted factors to comprehensively evaluate the potential of each individual. The higher the fitness, the more likely the experimental parameter dataset is to be close to the optimal solution; specifically, at initialization, it is calculated based on the true standardized experimental reaction result, and in the iterative optimization process, it is calculated according to the predicted reaction result of each individual. The predicted reaction result of the individual is calculated through the existing linear regression model; then, analyze the deviation of each experimental parameter from the average value of the initial population. For each experimental parameter, calculate the absolute deviation between the standardized parameter value and the average value of the standardized parameters, and use the negative absolute deviation value as the input of the exponential function to ensure that the function value is smaller when the deviation is larger, to reflect the penalty for the individual deviating from the initial state, and adjust according to the importance of the experimental parameter (i.e., the relative weight of the experimental parameter). The experimental parameter with a larger relative weight contributes more to the fitness;

[0069] The calculation formula for fitness is as follows:

[0070]

[0071] where, represents the fitness of the th individual in the th generation; represents the adjustment coefficient, which is used to balance the relative weights of the experimental reaction results and experimental parameters, and can be specifically set according to the specific implementation scenario, and is not limited herein; represents the sum of experimental parameters; represents the exponential function with the natural constant as the base; represents the th standardized parameter value of the th individual in the th generation population; represents the initial mean value of the th standardized parameter, ; represents the absolute deviation between the th standardized parameter value of the th individual in the th generation population and the initial mean value; represents the predicted reaction result of the th individual in the th generation, which is predicted by an existing linear regression model, and the calculation formula is:

[0072]

[0073] where, , represents the set of predicted reaction results, and the regression coefficient vector is calculated through the regression coefficient formula, which is a well-known technical means for those skilled in the art and will not be elaborated herein;

[0074] To generate a new generation of population, the individuals in the current population are paired in pairs and crossover operations are performed; the pairing rule ensures that each individual is used only once in one iteration. If the number of population individuals is even, they are exactly divided into several pairs. If it is odd, one individual is randomly selected and directly retained in the next generation, and the remaining individuals are paired; for each pair of individuals, a crossover point is randomly selected, and the parts of the parameter vectors of the two individuals before and after the point are swapped to form two new individuals, that is, the individuals after crossover. The crossover operation simulates gene recombination in biology and increases the diversity of the population;

[0075] The crossover operation is shown as follows:

[0076]

[0077]

[0078] Among them, and respectively represent the th individual and the th individual in the th generation population after crossover, and the th normalized parameter value; represents the random crossover point, ([[]] ); and respectively represent the th individual and the th individual randomly selected from the th generation population, and the th normalized parameter value;

[0079] The individuals after crossover are not directly added to the population, but need to repeat the steps of the previous fitness calculation to calculate the fitness and of the individuals after crossover to ensure that the individuals after crossover can also be fairly compared;

[0080] To further increase the population diversity, an adaptive mutation mechanism is introduced to perform mutation operations on the individuals after crossover; the mutation probability is dynamically adjusted according to the relative weights of the experimental parameters, the current iteration progress, and the dispersion degree of the population; specifically, for each experimental parameter, calculate the product of the relative weight of the experimental parameter and a sine function; use the ratio of the current iteration number, the total iteration number, and the deviation degree of the normalized parameter value in the population to the standard deviation as the input of the sine function, then divide by the sum of the relative weights of all experimental parameters, and multiply by a global adjustment mutation probability coefficient to obtain the mutation probability; if the mutation probability is greater than the preset probability mutation threshold, the experimental parameter undergoes mutation, and a mutated experimental parameter is obtained by adding a random perturbation (obtained by multiplying a random number ranging from -1 to 1 by the mutation probability) to the current normalized parameter value, otherwise it remains unchanged; the adaptive mutation mechanism ensures a wide exploration space in the early stage and gradually converges in the later stage;

[0081] The calculation formula for the mutation probability is:

[0082]

[0083] Among them, represents the mutation probability of the th experimental parameter; represents the sine function used to periodically adjust the mutation probability; represents pi; represents the iteration progress ratio, making the mutation probability vary with the number of iterations; represents the standardized degree of dispersion, used to reflect the population diversity and affect the mutation probability; represents the th parameter's standard deviation in the group of parallel chemical reaction experiments;

[0084] The calculation formula for the mutated experimental parameters is:

[0085]

[0086]

[0087] where, represents the th generation's th individual's th parameter value; represents the th generation's th individual's th parameter value; represents a random number within the range; represents the mutation probability threshold, which can be specifically set according to the specific implementation scenario and is not limited here;

[0088] The mutated individual also needs to re-evaluate the fitness and , and the calculation process is the same as before;

[0089] For each pair of paired individuals, compare the fitness values of the original individual, the crossed individual, and the mutated individual, and select the individual with the highest fitness as the individual of the next generation, ensuring that the individuals in each generation of the population are the current best, thus promoting the continuous progress of the overall optimization process. The formula is expressed as follows:

[0090]

[0091]

[0092] where, and represent the updated individuals of the next generation; represents the maximum value operation to select the individual with the highest fitness;

[0093] Repeat the above processes of crossover, mutation, selection, and update until a predetermined number of iterations is reached. In the last generation of the population, traverse all individuals and select the individual with the highest fitness as the final solution. The optimal individual is called the elite individual, and the parameter vector of the elite individual represents the best experimental conditions selected through multiple rounds of evolution screening. Further, perform an inverse normalization process to convert it into actual parameter values for guiding subsequent experiments or applications.

[0094] In summary, the high-throughput reaction screening system and method based on computer control and data processing are completed.

[0095] The sequence of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0096] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0097] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention and should all be included in the protection scope of the present invention.

Claims

1. A high-throughput reaction screening method based on computer control and data processing, characterized in that: The following steps are involved: S1. Perform a parallel chemical reaction experiment to obtain experimental parameters and experimental reaction results; standardize the experimental parameters and experimental reaction results to obtain standardized parameter values ​​and standardized experimental reaction results, and calculate the relative weights of the experimental parameters by analyzing the correlation between the experimental parameters and the experimental reaction results; S2. Based on the relative weights of the standardized parameter values ​​and the experimental parameters, the optimal parameter vector is selected through a high-throughput reaction parameter screening algorithm, and de-normalization is performed to obtain the actual parameter value to guide subsequent experiments.

2. The high-throughput reaction screening method based on computer control and data processing according to claim 1, characterized in that: The S1 specifically includes: Based on the standardized experimental reaction results, the experimental reaction result deviation is calculated; the relative weight of the experimental parameter is obtained by calculating the product of the standardized parameter value and the experimental reaction result deviation and performing normalization processing.

3. The high-throughput reaction screening method based on computer control and data processing according to claim 1, characterized in that: The S2 specifically includes: The high-throughput reaction parameter screening algorithm combines a genetic algorithm with a weighted fitness evaluation, and by simulating the biological evolution process, gradually iterates and optimizes the experimental parameters to obtain an optimal parameter vector.

4. The high-throughput reaction screening method based on computer control and data processing according to claim 3, characterized in that: The S2 specifically includes: In the implementation process of the high-throughput reaction parameter screening algorithm, the standardized experimental parameter data set is used as the initial population; for each experimental parameter, the absolute deviation value between the standardized parameter value and the standardized parameter average value is calculated; based on the absolute deviation value, an exponential function is introduced to combine the individual's predicted reaction results and the relative weight of the experimental parameters to calculate the individual's fitness; The predicted reaction result of the individual is calculated based on the linear regression model, and the fitness of the individual is calculated using the real standardized experimental reaction result during initialization.

5. The high-throughput reaction screening method based on computer control and data processing according to claim 4, characterized in that: The S2 specifically includes: Pair the individuals of the current population in pairs and perform a crossover operation to obtain the individuals after the crossover; calculate the fitness of the individuals after the crossover to obtain the fitness of the individuals after the crossover.

6. The high-throughput reaction screening method based on computer control and data processing according to claim 5, characterized in that: The S2 specifically includes: An adaptive mutation mechanism is introduced to perform mutation operations on individuals after crossover to obtain mutated individuals.

7. The high-throughput reaction screening method based on computer control and data processing according to claim 6, characterized in that: The S2 specifically includes: In the process of implementing the adaptive mutation mechanism, the mutation probability is calculated based on the relative weights of the experimental parameters, the current iteration progress and the discrete degree of the population. The specific formula is as follows: in, Indicates The probability of variation of experimental parameters; Indicates The relative weight of the experimental parameters; represents the sine function; represents pi; Indicates the total number of iterations; Indicates the iteration progress ratio; Indicates the number of groups in parallel chemical reaction experiments; Indicates Generation population The individual standardized parameter values; Indicates The initial mean of the standardized parameters; Indicates the standardized dispersion of the population; Indicates The parameters are The standard deviation of a group of parallel chemical reaction experiments; Indicates the number of parameters in each set of experimental data; Represents the global adjustment variation probability coefficient.

8. The high-throughput reaction screening method based on computer control and data processing according to claim 7, characterized in that: The S2 specifically includes: When the mutation probability is greater than the preset probability mutation threshold, it means that the experimental parameters have mutated. By adding random perturbations to the current standardized parameter values, the mutated experimental parameters are calculated to obtain the mutated individuals. The fitness of the mutated individuals is re-evaluated to obtain the fitness of the mutated individuals.

9. The high-throughput reaction screening method based on computer control and data processing according to claim 8, characterized in that: The S2 specifically includes: Compare the fitness of the original individual, the individual after crossover and the individual after mutation, and select the individual with the highest fitness as the next generation of individuals; repeat the crossover, mutation, selection and update process until the predetermined number of iterations is reached. In the last generation of the population, traverse all individuals, select the individual with the highest fitness as the elite individual, and use the parameter vector of the elite individual as the optimal parameter vector.

10. A high-throughput reaction screening system based on computer control and data processing, applied to the high-throughput reaction screening method based on computer control and data processing as claimed in claim 1, characterized in that: Includes the following sections: Reaction device, data acquisition module, data processing module, optimization and screening module, control module; Reaction device: As a physical hardware part, it is used to perform parallel chemical reaction experiments and generate experimental data; the experimental data includes experimental parameters and corresponding experimental reaction results; the experimental data is output to the data acquisition module, and the control signal of the control module is received to perform chemical reactions; Data acquisition module: obtains experimental data from the reaction device and outputs it to the data processing module; Data processing module: standardizes the experimental data from the data acquisition module to obtain standardized parameter values ​​and standardized experimental reaction results, and calculates the relative weights of the experimental parameters; outputs the standardized parameter values, standardized experimental reaction results and relative weights of the experimental parameters to the optimization screening module; Optimization and screening module: Based on the standardized parameter values ​​of the data processing module, the standardized experimental reaction results and the relative weights of the experimental parameters, the optimal parameter vector is selected through a high-throughput reaction parameter screening algorithm, and de-standardized and converted into actual parameter values; the actual parameter values ​​are output to the control module; Control module: receives the actual parameter values ​​from the optimization and screening module, generates control signals for guiding subsequent experiments, and outputs the control signals to the reaction device.

Images