Transfection efficiency detection method for high-precision test of transfection reagent

Abstract

The invention discloses a transfection efficiency detection method for high-precision testing of a transfection reagent, and relates to the field of transfection efficiency detection.The transfection efficiency detection method comprises the steps that corresponding transfection condition labels are set for the type of a cell to be transfected, the type of a coloring agent, the quality of an exogenous gene and environmental conditions; a transfection efficiency detection control test is carried out, and an experiment data set is established; calculating the influence of each transfection condition label on the transfection efficiency; transfection condition labels in the transfection efficiency detection process are automatically identified and selected, and optimal transfection efficiency detection conditions are screened out; and updating and optimizing the reinforcement learning algorithm model according to a transfection efficiency detection result and the novel transfection condition label. The method has the advantages that different types of transfection condition labels are automatically identified through the reinforcement learning algorithm model, so that the optimal transfection efficiency detection condition is automatically screened out, and high-precision transfection efficiency detection can be intelligently and conveniently realized.

Description

Technical Field

[0001] The present invention relates to the field of transfection efficiency detection, and in particular to a transfection efficiency detection method for high-precision testing of transfection reagents. Background Art

[0002] The transfection efficiency test of transfection reagent with high precision is a complex and delicate process. Transfection efficiency is a key step in evaluating transfection reagents and an important indicator to ensure that transfection reagents can fully transfect the cells to be tested, making the performance of transfection reagents stable and reliable, providing technical support for gene function research, protein expression and drug development. Cell transfection efficiency is affected by the type of cells to be transfected, the type of dye, the quality of exogenous genes and environmental conditions. Through a systematic transfection detection method, the optimal transfection efficiency detection conditions can be accurately and automatically assigned to the cells to be tested, which is of great significance to improving the high-precision testing of transfection reagents and realizing high-precision transfection efficiency detection in an intelligent and convenient way.

[0003] Existing transfection efficiency detection technology focuses on the development of new detection methods and the use of detection equipment to monitor data when transfecting cells. This method requires certain transfection detection experience and subjectively selects various transfection condition labels in the detection process based on the test cell type and the required test results. It lacks systematic and accurate screening of transfection efficiency detection methods. In particular, in the transfection process, sterile conditions are required, and the use of intelligent and automated system processing is more stable, accurate and precise than manual operation. Summary of the invention

[0004] In order to solve the above technical problems, a transfection efficiency detection method for high-precision testing of transfection reagents is provided. The technical solution solves the problem that the method proposed in the above background technology requires certain transfection detection experience, and subjectively selects various transfection condition labels in the detection process according to the detected cell type and the required test results, lacks systematic and accurate screening of transfection efficiency detection methods. In particular, in the transfection process, sterile conditions are required, and the use of intelligent and automated system processing is more stable, accurate and high-precision than manual operation.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A transfection efficiency detection method for high-precision testing of transfection reagents, comprising:

[0007] Set the corresponding transfection condition labels for the cell type, stain type, exogenous gene quality and environmental conditions to be transfected;

[0008] Based on historical data and the control variable method, a transfection efficiency control test was conducted and an experimental data set was established;

[0009] Based on the Pearson correlation coefficient formula, the effect of each transfection condition label on the transfection efficiency was calculated;

[0010] Based on the reinforcement learning algorithm model, the transfection condition labels for the transfection efficiency detection process are automatically identified and selected to screen out the optimal transfection efficiency detection conditions;

[0011] Set up an update and feedback platform to update and optimize the reinforcement learning algorithm model based on transfection efficiency test results and new transfection condition labels.

[0012] Preferably, the transfection condition labels corresponding to the cell type to be transfected, the dye type, the quality of the exogenous gene and the environmental conditions specifically include:

[0013] Analyze and classify the transfected cells, group the cells with the same properties, the same detection transfection reagents and the same exogenous gene quality into one category, and label them with the same identifiable label;

[0014] Different identifiable labels are set according to the type of dye and its advantages and disadvantages, wherein the types of dyes include: ion-based transfection reagents, carrier-based transfection reagents, special substance-assisted transfection reagents and other types of transfection reagents;

[0015] Different identifiable tags are set according to different fragments, concentrations, masses and OD260 / 280 values ​​of exogenous genes, wherein the exogenous genes include: exogenous DNA, exogenous RNA and exogenous proteins;

[0016] According to the different environmental conditions required by the cells to be transfected, the environmental factors are combined and classified, and different identifiable labels are set, where the environmental factors include: temperature, humidity, pH, and oxygen concentration.

[0017] Preferably, the method of conducting a transfection efficiency detection control test based on historical data and a control variable method and establishing an experimental data set specifically includes:

[0018] Set up a plan for transfection efficiency test control experiment based on historical data and professional test results;

[0019] Based on the control variable method, a transfection efficiency control experiment was carried out to detect the transfection efficiency under different transfection condition labels;

[0020] Record and analyze the test results of the control experiment and establish a transfection efficiency experimental data set.

[0021] Preferably, the calculation of the effect of each transfection condition label on the transfection efficiency based on the Pearson correlation coefficient formula specifically includes:

[0022] According to the transfection efficiency experimental data set, the correlation coefficient of each transfection condition label to the transfection efficiency was calculated based on the Pearson correlation coefficient formula;

[0023] The t statistic is used to test whether the correlation between each transfection condition label and the transfection efficiency is significant, and whether the t value is greater than If yes, it indicates that the correlation is significant, if no, it indicates that the correlation is not significant;

[0024] Record the correlation coefficient and significant relationship between each transfection condition label and transfection efficiency, and establish a transfection efficiency detection comparison table;

[0025] The Pearson correlation coefficient expression is:

[0026]

[0027] Among them, r is the correlation coefficient of each transfection condition label to transfection efficiency, x i is the i-th transfection condition label, is the average value of the label of the i-th transfection condition, y i is the transfection efficiency corresponding to the i-th transfection condition label, is the average transfection efficiency corresponding to the i-th transfection condition label;

[0028] The t statistic expression is:

[0029]

[0030] Among them, t is the t statistic corresponding to each transfection condition label, r is the correlation coefficient of each transfection condition label to transfection efficiency, and n is the number of data sets in the transfection efficiency experimental data set for each transfection condition label.

[0031] Preferably, the reinforcement learning algorithm model is used to automatically identify and select transfection condition labels for the transfection efficiency detection process, and the optimal transfection efficiency detection conditions are selected, specifically including:

[0032] According to the correlation coefficient value in the transfection efficiency detection comparison table, the probability of selecting the corresponding transfection condition label during the transfection efficiency detection process is set, and a state transition probability matrix is ​​formed;

[0033] According to the expected transfection efficiency test, set the corresponding reward value for completing one selection of the transfection efficiency test, and calculate the cumulative reward value for completing one round of screening process;

[0034] According to the Markov algorithm, calculate the probability of selecting the corresponding transfection condition label and reward value in the next state;

[0035] According to the Bellman formula, calculate the expected value of the optimal cumulative reward value after completing a round of screening process;

[0036] Based on the reinforcement learning algorithm model, the reward value in the process of screening transfection efficiency detection conditions is adjusted by training the model and learning the results;

[0037] The probability formula for selecting the corresponding transfection condition label during the transfection efficiency detection process is:

[0038] π(a|s)=P(A=a|S=s)

[0039] Among them, π(a|s) is the probability of selecting the ath transfection condition label in the sth state for the transfection efficiency detection, A is the probability set corresponding to the transfection condition label, and S is the set of the current state of the transfection efficiency detection;

[0040] The state transition probability matrix is:

[0041]

[0042] Among them, P(s1|s n ) represents the state s1 to s n The probability that s1 to s n The probability sum is 1;

[0043] The calculation of the cumulative reward value after completing a round of screening process is expressed as:

[0044]

[0045] Among them, G k is the cumulative reward feedback value corresponding to the kth state after completing a transfection efficiency detection decision, γ is the future discount factor for the current state, and r i+k+1 The cumulative reward feedback value corresponding to the k+1th state for completing a transfection efficiency detection decision;

[0046] The probability expression for calculating the next state selection corresponding to the transfection condition label and reward value is:

[0047]

[0048] Among them, P[s k+1 |a k+1 ,s k ] is the probability of the k+1th state in the kth state of transfection efficiency detection, P[r k+1 |a k+1 ,s k] is the probability of the k+1th state reward value of transfection efficiency detection, s k+1 The k+1th state is used to detect the transfection efficiency, s k Detect the current k-th state for transfection efficiency;

[0049] The expected value expression of the optimal cumulative reward value after completing a round of screening process is:

[0050]

[0051] Among them, v k+1 is the expected value of the k+1th updated state, G π is the cumulative reward feedback value set corresponding to the kth state after completing a transfection efficiency detection decision, P π The i-th row and j-th column element in the state transition probability matrix is ​​from s i to j The probability and set of , v k is the expected value of the kth state.

[0052] Preferably, the setting of the update and feedback platform to update and optimize the reinforcement learning algorithm model according to the transfection efficiency test results and the new transfection condition label specifically includes:

[0053] Set up an update and feedback platform to record and display transfection efficiency test results and control test results;

[0054] Record and analyze new transfection condition labels, update control experiments and reinforcement learning algorithm models;

[0055] Create a visual chart to display the comparison results between the screening results of the reinforcement learning algorithm model and the ideal values, and optimize the relevant parameters of the reinforcement learning algorithm model.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] By setting labels for different transfection conditions in the transfection efficiency detection process, using control experiments and Pearson correlation coefficients to establish a transfection efficiency detection comparison table, and based on the reinforcement learning algorithm model, corresponding to the sample data of the transfection efficiency detection comparison table, various transfection condition labels in the transfection efficiency detection process are learned and trained, thereby achieving automatic and optimal selection of transfection condition labels and completing a high-precision transfection efficiency detection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of a transfection efficiency detection method for high-precision testing of transfection reagents of the present invention;

[0059] Figure 2This is a flow chart of calculating the effect of each transfection condition label on transfection efficiency based on the Pearson correlation coefficient formula of the present invention;

[0060] Figure 3 The reinforcement learning algorithm model of the present invention is used to automatically identify and select transfection condition labels for the transfection efficiency detection process, and screen out the optimal transfection efficiency detection condition flow chart;

[0061] Figure 4 It is a schematic diagram of the structure of the electronic device of the present invention;

[0062] Figure 5 It is a schematic diagram of the computer-readable storage medium structure of the present invention. DETAILED DESCRIPTION

[0063] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0064] Reference Figure 1 As shown, a transfection efficiency detection method for high-precision testing of transfection reagents comprises:

[0065] Set the corresponding transfection condition labels for the cell type, stain type, exogenous gene quality and environmental conditions to be transfected;

[0066] Based on historical data and the control variable method, a transfection efficiency control test was conducted and an experimental data set was established;

[0067] Based on the Pearson correlation coefficient formula, the effect of each transfection condition label on the transfection efficiency was calculated;

[0068] Based on the reinforcement learning algorithm model, the transfection condition labels for the transfection efficiency detection process are automatically identified and selected to screen out the optimal transfection efficiency detection conditions;

[0069] Set up an update and feedback platform to update and optimize the reinforcement learning algorithm model based on transfection efficiency test results and new transfection condition labels.

[0070] What can be explained is that, for different cells to be transfected, through preliminary control experiments and the calculation results of the Pearson phase relationship, the influence and correlation of different transfection condition labels on the transfected cells are determined, and the decision probability of selecting different transfection condition labels under different states in the reinforcement learning process is determined according to the calculated correlation. The optimal reward value is set according to the probability value, and the most suitable transfection condition label is screened out based on the feedback results of the reward value, so that through learning and training, the optimal detection method for automatic screening of transfection efficiency detection is realized.

[0071] Reference Figure 2 As shown, the calculation of the effect of each transfection condition label on the transfection efficiency based on the Pearson correlation coefficient formula specifically includes:

[0072] According to the transfection efficiency experimental data set, the correlation coefficient of each transfection condition label to the transfection efficiency was calculated based on the Pearson correlation coefficient formula;

[0073] The t statistic is used to test whether the correlation between each transfection condition label and the transfection efficiency is significant, and whether the t value is greater than If yes, it indicates that the correlation is significant, if no, it indicates that the correlation is not significant;

[0074] Record the correlation coefficient and significant relationship between each transfection condition label and transfection efficiency, and establish a transfection efficiency detection comparison table;

[0075] The Pearson correlation coefficient expression is:

[0076]

[0077] Among them, r is the correlation coefficient of each transfection condition label to transfection efficiency, x i is the i-th transfection condition label, is the average value of the label of the i-th transfection condition, y i is the transfection efficiency corresponding to the i-th transfection condition label, is the average transfection efficiency corresponding to the i-th transfection condition label;

[0078] The t statistic expression is:

[0079]

[0080] Among them, t is the t statistic corresponding to each transfection condition label, r is the correlation coefficient of each transfection condition label to transfection efficiency, and n is the number of data sets in the transfection efficiency experimental data set for each transfection condition label.

[0081] It can be explained that different transfection condition label combinations have different transfection efficiency test results. This scheme determines the impact of each transfection condition label on the transfection efficiency by calculating the correlation of different transfection condition labels. At the same time, through the test of t statistics, the significance of the impact of each transfection condition label on the transfection efficiency is judged, so as to provide data support for the subsequent reinforcement learning process and improve the accuracy and stability of model establishment.

[0082] Reference Figure 3As shown, the reinforcement learning algorithm model is used to automatically identify and select transfection condition labels for the transfection efficiency detection process, and the optimal transfection efficiency detection conditions are selected, specifically including:

[0083] According to the correlation coefficient value in the transfection efficiency detection comparison table, the probability of selecting the corresponding transfection condition label during the transfection efficiency detection process is set, and a state transition probability matrix is ​​formed;

[0084] According to the expected transfection efficiency test, set the corresponding reward value for completing one selection of the transfection efficiency test, and calculate the cumulative reward value for completing one round of screening process;

[0085] According to the Markov algorithm, calculate the probability of selecting the corresponding transfection condition label and reward value in the next state;

[0086] According to the Bellman formula, calculate the expected value of the optimal cumulative reward value after completing a round of screening process;

[0087] Based on the reinforcement learning algorithm model, the reward value in the process of screening transfection efficiency detection conditions is adjusted by training the model and learning the results;

[0088] The probability formula for selecting the corresponding transfection condition label during the transfection efficiency detection process is:

[0089] π(a|s)=P(A=a|S=s)

[0090] Among them, π(a|s) is the probability of selecting the ath transfection condition label in the sth state for the transfection efficiency detection, A is the probability set corresponding to the transfection condition label, and S is the set of the current state of the transfection efficiency detection;

[0091] The state transition probability matrix is:

[0092]

[0093] Among them, P(s1|s n ) represents the state s1 to s n The probability that s1 to s n The probability sum is 1;

[0094] The calculation of the cumulative reward value after completing a round of screening process is expressed as:

[0095]

[0096] Among them, G k is the cumulative reward feedback value corresponding to the kth state after completing a transfection efficiency detection decision, γ is the future discount factor for the current state, and r i+k+1The cumulative reward feedback value corresponding to the k+1th state for completing a transfection efficiency detection decision;

[0097] The probability expression for calculating the next state selection corresponding to the transfection condition label and reward value is:

[0098]

[0099] Among them, P[s k+1 |a k+1 ,s k ] is the probability of the k+1th state in the kth state of transfection efficiency detection, P[r k+1 |a k+1 ,s k ] is the probability of the k+1th state reward value of transfection efficiency detection, s k+1 The k+1th state is used to detect the transfection efficiency, s k Detect the current k-th state for transfection efficiency;

[0100] The expected value expression of the optimal cumulative reward value after completing a round of screening process is:

[0101]

[0102] Among them, v k+1 is the expected value of the k+1th updated state, G π is the cumulative reward feedback value set corresponding to the kth state after completing a transfection efficiency detection decision, P π The i-th row and j-th column element in the state transition probability matrix is ​​from s i to j The probability and set of , v k is the expected value of the kth state.

[0103] It can be explained that reinforcement learning is to screen out the combination of transfection efficiency detection with the highest expected reward value by comparing the reward expectation feedback results when completing a transfection efficiency test when facing different identifiable labels in different states, thereby intelligently realizing the automatic identification and selection of transfection condition labels in the transfection efficiency test process, and achieving the purpose of screening out the optimal transfection efficiency test conditions.

[0104] Furthermore, the method according to the embodiment of the present application can also be performed by Figure 4 The electronic device architecture shown in FIG. Figure 4As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a transfection efficiency detection method for high-precision testing of transfection reagents provided in the present application. The electronic device 500 may also include a user interface 508. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of an electronic device are shown.

[0105] Figure 5 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 5 As shown, it is a computer-readable storage medium 600 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a transfection efficiency detection method for high-precision testing of transfection reagents according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0106] In summary, the advantages of the present invention are: by setting labels for different transfection conditions in the transfection efficiency detection process, using control experiments and Pearson correlation coefficients to establish a transfection efficiency detection comparison table, and according to the reinforcement learning algorithm model, corresponding to the sample data of the transfection efficiency detection comparison table, various transfection condition labels in the transfection efficiency detection process are learned and trained, thereby realizing automatic and optimal selection of transfection condition labels and completing a high-precision transfection efficiency detection process.

[0107] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A transfection efficiency detection method for high-precision testing of transfection reagents, characterized in that: include: Set the corresponding transfection condition labels for the cell type, stain type, exogenous gene quality and environmental conditions to be transfected; Based on historical data and the control variable method, a transfection efficiency control test was conducted and an experimental data set was established; Based on the Pearson correlation coefficient formula, the effect of each transfection condition label on the transfection efficiency was calculated; Based on the reinforcement learning algorithm model, the transfection condition labels for the transfection efficiency detection process are automatically identified and selected to screen out the optimal transfection efficiency detection conditions; Set up an update and feedback platform to update and optimize the reinforcement learning algorithm model based on transfection efficiency test results and new transfection condition labels.

2. A transfection efficiency detection method for high-precision testing of transfection reagents according to claim 1, characterized in that: The transfection condition labels corresponding to the cell type to be transfected, the type of dye, the quality of the exogenous gene and the environmental conditions specifically include: Analyze and classify the transfected cells, group the cells with the same properties, the same detection transfection reagents and the same exogenous gene quality into one category, and label them with the same identifiable label; Different identifiable labels are set according to the type of dye and its advantages and disadvantages, wherein the types of dyes include: ion-based transfection reagents, carrier-based transfection reagents, special substance-assisted transfection reagents and other types of transfection reagents; Different identifiable tags are set according to different fragments, concentrations, masses and OD260 / 280 values ​​of exogenous genes, wherein the exogenous genes include: exogenous DNA, exogenous RNA and exogenous proteins; According to the different environmental conditions required by the cells to be transfected, the environmental factors are combined and classified, and different identifiable labels are set, where the environmental factors include: temperature, humidity, pH, and oxygen concentration.

3. A transfection efficiency detection method for high-precision testing of transfection reagents according to claim 2, characterized in that: The method of conducting a transfection efficiency detection control test based on historical data and the control variable method and establishing an experimental data set specifically includes: Set up a plan for transfection efficiency test control experiment based on historical data and professional test results; Based on the control variable method, a transfection efficiency control experiment was carried out to detect the transfection efficiency under different transfection condition labels; Record and analyze the test results of the control experiment and establish a transfection efficiency experimental data set.

4. A transfection efficiency detection method for high-precision testing of transfection reagents according to claim 3, characterized in that: The calculation of the effect of each transfection condition label on the transfection efficiency based on the Pearson correlation coefficient formula specifically includes: According to the transfection efficiency experimental data set, the correlation coefficient of each transfection condition label to the transfection efficiency was calculated based on the Pearson correlation coefficient formula; The t statistic is used to test whether the correlation between each transfection condition label and the transfection efficiency is significant, and whether the t value is greater than If yes, it indicates that the correlation is significant, if no, it indicates that the correlation is not significant; Record the correlation coefficient and significant relationship between each transfection condition label and transfection efficiency, and establish a transfection efficiency detection comparison table; The Pearson correlation coefficient expression is: Among them, r is the correlation coefficient of each transfection condition label to transfection efficiency, x i is the i-th transfection condition label, is the average value of the label of the i-th transfection condition, y i is the transfection efficiency corresponding to the i-th transfection condition label, is the average transfection efficiency corresponding to the i-th transfection condition label; The t statistic expression is: Among them, t is the t statistic corresponding to each transfection condition label, r is the correlation coefficient of each transfection condition label to transfection efficiency, and n is the number of data sets in the transfection efficiency experimental data set for each transfection condition label.

5. A transfection efficiency detection method for high-precision testing of transfection reagents according to claim 4, characterized in that: The reinforcement learning algorithm model is used to automatically identify and select transfection condition labels for the transfection efficiency detection process, and the optimal transfection efficiency detection conditions are selected, specifically including: According to the correlation coefficient value in the transfection efficiency detection comparison table, the probability of selecting the corresponding transfection condition label during the transfection efficiency detection process is set, and a state transition probability matrix is ​​formed; According to the expected transfection efficiency test, set the corresponding reward value for completing one selection of the transfection efficiency test, and calculate the cumulative reward value for completing one round of screening process; According to the Markov algorithm, calculate the probability of selecting the corresponding transfection condition label and reward value in the next state; According to the Bellman formula, calculate the expected value of the optimal cumulative reward value after completing a round of screening process; Based on the reinforcement learning algorithm model, the reward value in the process of screening transfection efficiency detection conditions is adjusted by training the model and learning the results; The probability formula for selecting the corresponding transfection condition label during the transfection efficiency detection process is: π(a|s)=P(A=a|S=s) Among them, π(a|s) is the probability of selecting the ath transfection condition label in the sth state for the transfection efficiency detection, A is the probability set corresponding to the transfection condition label, and S is the set of the current state of the transfection efficiency detection; The state transition probability matrix is: Among them, P(s1|s n ) represents the state s1 to s n The probability that s1 to s n The probability sum is 1; The calculation of the cumulative reward value after completing a round of screening process is expressed as: Among them, G k is the cumulative reward feedback value corresponding to the kth state after completing a transfection efficiency detection decision, γ is the future discount factor for the current state, and r i+k+1 The cumulative reward feedback value corresponding to the k+1th state for completing a transfection efficiency detection decision; The probability expression for calculating the next state selection corresponding to the transfection condition label and reward value is: Among them, P[s k+1 |a k+1 ,s k ] is the probability of the k+1th state in the kth state of transfection efficiency detection, P[r k+1 |a k+1 ,s k ] is the probability of the k+1th state reward value of transfection efficiency detection, s k+1 The k+1th state is used to detect the transfection efficiency, s k Detect the current k-th state for transfection efficiency; The expected value expression of the optimal cumulative reward value after completing a round of screening process is: Among them, v k+1 is the expected value of the k+1th updated state, G π is the cumulative reward feedback value set corresponding to the kth state after completing a transfection efficiency detection decision, P π The i-th row and j-th column element in the state transition probability matrix is ​​from s i to j The probability and set of , v k is the expected value of the kth state.

6. A transfection efficiency detection method for high-precision testing of transfection reagents according to claim 5, characterized in that: The setting update and feedback platform, updating and optimizing the reinforcement learning algorithm model according to the transfection efficiency test results and the new transfection condition label, specifically includes: Set up an update and feedback platform to record and display transfection efficiency test results and control test results; Record and analyze new transfection condition labels, update control experiments and reinforcement learning algorithm models; Create a visual chart to display the comparison results between the screening results of the reinforcement learning algorithm model and the ideal values, and optimize the relevant parameters of the reinforcement learning algorithm model.

7. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a transfection efficiency detection method for high-precision testing of transfection reagents as described in any one of claims 1-6.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, a transfection efficiency detection method for high-precision testing of a transfection reagent according to any one of claims 1 to 6 is implemented.

Images