DOE experiment software implementation method, system and apparatus

Abstract

The present application provides a kind of DOE experimental software implementation method, system and equipment, the method includes the following steps: obtaining the experimental design parameter input by user;From the pre-set reference experimental method list, obtain at least one reference experimental method matched with experimental design parameter, and show reference experimental method to user, for user to select;The reference experimental method selected by user is used as alternative experimental method;Based on experimental design parameter and alternative experimental method, generate training sample set;Based on training sample set, the pre-set analysis model is trained, and target analysis model is obtained;According to target analysis model, target independent variable factor is obtained from initial independent variable factor;And according to target independent variable factor, alternative experimental method is corrected, and target experimental method is obtained;The present application improves the standardization and automation degree of biological experiment process based on DOE experimental design method, and is conducive to improving DOE experimental implementation efficiency.

Description

Technical Field

[0001] This invention relates to the field of biotechnology, and more specifically, to a method, system, and device for implementing DOE experimental software. Background Technology

[0002] Design of Experiment (DOE) is a statistical method that minimizes the number of experiments and improves efficiency and success rate when testing different combinations of factors. It is widely used in fields such as cell engineering, drug testing, and culture medium optimization. However, currently, there is no standardized workflow developed based on DOE in this field, meaning the standardization of experimental design and analysis is low. This results in high time and labor costs associated with manual operations.

[0003] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] In view of this, the present invention provides a method, system and equipment for implementing DOE experimental software, which is beneficial to improving the implementation efficiency of experiments designed based on DOE experimental methods.

[0005] According to one aspect of the present invention, a method for implementing DOE experimental software is provided, comprising the following steps:

[0006] S110, Obtain the experimental design parameters input by the user; the experimental design parameters include multiple initial independent variable factors;

[0007] S120: From the preset list of reference experimental methods, at least one reference experimental method that matches the experimental design parameters is obtained, and the reference experimental method is displayed to the user for the user to select.

[0008] S130, Obtain the reference experimental method selected by the user as an alternative experimental method;

[0009] S140, Based on the experimental design parameters and the alternative experimental methods, generate a training sample set;

[0010] S150, Based on the training sample set, the preset analysis model is trained to obtain the target analysis model;

[0011] S160, Based on the target analysis model, target independent variable factors are selected from the initial independent variable factors; and

[0012] S170, The alternative experimental methods are corrected based on the target independent variable factor to obtain the target experimental method.

[0013] Optionally, step S110 further includes:

[0014] Obtain the experiment category selected by the user; the experiment category is either a screening experiment or an optimization analysis experiment.

[0015] The method includes:

[0016] When the experiment category is a screening experiment, the target independent variable factors are selected from the initial independent variable factors according to the target analysis model;

[0017] When the experiment category is an optimization analysis experiment, according to the target analysis model, target independent variable factors and their corresponding value ranges are obtained from the initial independent variable factors; and

[0018] Based on the target independent variable factors and the corresponding value ranges of each target independent variable factor, the alternative experimental methods are corrected to obtain the target experimental method.

[0019] Optionally, the experimental design parameters further include an initial dependent variable factor; step S160 further includes:

[0020] The target dependent variable factors are predicted based on the target analysis model.

[0021] The initial dependent variable factors in the experimental design parameters are corrected based on the target dependent variable factors.

[0022] Optionally, step S150 includes:

[0023] Based on the training sample set, the preset analysis model is trained multiple times;

[0024] During multiple training sessions, the training values ​​obtained from each training session are recorded.

[0025] After training is completed, multiple recorded training values ​​will be displayed for users to select from.

[0026] Based on the training data selected by the user, the preset analysis model is rolled back, and the rolled-back preset analysis model is used as the target analysis model.

[0027] Optionally, step S120 includes:

[0028] Obtain the first value range corresponding to each of the initial independent variable factors in the experimental design parameters;

[0029] Based on the first value interval corresponding to each of the initial independent variable factors, at least one matching reference experimental method is selected from the preset list of reference experimental methods; wherein, the second value interval corresponding to the independent variable factor in the reference experimental method includes the first value interval corresponding to the initial independent variable factor.

[0030] Optionally, step S120 further includes:

[0031] Obtain the consumables required for each experiment corresponding to the matched reference experimental method, as well as the consumption amount of each consumable;

[0032] Obtain the current inventory level of each of the aforementioned consumables;

[0033] Based on the consumption and the current inventory, determine the number of experiments that can be performed for each matched reference experimental method;

[0034] The reference experimental methods and the corresponding number of experiments are presented to the user.

[0035] Optionally, step S120 further includes:

[0036] The second value range corresponding to the independent variable factor in each of the matched reference experimental methods will be displayed to the user.

[0037] Optionally, the experimental design parameters further include initial dependent variable factors; when the experimental category is an optimization analysis experiment, according to the target analysis model, selecting target independent variable factors and the value ranges corresponding to each target independent variable factor from the initial independent variable factors includes:

[0038] During the optimization analysis experiment of the target analysis model, a comprehensive residual test plot and a residual normal distribution probability plot are obtained regarding the initial dependent variable factors;

[0039] The comprehensive residual test plot and the residual normal distribution probability plot are displayed to the user so that the user can further filter the initial dependent variable factors.

[0040] Optionally, the experimental design parameters may further include the initial independent variable factor category, the initial dependent variable factor, and the corresponding trend of the initial dependent variable factor, wherein the trend of the initial dependent variable factor is either increasing or decreasing.

[0041] Optionally, the preset analysis model is a linear regression model, and / or the reference experimental methods in the preset reference experimental method list are all DOE experimental design methods.

[0042] According to another aspect of the present invention, a DOE experimental software implementation system is provided for implementing any of the above-described DOE experimental software implementation methods, comprising:

[0043] The experimental design parameter acquisition module acquires the experimental design parameters input by the user; the experimental design parameters include multiple initial independent variable factors;

[0044] The reference experimental method screening module retrieves at least one reference experimental method that matches the experimental design parameters from a preset list of reference experimental methods and displays the reference experimental method to the user for selection.

[0045] The alternative experimental method determination module obtains the reference experimental method selected by the user as an alternative experimental method;

[0046] The training sample set generation module generates a training sample set based on the experimental design parameters and the alternative experimental methods.

[0047] The target analysis model generation module trains a preset analysis model based on the training sample set to obtain the target analysis model.

[0048] The independent variable factor selection module selects target independent variable factors from the initial independent variable factors according to the target analysis model; and

[0049] The target experimental method generation module corrects the candidate experimental methods based on the target independent variable factors to obtain the target experimental method.

[0050] The present invention also provides a DOE experimental software implementation device, comprising:

[0051] processor;

[0052] A memory in which an executable program of the processor is stored;

[0053] The processor is configured to execute the steps of any of the above-described DOE experimental software implementation methods by executing the executable program.

[0054] The present invention also provides a computer-readable storage medium for storing a program, which, when executed by a processor, implements the steps of any of the above-described DOE experimental software implementation methods.

[0055] The advantages of this invention compared to the prior art are as follows:

[0056] The DOE experimental software implementation method, system, and equipment provided by this invention improve the standardization and automation of biological experimental procedures based on the DOE experimental design method, reduce the time and labor costs required for manual operation, and help improve the efficiency of DOE experimental implementation. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0058] Figure 1 This is a flowchart illustrating a DOE experimental software implementation method disclosed in an embodiment of the present invention;

[0059] Figure 2 This is a flowchart illustrating a DOE experimental software implementation method disclosed in another embodiment of the present invention;

[0060] Figure 3 This is a flowchart illustrating a DOE experimental software implementation method disclosed in another embodiment of the present invention;

[0061] Figure 4 This is a flowchart illustrating step S150 in a DOE experimental software implementation method disclosed in another embodiment of the present invention;

[0062] Figure 5 This is a flowchart illustrating a DOE experimental software implementation method disclosed in another embodiment of the present invention;

[0063] Figure 6 This is a flowchart illustrating step S120 in a DOE experimental software implementation method disclosed in another embodiment of the present invention;

[0064] Figure 7 This is a schematic diagram of the structure of a DOE experimental software implementation system disclosed in an embodiment of the present invention;

[0065] Figure 8 This is a schematic diagram of a DOE experimental software implementation device disclosed in an embodiment of the present invention. Detailed Implementation

[0066] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that the invention will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore repeated descriptions of them will be omitted.

[0067] like Figure 1As shown, an embodiment of the present invention discloses a method for implementing DOE (Design of Experiments) experiments in software. This method is implemented in a software system based on the DOE experimental design method. The method includes the following steps:

[0068] S110, Obtain the experimental design parameters input by the user. Specifically, this embodiment provides an interactive interface in the software system to assist the user in interactively operating some experimental design parameters. The user is the experimenter. In this embodiment, the experimental design parameters include initial independent variable factors and initial dependent variable factors, and may also include the category of the initial independent variable factors and the corresponding trend of the initial dependent variable factors. The initial independent variable factors may include, for example, plasmid concentration, protein content, etc., and the initial dependent variable factors may include, for example, drug loading, and / or cell growth rate, and / or cell growth concentration, etc. The category of the initial independent variable factors may be, for example, a numerical quantification type, an attribute type, etc. This invention is not limited thereto.

[0069] The trend of change of the initial dependent variable factor is the experimental objective. This trend can be either increasing or decreasing. Specifically, when the initial dependent variable factor shows an increasing trend, it means that the larger the dependent variable is in subsequent model iterations, the better the model's performance. Conversely, when the initial dependent variable factor shows a decreasing trend, it means that the smaller the dependent variable is in subsequent model iterations, the better the model's performance. This invention is not limited to these limitations.

[0070] S120: From the preset list of reference experimental methods, at least one reference experimental method matching the above experimental design parameters is retrieved, and the reference experimental method is displayed to the user for selection. Specifically, the preset list of reference experimental methods contains multiple reference experimental methods, and all reference experimental methods in the preset list are DOE experimental design methods.

[0071] The matching process can be achieved based on the boundary values ​​of the initial independent variable factors, i.e., the upper and lower limits of the value range. In other words, the boundary values ​​corresponding to the initial independent variable factors need to be within the boundary values ​​corresponding to the reference experimental method. For example, if the value range of the initial independent variable factors is [3,5], and the value range of the reference experimental method is [1,7], since the value range [3,5] is within [1,7], the requirement is met, and the user-input data can be successfully matched with the reference experimental method. This helps users quickly and accurately match DOE experimental design methods that meet their experimental needs, thereby improving the efficiency and success rate of DOE biological experiments.

[0072] The matching process can also be implemented by matching the number of identical independent variables in the reference experimental method and the number of identical initial independent variable factors input by the user, or by matching the number of identical dependent variables in the reference experimental method and the number of identical initial dependent variable factors input by the user. This invention does not limit this, and those skilled in the art can choose according to their needs. Multiple reference experimental methods can be matched.

[0073] S130: Obtain the reference experimental method selected by the user as a candidate experimental method. In this embodiment, there is only one candidate experimental method. The subsequent iterative process of the model is used to determine the parameters in the candidate experimental method. In other embodiments, there may be multiple candidate experimental methods, and the user can select the final experimental method based on the iterative effects of each candidate experimental method. This invention does not limit this process. Furthermore, the candidate experimental methods belong to the Design of Experiments (DOE) experimental design method.

[0074] S140, Based on the above experimental design parameters and alternative experimental methods, a training sample set is generated. Specifically, this step is implemented based on a preset sample set template, which contains some missing attribute items such as independent variable factors, dependent variable factors, or experimental methods. The experimental design parameters and alternative experimental methods obtained in the above steps are then used to fill the corresponding attribute items in the preset sample set template to obtain the training sample set.

[0075] S150, Based on the aforementioned training sample set, the preset analysis model is trained to obtain the target analysis model. This step is the training process of the preset analysis model, and its specific implementation process can be found in existing technologies, which will not be elaborated here. In this embodiment, the aforementioned preset analysis model is a linear regression model, such as an OLS (ordinary least squares) model, but this invention is not limited thereto. Those skilled in the art can set it as needed.

[0076] S160, Based on the above target analysis model, target independent variable factors are obtained from the initial independent variable factors. Specifically, this means combining the experimental design parameters input by the user, using the above target analysis model to make predictions, and selecting factors that have a significant impact on the experimental results, thus obtaining the target independent variable factors.

[0077] S170, the candidate experimental methods are corrected based on the target independent variable factor to obtain the target experimental method. That is, by replacing the independent variable factor in the candidate experimental methods with the target independent variable factor, the target experimental method is obtained. Then, the user, i.e., the experimenter, can conduct DOE biological experiments according to the target experimental method.

[0078] This embodiment uses programming technology to improve the automation of experimental design and data analysis processes, reducing the time and labor costs for researchers to conduct biological experiments using the DOE experimental design method, thereby improving the efficiency of researchers in implementing biological experiments using the DOE experimental design method.

[0079] In another embodiment of this application, another method for implementing DOE experimental software is disclosed. For example... Figure 2 As shown, the method described above Figure 1 Based on the corresponding embodiment, step S110 is replaced by step S111: obtaining the experimental design parameters input by the user, and obtaining the experimental category selected by the user. The experimental category is either a screening experiment or an optimization analysis experiment. A screening experiment refers to selecting independent variable factors that have a significant impact on the experimental results. An optimization analysis experiment refers to not only selecting independent variable factors that have a significant impact on the experimental results, but also obtaining suitable value ranges for the independent variable factors.

[0080] In this embodiment, after step S150, the following step is also included:

[0081] S151, determine whether the above experiment category is a screening experiment. If so, proceed to steps S160 and S170.

[0082] If not, that is, when the experiment category is an optimization analysis experiment, replace step S160 with step S161 and execute it, and replace step S170 with step S171 and execute it; that is, execute steps S161 and S171.

[0083] Step S161 involves: based on the target analysis model described above, selecting target independent variable factors and their corresponding value ranges from the initial independent variable factors.

[0084] Step S171 involves correcting the candidate experimental methods based on the target independent variable factors and their corresponding value ranges to obtain the target experimental method. Specifically, this means replacing the independent variable factors and their value ranges in the candidate experimental methods with the target independent variable factors and their corresponding value ranges to obtain the target experimental method. The user, i.e., the experimenter, can then conduct DOE biological experiments according to the target experimental method.

[0085] In another embodiment of this application, another method for implementing DOE experimental software is disclosed. This method is described above... Figure 1 Based on the corresponding embodiments, the above experimental design parameters also include initial dependent variable factors. For example... Figure 3As shown, step S160 is replaced by step S162: according to the above target analysis model, target independent variable factors are selected from the above initial independent variable factors; and target dependent variable factors are predicted based on the above target analysis model; and the initial dependent variable factors in the experimental design parameters are corrected according to the above target dependent variable factors.

[0086] Specifically, for example, all the initial dependent variable factors in the experimental design parameters can be replaced with the aforementioned target dependent variable factors, which will help to find effective solutions with the fewest number of trials using DOE design, such as determining the optimal parameter ratio, thereby improving the efficiency and success rate of DOE experiments.

[0087] In another embodiment of this application, another method for implementing DOE experimental software is disclosed.

[0088] like Figure 4 As shown, the method described above Figure 1 Based on the corresponding embodiment, step S150 includes:

[0089] S151, Based on the above training sample set, the preset analysis model is trained multiple times.

[0090] S152 records the training values ​​obtained in each training session during multiple training sessions.

[0091] S153, after training is complete, displays multiple recorded training values ​​for the user to select from.

[0092] S154, Based on the training data selected by the user, roll back the above-mentioned preset analysis model, and use the rolled-back preset analysis model as the target analysis model.

[0093] Specifically, when training the preset analysis model using the generated training sample set, the user is supported in rolling back the training results. This embodiment involves performing multiple training runs and recording the results of each run. Because the training results don't necessarily improve over time, for example, if the results initially improve and then gradually deteriorate, the user can observe the recorded training results to determine which result best suits their needs and make a selection. The user then rolls back the selected training result, restoring the parameters in the preset analysis model to the values ​​corresponding to that selected result, thus obtaining the target analysis model.

[0094] In other words, this embodiment can assist experimenters in selecting appropriate target analysis models, thereby accurately determining the final DOE experimental design method, which helps to improve the efficiency and success rate of DOE experiments.

[0095] In another embodiment of this application, another method for implementing DOE experimental software is disclosed.

[0096] like Figure 5 As shown, the method described above Figure 1 Based on the corresponding embodiment, step S120 includes:

[0097] S121, obtain the first value interval corresponding to each initial independent variable factor in the above experimental design parameters.

[0098] S122, based on the first value range corresponding to each initial independent variable factor, select at least one matching reference experimental method from the preset reference experimental method list, and display the matching reference experimental method to the user for selection.

[0099] The second value interval corresponding to the independent variable factor of the successfully matched reference experimental method includes the first value interval corresponding to the initial independent variable factor. That is, the first value interval corresponding to the initial independent variable factor is located within the second value interval corresponding to the independent variable factor of the successfully matched reference experimental method. For example, if the first value interval corresponding to the initial independent variable factor is [3,5], and the second value interval corresponding to the independent variable factor of the successfully matched reference experimental method is [1,7], since the value interval [3,5] is within [1,7], the requirement is met, and the user-input data can be successfully matched with the reference experimental method.

[0100] This embodiment can help users quickly and accurately match DOE experimental design methods that meet their experimental needs, thereby improving the efficiency and success rate of DOE biological experiments.

[0101] As some optional embodiments, in the above Figure 5 Based on the corresponding embodiment, step S120 further includes: displaying the second value range corresponding to the independent variable factor in each of the matched reference experimental methods to the user. This facilitates the user in selecting the reference experimental method whose second value range best matches their experimental needs, thereby improving the efficiency and success rate of the user's DOE biological experiments.

[0102] In some embodiments, such as Figure 6 As shown above, in the above Figure 5 Based on the corresponding embodiment, step S120 further includes:

[0103] S123, obtain the consumables required for each experiment corresponding to the matched reference experimental method, as well as the consumption amount of each consumable.

[0104] S124, obtain the current inventory quantity of each of the above consumables.

[0105] S125, based on the aforementioned consumption and current inventory levels, determine the number of experiments that can be performed for each matched reference experimental method.

[0106] S126, The above-mentioned reference experimental methods and the corresponding number of experiments are displayed to the user.

[0107] Specifically, this involves obtaining the amount of consumables required for each experiment using each reference experimental method, as well as the corresponding inventory of consumables, thereby determining the number of experiments that each reference experimental method can currently be performed under the given conditions. By presenting each reference experimental method and its corresponding number of experiments to the user, it becomes easier for the user to accurately select the reference experimental method that matches their experimental needs, thus improving the efficiency and success rate of DOE biological experiments.

[0108] In another embodiment of this application, another method for implementing DOE experimental software is disclosed. This method is described above... Figure 2 Based on the corresponding embodiment, step S161 above includes:

[0109] During the optimization analysis experiment of the above target analysis model, comprehensive residual test plots and residual normal distribution probability plots were obtained for the initial dependent variable factors.

[0110] The above comprehensive residual test chart and the above residual normal distribution probability chart are displayed to the above users so that the users can further screen the above initial dependent variable factors.

[0111] Specifically, this embodiment uses mathematical statistical methods to analyze possible abnormal data throughout the experimental process, and uses this to further screen the initial dependent variable factors, thereby enabling users to more accurately select the target experimental method that matches their experimental needs, thus improving the efficiency and success rate of users conducting DOE biological experiments.

[0112] It should be noted that all the embodiments disclosed in this application can be freely combined, and the resulting technical solutions are also within the protection scope of this application.

[0113] Another embodiment of the present invention discloses a technical solution for optimizing cell culture medium formulation based on the target experimental method, namely the DOE experimental method, obtained from any of the above embodiments, so as to improve cell culture efficiency.

[0114] Specifically, cell culture is an important research method in the fields of biology and medicine. Cell culture typically involves placing cell seeds in a culture medium to provide sufficient nutrients and a suitable environment, enabling cells to grow and multiply in vitro. To improve cell growth and proliferation efficiency, optimizing cell culture medium formulations has become a critical issue, especially in drug development and biomedical engineering.

[0115] In cell culture, the culture medium is a crucial factor, providing the necessary nutrients and suitable environmental conditions for cells. Therefore, by altering the concentration and composition of different components in the culture medium, the formulation can be optimized to improve cell growth efficiency and yield, while simultaneously reducing costs and time, and making the production process more controllable and stable. This has significant application value in many fields, including biopharmaceuticals, bioreactor engineering, and cell research.

[0116] The biological experimental procedure for optimizing culture medium formulation in this embodiment includes the following six steps:

[0117] Step 1, Data Preparation:

[0118] Considering the effects of essential amino acid concentration, sugar concentration, and culture medium pH on cell growth, these three factors were used as independent variables. Specifically, the range for essential amino acid concentration was 50-150 mg / L, the range for sugar concentration was 10-30 g / L, and the range for culture medium pH was 6.5-7.5.

[0119] The second step is to create the experimental design:

[0120] Since each independent variable factor needs to be set with three levels (i.e., high, medium, and low), a center point needs to be set. Other experimental settings are not restricted. The purpose of this scheme is to improve cell culture efficiency, so the experimental design used is RSM (Response Surface Methodology), and this embodiment involves a total of 15 experiments.

[0121] The third step is data validation:

[0122] The recorded cell growth number and cell density are written into the response value to determine the cell culture efficiency. The growth number and cell density of all cells are checked to determine whether the data is normally distributed and whether the reliability of the data is sufficient to support the credibility of the experiment.

[0123] Part Four, Building the Model:

[0124] Based on the OLS regression model, a model was finally constructed to describe the relationship between cell growth and concentration, essential amino acid concentration, sugar concentration, and culture medium pH.

[0125] Step 5, Model Analysis:

[0126] Since all influencing factors have been identified as necessary, the evaluation results of the model metrics can be directly examined. The evaluation revealed the following: model fit 0.88, predictive power 0.8, effectiveness 0.45, and reproducibility 0.6. These metrics confirm the usability of the generated model. T-analysis and ANOVA are then used to examine the impact of each factor on the final result.

[0127] Step 6, Result Prediction:

[0128] Within the set ranges of essential amino acid concentration, sugar concentration, and culture medium concentration, the optimal combination for fastest cell growth and highest cell density was calculated, and the optimal formula is as follows:

[0129] Essential amino acid concentration: 126 mg / L;

[0130] Sugar concentration: 20.7 g / L;

[0131] Culture medium pH: 7.13;

[0132] Under these conditions, the cell growth rate and cell density are significantly increased, and the efficiency of cell growth is also significantly enhanced.

[0133] This leads to the conclusion that the optimal culture medium formulation and operating conditions were found using the RSM method, further improving the cell growth and proliferation efficiency during the culture of liver cancer cells. This experiment demonstrates that the DOE experimental design method can determine the optimal parameter ratios and find effective solutions with a minimal number of experiments, thereby greatly improving experimental efficiency and success rate, and has wide applications in cell engineering, drug testing, and other fields.

[0134] This embodiment generalizes the inputs and outputs of conventional experimental design to facilitate the comparison of various experimental design methods. It also adds data verification and data analysis to complete the construction of mathematical models, thereby achieving the ultimate goal of the experimenters and greatly improving the efficiency of biological experiments.

[0135] This embodiment achieves the first goal: using programming technology can automate the experimental design and data analysis process, thereby reducing the time and labor costs of manual operations and improving the standardization of experimental design and data analysis;

[0136] Second: Programming technology can be used to trace the experimental design and data processing process, as well as the process of drawing conclusions, thereby ensuring the reproducibility and reliability of experimental results.

[0137] Third: Programming technology allows for the flexible selection and combination of various statistical and machine learning techniques, resulting in diverse methods for more accurate and efficient experimental design and data analysis.

[0138] like Figure 7 As shown, an embodiment of the present invention also discloses a DOE experimental software implementation system 7, which includes:

[0139] The experimental design parameter acquisition module 71 acquires the experimental design parameters input by the user. These experimental design parameters include multiple initial independent variable factors.

[0140] The reference experimental method screening module 72 selects at least one reference experimental method from the preset list of reference experimental methods that matches the above experimental design parameters, and displays the above reference experimental method to the user for the user to select.

[0141] The alternative experimental method determination module 73 obtains the reference experimental method selected by the user as an alternative experimental method.

[0142] The training sample set generation module 74 generates a training sample set based on the above experimental design parameters and the above alternative experimental methods.

[0143] The target analysis model generation module 75 trains the preset analysis model based on the above training sample set to obtain the target analysis model.

[0144] Independent variable factor screening module 76, based on the above target analysis model, screens target independent variable factors from the initial independent variable factors to obtain them.

[0145] The target experimental method generation module 77 corrects the above-mentioned alternative experimental methods based on the target independent variable factors to obtain the target experimental method.

[0146] It is understood that the DOE experimental software implementation system of the present invention also includes other existing functional modules that support the operation of the DOE experimental software implementation system. Figure 7 The DOE experimental software implementation system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0147] The DOE experimental software implementation system in this embodiment is used to implement the above-described DOE experimental software implementation method. Therefore, the specific implementation steps of the DOE experimental software implementation system can be referred to the above description of the DOE experimental software implementation method, and will not be repeated here.

[0148] An embodiment of the present invention also discloses a DOE experimental software implementation device, including a processor and a memory, wherein the memory stores an executable program of the processor; the processor is configured to execute the steps in the above-described DOE experimental software implementation method by executing the executable program. Figure 8 This is a schematic diagram of the DOE experimental software implementation device disclosed in this invention. See below for reference. Figure 8 To describe an electronic device 600 according to this embodiment of the present invention. Figure 8 The electronic device 600 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0149] like Figure 8 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0150] The storage unit stores program code, which can be executed by the processing unit 610, causing the processing unit 610 to perform the steps described in the above-described DOE experimental software implementation method section of this specification, according to various exemplary embodiments of the present invention. For example, the processing unit 610 can perform, as follows: Figure 1 The steps are shown in the figure.

[0151] Storage unit 620 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include a read-only memory (ROM) 6203.

[0152] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0153] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0154] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0155] The present invention also discloses a computer-readable storage medium for storing a program that, when executed, implements the steps in the DOE experimental software implementation method described above. In some possible embodiments, various aspects of the present invention can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the DOE experimental software implementation method of the present invention according to various exemplary embodiments.

[0156] As shown above, when the program on the computer-readable storage medium of this embodiment is executed, it improves the standardization and automation of the biological experimental process based on the DOE experimental design method, reduces the time and labor costs required for manual operation, and helps to improve the efficiency of DOE experimental implementation.

[0157] One embodiment of the present invention discloses a computer-readable storage medium. This storage medium is a program product implementing the above-described method, which may be a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0158] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0159] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0160] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0161] The DOE experimental software implementation method, system, equipment, and storage medium provided in this invention improve the standardization and automation of biological experimental procedures based on the DOE experimental design method, reduce the time and labor costs required for manual operation, and help improve the efficiency of DOE experimental implementation.

[0162] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A method for implementing DOE experimental software, characterized in that, Includes the following steps: S110, Obtain the experimental design parameters input by the user; the experimental design parameters include multiple initial independent variable factors, and also include initial dependent variable factors; Obtain the experiment category selected by the user; the experiment category is either a screening experiment or an optimization analysis experiment. S120, from a preset list of reference experimental methods, at least one reference experimental method matching the experimental design parameters is retrieved, and the reference experimental method is displayed to the user for selection, including: Obtain the first value range corresponding to each of the initial independent variable factors in the experimental design parameters; Based on the first value interval corresponding to each of the initial independent variable factors, at least one matching reference experimental method is selected from the preset reference experimental method list; wherein, the second value interval corresponding to the independent variable factor in the reference experimental method includes the first value interval corresponding to the initial independent variable factor; S130, Obtain the reference experimental method selected by the user as an alternative experimental method; S140, Based on the experimental design parameters and the alternative experimental methods, generate a training sample set; S150, Based on the training sample set, the preset analysis model is trained to obtain the target analysis model; S160, Based on the target analysis model, target independent variable factors are selected from the initial independent variable factors: Specifically, when the experiment type is a screening experiment, target independent variable factors are selected from the initial independent variable factors according to the target analysis model; when the experiment type is an optimization analysis experiment, target independent variable factors and their corresponding value ranges are selected from the initial independent variable factors according to the target analysis model; and S170, the candidate experimental methods are corrected to obtain the target experimental method. When the experimental category is a screening experiment, the candidate experimental methods are corrected according to the target independent variable factor. When the experimental category is an optimization analysis experiment, the candidate experimental methods are corrected according to the target independent variable factor and the value range corresponding to each target independent variable factor. Step S160 also includes: The target dependent variable factors are predicted based on the target analysis model. The initial dependent variable factors in the experimental design parameters are corrected based on the target dependent variable factors.

2. The DOE experimental software implementation method as described in claim 1, characterized in that, Step S150 includes: Based on the training sample set, the preset analysis model is trained multiple times; During multiple training sessions, the training values ​​obtained from each training session are recorded. After training is completed, multiple recorded training values ​​will be displayed for users to select from. Based on the training data selected by the user, the preset analysis model is rolled back, and the rolled-back preset analysis model is used as the target analysis model.

3. The DOE experimental software implementation method as described in claim 1, characterized in that, Step S120 also includes: Obtain the consumables required for each experiment corresponding to the matched reference experimental method, as well as the consumption amount of each consumable; Obtain the current inventory level of each of the aforementioned consumables; Based on the consumption and the current inventory, determine the number of experiments that can be performed for each matched reference experimental method; The reference experimental methods and the corresponding number of experiments are presented to the user.

4. The DOE experimental software implementation method as described in claim 1, characterized in that, Step S120 also includes: The second value range corresponding to the independent variable factor in each of the matched reference experimental methods will be displayed to the user.

5. The DOE experimental software implementation method as described in claim 1, characterized in that, When the experiment category is an optimization analysis experiment, according to the target analysis model, target independent variable factors and the value ranges corresponding to each target independent variable factor are selected from the initial independent variable factors, including: During the optimization analysis experiment of the target analysis model, a comprehensive residual test plot and a residual normal distribution probability plot are obtained regarding the initial dependent variable factors; The comprehensive residual test plot and the residual normal distribution probability plot are displayed to the user so that the user can further filter the initial dependent variable factors.

6. The DOE experimental software implementation method as described in claim 1, characterized in that, The experimental design parameters also include the initial independent variable factor category and the changing trend of the initial dependent variable factor, wherein the changing trend of the initial dependent variable factor is either increasing or decreasing.

7. The DOE experimental software implementation method as described in claim 1, characterized in that, The preset analysis model is a linear regression model, and / or the reference experimental methods in the preset reference experimental method list are all DOE experimental design methods.

8. A DOE experimental software implementation system, used to implement the DOE experimental software implementation method as described in claim 1, characterized in that, include: The experimental design parameter acquisition module acquires the experimental design parameters input by the user; the experimental design parameters include multiple initial independent variable factors and initial dependent variable factors; And obtain the experiment category selected by the user, wherein the experiment category is either a screening experiment or an optimization analysis experiment; The reference experimental method filtering module retrieves at least one reference experimental method matching the experimental design parameters from a preset list of reference experimental methods and displays the reference experimental method to the user for selection. The reference experimental method filtering module is used to: obtain a first value range corresponding to each initial independent variable factor in the experimental design parameters; and filter at least one matching reference experimental method from the preset list of reference experimental methods based on the first value range corresponding to each initial independent variable factor; wherein, the second value range corresponding to the independent variable factor in the reference experimental method includes the first value range corresponding to the initial independent variable factor. The alternative experimental method determination module obtains the reference experimental method selected by the user as an alternative experimental method; The training sample set generation module generates a training sample set based on the experimental design parameters and the alternative experimental methods. The target analysis model generation module trains a preset analysis model based on the training sample set to obtain the target analysis model. The independent variable factor screening module, based on the target analysis model, screens target independent variable factors from the initial independent variable factors. When the experiment type is a screening experiment, it screens target independent variable factors from the initial independent variable factors according to the target analysis model; when the experiment type is an optimization analysis experiment, it screens target independent variable factors and their corresponding value ranges from the initial independent variable factors according to the target analysis model; it predicts target dependent variable factors based on the target analysis model; and it corrects the initial dependent variable factors in the experimental design parameters based on the target dependent variable factors. The target experimental method generation module corrects the candidate experimental methods to obtain the target experimental method. Specifically, when the experimental category is a screening experiment, the candidate experimental methods are corrected based on the target independent variable factors. When the experimental category is an optimization analysis experiment, the candidate experimental methods are corrected based on the target independent variable factors and the value ranges corresponding to each target independent variable factor.

9. A device for implementing DOE experimental software, characterized in that, include: processor; A memory in which an executable program of the processor is stored; The processor is configured to execute the steps of the DOE experimental software implementation method according to any one of claims 1 to 7 by executing the executable program.

Images