Microplastic influence resistance gene transmission evaluation method and device based on machine learning
By constructing a resistance gene abundance prediction model based on machine learning, using a random forest model to evaluate the impact of microplastics on resistant gene propagation, solving the problems of evaluating complex environmental factors and high costs in the existing technology, and achieving efficient and accurate Measurement of resistance gene contamination.
Patent Information
- Application Number
- CN202410799264.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-20
- Publication Date
- 2024-11-01
AI Technical Summary
The prior art is difficult to effectively evaluate the impact of microplastics on resistant gene transmission, and the experimental period is long and costly, so it is impossible to consider complex environmental factors and other influencing conditions in the soil.
Using a machine learning-based method, the data sets of resistance gene abundance and microplastic distribution characteristics are obtained for preprocessing, and the resistance gene abundance prediction model is constructed, and the biochemical data is learned using a random forest model, important influencing factors are evaluated and predicted. Its change pattern improves the accuracy and efficiency of evaluating resistant gene pollution.
It significantly improves the accuracy and efficiency of resistance gene contamination assessment, automatically processes complex data, reduces experimental time and cost, and can accurately identify complex impact conditions.
Smart Images

Figure CN118888005A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of artificial intelligence and resistance gene prediction, and specifically relates to a method and device for evaluating the impact of microplastics on the spread of resistance genes based on machine learning. Background Art
[0002] The problem of bacterial resistance caused by the spread of antibiotic resistance genes (ARGs) is an international research hotspot. The failure of antibiotics caused by bacterial resistance poses a threat to human health. The excessive use of antibiotics has made livestock and poultry manure and fertilized soil the source and reservoir of ARGs. Due to excessive use and improper disposal, a large amount of plastic has entered the earth's ecosystem. A large number of studies have shown that the accumulation of microplastics (MPs) in ecosystems will have an adverse impact on the environment. The increase in plastic waste has become an emerging global environmental problem. Moreover, since microbiota can colonize on the surface of MPs to form biofilms, MPs provide new environmental niches that are conducive to the survival of pathogens and resistant bacteria, which increases the risk of ARG transmission.
[0003] Studies have reported the diversity and abundance of ARGs in the plasticsphere. The surface of plastic can be colonized by microbial communities, thus becoming a platform for microbial film formation and plasmid transfer. The livestock breeding environment is seriously polluted by MP and ARG. Livestock and poultry manure in the breeding process is usually composted into organic fertilizer and applied to the soil. Even after composting, livestock and poultry manure contains potential pathogens and antibiotic-resistant bacteria. Once these harmful microorganisms attach to MPs and form biofilms, they may exist in the soil for a long time. Existing studies mainly rely on laboratory simulations of natural environments to observe the effects of microplastics on resistance gene changes. The test cycle is long and the cost is high. It is impossible to consider and balance the complex environmental factors in the soil and other influencing conditions. The development of artificial intelligence in recent years has provided new technical support for controlling resistance gene pollution. At present, studies have applied machine learning methods to predict the diffusion trend of antibiotics. Therefore, it is necessary to take advantage of big data analysis to explore the influence of MP, environmental factors, etc. on ARG, clarify important influencing characteristics, and provide theoretical guidance for assessing the risk of ARG in the plasticsphere. Summary of the invention
[0004] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and to provide a method and device for evaluating the impact of microplastics on the spread of resistance genes based on machine learning. By learning a large amount of biochemical data and laws through machine learning, important influencing factors are evaluated and their changing laws are predicted, thereby improving the accuracy and efficiency of evaluating resistance gene pollution.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions:
[0006] In a first aspect, the present invention provides a method for evaluating the spread of resistance genes affected by microplastics based on machine learning, comprising the following steps:
[0007] Obtain a data set of resistance gene abundance and corresponding microplastic distribution characteristics, and preprocess the data set;
[0008] Construct a resistance gene abundance prediction model, which includes a data screening module and a sample analysis module; use the data screening module to screen the data set to obtain soil physical and chemical properties and resistance gene pollution; use the sample analysis module to sort the importance of soil physical and chemical properties affecting resistance gene pollution and obtain importance characteristics;
[0009] The important features were input into the resistance gene abundance prediction model to obtain the resistance gene abundance of the sample.
[0010] As a preferred technical solution, the pretreatment is specifically:
[0011] digitize the acquired data set;
[0012] Delete the features with many missing values and the data strips with missing labels;
[0013] The abundance of the tag resistance gene was logarithmic;
[0014] Character variables are one-hot encoded and the data is standardized.
[0015] As a preferred technical solution, different random seeds are used to divide the data set to obtain test sets and training sets of different proportions;
[0016] According to the division of different data sets, resistance gene abundance prediction models based on multiple algorithms were constructed respectively;
[0017] Using the coefficient of determination R 2 The model is scored using three performance evaluation indicators: root mean square error (RMSE) and mean absolute error (MAE), and the random seed with the highest model score is selected;
[0018] The random seeds with the highest model scores were used to divide the data set, and the resistance gene abundance prediction model was optimized and evaluated. The model scoring results were compared, and the one with the highest model score and the best fitting effect was selected. The average score of the algorithm model was calculated, and the parameters of the resistance gene abundance prediction model were determined.
[0019] As a preferred technical solution, the resistance gene abundance prediction model is optimized and evaluated, specifically: validation is performed by performing five-fold cross validation and external validation, and the performance of the prediction model is evaluated.
[0020] As a preferred technical solution, the sample analysis module is used to sort the soil resistance gene contamination status according to its importance in terms of soil physical and chemical properties, including:
[0021] Use the feature_importances attribute to get the importance of each feature in the model;
[0022] Sort the importance of each feature in descending order to obtain the feature importance sequence, and extract the first few items to obtain the important features.
[0023] As a preferred technical solution, the input of important features into the resistance gene abundance prediction model is specifically as follows:
[0024] The important features were input into the resistance gene abundance prediction model to simulate the growth of microbial communities and predict the abundance of acquired resistance genes;
[0025] The important characteristics include soil pH, moisture content, fertilizer application and microplastic characteristics.
[0026] As a preferred technical solution, the step of verifying the resistance gene abundance prediction model is also included, including:
[0027] The important characteristics were selected as experimental variables for soil cultivation experiments;
[0028] Detecting soil physicochemical properties and resistance gene abundance of samples; the soil physicochemical properties include microplastic characteristics;
[0029] The soil physical and chemical properties obtained from the experiment were used as data points to input into the resistance gene abundance prediction model to obtain the resistance gene abundance predicted by the model;
[0030] Compare the resistance gene abundance predicted by the model with the resistance gene abundance of the sample to obtain the verification result;
[0031] The verification results are fed back to the resistance gene abundance prediction model, and the model parameters are optimized.
[0032] In a second aspect, the present invention also provides a system for evaluating the spread of resistance genes by microplastics based on machine learning, which is applied to the method for evaluating the spread of resistance genes by microplastics based on machine learning, and includes a data processing module, a model training module, and a data evaluation module;
[0033] A data processing module is used to obtain a data set of resistance gene abundance and corresponding microplastic distribution characteristics, and to pre-process the data set;
[0034] The model training module is used to construct a resistance gene abundance prediction model, which includes a data screening module and a sample analysis module. The data screening module is used to screen the data set to obtain soil physical and chemical properties and the pollution status of resistance genes. The sample analysis module is used to sort the importance of soil physical and chemical properties in affecting the pollution status of resistance genes and obtain importance characteristics.
[0035] The data evaluation module is used to input the important features into the resistance gene abundance prediction model to obtain the resistance gene abundance of the sample.
[0036] In a third aspect, the present invention provides an electronic device, the electronic device comprising:
[0037] at least one processor; and,
[0038] a memory communicatively connected to the at least one processor; wherein,
[0039] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor to enable the at least one processor to execute the method for evaluating the spread of resistance genes affected by microplastics based on machine learning.
[0040] In a fourth aspect, the present invention provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the method for evaluating the spread of resistance genes affected by microplastics based on machine learning.
[0041] Compared with the prior art, the present invention has the following advantages and beneficial effects:
[0042] (1) The random forest model used in the present invention evaluates important influencing factors and predicts their changing patterns by learning a large amount of biochemical data and laws; this method breaks through the limitations of traditional biochemical experiments and significantly improves the accuracy and efficiency of evaluating resistance gene contamination through algorithm simulation and data-driven methods.
[0043] (2) The resistance gene abundance prediction model of the present invention automatically processes complex data through algorithms and accurately identifies complex influencing conditions, thus avoiding the tediousness and time consumption of traditional experiments and significantly reducing the time and cost of experiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0045] Figure 1 This is a flow chart of a method for evaluating the spread of resistance genes affected by microplastics based on machine learning in an embodiment of the present invention;
[0046] Figure 2 is a schematic diagram of a data set according to an embodiment of the present invention;
[0047] Figure 3 Schematic diagram of the fitting results of three models in the embodiment of the present invention;
[0048] Figure 4 A schematic diagram of feature importance evaluation of a random forest model according to an embodiment of the present invention;
[0049] Figure 5 This is a schematic diagram of the structure of a microplastics impact resistance gene propagation assessment system based on machine learning in an embodiment of the present invention;
[0050] Figure 6 4 is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0051] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.
[0052] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.
[0053] See also Figure 1 This embodiment provides a method for evaluating the spread of resistance genes affected by microplastics based on machine learning, comprising the following steps:
[0054] S1. Obtain a dataset of resistance gene abundance and corresponding microplastic distribution characteristics, and preprocess the dataset.
[0055] In step S1, first, the following data are collected: longitude and latitude, soil physical and chemical properties (pH value, conductivity, total carbon, total nitrogen, temperature and humidity, etc.), microplastic characteristics (microplastic type, shape, abundance), microbial community characteristics (phylum abundance, Shannon index, etc.), resistance gene type and absolute abundance, and at the same time, these data are imaged using origin. In this embodiment, the label is the absolute abundance of resistance genes, there are 28 features, and 244 valid data are collected; the data set content is as follows Figure 2 shown.
[0056] Secondly, after the data is collected, a preliminary screening is performed on the data, and the features with many missing values and data bars with missing labels are deleted; the abundance of label resistance genes is logarithmic.
[0057] Finally, the character variables are encoded using OneHotEncoder in sklearn.preprocessing, and the data is standardized using StandardScaler.
[0058] S2. Construct a resistance gene abundance prediction model, which includes a data screening module and a sample analysis module. Use the data screening module to screen the data set to obtain soil physical and chemical properties and resistance gene pollution conditions. Use the sample analysis module to sort the soil physical and chemical properties according to their importance in affecting resistance gene pollution conditions and obtain importance characteristics.
[0059] Regarding using the data screening module, the following steps are included:
[0060] Import the RandomForestRegressor module in sklearn.ensemble, set 500 random seeds to divide the data set into test set and training set, and record the division. According to the division of the data set, establish a resistance gene abundance prediction model based on random forest, score the model through five-fold cross validation cross_val_score, and screen out the random state with the highest model score. This step tries different random seed values in a cycle multiple times to determine the random seed value for the data set partition with the highest random forest model score; in this embodiment, random state = 443.
[0061] Through cyclic iteration, the average score of the model is calculated using five-fold cross validation, and finally the optimal values of the four parameters of the random forest model, random_state, n_estimator, Max_depth, and max_features, are determined; in this embodiment, random_state = 369, n_estimator = 85, Max_depth = 19, max_features = 27, and the random forest fitting results are as follows Figure 3 As shown in part a of FIG.
[0062] Using the best parameter configuration obtained, a random forest model was established, and the performance of the model was evaluated using five-fold cross validation. The average score, root mean square error (RMSE), and mean absolute error (MAE) were calculated.
[0063] The calculation formulas are:
[0064]
[0065] Among them, y i is the experimental value, f i is the predicted value, is the average value of the features of the descriptor, SS res is the residual sum of squares, SS tot is the sum of squares, and n is the number of prediction samples.
[0066] Import the KNeighborsRegressor module in sklearn.neighbors and filter out the random state with the highest score in the K nearest neighbor model; in this embodiment, random state = 171. Through iterative cycles, use five-fold cross validation to calculate the average score of the model, and finally determine the optimal values of the four parameters of the K nearest neighbor model n_neighbors, weights, algorithm, and leaf_size; in this embodiment, n_neighbors = 2, weights = uniform, algorithm = kd_tree, leaf_size = 88, and the K nearest neighbor fitting results are as follows Figure 3 As shown in part b.
[0067] Import the SVR module in sklearn.svm and filter out the random state with the highest SVM model score; in this example, random state = 258. Through iterative cycles, use five-fold cross validation to calculate the average score of the model, and finally determine the optimal values of the three parameters of the SVM model kernel, C, and gamma; in this example, kernel = rbf, C = 100, gamma = auto, and the SVM model fitting results are as follows Figure 3 As shown in part c.
[0068] By comparing the average scores, root mean square error (RMSE) and mean absolute error (MAE) of the three models, it was found that the random forest model had the highest average score, and the root mean square error and mean absolute error were relatively low. It can be seen that the random forest model has the best fitting effect. Therefore, the random forest model is used in subsequent sample analysis and prediction modules.
[0069] Regarding the use of the sample analysis module, the following steps are included: Use the feature_importances attribute to obtain the importance of each feature in the random forest model and rank them, and find that soil pH, moisture content, fertilizer application, and microplastic characteristics (type, shape, content) are important features; the feature importance ranking is as follows Figure 4 shown.
[0070] S3. Input the important features into the resistance gene abundance prediction model to obtain the resistance gene abundance of the sample.
[0071] In order to adjust and improve the accuracy of the resistance gene abundance prediction model, this implementation also includes a step of validating the resistance gene abundance prediction model for feedback and adjustment of model parameters, including the following steps
[0072] Farmland soil with no fertilization history was selected as the test material, and six features with high model feature importance were selected as test variables, namely soil pH (8.5, 8.0, 7.5), moisture content (15%, 20%), fertilizer application (0%, 2%, 5%), microplastic types (PP, PE), microplastic shape (particles, fragments), and microplastic content (1%, 2%). The six groups of variables were divided into two 42-day soil cultivation experiments. The first test variable was soil pH (8.5, 8.0, 7.5), moisture content (15%, 20%), and fertilizer application (0%, 2%, 5%). PP plastic particles with a concentration of 1% were added, for a total of 18 test groups; the natural moisture content, pH value and fertilizer application were controlled, and no microplastics were added as blank groups, for a total of 6 blank groups, and a 42-day cultivation experiment was carried out after 7 days of pre-cultivation. Destructive sampling was carried out every two weeks. The variables of the second test were the type of microplastics (PP, PE), the shape of microplastics (particles, fragments), and the content of microplastics (1%, 2%), and the other conditions were the same as the first test;
[0073] The three indicators of soil physicochemical properties, resistance genes, and microbial community structure and diversity of the test samples are: soil physicochemical properties (pH value, electrical conductivity, total nitrogen, total carbon, organic carbon, antibiotic content), the types and abundance of resistance genes in soil samples and microplastic samples (including 25 resistance genes including eight major types of antibiotic resistance genes), and the microbial community structure and diversity of soil samples and microplastic samples;
[0074] The soil physical and chemical properties and microplastic characteristics obtained from the experiment were input into the prediction model as data points to obtain the resistance gene abundance predicted by the model, which was compared with the resistance gene abundance measured in the experiment to evaluate the accuracy of the prediction model.
[0075] It should be noted that, for the sake of convenience, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited to the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously.
[0076] Based on the same idea as the method for evaluating the spread of resistance genes by microplastics based on machine learning in the above-mentioned embodiment, the present invention also provides a system for evaluating the spread of resistance genes by microplastics based on machine learning, which can be used to execute the above-mentioned method for evaluating the spread of resistance genes by microplastics based on machine learning. For ease of explanation, the structural schematic diagram of the embodiment of the system for evaluating the spread of resistance genes by microplastics based on machine learning only shows the parts related to the embodiment of the present invention. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown in the diagram, or combine certain components, or arrange the components differently.
[0077] See also Figure 5 In another embodiment of the present application, a system 10 for evaluating the spread of resistance genes affected by microplastics based on machine learning is provided, the system comprising a data processing module 11, a model training module 12 and a data evaluation module 13;
[0078] The data processing module 11 is used to obtain a data set of resistance gene abundance and corresponding microplastic distribution characteristics, and pre-process the data set;
[0079] The model training module 12 is used to construct a resistance gene abundance prediction model, which includes a data screening module and a sample analysis module; the data screening module is used to screen the data set to obtain soil physical and chemical properties and resistance gene pollution conditions; the sample analysis module is used to sort the importance of soil physical and chemical properties affecting resistance gene pollution conditions to obtain importance characteristics;
[0080] The data evaluation module 13 is used to input the important features into the resistance gene abundance prediction model to obtain the resistance gene abundance of the sample.
[0081] It should be noted that the microplastics effect on resistance gene transmission assessment system based on machine learning of the present invention corresponds one to one with the microplastics effect on resistance gene transmission assessment method based on machine learning of the present invention. The technical features and beneficial effects described in the embodiment of the above-mentioned microplastics effect on resistance gene transmission assessment method based on machine learning are applicable to the embodiment of the microplastics effect on resistance gene transmission assessment method based on machine learning. For specific contents, please refer to the description in the embodiment of the method of the present invention, which will not be repeated here. This is hereby declared.
[0082] In addition, in the implementation of the microplastics-resistance gene transmission assessment system based on machine learning in the above-mentioned embodiment, the logical division of each program module is only an example. In actual applications, the above-mentioned functions can be assigned to different program modules as needed, for example, for the configuration requirements of the corresponding hardware or the convenience of software implementation. That is, the internal structure of the microplastics-resistance gene transmission assessment system based on machine learning is divided into different program modules to complete all or part of the functions described above.
[0083] See also Figure 6 In one embodiment, an electronic device that implements a method for evaluating the spread of resistance genes affected by microplastics based on machine learning is provided. The electronic device 20 may include a first processor 21, a first memory 22, and a bus. It may also include a computer program stored in the first memory 22 and executable on the first processor 21, such as a program 23 for evaluating the spread of resistance genes affected by microplastics based on machine learning.
[0084] Among them, the first memory 22 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the first memory 22 can be an internal storage unit of the electronic device 20, such as a mobile hard disk of the electronic device 20. In other embodiments, the first memory 22 can also be an external storage device of the electronic device 20, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 20. Further, the first memory 22 can also include both an internal storage unit of the electronic device 20 and an external storage device. The first memory 22 can not only be used to store application software and various types of data installed in the electronic device 20, such as the code of the microplastic impact resistance gene transmission assessment program 23 based on machine learning, but also can be used to temporarily store data that has been output or is to be output.
[0085] In some embodiments, the first processor 21 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The first processor 21 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device 20 by running or executing programs or modules stored in the first memory 22, and calling data stored in the first memory 22.
[0086] Figure 6 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the electronic device 20 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0087] The microplastics impact resistance gene transmission assessment program 23 based on machine learning stored in the first memory 22 in the electronic device 20 is a combination of multiple instructions. When running in the first processor 21, it can achieve:
[0088] Obtain a data set of resistance gene abundance and corresponding microplastic distribution characteristics, and preprocess the data set;
[0089] Construct a resistance gene abundance prediction model, which includes a data screening module and a sample analysis module; use the data screening module to screen the data set to obtain soil physical and chemical properties and resistance gene pollution; use the sample analysis module to sort the importance of soil physical and chemical properties affecting resistance gene pollution and obtain importance characteristics;
[0090] The important features were input into the resistance gene abundance prediction model to obtain the resistance gene abundance of the sample.
[0091] Furthermore, if the module / unit integrated in the electronic device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).
[0092] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0093] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0094] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.
Claims
1. A method for evaluating the spread of resistance genes affected by microplastics based on machine learning, characterized in that: The steps include: Obtain a data set of resistance gene abundance and corresponding microplastic distribution characteristics, and preprocess the data set; Construct a resistance gene abundance prediction model, which includes a data screening module and a sample analysis module; use the data screening module to screen the data set to obtain soil physical and chemical properties and resistance gene pollution; use the sample analysis module to sort the importance of soil physical and chemical properties affecting resistance gene pollution and obtain importance characteristics; The important features were input into the resistance gene abundance prediction model to obtain the resistance gene abundance of the sample.
2. According to the method for evaluating the spread of resistance genes affected by microplastics based on machine learning in claim 1, it is characterized in that: The preprocessing is specifically as follows: Convert the acquired data set into image data; Delete the features with many missing values and the data strips with missing labels; The abundance of the tag resistance gene was logarithmic; Character variables are one-hot encoded and the data is standardized.
3. According to the method for evaluating the spread of resistance genes affected by microplastics based on machine learning in claim 1, it is characterized in that: Use different random seeds to divide the data set to obtain test sets and training sets of different proportions; According to the division of different data sets, resistance gene abundance prediction models based on multiple algorithms were constructed respectively; Using the coefficient of determination R 2 The model is scored using three performance evaluation indicators: root mean square error (RMSE) and mean absolute error (MAE), and the random seed with the highest model score is selected; The random seeds with the highest model scores were used to divide the data set, and the resistance gene abundance prediction model was optimized and evaluated. The model scoring results were compared, and the one with the highest model score and the best fitting effect was selected. The average score of the algorithm model was calculated, and the parameters of the resistance gene abundance prediction model were determined.
4. The method for evaluating the spread of resistance genes affected by microplastics based on machine learning according to claim 3 is characterized in that: The resistance gene abundance prediction model is optimized and evaluated, specifically: validation is performed by performing five-fold cross validation and external validation, and the performance of the prediction model is evaluated.
5. According to the method for evaluating the spread of resistance genes affected by microplastics based on machine learning in claim 1, it is characterized in that: The sample analysis module is used to sort the soil according to the importance of the soil physical and chemical properties affecting the resistance gene contamination, including: Use the feature_importances attribute to get the importance of each feature in the model; Sort the importance of each feature in descending order to obtain the feature importance sequence, and extract the first few items to obtain the important features.
6. According to the method for evaluating the spread of resistance genes affected by microplastics based on machine learning in claim 1, it is characterized in that: The input of important features into the resistance gene abundance prediction model is specifically: The important features were input into the resistance gene abundance prediction model to simulate the growth of microbial communities and predict the abundance of acquired resistance genes; The important characteristics include soil pH, moisture content, fertilizer application and microplastic characteristics.
7. The method for evaluating the spread of resistance genes affected by microplastics based on machine learning according to claim 1 is characterized in that: It also includes steps to validate the resistance gene abundance prediction model, including: The important characteristics were selected as experimental variables for soil cultivation experiments; Detecting soil physicochemical properties and resistance gene abundance of samples; the soil physicochemical properties include microplastic characteristics; The soil physical and chemical properties obtained from the experiment were used as data points to input into the resistance gene abundance prediction model to obtain the resistance gene abundance predicted by the model; Compare the resistance gene abundance predicted by the model with the resistance gene abundance of the sample to obtain the verification result; The verification results are fed back to the resistance gene abundance prediction model, and the model parameters are optimized.
8. A microplastics impact resistance gene propagation assessment system based on machine learning, characterized in that: A method for evaluating the spread of resistance genes affected by microplastics based on machine learning, applied to any one of claims 1 to 7, comprising a data processing module, a model training module and a data evaluation module; A data processing module is used to obtain a data set of resistance gene abundance and corresponding microplastic distribution characteristics, and to pre-process the data set; The model training module is used to construct a resistance gene abundance prediction model, which includes a data screening module and a sample analysis module. The data screening module is used to screen the data set to obtain soil physical and chemical properties and the pollution status of resistance genes. The sample analysis module is used to sort the importance of soil physical and chemical properties in affecting the pollution status of resistance genes and obtain importance characteristics. The data evaluation module is used to input the important features into the resistance gene abundance prediction model to obtain the resistance gene abundance of the sample.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the method for evaluating the spread of resistance genes affected by microplastics based on machine learning as described in any one of claims 1-7.
10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by a processor, the method for evaluating the spread of resistance genes affected by microplastics based on machine learning as described in any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Construction method and device of agricultural pollution database, electronic equipment and storage medium
CN118210779A
Coronavirus environmental stability prediction method and system based on machine learning
CN118212978A
Cited By
Method for evaluating risk of antibiotics in environmental medium
CN121169650A
