Rapid determination method for comprehensive toxicity of sewage

By establishing a comprehensive toxicity prediction model for sewage based on zebrafish embryo toxicity indicators, the problem of cumbersome operation of traditional methods and the inability to fully reflect sewage toxicity is solved, and rapid and accurate comprehensive toxicity detection of sewage is achieved, reducing costs and improving detection accuracy .

CN119001044APending Publication Date: 2024-11-22NANJING UNIV
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411320177.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-20
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The traditional comprehensive toxicity determination method for sewage requires multiple concentration gradients and parallel experiments, which increases the experimental operation time and embryo usage, and cannot fully reflect the actual situation of sewage. It can only detect neurotoxicity rather than comprehensive toxicity.

Method used

By measuring the traditional toxicity and behavioral toxicity indicators of zebrafish embryos, a comprehensive toxicity prediction model for sewage based on different target variables was established. The Lasso model and data preprocessing technology were used to quickly screen out the comprehensive toxicity of sewage samples, reducing the number of embryos and experimental time .

Benefits of technology

The rapid and accurate toxicity detection of large-scale sewage samples is achieved, which reduces costs and improves detection accuracy. The model determination coefficient R2>0.85 is achieved, ensuring high accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119001044A_ABST
    Figure CN119001044A_ABST
Patent Text Reader

Abstract

The invention discloses a rapid determination method for comprehensive toxicity of sewage. The rapid determination method comprises the following steps: (S1) determining zebra fish embryotoxicity indexes of a whole-process sewage sample of a sewage plant and carrying out data preprocessing; the zebrafish embryotoxicity index comprises a traditional toxicity index and a behavioral toxicity index; (S2) establishing a sewage comprehensive toxicity prediction model based on different target variables by taking the traditional toxicity indexes as the target variables and the behavioral toxicity indexes as characteristics; and (S3) inputting zebrafish embryo behavioral toxicity index data of a to-be-detected sewage sample as input data into the prediction model, and screening the corresponding prediction model according to a target variable prediction result to obtain the comprehensive toxicity of the to-be-detected sewage sample. According to the method, standardized comprehensive toxicity indexes can be obtained aiming at actual sewage samples, and the advantages of high speed, simplicity and convenience in operation and low cost can be kept, so that the method is suitable for rapid comprehensive toxicity detection of large-batch actual sewage samples.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of water quality monitoring, and in particular to a method for quickly determining the comprehensive toxicity of sewage. Background Art

[0002] Human activities have caused many pollutants to be dispersed into the environment, which may pose potential risks to human health and the environment. Although traditional chemical methods are often used to measure specific pollutants in sewage, since sewage usually exists in the form of complex mixtures, many components cannot be identified by chemical analysis, which increases the uncertainty in water quality assessment. Compared with chemical analysis, biological analysis can comprehensively measure the actual toxicity of all pollutants, that is, the comprehensive toxicity of sewage. Among biological analysis methods, zebrafish embryos are widely used because of their rapid reproduction cycle and transparent embryos. The comprehensive toxicity index obtained by traditional experimental methods is LC 10 or LC 50 (Unit is the percentage of water sample concentration), which is standardized and widely recognized. However, this method requires setting up multiple concentration gradients and multiple parallel experiments, which increases the amount of embryos used and the experimental operation time. In order to solve this problem, Chinese Patent Application No. 202010577907.X discloses a method for assessing the developmental neurotoxicity of wastewater, which exposes transgenic zebrafish embryos to concentrated or diluted wastewater to be tested to 24hpf, removes the exposed embryos, observes them under a fluorescent inverted microscope, and collects images for analysis, which has the advantages of simple operation, fast and efficient. However, the water samples detected by this method need to be filtered and concentrated, which may result in the measurement results not reflecting the actual situation of sewage; and this method can only obtain neurotoxicity indicators, not the comprehensive toxicity of sewage. Summary of the invention

[0003] Purpose of the invention: The present invention aims to provide a method for rapid determination of the comprehensive toxicity of sewage, which can obtain standardized comprehensive toxicity indicators for actual sewage samples while maintaining the advantages of fast speed, simple operation and low cost, so as to be suitable for rapid detection of comprehensive toxicity of large quantities of actual sewage samples.

[0004] Technical solution: The method for rapid determination of comprehensive toxicity of sewage described in the present invention comprises the following steps:

[0005] (S1) determining zebrafish embryo toxicity indicators of sewage samples from the entire process of several sewage treatment plants and performing data preprocessing; the zebrafish embryo toxicity indicators include traditional toxicity indicators and behavioral toxicity indicators;

[0006] (S2) Taking traditional toxicity indicators as target variables and behavioral toxicity indicators as features, a comprehensive sewage toxicity prediction model based on different target variables was established;

[0007] (S3) The zebrafish embryo behavioral toxicity index data of the sewage sample to be tested is input into the prediction model as input data, and the corresponding prediction model is selected according to the prediction result of the target variable to obtain the comprehensive toxicity of the sewage sample to be tested.

[0008] Preferably, the traditional toxicity index includes the median lethal concentration LC 50 and 10% lethal concentration LC 10 , measured by observing the mortality rate of zebrafish embryos over a specific period of time.

[0009] Preferably, the step (S2) of establishing a comprehensive sewage toxicity prediction model based on different target variables comprises:

[0010] Depending on the target variable, select LC 50 For sewage samples with a concentration of <100, use LC 50 Train the prediction model 1 for the target variable; select LC 50 For wastewater samples with a value of ≥100, the 10 The prediction model 2 is trained for the target variable.

[0011] Preferably, the step (S3) of screening the corresponding prediction model according to the prediction result of the target variable to obtain the comprehensive toxicity of the sewage sample to be tested includes:

[0012] The embryonic behavioral toxicity index data of the wastewater sample to be tested is input into prediction model 1 as input data. If the output value of prediction model 1 is LC 50 <100, then the LC 50 The value is the comprehensive toxicity of the sewage sample to be tested;

[0013] If the prediction model 1 outputs the value LC 50 ≥100, the embryonic behavioral toxicity index data of the sewage sample to be tested is used as input data into prediction model 2 to obtain the output value LC of prediction model 2 10 That is the comprehensive toxicity of the sewage sample to be tested.

[0014] Preferably, the behavioral toxicity indicators include zebrafish embryo activity under dark conditions within a specific time, zebrafish embryo activity under light conditions within a specific time, the total movement distance of zebrafish embryos under dark conditions within a specific time, the total movement distance of zebrafish embryos under light conditions within a specific time, the zebrafish embryo bursting distance within a specific time, the zebrafish embryo cruising distance within a specific time and the zebrafish embryo freezing distance within a specific time, which are measured using a zebrafish behavioral detector.

[0015] Preferably, the Lasso model is used to establish a comprehensive sewage toxicity prediction model.

[0016] Preferably, in the process of establishing the prediction model, based on the determination coefficient R2 To evaluate the performance of the prediction model, the coefficient of determination R 2 The calculation method is:

[0017]

[0018] Among them, R 2 is the coefficient of determination, y i is the value of the i-th traditional toxicity index in the test set, is the average value of traditional toxicity indicators in the test set, is the predicted value output by the prediction model, and n is the number of traditional toxicity index values.

[0019] Preferably, the data preprocessing includes data cleaning, data standardization and feature selection.

[0020] Preferably, the data normalization adopts the Z-Score value method or the Max-Min method.

[0021] Preferably, the feature selection method adopts Pearson correlation coefficient determination method.

[0022] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages: 1. The present invention can quickly and simply realize the toxicity detection of large quantities of sewage samples, and the number of embryos used is greatly reduced compared with traditional experiments, thereby reducing costs; 2. The corresponding prediction model is selected according to the prediction results of the target variable, which further improves the accuracy of the model in practical applications; 3. The determination coefficient R of the model established by the present invention is 2 >0.85, its accuracy is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0024] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0025] like Figure 1 As shown, the method for rapid determination of comprehensive toxicity of sewage described in the present invention mainly includes a stage of establishing a comprehensive toxicity model of sewage (1) and a stage of determining comprehensive toxicity of sewage (2).

[0026] The stage of establishing the comprehensive sewage toxicity model (1) mainly includes the following steps:

[0027] (1.1) Data collection: Determination of zebrafish embryo toxicity indicators of wastewater samples from several sewage treatment plants.

[0028] The zebrafish embryo toxicity indicators include traditional toxicity indicators and behavioral toxicity indicators. Among them, the traditional toxicity indicators include the median lethal concentration LC 50 and 10% lethal concentration LC 10 , measured by observing embryonic mortality over a specific period of time;

[0029] Behavioral toxicity indicators include embryonic activity under dark conditions for a specific time (activity-dark), embryonic activity under light conditions for a specific time (activity-light), total movement distance under dark conditions for a specific time (total distance-dark), total movement distance under light conditions for a specific time (total distance-light), blasting distance under dark and light conditions for a specific time, cruising distance under dark and light conditions for a specific time, and freezing distance under dark and light conditions for a specific time, which are measured using a zebrafish behavioral detector.

[0030] (1.2) Data preprocessing: including data cleaning, data standardization and feature selection.

[0031] The data standardization method includes but is not limited to the Z-Score method, the Max-Min method, etc. In this embodiment, the Z-Score method is used, and the calculation method is:

[0032]

[0033] Among them, Z is the standard score, x is the value of a certain indicator in the behavioral toxicity index, μ is the mean of the indicator data, and σ is the standard deviation of the indicator data.

[0034] The feature selection method adopts the Pearson correlation coefficient determination method. If the correlation coefficient of two indicators is r 2 > 0.8, then delete any one of the indicators so that the correlation coefficient between every two features is r 2 <0.8.

[0035] The processed data is divided into training set and test set.

[0036] (1.3) Model establishment

[0037] Taking traditional toxicity indicators as target variables and behavioral toxicity indicators as features, a comprehensive sewage toxicity prediction model was established based on the Lasso model.

[0038] (1.4) Model training and testing

[0039] The prediction model is trained using the training set data and the test set is used based on the determination coefficient R 2 Evaluate predictive model performance.

[0040] Among them, the coefficient of determination R 2 The calculation method is:

[0041]

[0042] Among them, R 2 is the coefficient of determination, y i is the value of the i-th traditional toxicity index in the test set, is the average value of traditional toxicity indicators in the test set, is the i-th predicted value output based on the features in the test set, and n is the number of traditional toxicity index values.

[0043] Specifically, depending on the target variable, select LC 50 <100 (i.e. water sample concentration is 100%), LC 50 Train the prediction model 1 for the target variable; select LC 50 For wastewater samples with a value of ≥100, the 10 The prediction model 2 is trained for the target variable.

[0044] The comprehensive toxicity test phase (2) includes the following steps:

[0045] (2.1) Determination of behavioral toxicity indexes of zebrafish embryos of wastewater samples to be tested: Use zebrafish embryos to determine the behavioral toxicity indexes of wastewater samples to be tested and perform data preprocessing;

[0046] (2.2) The pre-processed behavioral toxicity index data is input into prediction model 1 as input data. If the output value of prediction model 1 is LC 50 <100, then the LC 50 The value is the comprehensive toxicity of the sewage sample to be tested;

[0047] If the prediction model 1 outputs the value LC 50 If the value is ≥100, the embryonic behavioral toxicity index data of the sewage sample to be tested is used as input data to input into prediction model 2 to obtain the output value LC of prediction model 2 10 That is the comprehensive toxicity of the sewage sample to be tested.

[0048] The method of the present invention is further illustrated by way of examples below.

[0049] The sewage samples used to establish the comprehensive sewage toxicity prediction model came from multiple process sections of 40 sewage treatment plants, with a total of 300 sewage samples; the sewage samples to be tested were the actual influent and effluent of a municipal sewage treatment plant.

[0050] The method for rapid determination of comprehensive toxicity of sewage according to the present invention comprises the following steps:

[0051] (1) Establishing LC based on zebrafish embryo behavioral data 50 and LC 10prediction model.

[0052] (1.1) Data collection: The zebrafish embryo toxicity of 300 sewage samples was measured, including traditional toxicity indicators and behavioral toxicity indicators. Traditional toxicity indicators include LC 50 and LC 10 , measured by observing the embryonic mortality rate within a specific period of time; in this embodiment, LC 50 There are 130 sewage samples with a value less than 100, LC 50 There were 170 wastewater samples with a value ≥ 100. The behavioral toxicity indicators included embryonic activity under 5-min dark conditions, embryonic activity under 5-min light conditions, total movement distance under 5-min dark conditions, total movement distance under 5-min light conditions, bursting distance, cruising distance, and freezing distance under 5-min dark and 5-min light conditions, which were measured using a zebrafish behavioral detector.

[0053] (1.2) Data preprocessing: Data cleaning, data standardization and feature selection are performed on the collected data. Data standardization is performed using the Z-Score value method; the feature selection method is the Pearson correlation coefficient determination method. The final correlation coefficient r between each two features is 2 The range is: 0.496-0.770.

[0054] (1.3) Model training: The data set was divided into a 70% training set and a 30% test set. Traditional toxicity indicators were used as target variables and behavioral toxicity indicators were used as features. The Lasso model was selected for training. 50 There are 130 water samples with a concentration less than 100, LC 50 There are 170 water samples with a value of ≥100, so 130 water samples are classified by LC 50 The prediction model 1 was trained for the target variable. There are 170 water samples with LC 10 The prediction model 2 is trained for the target variable.

[0055] (1.4) Model testing: Based on the trained model, the test set data is used to determine the coefficient of determination R 2 Evaluate model performance. The determination coefficient R of prediction model 1 2 =0.874, the coefficient of determination R of prediction model 2 2 =0.893. It can be seen that the determination coefficient R of the two prediction models 2 >0.85, the prediction accuracy is relatively high.

[0056] (2) Use the established model to conduct comprehensive toxicity determination of wastewater.

[0057] (a) When the wastewater sample to be tested is the actual influent of a municipal wastewater treatment plant:

[0058] (2.1a) Determination of behavioral toxicity indicators: The behavioral toxicity indicators of the wastewater samples to be tested were determined using zebrafish embryos. Ten parallel groups were set up for each water sample. The obtained behavioral toxicity indicator data are shown in Table 1.

[0059] Table 1 Behavioral toxicity index data of sewage samples to be tested

[0060]

[0061] (2.2a) Model selection: The average value of the behavioral toxicity index obtained was used as input data and input into prediction model 1 to obtain the influent LC 50 =65, due to LC 50 <100, so LC 50 =65 is the comprehensive toxicity of the water sample.

[0062] (b) When the wastewater sample to be tested is the actual effluent from a municipal wastewater treatment plant:

[0063] (2.1b) Determination of behavioral toxicity indicators: The behavioral toxicity indicators of the wastewater samples were determined using zebrafish embryos. Ten parallel groups were set up for each water sample. The obtained behavioral toxicity indicator data are shown in Table 2.

[0064] Table 2 Behavioral toxicity index data of sewage samples to be tested

[0065]

[0066]

[0067] (2.2b) Model selection: The average value of the behavioral toxicity index obtained was used as input data and input into prediction model 1 to obtain the effluent LC 50 =136. Due to the outlet LC 50 >100, indicating that the toxicity of the wastewater sample to be tested is low and is not suitable for LC 50 As a toxicity index, the behavioral toxicity index parameters of the effluent were input into prediction model 2 to obtain LC 10 =43, which is the comprehensive toxicity of the water sample.

Claims

1. A method for rapid determination of comprehensive toxicity of sewage, characterized in that: The following steps are involved: (S1) determining zebrafish embryo toxicity indicators of sewage samples from the entire process of several sewage treatment plants and performing data preprocessing; the zebrafish embryo toxicity indicators include traditional toxicity indicators and behavioral toxicity indicators; (S2) Taking traditional toxicity indicators as target variables and behavioral toxicity indicators as features, a comprehensive sewage toxicity prediction model based on different target variables was established; (S3) The zebrafish embryo behavioral toxicity index data of the sewage sample to be tested is input into the prediction model as input data, and the corresponding prediction model is selected according to the prediction result of the target variable to obtain the comprehensive toxicity of the sewage sample to be tested.

2. A method for rapid determination of comprehensive toxicity of sewage according to claim 1, characterized in that: The traditional toxicity indexes include the median lethal concentration (LC) 50 and 10% lethal concentration LC 10 .

3. A method for rapid determination of comprehensive toxicity of sewage according to claim 2, characterized in that: The step (S2) of establishing a comprehensive sewage toxicity prediction model based on different target variables includes: Depending on the target variable, select LC 50 For sewage samples with a concentration of <100, use LC 50 Train the prediction model 1 for the target variable; select LC 50 For wastewater samples with a value of ≥100, the 10 The prediction model 2 is trained for the target variable.

4. A method for rapid determination of comprehensive toxicity of sewage according to claim 3, characterized in that: The step (S3) of screening the corresponding prediction model according to the prediction result of the target variable to obtain the comprehensive toxicity of the sewage sample to be tested includes: The embryonic behavioral toxicity index data of the wastewater sample to be tested is input into prediction model 1 as input data. If the output value of prediction model 1 is LC 50 <100, then the LC 50 The value is the comprehensive toxicity of the sewage sample to be tested; If the prediction model 1 outputs the value LC 50 ≥100, the embryonic behavioral toxicity index data of the sewage sample to be tested is used as input data into prediction model 2 to obtain the output value LC of prediction model 2 10 That is the comprehensive toxicity of the sewage sample to be tested.

5. The method for rapid determination of comprehensive toxicity of sewage according to claim 1, characterized in that: The behavioral toxicity indicators include the activity of zebrafish embryos under dark conditions within a specific time, the activity of zebrafish embryos under light conditions within a specific time, the total distance of movement of zebrafish embryos under dark conditions within a specific time, the total distance of movement of zebrafish embryos under light conditions within a specific time, the bursting distance of zebrafish embryos within a specific time, the cruising distance of zebrafish embryos within a specific time, and the freezing distance of zebrafish embryos within a specific time.

6. A method for rapid determination of comprehensive toxicity of sewage according to claim 1, characterized in that: The Lasso model is used to establish a comprehensive sewage toxicity prediction model.

7. A method for rapid determination of comprehensive toxicity of sewage according to claim 1, characterized in that: In the process of predictive model establishment, based on the coefficient of determination R 2 To evaluate the performance of the prediction model, the coefficient of determination R 2 The calculation method is: Among them, R 2 is the coefficient of determination, y i is the value of the i-th traditional toxicity index in the test set, is the average value of traditional toxicity indicators in the test set, is the predicted value output by the prediction model, and n is the number of traditional toxicity index values.

8. A method for rapid determination of comprehensive toxicity of sewage according to claim 1, characterized in that: The data preprocessing includes data cleaning, data standardization and feature selection.

9. A method for rapid determination of comprehensive toxicity of sewage according to claim 8, characterized in that: The data standardization adopts the Z-Score value method or the Max-Min method.

10. A method for rapid determination of comprehensive toxicity of sewage according to claim 8, characterized in that: The feature selection method adopts the Pearson correlation coefficient determination method.

Citation Information

Cited By

  • Refining wastewater biotoxicity detection method based on dual levels of zebra fish embryos

    CN121450751A