Methods, devices and media for screening PFAS vascular toxicity indicators

Abstract

This application discloses a method, system, apparatus, and storage medium for screening PFAS vascular toxicity indicators. The method includes the following steps: acquiring high-content fluorescence atlases of zebrafish at different exposure concentrations; the high-content fluorescence atlas includes several sub-fluorescence images; segmenting several vascular regions from the sub-fluorescence images and extracting all morphological indicators of the vascular regions; determining several first total scores for different vascular regions based on all morphological indicators; determining the target vascular region and vascular toxicity score based on the first total scores; analyzing the morphological characteristics of the target vascular region and determining a first weight and a second weight; and determining several second total scores for the target vascular region based on the first weight and the second weight. This method can quickly identify target vascular regions, screen vascular toxicity indicators, and obtain vascular toxicity scores. This application can be widely applied in the field of data processing technology.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, system, apparatus and storage medium for screening PFAS vascular toxicity indicators. Background Technology

[0002] Perfluoroalkyl and polyfluoroalkyl substances (PFAS) are a large class of industrial chemicals with diverse structures, consisting of thousands of synthetic compounds. They are widely used in packaging products, textiles, food processing, medicine, non-stick cookware, and many other aspects of daily life. Due to the presence of carbon-fluorine bonds in their structure, they are chemically extremely stable, difficult to degrade, and persist in the environment, potentially accumulating in the human body. This poses increasingly prominent health risks. Currently, numerous epidemiological and experimental studies have demonstrated that PFAS have vascular toxicity and are closely related to thrombosis, hypertension, stroke, and coronary heart disease.

[0003] In previous experiments, when zebrafish were selected for PFAS vascular toxicity assessment, simple t-tests and ANOVA were often used to qualitatively evaluate whether there were statistically significant differences in morphological indicators compared with the control group. However, this approach can only determine whether a compound is toxic to some blood vessels in zebrafish, and cannot compare the vascular toxicity of multiple compounds simultaneously, nor can it screen for sensitive vascular toxicity indicators of compounds.

[0004] Previous studies evaluating the vascular toxicity of compounds in zebrafish have primarily relied on effect indicators such as heart rate, blood flow velocity, and thrombus formation, observed under a stereomicroscope. This approach is subjective, inefficient, time-consuming, and limited in the number of samples that can be observed. Therefore, several technical challenges remain to be addressed in this research. Summary of the Invention

[0005] The purpose of this application is to at least partially solve one of the technical problems existing in the prior art.

[0006] Therefore, one objective of this application is to provide a method, system, device, and storage medium for screening PFAS vascular toxicity indicators. This method can quickly determine the target vascular region, screen vascular toxicity indicators, and obtain a vascular toxicity score.

[0007] To achieve the above-mentioned technical objectives, the technical solution adopted in this application includes: a method for screening PFAS vascular toxicity indicators, comprising: acquiring a high-content fluorescence atlas of zebrafish at different exposure concentrations; the high-content fluorescence atlas includes several sub-fluorescence images; segmenting several vascular regions from the several sub-fluorescence images and extracting all morphological indicators of the several vascular regions; determining several first total scores for different vascular regions based on all morphological indicators; the first total score is used to characterize the total score of all morphological indicators in a certain vascular region under all different exposure concentrations; determining a target vascular region and a vascular toxicity score based on the first total score; analyzing the morphological features of the target vascular region and determining a first weight and a second weight; determining several second total scores for the target vascular region based on the first weight and the second weight; the second total score is used to characterize the total score of each morphological indicator in the target vascular region under all different exposure concentrations.

[0008] In addition, the method for screening PFAS vascular toxicity indicators according to the above embodiments of the present invention may also have the following additional technical features:

[0009] Furthermore, in this embodiment of the application, the step of segmenting several vascular regions from the several sub-fluorescence images and extracting all morphological indicators of the several vascular regions specifically includes: acquiring several zebrafish high-intensity sub-fluorescence images; for any one of the zebrafish high-intensity sub-fluorescence images, using a fully convolutional neural network algorithm to segment a first blood vessel from the zebrafish high-intensity sub-fluorescence image, the first blood vessel including the common main vein, intersegmental vessels, caudal venous plexus, cerebral vessels, posterior main vein, dorsal aorta, and inferior intestinal venous plexus; extracting morphological indicators of the first blood vessel; the morphological indicators include total area, perimeter, diameter, irregularity, number of vascular pores, average distance between vessels, vessel area, area-to-perimeter ratio, shape factor, appearance ratio, and rectangularity feature.

[0010] Further, in this embodiment of the application, the step of determining several first total scores for different vascular regions based on all the morphological indicators, wherein the first total score is used to characterize the total score of all morphological indicators in a certain vascular region under all different exposure concentrations, specifically includes: determining a first rate of change of all morphological indicators in several vascular regions under different concentrations; normalizing the first rate of change to obtain a first normalized rate of change; determining several third total scores based on the first normalized rate of change; the third total score is used to characterize the total score of all different morphological features in the same vascular region under the same exposure concentration; normalizing each of the third total scores to obtain several normalized third total scores; and obtaining a first total score based on each of the normalized third total scores.

[0011] Furthermore, in this embodiment of the application, the step of determining the target vascular region and the vascular toxicity score based on the first total score specifically includes: comparing the plurality of vascular regions and taking the vascular region with the largest first total score as the target region; summing the plurality of first total scores to obtain the vascular toxicity score.

[0012] Further, in this embodiment, the step of analyzing the morphological features of the target vascular region and determining the first and second weights specifically includes: using ANOVA one-way ANOVA in SPSS to perform a linear trend test on each morphological feature in the target vascular region, eliminating the first morphological features, and calculating the corresponding baseline dose for the remaining second morphological features; the first morphological features are used to characterize morphological features with insignificant dose-response relationships. The multiple correlation coefficients between each of the second morphological features are calculated using SPSS; the first weight system and the second weight for each selected morphological feature are obtained using the baseline dose and the reciprocal of the multiple correlation coefficients.

[0013] Furthermore, in this embodiment of the application, the step of determining several second total scores for the target vascular region based on a first weight and a second weight, wherein the second total score is used to characterize the total score of each morphological index in the target vascular region under all different exposure concentrations, specifically includes:

[0014] Determine the fourth total score for all second morphological features of the target vascular region at all exposure concentrations;

[0015] The second total score is determined based on the fourth total score, the first weight, and the second weight.

[0016] Further, in this embodiment of the application, the step of determining the second total score based on the fourth total score, the first weight, and the second weight specifically includes: inputting a score calculation formula based on the fourth total score, the first weight, and the second weight, and determining the second total score, wherein the score calculation formula includes:

[0017] Score4 = Score3 × w2 × w3 × 10

[0018] Score4 is the second total score, Score3 is the fourth total score, w2 is the first weight, and w3 is the second weight.

[0019] On the other hand, embodiments of this application also provide a system for screening PFAS vascular toxicity indicators, comprising:

[0020] The acquisition unit is used to acquire high-content fluorescence atlases of zebrafish with different exposure concentrations; the high-content fluorescence atlases include several sub-fluorescence maps;

[0021] The first processing unit is used to segment several vascular regions from the several sub-fluorescence images and extract all morphological indicators of the several vascular regions;

[0022] The second processing unit is used to determine several first total scores for different vascular regions based on all the morphological indicators; the first total score is used to characterize the total score of all morphological indicators in a certain vascular region under all different exposure concentrations;

[0023] The third processing unit is used to determine the target vascular region and vascular toxicity score based on the first total score.

[0024] The fourth processing unit is used to analyze the morphological features of the target vascular region and determine the first weight and the second weight.

[0025] The fifth processing unit is used to determine several second total scores of the target vascular region based on the first weight and the second weight; the second total score is used to characterize the total score of each morphological index in the target vascular region under all different exposure concentrations.

[0026] On the other hand, this application also provides a device for screening indicators of PFAS vascular toxicity effects, comprising:

[0027] At least one processor;

[0028] At least one memory for storing at least one program;

[0029] When the at least one program is executed by the at least one processor, the at least one processor implements a method for screening PFAS vascular toxicity indicators as described in any one of the invention.

[0030] In addition, this application also provides a storage medium storing processor-executable instructions, which, when executed by a processor, are used to perform a method for screening indicators of PFAS vascular toxicity effects as described in any of the preceding claims.

[0031] The advantages and beneficial effects of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application:

[0032] This application can obtain a high-content fluorescence atlas of zebrafish with different exposure concentrations, including several sub-fluorescence images; segment several vascular regions from the sub-fluorescence images and extract all morphological indicators of several vascular regions; determine several first total scores for different vascular regions based on all morphological indicators; the first total score is used to characterize the total score of all morphological indicators in a certain vascular region under all different exposure concentrations; determine the target vascular region and vascular toxicity score based on the first total score; analyze the morphological characteristics of the target vascular region and determine the first weight and second weight; determine several second total scores for the target vascular region based on the first weight and second weight; the second total score is used to characterize the total score of each morphological indicator in the target vascular region under all different exposure concentrations. This application can quickly determine the target vascular region, screen vascular toxicity sensitive indicators, and obtain a vascular toxicity score, which is convenient for subsequent toxicity assessment. This application can improve the efficiency of PFAS toxicity assessment. Attached Figure Description

[0033] Figure 1 This is a schematic diagram illustrating the steps of a method for screening PFAS vascular toxicity indicators in a specific embodiment of the present invention;

[0034] Figure 2 This is experimental data on the effect of PFHS on the morphological characteristics of various vascular regions in zebrafish in the comparative experimental examples of this invention;

[0035] Figure 3 This is experimental data on the effect of PFDA on the morphological characteristics of various vascular regions in zebrafish in the comparative experimental examples of this invention.

[0036] Figure 4 This is experimental data on the effect of PFNA on the morphological characteristics of various vascular regions in zebrafish in the comparative experimental examples of this invention.

[0037] Figure 5 This is a schematic diagram of the structure of a system for screening PFAS vascular toxicity indicators in a specific embodiment of the present invention;

[0038] Figure 6 This is a schematic diagram of a device for screening PFAS vascular toxicity indicators in a specific embodiment of the present invention. Detailed Implementation

[0039] The embodiments of the present invention are described in detail below with reference to the accompanying drawings, and the principles and processes of the methods, systems, devices and storage media for screening PFAS vascular toxicity indicators in the embodiments of the present invention are explained as follows.

[0040] Reference Figure 1 This invention provides a method for screening indicators of PFAS vascular toxicity effects. The method may include the following steps:

[0041] S101. Obtain high-content fluorescence atlases of zebrafish with different exposure concentrations; the high-content fluorescence atlas includes several sub-fluorescence maps;

[0042] S102. Segment several vascular regions from several sub-fluorescence images and extract all morphological indicators of several vascular regions.

[0043] S103. Based on all morphological indicators, determine several first total scores for different vascular regions; the first total score is used to characterize the total score of all morphological indicators in a certain vascular region under all different exposure concentrations;

[0044] S104. Based on the first total score, determine the target vascular region and the vascular toxicity score;

[0045] S105. Analyze the morphological features of the target vascular region and determine the first weight and the second weight;

[0046] S106. Based on the first weight and the second weight, determine several second total scores for the target vascular region; the second total scores are used to characterize the total scores of each morphological index in the target vascular region under all different exposure concentrations.

[0047] Furthermore, in some embodiments of this application, the step of segmenting several vascular regions from several sub-fluorescence images and extracting all morphological indicators of several vascular regions specifically includes steps S201-S203.

[0048] S201. Obtain several high-enrichment fluorescence images of zebrafish;

[0049] S202. For any zebrafish high-endon fluorescence image, use a fully convolutional neural network algorithm to segment the first blood vessel from the zebrafish high-endon fluorescence image. The first blood vessel includes the common main vein, intersegmental blood vessels, caudal venous plexus, cerebral blood vessels, posterior main vein, dorsal aorta, and inferior intestinal venous plexus.

[0050] S203. Extract the morphological indicators of the first blood vessel; the morphological indicators include total area, perimeter, diameter, irregularity, number of vascular pores, average distance between blood vessels, blood vessel area, area-to-perimeter ratio, shape factor, appearance ratio, and rectangularity characteristics.

[0051] Furthermore, in some embodiments of this application, the step of determining several first total scores for different vascular regions based on all morphological indicators, wherein the first total score is used to characterize the total score of all morphological indicators in a certain vascular region under all different exposure concentrations, specifically includes steps S301-S305.

[0052] S301. Determine the first rate of change of all morphological parameters of all several vascular regions under different concentrations;

[0053] S302. The first rate of change is normalized to obtain the first normalized rate of change;

[0054] S303. Based on the first homogenization rate of change, determine several third total scores; the third total score is used to characterize the total score of all different morphological features of the same vascular region under the same exposure concentration.

[0055] S304. Normalize each third total score to obtain several normalized third total scores;

[0056] S305. Based on each uniformized third total score, obtain the first total score.

[0057] Furthermore, in some embodiments of this application, the step of determining the target vascular region and vascular toxicity score based on the first total score may specifically include steps S401-S402:

[0058] S401. Compare several vascular regions and select the vascular region with the highest total score as the target region.

[0059] S402. Sum the total scores of several first scores to obtain the vascular toxicity score.

[0060] Furthermore, in some embodiments of this application, the step of analyzing the morphological features of the target vascular region and determining the first weight and the second weight may specifically include steps S501-S503.

[0061] S501. Use ANOVA in SPSS to perform a linear trend test on each morphological feature in the target vascular region, eliminate the first morphological feature, and calculate the corresponding baseline dose for the remaining second morphological features; the first morphological feature is used to characterize morphological features where the dose-response relationship is not significant.

[0062] S502. Calculate the multiple correlation coefficients between each second morphological feature using SPSS.

[0063] S503. Using the baseline dose and the reciprocal of the multiple correlation coefficient, obtain the first weight system and the second weight for each screened morphological feature.

[0064] Furthermore, in some embodiments of this application, a number of second total scores for the target vascular region are determined based on the first weight and the second weight; the second total score is used to characterize the total score of each morphological index in the target vascular region under all different exposure concentrations. This step may specifically include steps S601-S602.

[0065] S601. Determine the fourth total score for all secondary morphological features of the target vascular region under all exposure concentrations;

[0066] S602. Based on the fourth total score, the first weight, and the second weight, determine several second total scores.

[0067] Furthermore, in some embodiments of this application, the step of determining several second total scores based on the fourth total score, the first weight, and the second weight may specifically include...

[0068] Input the fourth total score, the first weight, and the second weight into the score calculation formula to determine several second total scores. The score calculation formula includes:

[0069] Score4 = Score3 × w2 × w3 × 10

[0070] Score4 is the second total score, Score3 is the fourth total score, w2 is the first weight, and w3 is the second weight.

[0071] The specific calculation principle of this application is explained below with reference to the accompanying drawings:

[0072] This embodiment provides a rapid, simple, and accurate method for screening PFAS vascular toxicity indicators. In this embodiment, Score1 is the third total score, Score2 is the first total score, Score3 is the fourth total score, Score4 is the second total score, and Score5 is the vascular toxicity score. The most sensitive and stable effect indicators are screened by weighted scoring, and the vascular toxicity of multiple PFAS is compared simultaneously. The specific steps are as follows:

[0073] 1. PFAS exposure

[0074] Transgenic zebrafish embryos with specific vascular fluorescent labels were exposed to the test PFAS within 2 hours (2 hpf) after fertilization, and the exposure was continued until 72 hpf. The exposure solution was refreshed every 24 hours during the process. During the culture, N-phenylthiourea was added to the exposure solution at 24 hpf and 48 hpf to inhibit zebrafish pigment production.

[0075] 2. Acquisition and segmentation of the target blood vessel

[0076] High-content fluorescence images of zebrafish were obtained, and target vessels were segmented from the whole-body vascular fluorescence images using a fully convolutional neural network algorithm. The target vessels included the common cardinal vein (CCV), intersegmental vessels (ISV), caudal vessels posterior (CVP), macrovasculature, posterior cardinal vein (PCV), dorsal aorta (DA), and subintestinal venous plexus (SIV).

[0077] 3. Extraction of vascular morphological indicators

[0078] Extract morphological parameters of the target blood vessels, including total area, perimeter, diameter, irregularity, number of pores, average distance between vessels, vessel area, area-to-perimeter ratio, shape factor, appearance ratio, and rectangularity.

[0079] 4. Data Processing and Analysis

[0080] 5.1 Data for each vascular region were processed. Data within the mean ± 2 standard deviations were retained; data outside the mean ± 2 standard deviations were removed, as were samples with zero variance.

[0081] 5.2 Features with a coefficient of variation within 20% exhibit good stability and should be retained; candidate features with a coefficient of variation exceeding 20% ​​should be removed. Some vascular morphological features have excessively large coefficients of variation and require logarithmic transformation before statistical analysis, such as the number of vascular pores.

[0082] 5.3 Calculate the rate of change of morphological features in each vascular region

[0083]

[0084] X represents the original results for each fish in each vascular region at each concentration, and NC represents the results for the negative control group; RC represents the rate of change for each fish in each vascular region at each concentration.

[0085] 5.4 Homogenization of the rate of change

[0086]

[0087] RC represents the rate of change of each fish in each vascular region under different morphological characteristics at different concentrations; RC min The minimum RC value for a certain morphological feature within a vascular region; RC maxRC is the maximum value of a certain morphological feature within a certain vascular region; N This is the homogenized RC.

[0088] 5.5 Calculate the total PFAS vascular toxicity score for each concentration and vascular region.

[0089]

[0090] Score1 is the total PFAS vascular toxicity score for all morphological parameters in the same vascular region at the same concentration; RC Ni denoted as σn, represents the rate of change of homogenized morphological features in each vascular region at various exposure concentrations; w1 is the t-test comparing each morphological feature at each concentration in each region with the control group pairwise. When P < 0.05, w1 = 1; when P ≥ 0.05, w1 = 0; n is the number of morphological features in each vascular region. (Score1 is the total score of different morphological features in the same vascular region at the same concentration. Score1 has N concentrations * N vascular regions. Score1 represents all elements of the 2D data.)

[0091] 5.6Score1 homogenization

[0092]

[0093] Score 1min The minimum value of Score1 for each vascular region; Score 1max This represents the maximum value of Score1 within each vascular region.

[0094] 5.7 Calculate the score for each vascular region

[0095]

[0096] n represents the number of PFAS group concentrations used in the experiment; Score2 represents the score for each vascular region. Score2 is the total score for all different morphological features of the same vascular region. Score2 has N regions and consists of all elements of the 1-dimensional data.

[0097] The largest vascular region in Score2 is the most sensitive vascular region among the N sensitive vessels of this PFAS.

[0098] 5. Use SPSS ANOVA one-way ANOVA to test the linear trend of each morphological feature in the sensitive target blood vessel, remove features with no significant dose-response relationship, and calculate the corresponding baseline dose (BMD) for the remaining morphological features.

[0099] BMD was calculated using the Bayesian BMF Modeling System. The multiple correlation coefficient R between each selected morphological index was calculated using SPSS.

[0100] 6. Take the reciprocals of each BMD and R to obtain the weight coefficients w2 and w3 of the selected morphological features.

[0101] 7. Calculate the corresponding scores for each selected morphological feature.

[0102]

[0103] n is the number of PFAS group concentrations used in the experiment; RC VNi Score3 represents the uniformity rate of change of each selected morphological feature within the target vascular region at each concentration; Score3 represents the corresponding score of each selected morphological feature in the sensitive target vascular region.

[0104] 8. Calculate the total score for each selected morphological feature.

[0105] Score4 = Score3 × w2 × w3 × 10

[0106] Score4 is the total score of each morphological feature selected from the target blood vessel; the morphological feature with the highest score is the vascular toxicity index of this PFAS.

[0107] 9. Calculate the vascular toxicity score for each PFAS compound.

[0108]

[0109] n is the total number of vascular regions; Score 2i Score2 represents the vascular toxicity score for each PFAS in different vascular regions; Score5 represents the vascular toxicity score for each PFAS.

[0110] 10. The present invention, as a method for screening PFAS vascular toxicity indicators, has the following characteristics: it screens out sensitive and stable PFAS vascular toxicity indicators through a weighted scoring method, and simultaneously evaluates the vascular toxicity of multiple PFAS compounds, providing a basis for the assessment of PFAS vascular toxicity, as well as the detection and evaluation of environmental PFAS and the formulation of related technical standards.

[0111] In another specific embodiment of this application, the method for screening PFAS vascular toxicity indicators may include the following steps:

[0112] 1. PFAS exposure:

[0113] Transgenic zebrafish embryos with specific vascular fluorescent labels were exposed to PFHS, PFNA, and PFDA within 2 hours (2 hpf) post-fertilization, up to a concentration of 72 hpf, with the exposure solution refreshed every 24 hours. During culture, N-phenylthiourea was added to the exposure solution at 24 hpf and 48 hpf to inhibit zebrafish pigment production. The concentrations of PFHS, PFNA, and PFDA are shown in Table 1.

[0114]

[0115] Table 1: Exposure concentrations of various PFAS compounds

[0116] Extraction and segmentation of the target blood vessel:

[0117] High-content fluorescence images of zebrafish treated with PFHS, PFNA, and PFDA were obtained respectively. A fully convolutional neural network algorithm was used to segment the target blood vessels from the whole-body vascular fluorescence images. The target blood vessels included the common cardinal vein (CCV), intersegmental vessels (ISV), caudal vessels posterior (CVP), macrovasculature, posterior cardinal vein (PCV), dorsal aorta (DA), and subintestinal vessels (SIV).

[0118] Extraction of vascular morphological indicators

[0119] Extract morphological parameters of the target blood vessels, including total area, perimeter, diameter, irregularity, number of pores, average distance between vessels, vessel area, area-to-perimeter ratio, shape factor, appearance ratio, and rectangularity. Based on steps 5.1 and 5.2, eliminate and filter morphological features from each vessel region.

[0120] Data processing and analysis

[0121] 1) Screening of vascular effect markers of PFHS

[0122] According to the formula in the above embodiment, and as shown in Table 2, the sensitive vessel for PFHS is CVP. A score was obtained to normalize the PFHS concentration across different vessels. N1 And Score2 is shown in Table 2:

[0123]

[0124] Table 2: Scores for each vascular region N1and Score2

[0125] The target morphological features of CVP were selected, and the corresponding weight coefficients w2 and w3 were obtained, as shown in Table 3.

[0126]

[0127] Table 3: Weighting coefficients of morphological features BMD and R selected from CVP

[0128] The corresponding scores for each morphological feature are shown in Table 4:

[0129]

[0130] Table 4: Scores of various morphological features of CVP in PFHS-sensitive vessels (Score3 and total score (Score4)). The CVP shape factor was determined as the effect index of PFHS based on the Score4 values.

[0131] 2) Screening of PFNA vascular effect markers

[0132] The score for PFNA concentration and vessel homogenization at each concentration is obtained using the above formula. N1 And Score2 is shown in Table 5:

[0133]

[0134] Table 5: Scores for each vascular region N1 and Score2

[0135] As shown in Table 5, the CVP is the sensitive vessel for PFNA.

[0136] Based on the above formula, the target morphological features of CVP are selected to obtain the corresponding weight coefficients w2 and w3, such as...

[0137] As shown in Table 6:

[0138]

[0139] Table 6: The weight coefficients of morphological features BMD and R selected in CVP are calculated, and the corresponding scores and total scores of each morphological feature are shown in Table 7.

[0140]

[0141] Table 7: Scores of various morphological features of PFNA-sensitive CVP vessels (Score3 and total score (Score4)). Based on the size of Score4, the CVP vessel density was finally determined as the effect index of PFNA.

[0142] 3) Screening of PFDA vascular effect indicators

[0143] Based on the above formula, the score for PFDA concentration and vessel homogenization is obtained. N1 And Score2 is shown in Table 8:

[0144]

[0145] Table 8: Scores for each vascular region N1 and Score2

[0146] According to Table 8, the sensitive blood vessels for PFDA are SIV.

[0147] Based on the above steps, the target morphological features of SIV are selected to obtain the corresponding weight coefficients w2 and w3, as shown in Table 9:

[0148]

[0149] Table 9: The weight coefficients of morphological features BMD and R selected in SIV are used to calculate the corresponding scores and total scores of each morphological feature. Table 10 shows the scores of each morphological feature.

[0150]

[0151] Table 10: Score3 and total score4 of each morphological feature of PFDA-sensitive vascular SIV. The results were sorted according to the size of Score4, and the total area of ​​SIV was finally determined as the effect index of PFDA.

[0152] Based on the calculation method of the above formula, the Score5 scores of PFHS, PFNA and PFDA are 19.57, 1.26 and 2.85 respectively. Therefore, it can be determined that the order of vascular toxicity of each PFAS is PFHS > PFDA > PFNA.

[0153] Comparative experimental examples Figures 2-4 :

[0154] Previous studies have used simple one-way ANOVA for statistical analysis when evaluating the vascular toxicity of compounds, and the results are referenced. Figures 2-4 As shown.

[0155] According to the appendix Figures 2-4 The experimental results show that traditional statistical methods can only be used to determine whether a specific PFAS compound has a significant effect on specific morphological features of zebrafish vascular regions at a specific exposure concentration. However, they cannot intuitively compare the strength of the effects of a specific PFAS on the morphological features of each vascular region, nor can they screen out sensitive biomarkers of vascular toxicity effects of a specific PFAS.

[0156] Secondly, the median lethal dose (LD50) varies among different PFAS, leading to variations in the exposure concentrations for each PFAS when determining the LD50. Therefore, these results alone are insufficient for comparing the vascular toxicity of different PFAS at varying exposure concentrations. However, using a combined weighted scoring method effectively addresses this issue and allows for the screening of sensitive indicators of PFAS vascular toxicity effects.

[0157] In addition, refer to Figure 5 ,and Figure 1 Corresponding to the method described above, embodiments of this application also provide a system for screening PFAS vascular toxicity indicators. The system may include an acquisition unit 1001, a first processing unit 1002, a second processing unit 1003, a third processing unit 1004, a fourth processing unit 1005, and a fifth processing unit 1006: the acquisition unit 1001 can be used to acquire high-content fluorescence atlases of zebrafish at different exposure concentrations; the high-content fluorescence atlas includes several sub-fluorescence atlases; the first processing unit 1002 can be used to segment several vascular regions from the several sub-fluorescence atlases and extract all morphological indicators of the several vascular regions; the second processing unit 1003 can be used to determine several morphological indicators of different vascular regions based on all morphological indicators. The first total score is used to characterize the total score of all morphological indicators in a vascular region under all different exposure concentrations. The third processing unit 1004 can be used to determine the target vascular region and vascular toxicity score based on the first total score. The fourth processing unit 1005 can be used to analyze the morphological characteristics of the target vascular region and determine the first weight and the second weight. The fifth processing unit 1006 can be used to determine several second total scores of the target vascular region based on the first weight and the second weight. The second total score is used to characterize the total score of each morphological indicator in the target vascular region under all different exposure concentrations.

[0158] It should be noted that the content of the above-described method embodiments for screening PFAS vascular toxicity indicators is applicable to the system embodiments for screening PFAS vascular toxicity indicators. The specific functions implemented by the system embodiments for screening PFAS vascular toxicity indicators are the same as those of the above-described method embodiments for screening PFAS vascular toxicity indicators, and the beneficial effects achieved are also the same as those achieved by the above-described method embodiments for screening PFAS vascular toxicity indicators.

[0159] and Figure 1 Corresponding to the method, this application also provides a device for screening PFAS vascular toxicity indicators, the specific structure of which can be referred to Figure 6 ,include:

[0160] At least one processor;

[0161] At least one memory for storing at least one program;

[0162] When the at least one program is executed by the at least one processor, the at least one processor implements the method for screening PFAS vascular toxicity indicators.

[0163] It should be noted that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0164] and Figure 1 Corresponding to the method described above, this application also provides a storage medium storing processor-executable instructions, which, when executed by a processor, are used to perform the method for screening PFAS vascular toxicity indicators.

[0165] It should be noted that the content of the above-described method embodiments for screening PFAS vascular toxicity indicators is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above-described method embodiments for screening PFAS vascular toxicity indicators, and the beneficial effects achieved are also the same as those achieved in the above-described method embodiments for screening PFAS vascular toxicity indicators.

[0166] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0167] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0168] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0169] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable programs for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can retrieve and execute a program from or in conjunction with such a program execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with a program execution system, apparatus, or device.

[0170] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0171] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0172] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0173] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0174] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method of screening for an indicator of PFAS vascular toxicity effect, characterized in that, include: High-content fluorescence atlases of zebrafish with different exposure concentrations were obtained; the high-content fluorescence atlases include several sub-fluorescence maps; Several vascular regions are segmented from the several sub-fluorescence images and all morphological indicators of the several vascular regions are extracted; Based on all the morphological indicators, several first total scores are determined for different vascular regions; the first total score is used to characterize the total score of all morphological indicators in a vascular region under all different exposure concentrations; Based on the first total score, the target vascular region and vascular toxicity score are determined; The morphological features of the target vascular region are analyzed, and a first weight and a second weight are determined. Based on the first weight and the second weight, several second total scores are determined for the target vascular region; the second total score is used to characterize the total score of each morphological index in the target vascular region under all different exposure concentrations. The step of determining several first total scores for different vascular regions based on all the morphological indicators, wherein the first total score is used to characterize the total score of all morphological indicators in a vascular region under all different exposure concentrations, specifically includes: Determine the first rate of change for all morphological parameters in several vascular regions at different concentrations; The first rate of change is normalized to obtain the first normalized rate of change; Based on the first homogenization rate of change, several third total scores are determined; the third total score is used to characterize the total score of all different morphological features of the same vascular region under the same exposure concentration. Each of the aforementioned third total scores is normalized to obtain several normalized third total scores; The first total score is obtained based on each of the normalized third total scores.

2. The method for screening PFAS vascular toxicity indicators according to claim 1, characterized in that, The step of segmenting several vascular regions from the several sub-fluorescence images and extracting all morphological indicators of the several vascular regions specifically includes: Obtain several high-enrichment fluorescence images of zebrafish; For any zebrafish high-endon fluorescence image, a first blood vessel is segmented from the zebrafish high-endon fluorescence image using a fully convolutional neural network algorithm. The first blood vessel includes the common main vein, intersegmental vessels, caudal venous plexus, cerebral vessels, posterior main vein, dorsal aorta, and inferior intestinal venous plexus. The morphological parameters of the first blood vessel are extracted; the morphological parameters include total area, perimeter, diameter, irregularity, number of vascular pores, average distance between blood vessels, blood vessel area, area-to-perimeter ratio, shape factor, appearance ratio, and rectangularity feature.

3. The method for screening PFAS vascular toxicity indicators according to claim 1, characterized in that, The step of determining the target vascular region and vascular toxicity score based on the first total score specifically includes: Compare the several vascular regions and select the vascular region with the highest first total score as the target region; The vascular toxicity score is obtained by summing the sum of the aforementioned first total scores.

4. The method for screening PFAS vascular toxicity indicators according to claim 1, characterized in that, The step of analyzing the morphological features of the target vascular region and determining the first weight and the second weight specifically includes: One-way ANOVA in SPSS was used to test the linear trend of each morphological feature in the target vascular region. The first morphological feature was removed, and the corresponding baseline dose was calculated for the remaining second morphological features. The first morphological feature was used to characterize morphological features where the dose-response relationship was not significant. The multiple correlation coefficients between each of the second morphological features were calculated using SPSS. The first weight and the second weight of each selected morphological feature are obtained using the baseline dose and the reciprocal of the multiple correlation coefficient.

5. The method for screening PFAS vascular toxicity indicators according to claim 4, characterized in that, The second total score of the target vascular region is determined based on the first weight and the second weight. The second total score, used to characterize the total score of each morphological index in the target vascular region under all different exposure concentrations, specifically includes: Determine the fourth total score for all second morphological features of the target vascular region at all exposure concentrations; Based on the fourth total score, the first weight, and the second weight, a number of second total scores are determined.

6. The method for screening PFAS vascular toxicity indicators according to claim 5, characterized in that, The step of determining several second total scores based on the fourth total score, the first weight, and the second weight specifically includes: Based on the fourth total score, the first weight, and the second weight, a score calculation formula is input to determine several second total scores, wherein the score calculation formula includes: Score4 is the second total score, Score3 is the fourth total score, w2 is the first weight, and w3 is the second weight.

7. A system for screening PFAS vascular toxicity indicators, characterized in that, include: The acquisition unit is used to acquire high-content fluorescence atlases of zebrafish with different exposure concentrations; the high-content fluorescence atlases include several sub-fluorescence maps; The first processing unit is used to segment several vascular regions from the several sub-fluorescence images and extract all morphological indicators of the several vascular regions; The second processing unit is used to determine several first total scores for different vascular regions based on all the morphological indicators; the first total score is used to characterize the total score of all morphological indicators in a certain vascular region under all different exposure concentrations; The third processing unit is used to determine the target vascular region and vascular toxicity score based on the first total score. The fourth processing unit is used to analyze the morphological features of the target vascular region and determine the first weight and the second weight. The fifth processing unit is used to determine several second total scores of the target vascular region based on the first weight and the second weight; the second total score is used to characterize the total score of each morphological index in the target vascular region under all different exposure concentrations. The second processing unit is specifically used for: Determine the first rate of change for all morphological parameters in several vascular regions at different concentrations; The first rate of change is normalized to obtain the first normalized rate of change; Based on the first homogenization rate of change, several third total scores are determined; the third total score is used to characterize the total score of all different morphological features of the same vascular region under the same exposure concentration. Each of the aforementioned third total scores is normalized to obtain several normalized third total scores; The first total score is obtained based on each of the normalized third total scores.

8. A device for screening PFAS vascular toxicity indicators, characterized in that... include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a method for screening PFAS vascular toxicity indicators as described in any one of claims 1-6.

9. A storage medium storing processor-executable instructions, characterized in that, The processor-executable instructions, when executed by the processor, are used to perform a method for screening PFAS vascular toxicity indicators as described in any one of claims 1-6.

Images