A method for detecting pefloxacin with the aid of a web-based concentration prediction system

Abstract

This invention belongs to the fields of nanocomposite material preparation and machine learning technology. Specifically, it is a web-based concentration prediction system-assisted method for detecting pefloxacin. Based on the interaction between a ratiometric fluorescent probe (BSA-AuNCs-GTP-Tb) and pefloxacin, it exhibits a variety of visible fluorescent colors under ultraviolet light. The concentration prediction system detects the target object, extracts the fluorescent colors, and identifies the relationship between pefloxacin concentration and color data. The ratiometric fluorescent probe itself has good stability and, compared to single-signal fluorescent probes, is less affected by external factors, exhibiting higher anti-interference capabilities. The concentration prediction system, embedded with deep learning and machine learning, offers high efficiency, accuracy, and stable operation, along with advantages such as simple operation, ease of use, and wide applicability.

Description

Technical Field

[0001] This invention belongs to the fields of nanocomposite material preparation and machine learning technology, specifically a method for detecting pefloxacin using a web-based concentration prediction system. Background Technology

[0002] Through long-term experiments and observations, it has been found that there are currently many methods for the detection of pefloxacin, such as chemiluminescence, high performance liquid chromatography, longitudinal surface plasmon resonance, and capillary electrophoresis. Although these traditional detection methods have the advantage of high sensitivity, they require expensive instruments and professional operation, which limits their scope of use and application.

[0003] Fluorescence methods are widely used for antibiotic detection due to their fast response, good visualization, and high sensitivity. The BSA-AuNCs-GTP-Tb ratiometric fluorescent nanoprobe uses red fluorescence at the 669nm emission peak as an internal standard and green fluorescence at the 545nm emission peak as the response signal. 545 (The fluorescence intensity corresponding to the emission peak of the response signal) and I 669 The ratio of fluorescence intensity corresponding to the emission peak of the internal standard signal can be used to detect pefloxacin, but this process requires certain professional knowledge, relevant professional measuring instruments, and a lot of manual calculation.

[0004] Therefore, this invention provides a method for detecting pefloxacin using a web-based concentration prediction system. Summary of the Invention

[0005] To overcome the shortcomings of existing technologies and solve at least one of the technical problems mentioned in the background art, this invention proposes a method for detecting pefloxacin using a Web-based concentration prediction system.

[0006] The technical solution adopted by this invention to solve its technical problem is as follows: A method for assisting in the detection of pefloxacin using a Web-based concentration prediction system, comprising the following steps:

[0007] S1: Synthesis of BSA-AuNCs: Bovine serum albumin (BSA) was placed in a flask washed with aqua regia, chloroauric acid (HAuCl4·4H2O) was added dropwise and stirred, the pH was adjusted with NaOH, and the mixture was placed in a water / oil bath and stirred to obtain a reddish-brown liquid. After centrifugation and dialysis, it was stored at 4°C for use.

[0008] S2: Preparation of GTP-Tb: Guanosine-5'-triphosphate (GTP) and terbium nitrate hexahydrate (Tb(NO3)3·6H2O) were dissolved in HEPES buffer, stirred at room temperature and washed with water. After centrifugation, the precipitate was dispersed in HEPES buffer for use.

[0009] S3: Preparation of BSA-AuNCs-GTP-Tb fluorescent nanoprobes: GTP solution, Tb(NO3)3·6H2O solution and BSA-AuNCs were mixed and stirred. The precipitate was washed once with HEPES buffer solution and then dispersed in HEPES buffer and stored at 4°C for use.

[0010] S4: Perform fluorescence detection. Place the BSA-AuNCs-GTP-Tb fluorescent probe in a glass cuvette and bring the volume to 2 mL with HEPES buffer solution to stabilize the system. Mix well. Dissolve pefloxacin (PFLX) in 10 mL of deionized water and dilute to different concentration gradients. Add PFLX solution to the stable system and record the corresponding fluorescence spectra. Under a 365 nm UV lamp, the fluorescence color of the fluorescent nanoprobe mixture solution shows a colorful change from red to orange to yellow to green, realizing the visual detection of PFLX.

[0011] S5: Quantitative detection of pefloxacin based on a web-based system. Take 70 μL of the BSA-AuNCs-GTP-Tb fluorescent probe in a glass cuvette and bring the volume to 2 mL with HEPES buffer solution for stability. Mix thoroughly. Add different amounts of pefloxacin solution and stir well. Use the camera function of a smart device to capture fluorescence images under a 365nm UV lamp. Alternatively, record fluorescence changes using video recording. Use the video screenshot as the image to be predicted. The smart device accesses the system, clicks the "Operation interface" option in the list, and jumps to the concentration prediction interface. The "Select File" and "Start Uploading" buttons allow for image selection and upload. Successfully uploaded image information is visualized in the Table component of the front-end framework. Clicking the "Predict Concentration" button performs concentration prediction. The prediction result will be displayed in the "PredictConcentration Value (Unit: μM)" column of the Table component. Users can query the prediction results and download the data displayed on the front-end interface. The development of a web system based on the Django framework, combined with BSA-AuNCs-GTP-Tb fluorescent nanoprobes, enabled rapid, quantitative detection and batch processing of pefloxacin.

[0012] The beneficial effects of this invention are as follows:

[0013] 1. The present invention provides a web-based concentration prediction system to assist in the detection of pefloxacin, solving the problems of traditional detection methods being limited by professional instruments, professional operation, and laboratory environment. It also avoids traditional manual calculations, achieving efficient, accurate, and batch processing. Users can access the system via a browser, without needing to download an app or plugin, learn relevant knowledge, or receive professional guidance. It is simple to operate, widely applicable, and not limited by the device's operating system. The web-based concentration prediction system uses deep learning algorithms for target detection and extraction of relevant color data, reducing the impact of the background environment on the detection results and providing users with a relatively lifelike detection environment. By learning from the color data and corresponding pefloxacin concentration data, the system finds patterns (such as functional relationships) between the two and uses these patterns to predict unknown or unavailable data. Compared to manually finding suitable functional relationships and then calculating the corresponding concentration from color values, machine learning algorithms are highly efficient and accurate. The ratiometric fluorescent probe (BSA-AuNCs-GTP-Tb) synthesized via simple coordination is easy to prepare, exhibits good stability, and interacts with pefloxacin as an analyte, displaying a rich array of visually recognizable fluorescent colors, enabling qualitative analysis of pefloxacin. Compared to single-signal fluorescent probes, this ratiometric fluorescent probe demonstrates higher resistance to interference and is less susceptible to external factors. Attached Figure Description

[0014] The invention will now be further described with reference to the accompanying drawings.

[0015] Figure 1 The fluorescence spectrum of BSA-AuNCs-GTP-Tb as a function of PFLX concentration is shown in the ranges of 0–5 μM (a) and 5–60 μM (b) in this invention.

[0016] Figure 2 This is a flowchart of the Web-based concentration prediction system used in this invention;

[0017] Figure 3 This is a diagram showing the processing results of a single image and multiple images by the Web-based concentration prediction system of this invention. Detailed Implementation

[0018] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0019] like Figures 1 to 3 As shown in the embodiment of the present invention, a method for detecting pefloxacin using a web-based concentration prediction system includes the following steps:

[0020] Example 1

[0021] S1: Preparation of GTP-Tb: 1.5 mg GTP and 11.33 mg Tb(NO3)3·6H2O were dissolved in 1 mL of HEPES (10 mM, pH=7.4) buffer solution, stirred at room temperature for 3 h, centrifuged (9600 rpm / min, 3 min), washed twice with HEPES buffer solution (10 mM, pH=7.4), and the precipitate was dispersed in 3 mL of HEPES (10 mM, pH=7.4) buffer solution for use.

[0022] S2: Preparation of BSA-AuNCs-GTP-Tb fluorescent nanoprobes: 1.5 mL of BSA aqueous solution (50 mg / mL) was placed in a flask washed with aqua regia. 15 mg / mL GTP solution, 113.3 mg / mL Tb(NO3)3·6H2O solution, and 1.5 mL HAuCl4·4H2O (10 mM) were added dropwise. The mixture was stirred at room temperature for 5 min, and the pH was adjusted to 11 using NaOH aqueous solution (1 M). The flask was then transferred to a water / oil bath at 37 °C and stirred continuously for 12 h to obtain a pink turbid liquid. The liquid was centrifuged (9600 rpm / min, 3 min), washed once with HEPES buffer solution (10 mM, pH = 7.4), and the precipitate was dispersed in 3 mL of HEPES (10 mM, pH = 7.4) buffer and stored at 4 °C for later use.

[0023] S3: Perform fluorescence detection. Place 80 μL of the BSA-AuNCs-GTP-Tb fluorescent probe in a glass cuvette and dilute to a stable volume of 3 mL with HEPES buffer (10 mM, pH = 4). Mix thoroughly. Dissolve 46.5 mg of PFLX in 10 mL of deionized water and dilute to different concentration gradients. Add PFLX solution to the stable system and record the corresponding fluorescence spectra. The results show that as the PFLX concentration increases, the fluorescence intensity at 669 nm gradually decreases and tends to stabilize, exhibiting Tb... 3+ Characteristic peaks (490nm, 545nm, 586nm, and 621nm) with gradually increasing fluorescence intensity, particularly noticeable at the 545nm emission peak. Tb 3+ The ratio of the fluorescence intensity of the main emission peak (545 nm) to that of the BSA-AuNCs emission peak (669 nm) showed a good linear relationship with the concentration of PFLX. Under a 365 nm UV lamp, the fluorescence color of the fluorescent nanoprobe mixture solution exhibited a colorful change from red to orange to yellow to green, enabling visual detection of PFLX.

[0024] S4: For PFLX quantitative detection based on a web-based system, 80 μL of the BSA-AuNCs-GTP-Tb fluorescent probe is placed in a glass cuvette and diluted to a stable 3 mL volume with HEPES buffer solution (10 mM, pH = 4). Different amounts of PFLX solution are added dropwise and stirred thoroughly. Fluorescence images under a 365 nm UV lamp are captured using the camera function of a smart device. Alternatively, the fluorescence change can be recorded using video recording, and the video screenshots are used as the images to be predicted. The smart device accesses the system (http: / / 127.0.0.1:8000, the local development URL). Clicking the "Operation interface" option in the list redirects to the concentration prediction interface. The "Select File" and "Start Uploading" buttons allow for image selection and upload. Successfully uploaded image information is visualized in the Table component of the front-end interface. Clicking the "Predict Concentration" button predicts the concentration. The prediction result is displayed in the "Predict Concentration Value (Unit: μM)" column of the Table. Users can export the data to a specified format file as needed. The development of a web system based on the Django framework, combined with BSA-AuNCs-GTP-Tb fluorescent nanoprobes, enabled rapid, quantitative detection and batch processing of PFLX.

[0025] Example 2

[0026] S1: Synthesis of BSA-AuNCs: 5 mL of BSA (500 mg / mL) was placed in a flask washed with aqua regia, and 5 mL of HAuCl4·4H2O (10 mM) was added dropwise. The mixture was stirred at room temperature for 5 min, and the pH was adjusted to 11 with NaOH aqueous solution (1 M). The flask was then transferred to a water bath at 37 °C and stirred continuously for 12 h to obtain a reddish-brown liquid. The liquid was centrifuged (9600 rpm / min, 3 min), and the supernatant was transferred to a 1 kDa dialysis bag and dialyzed for 12 h. The solution was stored at 4 °C for later use.

[0027] S2: Preparation of GTP-Tb: 1.5 mg GTP and 11.33 mg Tb(NO3)3·6H2O were dissolved in 1 mL of HEPES (10 mM, pH=7.4) buffer solution, stirred at room temperature for 3 h, centrifuged (9600 rpm / min, 3 min), washed twice with HEPES buffer solution (10 mM, pH=7.4) and the precipitate was dispersed in 3 mL of HEPES (10 mM, pH=7.4) buffer solution for use;

[0028] S3: Preparation of BSA-AuNCs-GTP-Tb fluorescent nanoprobes: 15 mg / mL GTP solution and 113.3 mg / mL Tb(NO3)3·6H2O solution were added dropwise to 3 mL of BSA-AuNCs. The mixture was stirred at room temperature for 3 h, centrifuged (9600 rpm / min, 5 min), washed twice with HEPES buffer solution (10 mM, pH = 7.4), and the precipitate was dispersed in 3 mL of HEPES (10 mM, pH = 7.4) buffer and stored at 4 °C for later use.

[0029] S4: Specific implementation method for fluorescence detection: 70 μL of the BSA-AuNCs-GTP-Tb fluorescent probe was placed in a glass cuvette and diluted to a stable volume of 2 mL with HEPES buffer solution (10 mM, pH = 4). The mixture was thoroughly mixed. 46.5 mg of PFLX was dissolved in 10 mL of deionized water and diluted to different concentration gradients. PFLX solution was added dropwise to the stable system, and the corresponding fluorescence spectra were recorded. The results showed that with the increase of PFLX, the fluorescence intensity at 669 nm gradually decreased and tended to stabilize, while the fluorescence intensity at 490 nm, 545 nm, 586 nm, and 621 nm was the peak fluorescence intensity for Tb. 3+ The characteristic peaks of Tb are observed, and the fluorescence intensity at 545 nm is significantly increased. 3+ The ratio of fluorescence intensity of the main emission peak (545nm) to that of BSA-AuNCs emission peak (669nm) showed a good linear relationship with the concentration of PFLX. Under a 365nm UV lamp, the fluorescence color of the fluorescent nanoprobe mixed solution showed a colorful change from red to orange to yellow to green, enabling visual detection of PFLX.

[0030] S5: Web-based quantitative detection of pefloxacin

[0031] Take 70 μL of the BSA-AuNCs-GTP-Tb fluorescent probe in a glass cuvette and dilute it to a stable 2 mL volume with HEPES buffer solution (10 mM, pH = 4), mixing thoroughly. Add different amounts of PFLX solution, stir well, and capture fluorescence images under a 365 nm UV lamp using the camera function of a smart device. Alternatively, record fluorescence changes using the video function, and use the video screenshots as the images to be predicted. Access the system using the smart device (http: / / 127.0.0.1:8000, the local development URL). Through user interface operations, the concentration prediction of the uploaded images can be achieved. The specific operation is as follows:

[0032] Clicking the "Operation interface" option in the website list will take you to the concentration prediction interface. The "Select File" and "Start Uploading" buttons allow you to select and upload images. Successfully uploaded image information is visualized in the Table component of the front-end framework. Clicking the "Predict Concentration" button will predict the concentration; the prediction result will be displayed in the "Predict Concentration Value (Unit: μM)" column of the Table component. Users can export the data displayed on the front-end interface to a specified file format as needed. This web system, developed based on the Django framework and combined with BSA-AuNCs-GTP-Tb fluorescent nanoprobes, enables rapid, quantitative detection and batch processing of PFLX.

[0033] Example 3

[0034] S1: Synthesis of BSA-AuNCs: 5 mL of BSA (500 mg / mL) was placed in a flask washed with aqua regia. 5 mL of HAuCl4·4H2O (10 mM) was added dropwise, and the mixture was stirred at room temperature for 5 min. The pH was adjusted to 11 using NaOH aqueous solution (1 M). The flask was then transferred to a water bath at 37°C, and stirring was continued for 12 h to obtain a reddish-brown liquid. The solution was centrifuged (9600 rpm / min, 3 min), and the supernatant was transferred to a 1 kDa dialysis bag. After 12 h, the solution was stored at 4°C for later use.

[0035] S2: Preparation of GTP-Tb: 5.7 mg GTP and 11.3 mg Tb(NO3)3·6H2O were dissolved in 1 mL of HEPES (10 mM, pH=7.4) buffer solution, stirred at room temperature for 3 h, centrifuged (9600 rpm / min, 3 min), washed three times with HEPES buffer solution (10 mM, pH=7.4), and the precipitate was dispersed in 1 mL of HEPES (10 mM, pH=7.4) buffer solution for use.

[0036] S3: Preparation of BSA-AuNCs-GTP-Tb fluorescent nanoprobes: 56.7 mg / mL GTP solution and 113 mg / mL Tb(NO3)3·6H2O solution were added dropwise to 1 mL of BSA-AuNCs. The mixture was stirred at room temperature for 3 h, centrifuged (9600 rpm / min, 5 min), washed twice with HEPES buffer solution (10 mM, pH = 7.4), and the precipitate was dispersed in 2 mL of HEPES (10 mM, pH = 7.4) buffer and stored at 4 °C for use.

[0037] S4: Specific implementation method for fluorescence detection: 70 μL of the BSA-AuNCs-GTP-Tb fluorescent probe was placed in a glass cuvette and diluted to a stable volume of 3 mL with HEPES buffer solution (10 mM, pH = 4), and mixed thoroughly. 46.5 mg of PFLX was dissolved in 10 mL of deionized water and diluted to solutions of different concentration gradients. PFLX solution was added dropwise to the stable system, and the corresponding fluorescence spectra were recorded. The results showed that with the increase of PFLX, the fluorescence intensity of the emission peak of BSA-AuNCs at 669 nm gradually decreased and tended to stabilize, while Tb... 3+ The fluorescence intensity of the characteristic peaks (490 nm, 545 nm, 586 nm, and 621 nm) increased, with the increase in fluorescence intensity of the main emission peak (545 nm) being particularly significant. 3+ The ratio of the fluorescence intensity of the main emission peak to that of the BSA-AuNCs emission peak showed a good linear relationship with the concentration of PFLX, which can be used for the quantitative analysis of PFLX. Under a 365nm UV lamp, the fluorescence color of the fluorescent nanoprobe mixture solution exhibited a colorful change from red to orange to yellow to green, enabling visual detection and qualitative analysis of PFLX.

[0038] S5: Quantitative detection of pefloxacin based on a web-based system. Take 70 μL of the BSA-AuNCs-GTP-Tb fluorescent probe in a glass cuvette and dilute it to a stable 3 mL with HEPES buffer solution (10 mM, pH = 4), mixing thoroughly. Add different amounts of PFLX solution, stir well, and capture fluorescence images under a 365 nm UV lamp using a smartphone camera. Alternatively, record fluorescence changes using video recording, and use the video screenshots as the images to be predicted.

[0039] Accessing the system via a smart device (http: / / 127.0.0.1:8000, the local development URL), clicking the "Operation interface" in the form bar redirects to the concentration prediction interface. The "Select File" and "Start Uploading" buttons allow for image selection and upload. Successfully uploaded image information is visualized in the Table component. Clicking the "PredictConcentration" button predicts the concentration, and the prediction result is displayed in the "PredictConcentration Value (Unit: μM)" column of the Table component. Users can export the data displayed on the front-end interface to a specified file format as needed. The development of this web system based on the Django framework, combined with BSA-AuNCs-GTP-Tb fluorescent nanoprobes, enables rapid, quantitative detection and batch processing of PFLX.

[0040] Working principle: The synthesized BSA-AuNCs-GTP-Tb fluorescent nanoprobe interacts with the pefloxacin analyte, and pefloxacin sensitizes Tb. 3+ And it transfers energy to it; the ratiometric fluorescent probe, through the antenna effect, exhibits Tb 3+ The green fluorescence of Tb increases with increasing PFLX concentration. 3+ It happened 5 D4 direction 7 F3, 7 F4 7 F5, 7 The electronic transition to the F6 level. Under a 365nm UV lamp, the BSA-AuNCs-GTP-Tb ratiometric fluorescent probe exhibits a visible multi-color fluorescence change from red to orange to yellow to green. Based on this rich fluorescence variation and the relationship between the fluorescence color of the ratiometric fluorescent probe and the PFLX concentration, a web-based concentration prediction system learns this relationship to create a learner for this type of problem, thereby enabling prediction of unknown data. The web-based concentration prediction system uses the Django web development framework. Data processing and computation are implemented through functions in the View module, the Template module visualizes the data to the front-end interface, and the Model module handles data interaction. Based on the MTV (Model-View-Model) mode, users can obtain prediction results simply by uploading a qualified fluorescence image (based on the BSA-AuNCs-GTP-Tb ratiometric fluorescent probe mixture) to the access interface (the system's front-end interface).

[0041] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting pefloxacin using a web-based concentration prediction system, characterized in that: The method for detecting pefloxacin using a web-based concentration prediction system includes the following steps: S1: Synthesis of BSA-AuNCs: Bovine serum albumin (BSA) was placed in a flask washed with aqua regia, chloroauric acid tetrahydrate (HAuCl4·4H2O) was added dropwise and stirred, the pH was adjusted with NaOH, and the mixture was placed in a water / oil bath and stirred to obtain a reddish-brown liquid; after centrifugation and dialysis, it was stored at 4°C for use. S2: Preparation of GTP-Tb: Guanosine-5'-triphosphate (GTP) and terbium nitrate hexahydrate (Tb(NO3)3·6H2O) were dissolved in HEPES buffer, stirred at room temperature and washed with water. After centrifugation, the precipitate was dispersed in HEPES buffer for use. S3: Preparation of BSA-AuNCs-GTP-Tb fluorescent nanoprobes: GTP solution, Tb(NO3)3·6H2O solution and BSA-AuNCs were mixed and stirred. The precipitate was washed once with HEPES buffer solution and then dispersed in HEPES buffer and stored at 4°C for use. S4: Perform fluorescence detection. Place the BSA-AuNCs-GTP-Tb fluorescent probe in a glass cuvette and bring the volume to 2 mL with HEPES buffer solution to stabilize the system. Mix well. Dissolve pefloxacin (PFLX) in 10 mL of deionized water and dilute to different concentration gradients. Add PFLX solution to the stable system and record the corresponding fluorescence spectra. Under a 365 nm UV lamp, the fluorescence color of the fluorescent nanoprobe mixture solution shows a colorful change from red to orange to yellow to green, realizing the visual detection of PFLX. S5: Quantitative detection of pefloxacin based on a web-based system. 70 μL of BSA-AuNCs-GTP-Tb fluorescent probe was placed in a glass cuvette and diluted to a stable 2 mL volume with HEPES buffer solution. Different amounts of pefloxacin solution were added and stirred thoroughly. Fluorescence images under a 365 nm UV lamp were captured using the camera function of a smart device, or the fluorescence change could be recorded using video recording. Video screenshots were used as images for prediction. The smart device accessed the system, and clicking the "Operation interface" option in the list redirected to the concentration prediction interface. The "Select File" and "Start Uploading" buttons enabled image selection and upload. Successfully uploaded image information was visualized in the Table component of the front-end interface. Clicking the "Predict Concentration" button predicted the concentration, and the prediction result was displayed in the "Predict Concentration Value" column of the Table. Users could view and download the results through the system's front-end interface. The development of a web system based on the Django framework, combined with the BSA-AuNCs-GTP-Tb fluorescent nanoprobe, enabled rapid, quantitative detection and batch processing of PFLX. The Django-based web system follows the MTV model, allowing users to easily obtain prediction results simply by uploading qualified fluorescence images. The processing of uploaded images is handled by the system's embedded deep learning algorithm for object detection and various machine learning algorithms.

Images