CN117434045A - Method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning - Google Patents
Method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning Download PDFInfo
- Publication number
- CN117434045A CN117434045A CN202311447153.6A CN202311447153A CN117434045A CN 117434045 A CN117434045 A CN 117434045A CN 202311447153 A CN202311447153 A CN 202311447153A CN 117434045 A CN117434045 A CN 117434045A
- Authority
- CN
- China
- Prior art keywords
- sers
- machine learning
- detection
- competitive
- aptamer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 238000004416 surface enhanced Raman spectroscopy Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000010801 machine learning Methods 0.000 title claims abstract description 27
- 239000000273 veterinary drug Substances 0.000 title claims abstract description 22
- 239000003814 drug Substances 0.000 claims abstract description 61
- 229940079593 drug Drugs 0.000 claims abstract description 56
- 108091023037 Aptamer Proteins 0.000 claims abstract description 46
- 230000002860 competitive effect Effects 0.000 claims abstract description 33
- 239000000523 sample Substances 0.000 claims abstract description 29
- 238000001069 Raman spectroscopy Methods 0.000 claims abstract description 25
- 238000001237 Raman spectrum Methods 0.000 claims abstract description 21
- 238000002156 mixing Methods 0.000 claims abstract description 16
- 239000000243 solution Substances 0.000 claims abstract description 15
- 239000010931 gold Substances 0.000 claims abstract description 13
- 239000011259 mixed solution Substances 0.000 claims abstract description 12
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 claims abstract description 7
- 229910052737 gold Inorganic materials 0.000 claims abstract description 7
- 229910052709 silver Inorganic materials 0.000 claims abstract description 7
- 239000004332 silver Substances 0.000 claims abstract description 7
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims abstract description 6
- 239000007853 buffer solution Substances 0.000 claims abstract description 6
- 239000002105 nanoparticle Substances 0.000 claims abstract description 6
- 229910052710 silicon Inorganic materials 0.000 claims abstract description 6
- 239000010703 silicon Substances 0.000 claims abstract description 6
- 239000011324 bead Substances 0.000 claims abstract description 4
- 230000000295 complement effect Effects 0.000 claims abstract description 4
- 239000002057 nanoflower Substances 0.000 claims abstract description 4
- 238000005406 washing Methods 0.000 claims abstract description 4
- 239000000725 suspension Substances 0.000 claims abstract description 3
- 239000003550 marker Substances 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 7
- 239000002245 particle Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 125000003396 thiol group Chemical group [H]S* 0.000 claims description 4
- 239000000872 buffer Substances 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 239000002086 nanomaterial Substances 0.000 claims description 3
- 238000011534 incubation Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 11
- VOXZDWNPVJITMN-ZBRFXRBCSA-N 17β-estradiol Chemical compound OC1=CC=C2[C@H]3CC[C@](C)([C@H](CC4)O)[C@@H]4[C@@H]3CCC2=C1 VOXZDWNPVJITMN-ZBRFXRBCSA-N 0.000 description 29
- WIIZWVCIJKGZOK-RKDXNWHRSA-N chloramphenicol Chemical compound ClC(Cl)C(=O)N[C@H](CO)[C@H](O)C1=CC=C([N+]([O-])=O)C=C1 WIIZWVCIJKGZOK-RKDXNWHRSA-N 0.000 description 28
- 229960005091 chloramphenicol Drugs 0.000 description 28
- 229960005309 estradiol Drugs 0.000 description 28
- 229930182833 estradiol Natural products 0.000 description 28
- 238000012549 training Methods 0.000 description 13
- 238000007637 random forest analysis Methods 0.000 description 7
- 235000013305 food Nutrition 0.000 description 6
- 238000012417 linear regression Methods 0.000 description 6
- 238000010200 validation analysis Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000011664 signaling Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- LMJXSOYPAOSIPZ-UHFFFAOYSA-N 4-sulfanylbenzoic acid Chemical compound OC(=O)C1=CC=C(S)C=C1 LMJXSOYPAOSIPZ-UHFFFAOYSA-N 0.000 description 3
- 230000005684 electric field Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- KIUMMUBSPKGMOY-UHFFFAOYSA-N 3,3'-Dithiobis(6-nitrobenzoic acid) Chemical compound C1=C([N+]([O-])=O)C(C(=O)O)=CC(SSC=2C=C(C(=CC=2)[N+]([O-])=O)C(O)=O)=C1 KIUMMUBSPKGMOY-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 239000003640 drug residue Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000001000 micrograph Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- KIUMMUBSPKGMOY-UHFFFAOYSA-L 5-[(3-carboxylato-4-nitrophenyl)disulfanyl]-2-nitrobenzoate Chemical compound C1=C([N+]([O-])=O)C(C(=O)[O-])=CC(SSC=2C=C(C(=CC=2)[N+]([O-])=O)C([O-])=O)=C1 KIUMMUBSPKGMOY-UHFFFAOYSA-L 0.000 description 1
- 229910017745 AgNP Inorganic materials 0.000 description 1
- 208000031295 Animal disease Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000037037 animal physiology Effects 0.000 description 1
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007636 ensemble learning method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004128 high performance liquid chromatography Methods 0.000 description 1
- 238000000589 high-performance liquid chromatography-mass spectrometry Methods 0.000 description 1
- 229940088597 hormone Drugs 0.000 description 1
- 239000005556 hormone Substances 0.000 description 1
- 238000003317 immunochromatography Methods 0.000 description 1
- 238000007885 magnetic separation Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910000510 noble metal Inorganic materials 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000003053 toxin Substances 0.000 description 1
- 231100000765 toxin Toxicity 0.000 description 1
- 108700012359 toxins Proteins 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
- G01N21/658—Raman scattering enhancement Raman, e.g. surface plasmons
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/50—Molecular design, e.g. of drugs
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Crystallography & Structural Chemistry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Medicinal Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Pharmacology & Pharmacy (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention is applicable to the technical field of Raman spectrum detection, and provides a method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning, which comprises the following steps: modifying Raman reporter molecules inside silver-coated gold nanoparticles, modifying drug aptamers on the surfaces, taking Jin Baoci bead nanoflower with modified aptamer complementary chains as a capture probe, constructing a competitive SERS aptamer sensor aiming at different drugs, and uniformly mixing the competitive SERS aptamer sensors in a ratio of 1:1; preparing mixed solution containing two medicines with different concentrations; then uniformly mixing the drug mixed solution with the competitive SERS aptamer sensor of the two drugs, incubating, magnetically separating, washing and re-suspending in PBS buffer solution; dripping the heavy suspension on the surface of a silicon wafer, collecting Raman spectrum, preprocessing the Raman spectrum, and establishing a machine learning model; and finally, testing the contents of the two medicaments in the solution to be tested by using the established prediction model. The detection method improves the efficiency and accuracy of the competitive SERS aptamer sensor for simultaneously detecting two medicaments.
Description
Technical Field
The invention relates to the technical field of Raman spectrum detection, in particular to a method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning.
Background
Veterinary drugs are commonly used in the animal husbandry and aquaculture industries to prevent, treat animal diseases or purposefully modulate animal physiology. In recent years, diseases in the cultivation process are increasingly serious along with the continuous expansion of cultivation scale and continuous improvement of intensification level. In order to improve economic benefit, a plurality of veterinary drugs are often used in excess in the cultivation process, and even forbidden drugs are abused, so that drug residues are formed due to incomplete accumulation or metabolism in organisms, great harm is caused to health of consumers, and rapid detection of the veterinary drug residues is an important way for guaranteeing food safety.
The veterinary drug detection method is mostly based on high performance liquid chromatography, high performance liquid chromatography-mass spectrometry and other instrument detection methods, but the instruments used by the detection methods are expensive, the detection process is complicated, the time consumption is long, and the detection method is required to be operated by a professional and is not suitable for on-site rapid screening of a large number of samples. The colloidal gold immunochromatography test strip is a rapid detection method for veterinary drug residues, which is commonly used in recent years, and the method is suitable for on-site rapid screening of a large number of samples, but has low detection sensitivity, high false positive/false negative rate and high interference caused by solvents and food matrixes, so that the establishment of a high-throughput, high-sensitivity and on-site rapid detection method for veterinary drug residues has urgent requirements.
Surface Enhanced Raman Spectroscopy (SERS) is a powerful molecular vibration spectroscopy technique that utilizes the greatly enhanced effect of noble metal surface nanostructures such as gold and silver on raman scattering to enable extremely high sensitivity detection of surface-adsorbed molecules. SERS has high sensitivity, high detection speed, flexible and convenient detection, and can provide information such as molecular "fingerprint" patterns, and in recent years, great attention has been paid to applications in fields such as chemical and biological sensing, material science, medical diagnosis, food safety, and the like. The detection mode of SERS can be classified into a non-labeling detection method based on a characteristic peak of a target, and a labeling detection method based on a raman probe molecule. By combining with target specific recognition elements such as an aptamer, an antibody and the like, the SERS label detection can realize ultra-high-sensitivity detection of the target. The competitive SERS aptamer sensor is a typical SERS labeling detection mode, is currently used for detecting various food risk factors such as agricultural and veterinary drugs, hormones, toxins, microorganisms and the like, and obtains better results. Although competitive SERS aptamer sensors have good performance in detecting one drug, detection efficiency is low, failing to meet rapid screening of large batches of samples. Meanwhile, the simultaneous and rapid detection of two or more drugs is an urgent need for food safety detection, however, when the competitive SERS aptamer sensor is used for simultaneously detecting the two drugs, signal probes of different drugs in a reaction system can interfere with each other, so that the distribution of Raman 'hot spots' of the whole system is affected, and the content of the two drugs cannot be accurately and quantitatively detected. The problem that a plurality of Raman signal probes in the same system are mutually interfered reduces the efficiency and accuracy of the competitive SERS aptamer sensor for simultaneously detecting multiple targets.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides a method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman scattering) marker detection and machine learning.
The invention is realized by the following technical scheme: a method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning specifically comprises the following steps:
s1: silver-coated gold nano particles (Au@AgNPs) for modifying drug aptamer are used as signal probes, and Jin Baoci bead nanoflower (Fe 3 O 4 @AuNFs) as a capture probe, uniformly mixing a signal probe and the capture probe, and incubating at 37 ℃ to obtain a competitive SERS aptamer sensor for a single drug; needle in step S1Modifying different Raman reporter molecules on the surface of gold cores of different drugs, wherein characteristic peaks of the different Raman reporter molecules are not overlapped;
s2: uniformly mixing competitive SERS aptamer sensors aiming at different medicines in S1, and incubating at 37 ℃ for 8 hours to obtain the competitive SERS aptamer sensor capable of detecting two medicines simultaneously;
s3: mixing the two drug solutions to be tested according to different proportions to obtain drug mixed solutions with different concentrations;
s4: uniformly mixing the drug mixed solution in the S3 and the competitive SERS aptamer sensor in the S2, incubating for 1 hour at 37 ℃, separating by a magnet, washing 3 times by using PBS buffer solution, and re-suspending in 15 mu L of PBS buffer solution;
s5: dripping the heavy suspension in the step S4 on the surface of a silicon wafer, aligning a Raman probe to the surface of the solution, collecting Raman spectra of the solution, preprocessing the Raman spectra, taking the collected Raman spectra of N medicine mixed solutions with different concentrations as a database, and establishing a machine learning model;
s6: and predicting the contents of the two medicines in the solution to be detected by using the machine learning model established in the step S5.
As a preferable scheme, the gold core of the silver-coated gold nano particle in the step S1 can be spherical, rod-shaped, regular polyhedron, star-shaped and other shapes, the particle size of Au@AgNPs is 30-60 nm, and Fe 3 O 4 The particle size of the @ AuNFs is 200-500 nm, and the aptamer of the drug and the complementary strand thereof modify sulfhydryl groups at the 5' end, and the aptamer is connected to the surface of a nano material through the sulfhydryl groups, and the incubation time of a signal probe and a capture probe is 1-2 hours;
as a preferred solution, the mixing ratio of the competitive SERS aptamer sensor for the two drugs in step S2 is 1:1.
As a preferable scheme, the concentration range of the two drugs in the step S3 is 0.001-1000 mug/L, and the two drug mixed solution for modeling contains different concentration combinations as much as possible.
As a preferable scheme, in the step S4, the volume ratio of the drug mixed solution to the competitive SERS aptamer sensor is 1:1, the pH of the PBS buffer solution is 7.4, and the concentration is 10 mM.
As a preferable scheme, the solution amount dropwise added on the surface of the silicon wafer in the step S5 is set to be 5-10 mu L, and a 785 nm wavelength laser is used for acquiring a Raman spectrum, wherein the detection range is 400-3200 cm -1 Number of spectra N>100。
As a preferred scheme, the preprocessing of the raman spectrum in step S5 includes baseline correction and smoothing filtering, and performs max-min normalization processing on a spectrum interval including a characteristic peak of a signal molecule, and then builds a machine learning model by using a PyTorch framework.
Preferably, after the model prediction in step S5 is completed, an inverse normalization process is performed to obtain an actual concentration value, and the test data set is used to further evaluate the performance thereof.
The invention adopts the technical proposal, and compared with the prior art, the invention has the following beneficial effects: the invention provides a novel, quick, simple, convenient, sensitive and accurate method for simultaneously detecting two drug residues, which constructs a competitive SERS aptamer sensor based on silver-coated gold nano particles and Jin Baoci bead nanoflower materials, and utilizes a magnet to carry out quick magnetic separation on a SERS substrate, thereby simplifying experimental operation steps; the constructed competitive SERS aptamer sensor can realize simultaneous and rapid detection of two targets, and the accuracy of simultaneous detection of the two targets is further improved by combining a machine learning method with competitive aptamer detection; by changing the aptamer and the Raman signal molecule, the detection mode can be expanded to three or even more target objects and simultaneously high-sensitivity detection is realized, and the detection method has important development significance for improving the detection efficiency of various medicine residues in foods and environments.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
fig. 1: (a) Fe (Fe) 3 O 4 An AuNFs transmission electron microscope image, (b) an Au@AgNP transmission electron microscope image
FIG. 2 evaluation of artificial neural network model performance of chloramphenicol and estradiol: (a-d) R for training, validating, testing and ensemble data sets, respectively 2 Values, (e) histogram of actual and predicted values of chloramphenicol, (f) histogram of actual and predicted values of estradiol, (g) model training loss and validation loss
FIG. 3 evaluation of the random forest model properties of chloramphenicol and estradiol: (a-c) R for training, testing, and validating sets, respectively 2 A histogram of actual and predicted values of (d) chloramphenicol (e), and of actual and predicted values of estradiol (e)
Fig. 4: quantitative model of chloramphenicol and estradiol: (a) Raman spectra of different chloramphenicol concentrations at estradiol concentration of 0.01 μg/L, (b) 1075cm -1 Regression curve for chloramphenicol quantification at displacement, (c) Raman spectra of different estradiol concentrations at a chloramphenicol concentration of 0.01. Mu.g/L, (d) 1330cm -1 Regression curve for estradiol quantification at displacement
Fig. 5: the time domain finite difference method theory simulates the raman hotspot change rule of the competitive SERS aptamer sensor: (a) xy view of model without drug addition, (b) xy view of model after drug addition, (c) electric field simulation result of model without drug addition, (d) electric field simulation result of model after drug addition
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
The method for simultaneous detection of two veterinary drugs based on SERS marker detection and machine learning according to the embodiment of the present invention will be specifically described with reference to fig. 1 to 5.
Example 1:
the embodiment provides a method for simultaneously detecting chloramphenicol and estradiol based on a competitive SERS aptamer sensor and an artificial neural network, which comprises the following steps:
s1: spherical Au@AgNPs (shown in FIG. 1 a) with particle diameters of about 40nm for modifying chloramphenicol and estradiol aptamers are used as signal probes, and Fe with particle diameters of about 300nm for modifying the complementary strands of chloramphenicol and estradiol aptamers 3 O 4 AuNFs (shown in FIG. 1 b) as capture probes, and signaling probes for chloramphenicol and estradiol modify 4-mercaptobenzoic acid and 5,5' -dithiobis (2-nitrobenzoic acid), respectively, as Raman reporter molecules; uniformly mixing a signal probe and a capture probe, and incubating for 1h at 37 ℃ to obtain a competitive SERS aptamer sensor aiming at a specific drug;
s2: uniformly mixing the competitive SERS aptamer sensor aiming at chloramphenicol and estradiol in the S1 in a ratio of 1:1, and incubating at 37 ℃ for 8 hours to obtain the competitive SERS aptamer sensor capable of simultaneously detecting chloramphenicol and estradiol;
s3: mixing two drug solutions of chloramphenicol and estradiol with the concentration range of 0.001-1000 mug/L according to different proportions, wherein the proportion of chloramphenicol and estradiol in the mixed solution is chloramphenicol (mug/L): estradiol (mug/L) =100: 500. 80:6200, 100:2000, 0.1:700, 50:50, 50:400, 300:700, 20:600, 0.01:0.01, 10: 800. 5:200, 10:100, 100:300, 10:10, 1:500, 5:100, 1:1200, 0.1:400, 1200:10, 10:10, 1:500, 60:130, 50:300, 5:50, 1:1, 20:200, 60:130, 1200:20, 5:5, 50:0.05, 70:80, 100:700, 10:400, 20:1000, 4300:1500, 1220:1500, 2000:3200, 2000:10000, 1500:3200, 3000:1800, 30:200, 130:1500, 120:80, 500:3300, 300:100, 1:100, 10:60, 1000:100, 1000:1000, to obtain pharmaceutical mixtures containing different concentrations of chloramphenicol and estradiol;
s4: mixing the drug mixture in S3 and the competitive SERS aptamer sensor of the two drugs in S2 uniformly in a ratio of 1:1, incubating for 1h at 37 ℃, then separating by a magnet, washing 3 times by using PBS buffer, and then re-suspending in 15 mu L of PBS buffer (pH=7.4) with a concentration of 10 mM;
s5: and (3) dropwise adding 5 mu L of the resuspension in S4 on the surface of a silicon wafer, aligning a Raman probe to the surface of the solution, collecting Raman spectra of the solution, preprocessing the Raman spectra, and taking the collected Raman spectra of 279 different-concentration drug mixed solutions as a database for establishing a machine learning model. The machine learning model adopted in the embodiment is an artificial neural network model, and the specific modeling process is as follows:
(1) Data preprocessing: the Raman spectrum is first subjected to baseline correction and smoothing filtering pretreatment, and then the spectrum interval is 1000-1400 cm -1 The peak of (2) is subjected to maximum-minimum normalization to ensure that all characteristic values are 0, 1]Within the range of (2), the normalization formula is as follows:
(1)
wherein the minimum and maximum values in the formula (1) are the minimum and maximum values of the feature, respectively.
(2) Model construction and configuration: and establishing an artificial neural network model by using a PyTorch framework. The architecture of the model includes several fully connected layers with interposed activation functions between the layers to increase the nonlinear expression capabilities of the network. Specifically, the input layer contains 400 nodes, corresponding to the number of features of the data. The model contains four hidden layers, 312, 144, 72 and 36 nodes respectively. Each layer is followed by a LeakyReLU activation function. The final layer has two nodes for predicting the concentration of the two chemicals.
(3) Training parameters and process: the Mean Square Error (MSE) is chosen as the loss function of the error, and the error back propagation and weight adjustment are performed by a random gradient descent (SGD) algorithm (momentum 0.9, learning rate 0.001). The dataset was divided into 70% training data, 15% validation data, and 15% test data. The model was run through 500 training iterations. To prevent overfitting, an early stop endurance value of 20 iterations was set by monitoring the validation loss.
(4) Model predictive ability assessment: after training is completed, the R-value is used to evaluate model predictive capability on the test set. As shown in fig. 2, the R-scores for training, validation, testing and global data sets were 0.959, 0.991, 0.976 and 0.970, respectively, and the loss trace during training showed effective learning without significant overfitting, demonstrating that the method performed well for predicting both drug levels simultaneously. All calculations were performed in a Python 3.8 environment using the TensorFlow 2.X framework.
S6: and predicting the contents of the two medicines in the sample to be detected by using the machine learning model established in the step S5, performing inverse normalization processing to obtain an actual concentration value, and qualitatively evaluating the accuracy of the model by comparing the predicted concentration value and the actual value of the test set, wherein the predicted value and the actual value have good consistency and the average absolute error is 244 mug/L as shown in the figure 2.
Example 2
The embodiment provides a method for simultaneously detecting chloramphenicol and estradiol based on a competitive SERS aptamer sensor and a random forest model, which has the detection steps similar to those of embodiment 1, wherein the machine learning model is a random forest model, and the specific modeling process is as follows:
(1) Data preprocessing: the Raman spectrum baseline is firstly corrected and smoothed and filtered, and then the spectrum interval of 1000-1400 cm is adopted -1 The peak of (2) is subjected to maximum-minimum normalization to ensure that all characteristic values are 0, 1]Within a range of (2).
(2) Model construction: random forests are chosen, which is an ensemble learning method by building multiple decision trees and integrating their outputs to generate the final prediction result.
(3) Multiple output regression processing: in order to be able to deal with the multiple output regression problem, the random forest model is packaged with a MultiOutputRaegressor, ensuring that the model can provide predictions for multiple target variables.
(3) Model parameters and training: the random forest model is built based on 100 decision trees, the trees are trained on different data subsets respectively, and the strategy of randomly selecting data increases the diversity of the model, so that the generalization performance of the model is improved.
(4) Performance evaluation: after training is completed, the model performance on the training, validation and test dataset is evaluated using R. As shown in fig. 3, R on the training, validation, and test datasets were 0.959, 0.580, and 0.796, respectively. It follows that the model exhibits a more robust performance. In order to further verify the accuracy of the model, 10 specific samples are selected for concentration prediction, and the matching degree between the predicted value and the actual value is good. The embodiment shows that the random forest as an integrated learning method can be combined with a competitive SERS aptamer sensor to realize simultaneous detection of two drugs, but the detection performance is slightly poorer than that of an artificial neural network.
Example 3
The embodiment provides a method for detecting chloramphenicol and estradiol based on a competitive SERS aptamer sensor, which has the same detection steps as those of embodiment 1, and is different in that the used model is a linear model established through raman characteristic peak intensity, and the specific modeling process is as follows:
(1) And (3) spectrum data acquisition: the preparation process of the material is the same as steps S1 and S2 of example 1. In the detection system, the amount of estradiol added was fixed at 0.01. Mu.g/L, and the amounts of chloramphenicol added were 0.001. Mu.g/L, 0.01. Mu.g/L, 0.1. Mu.g/L, 1. Mu.g/L, 10. Mu.g/L, 100. Mu.g/L, and 1000. Mu.g/L, respectively. Similarly, the amount of chloramphenicol added was fixed at 0.01. Mu.g/L, and the amount of estradiol added was 0.001. Mu.g/L, 0.01. Mu.g/L, 0.1. Mu.g/L, 1. Mu.g/L, 10. Mu.g/L, 100. Mu.g/L, and 1000. Mu.g/L, respectively. SERS detection conditions were the same as in example 1.
(2) And (3) establishing a model: for chloramphenicol detection, 4-mercaptobenzoic acid was selected to be at 1075cm -1 And (3) carrying out linear regression detection on chloramphenicol by the Raman characteristic peak intensity. For estradiol detection, 5' -dithiobis (2-nitrobenzoic acid) at 1330cm was selected -1 And (3) carrying out linear regression detection on the estradiol by the Raman characteristic peak intensity.
As shown in FIG. 4, when the content of estradiol is fixed and the content of chloramphenicol is different, the Raman signal intensity of the Raman reporter molecule 5,5' -dithiobis (2-nitrobenzoic acid) for detecting the estradiol is greatly different, and the chloramphenicol is quantitatively analyzed, so that the correlation coefficient of linear regression is only 0.6763. Similarly, when the chloramphenicol content is fixed and the estradiol content is different, the raman signal intensity of the raman reporter molecule 4-mercaptobenzoic acid for detecting chloramphenicol has a large difference, and the quantitative analysis is carried out on the estradiol, and the correlation coefficient of linear regression is only 0.8146. The result shows that the two compounds are detected simultaneously by adopting the traditional linear regression model, and the detection accuracy is poor.
Example 4
In this embodiment, the change rule of raman "hot spot" of the competitive SERS aptamer sensor after adding the drug molecule is simulated by the finite difference method theory in the time domain, as shown in fig. 5, and (a) and (b) are xy sectional views of the model constructed before and after adding the drug respectively. (c) And (d) is the electric field simulation result of the model before and after drug addition, wherein the color scale from deep to shallow represents how much of the raman "hot spot" is. From the simulation results, it can be seen that the signaling probe and capture probe bind when no drug is added, at which time the raman "hot spot" is highest. However, when one of the drugs is added, the originally bound signaling and capture probes dissociate due to the specific recognition of the aptamer, resulting in a reduction of the overall raman "hot spot" in the system. Thus, the raman signals of the two signaling probes in the detection system will be affected. In an actual detection environment, the contents of the two medicines are unknown, so that the two medicines cannot be accurately and quantitatively analyzed simultaneously by using a traditional linear regression model.
In the description of the present specification, the terms "one embodiment," "some embodiments," "particular embodiments," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The method for simultaneously detecting two veterinary drugs based on SERS marker detection and machine learning is characterized by comprising the following steps of:
s1: silver-coated gold nano particles (Au@AgNPs) for modifying drug aptamer are used as signal probes, and Jin Baoci bead nanoflower (Fe 3 O 4 @AuNFs) as a capture probe, uniformly mixing a signal probe and the capture probe, and incubating at 37 ℃ to obtain a competitive SERS aptamer sensor for a single drug;
s2: uniformly mixing competitive SERS aptamer sensors aiming at different medicines in S1, and incubating at 37 ℃ for 8 hours to obtain the competitive SERS aptamer sensor capable of detecting two medicines simultaneously;
s3: mixing the two drug solutions to be tested according to different proportions to obtain drug mixed solutions with different concentrations;
s4: uniformly mixing the drug mixed solution in the S3 and the competitive SERS aptamer sensor in the S2, incubating for 1 hour at 37 ℃, separating by a magnet, washing 3 times by using PBS buffer solution, and re-suspending in 15 mu L of PBS buffer solution;
s5: dripping the heavy suspension in the step S4 on the surface of a silicon wafer, aligning a Raman probe to the surface of the solution, collecting Raman spectra of the solution, preprocessing the Raman spectra, taking the collected Raman spectra of N medicine mixed solutions with different concentrations as a database, and establishing a machine learning model;
s6: and predicting the contents of the two medicines in the solution to be detected by using the machine learning model established in the step S5.
2. The method for simultaneous detection of two veterinary drugs based on SERS label detection and machine learning according to claim 1, wherein the gold core of the silver-coated gold nanoparticle in the step S1 can be spherical, rod-like, regular polyhedron, star-like, etc., the particle size of Au@AgNPs is 30-60 nm, fe 3 O 4 The particle size of the @ AuNFs is 200-500 nm, the aptamer of the drug and the complementary strand thereof modify sulfhydryl groups at the 5' end, the aptamer is connected to the surface of the nano material through the sulfhydryl groups, and the incubation time of the signal probe and the capture probe is 1-2 hours.
3. The method for simultaneous detection of two veterinary drugs based on SERS marker detection and machine learning according to claim 1, wherein the competitive SERS aptamer sensor mixing ratio of the two drugs is 1:1.
4. The method for simultaneous detection of two veterinary drugs based on SERS marker detection and machine learning according to claim 1, wherein the concentration range of the two drugs in the step S3 is 0.001 to 1000 μg/L.
5. The method for simultaneous detection of two veterinary drugs based on SERS marker detection and machine learning according to claim 1, wherein the volume ratio of the drug mixture to the competitive SERS aptamer sensor in step S4 is 1:1, the pH of the pbs buffer is 7.4, and the concentration is 10 mM.
6. The method for simultaneous detection of two veterinary drugs based on SERS marker detection and machine learning according to claim 1, wherein the amount of solution dropped on the surface of the silicon wafer in step S5 is defined to be 5 to 10 μl, and a 785 nm wavelength laser is used to obtain raman spectrum, the detection range of which is 400 to 3200 cm -1 Number of spectra N>100。
7. The method for simultaneous detection of two veterinary drugs based on SERS marker detection and machine learning according to claim 1, wherein the preprocessing of raman spectrum in step S5 comprises baseline correction and smoothing filtering, and performing max-min normalization processing on spectrum intervals containing characteristic peaks of signal molecules, and then using a PyTorch frame to build a machine learning model.
8. A method for simultaneous detection of two veterinary drugs based on SERS marker detection and machine learning according to claim 1, wherein after the model prediction in step S5 is completed, an inverse normalization process is performed to obtain an actual concentration value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311447153.6A CN117434045B (en) | 2023-11-02 | 2023-11-02 | Method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311447153.6A CN117434045B (en) | 2023-11-02 | 2023-11-02 | Method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117434045A true CN117434045A (en) | 2024-01-23 |
| CN117434045B CN117434045B (en) | 2024-07-19 |
Family
ID=89547783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311447153.6A Active CN117434045B (en) | 2023-11-02 | 2023-11-02 | Method for simultaneously detecting two veterinary drugs based on SERS (surface enhanced Raman Scattering) mark detection and machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117434045B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022108218A1 (en) * | 2020-11-23 | 2022-05-27 | 고려대학교 산학협력단 | Method for detecting biomaterial using magnetic microparticles and surface-enhanced raman signals |
| CN114739976A (en) * | 2022-04-12 | 2022-07-12 | 海南医学院 | SERS probe biosensor and preparation method and application method thereof |
| CN114859036A (en) * | 2022-04-06 | 2022-08-05 | 中国计量大学 | Preparation of pesticide and veterinary drug residue multi-target nano enzyme probe and visual rapid detection system and method |
| CN115236057A (en) * | 2022-06-21 | 2022-10-25 | 新疆师范大学 | Method for simultaneously detecting three pathogenic bacteria based on lectin and aptamer dual recognition |
| CN116067937A (en) * | 2022-07-14 | 2023-05-05 | 宁海县浙工大科学技术研究院 | SERS aptamer sensor based on core-shell nano assembly structure and preparation and application thereof |
| CN116858822A (en) * | 2023-08-24 | 2023-10-10 | 广东工业大学 | Quantitative analysis method for sulfadiazine in water based on machine learning and Raman spectrum |
-
2023
- 2023-11-02 CN CN202311447153.6A patent/CN117434045B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022108218A1 (en) * | 2020-11-23 | 2022-05-27 | 고려대학교 산학협력단 | Method for detecting biomaterial using magnetic microparticles and surface-enhanced raman signals |
| CN114859036A (en) * | 2022-04-06 | 2022-08-05 | 中国计量大学 | Preparation of pesticide and veterinary drug residue multi-target nano enzyme probe and visual rapid detection system and method |
| CN114739976A (en) * | 2022-04-12 | 2022-07-12 | 海南医学院 | SERS probe biosensor and preparation method and application method thereof |
| CN115236057A (en) * | 2022-06-21 | 2022-10-25 | 新疆师范大学 | Method for simultaneously detecting three pathogenic bacteria based on lectin and aptamer dual recognition |
| CN116067937A (en) * | 2022-07-14 | 2023-05-05 | 宁海县浙工大科学技术研究院 | SERS aptamer sensor based on core-shell nano assembly structure and preparation and application thereof |
| CN116858822A (en) * | 2023-08-24 | 2023-10-10 | 广东工业大学 | Quantitative analysis method for sulfadiazine in water based on machine learning and Raman spectrum |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117434045B (en) | 2024-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Surface‐enhanced Raman spectroscopy for the chemical analysis of food | |
| Askim et al. | Optical sensor arrays for chemical sensing: the optoelectronic nose | |
| Jia et al. | Machine vision-based colorimetric sensor systems for food applications | |
| Liu et al. | Exciton energy transfer-based quantum dot fluorescence sensing array:“chemical noses” for discrimination of different nucleobases | |
| Bräuer et al. | Biomimetic sensors to detect bioanalytes in real-life samples using molecularly imprinted polymers: a review | |
| Zhao et al. | A portable and automatic dual-readout detector integrated with 3D-printed microfluidic nanosensors for rapid carbamate pesticides detection | |
| Wei et al. | Fabrication of conducting polymer/noble metal nanocomposite modified electrodes for glucose, ascorbic acid and tyrosine detection and its application to identify the marked ages of rice wines | |
| McLamore et al. | FEAST of biosensors: Food, environmental and agricultural sensing technologies (FEAST) in North America | |
| Xu et al. | Machine learning assisted dual-emission fluorescence/colorimetric sensor array detection of multiple antibiotics under stepwise prediction strategy | |
| Sheini et al. | A chemosensor array for the colorimetric identification of some carboxylic acids in human urine samples | |
| Suah et al. | Optimisation of the range of an optical fibre pH sensor using feed-forward artificial neural network | |
| Wei et al. | Biosensors for detection of paralytic shellfish toxins: Recognition elements and transduction technologies | |
| Lowdon et al. | A molecularly imprinted polymer-based dye displacement assay for the rapid visual detection of amphetamine in urine | |
| Zhang et al. | Fluorimetric identification of sulfonamides by carbon dots embedded photonic crystal molecularly imprinted sensor array | |
| CN106596490B (en) | The supermolecule sensor array and method of synchronous detection paraquat and diquat dibromide | |
| Jiang et al. | Determination of tetracyclines in milk with a molecularly imprinted polymer-based microtiter chemiluminescence sensor | |
| Abbasi-Moayed et al. | Multiplex Detection of Biogenic Amines for Meat Freshness Monitoring Using Nanoplasmonic Colorimetric Sensor Array | |
| Liang et al. | [Retracted] A Review of Detection of Antibiotic Residues in Food by Surface‐Enhanced Raman Spectroscopy | |
| Guo et al. | Flexible Au@ AgNRs/MAA/PDMS-based SERS sensor coupled with intelligent algorithms for in-situ detection of thiram on apple | |
| Zhou et al. | Machine-learning-driven optical immunosensor based on microspheres-encoded signal transduction for the rapid and multiplexed detection of antibiotics in milk | |
| Yu et al. | Multivariate chemical analysis: From sensors to sensor arrays | |
| Li et al. | Machine learning-assisted fluorescence sensor array for qualitative and quantitative analysis of pyrethroid pesticides | |
| Li et al. | SERS-activated platforms for chemical contaminants in food: Probes, encoding methods, and detection | |
| Fargher et al. | Pushing Differential Sensing Further: The Next Steps in Design and Analysis of Bio‐Inspired Cross‐Reactive Arrays | |
| Basabe-Desmonts et al. | Cross-reactive sensor array for metal ion sensing based on fluorescent SAMs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |