CN116500263A - Method and system for detecting food-borne disease pathogens based on microfluidics - Google Patents
Method and system for detecting food-borne disease pathogens based on microfluidics Download PDFInfo
- Publication number
- CN116500263A CN116500263A CN202310511188.5A CN202310511188A CN116500263A CN 116500263 A CN116500263 A CN 116500263A CN 202310511188 A CN202310511188 A CN 202310511188A CN 116500263 A CN116500263 A CN 116500263A
- Authority
- CN
- China
- Prior art keywords
- pathogen
- sample
- food
- target
- mass spectrum
- 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.)
- Pending
Links
- 244000052769 pathogen Species 0.000 title claims abstract description 783
- 238000000034 method Methods 0.000 title claims abstract description 47
- 208000019331 Foodborne disease Diseases 0.000 title claims abstract description 37
- 230000001717 pathogenic effect Effects 0.000 claims abstract description 748
- 238000001819 mass spectrum Methods 0.000 claims abstract description 126
- 235000013305 food Nutrition 0.000 claims abstract description 123
- 238000001514 detection method Methods 0.000 claims abstract description 65
- 238000005070 sampling Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000001917 fluorescence detection Methods 0.000 claims abstract description 14
- 239000000523 sample Substances 0.000 claims description 137
- 239000012468 concentrated sample Substances 0.000 claims description 49
- 238000009826 distribution Methods 0.000 claims description 46
- 238000012986 modification Methods 0.000 claims description 19
- 230000004048 modification Effects 0.000 claims description 19
- 238000000926 separation method Methods 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 19
- 239000012535 impurity Substances 0.000 claims description 16
- 238000000354 decomposition reaction Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 15
- 239000012530 fluid Substances 0.000 claims description 15
- 239000012528 membrane Substances 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 14
- 239000000243 solution Substances 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000000295 complement effect Effects 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 9
- 238000004925 denaturation Methods 0.000 claims description 7
- 230000036425 denaturation Effects 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims description 6
- 238000007385 chemical modification Methods 0.000 claims description 6
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000005119 centrifugation Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000000137 annealing Methods 0.000 claims description 4
- 230000006037 cell lysis Effects 0.000 claims description 4
- 230000009089 cytolysis Effects 0.000 claims description 4
- 239000007850 fluorescent dye Substances 0.000 claims description 4
- 230000001172 regenerating effect Effects 0.000 claims description 4
- 239000012898 sample dilution Substances 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000002791 soaking Methods 0.000 claims description 4
- 238000000108 ultra-filtration Methods 0.000 claims description 4
- 238000005336 cracking Methods 0.000 claims description 3
- 238000009396 hybridization Methods 0.000 claims description 3
- 238000004949 mass spectrometry Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000003213 activating effect Effects 0.000 claims description 2
- 244000078673 foodborn pathogen Species 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 11
- 230000000007 visual effect Effects 0.000 description 5
- 108020004414 DNA Proteins 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 239000004952 Polyamide Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 229920002647 polyamide Polymers 0.000 description 3
- 239000003053 toxin Substances 0.000 description 3
- 231100000765 toxin Toxicity 0.000 description 3
- 108700012359 toxins Proteins 0.000 description 3
- 241000894006 Bacteria Species 0.000 description 2
- HEDRZPFGACZZDS-UHFFFAOYSA-N Chloroform Chemical compound ClC(Cl)Cl HEDRZPFGACZZDS-UHFFFAOYSA-N 0.000 description 2
- RTZKZFJDLAIYFH-UHFFFAOYSA-N Diethyl ether Chemical compound CCOCC RTZKZFJDLAIYFH-UHFFFAOYSA-N 0.000 description 2
- 241000233866 Fungi Species 0.000 description 2
- 239000004695 Polyether sulfone Substances 0.000 description 2
- 239000004743 Polypropylene Substances 0.000 description 2
- 239000007984 Tris EDTA buffer Substances 0.000 description 2
- 241000700605 Viruses Species 0.000 description 2
- 239000000872 buffer Substances 0.000 description 2
- 229920002678 cellulose Polymers 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 244000000010 microbial pathogen Species 0.000 description 2
- 244000045947 parasite Species 0.000 description 2
- 239000002953 phosphate buffered saline Substances 0.000 description 2
- 229920006393 polyether sulfone Polymers 0.000 description 2
- -1 polypropylene Polymers 0.000 description 2
- 229920001155 polypropylene Polymers 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 108091032973 (ribonucleotides)n+m Proteins 0.000 description 1
- QKNYBSVHEMOAJP-UHFFFAOYSA-N 2-amino-2-(hydroxymethyl)propane-1,3-diol;hydron;chloride Chemical compound Cl.OCC(N)(CO)CO QKNYBSVHEMOAJP-UHFFFAOYSA-N 0.000 description 1
- 241000251468 Actinopterygii Species 0.000 description 1
- 241000228212 Aspergillus Species 0.000 description 1
- 241000223935 Cryptosporidium Species 0.000 description 1
- 102000053602 DNA Human genes 0.000 description 1
- 241000588724 Escherichia coli Species 0.000 description 1
- 206010016952 Food poisoning Diseases 0.000 description 1
- 231100000678 Mycotoxin Toxicity 0.000 description 1
- 241001263478 Norovirus Species 0.000 description 1
- 108091034117 Oligonucleotide Proteins 0.000 description 1
- 108010002747 Pfu DNA polymerase Proteins 0.000 description 1
- ISWSIDIOOBJBQZ-UHFFFAOYSA-N Phenol Chemical compound OC1=CC=CC=C1 ISWSIDIOOBJBQZ-UHFFFAOYSA-N 0.000 description 1
- 241000702670 Rotavirus Species 0.000 description 1
- 241000607142 Salmonella Species 0.000 description 1
- 108020004682 Single-Stranded DNA Proteins 0.000 description 1
- 241000295644 Staphylococcaceae Species 0.000 description 1
- 241000191967 Staphylococcus aureus Species 0.000 description 1
- 229920002472 Starch Polymers 0.000 description 1
- 108010006785 Taq Polymerase Proteins 0.000 description 1
- 241000223996 Toxoplasma Species 0.000 description 1
- 241000224526 Trichomonas Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000001913 cellulose Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012136 culture method Methods 0.000 description 1
- 235000013365 dairy product Nutrition 0.000 description 1
- LOKCTEFSRHRXRJ-UHFFFAOYSA-I dipotassium trisodium dihydrogen phosphate hydrogen phosphate dichloride Chemical compound P(=O)(O)(O)[O-].[K+].P(=O)(O)([O-])[O-].[Na+].[Na+].[Cl-].[K+].[Cl-].[Na+] LOKCTEFSRHRXRJ-UHFFFAOYSA-I 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003365 glass fiber Substances 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000003068 molecular probe Substances 0.000 description 1
- 239000002636 mycotoxin Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 229920002492 poly(sulfone) Polymers 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 229920006295 polythiol Polymers 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 235000014102 seafood Nutrition 0.000 description 1
- 239000000238 shellfish toxin Substances 0.000 description 1
- 239000008107 starch Substances 0.000 description 1
- 235000019698 starch Nutrition 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 235000021404 traditional food Nutrition 0.000 description 1
- 241000701161 unidentified adenovirus Species 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
- B01L3/00—Containers or dishes for laboratory use, e.g. laboratory glassware; Droppers
- B01L3/50—Containers for the purpose of retaining a material to be analysed, e.g. test tubes
- B01L3/502—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures
- B01L3/5027—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures by integrated microfluidic structures, i.e. dimensions of channels and chambers are such that surface tension forces are important, e.g. lab-on-a-chip
- B01L3/502761—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures by integrated microfluidic structures, i.e. dimensions of channels and chambers are such that surface tension forces are important, e.g. lab-on-a-chip specially adapted for handling suspended solids or molecules independently from the bulk fluid flow, e.g. for trapping or sorting beads, for physically stretching molecules
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
- C12Q1/6813—Hybridisation assays
- C12Q1/6816—Hybridisation assays characterised by the detection means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
- G01N33/569—Immunoassay; Biospecific binding assay; Materials therefor for microorganisms, e.g. protozoa, bacteria, viruses
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
- B01L2200/00—Solutions for specific problems relating to chemical or physical laboratory apparatus
- B01L2200/06—Fluid handling related problems
- B01L2200/0647—Handling flowable solids, e.g. microscopic beads, cells, particles
- B01L2200/0668—Trapping microscopic beads
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
- B01L2300/00—Additional constructional details
- B01L2300/06—Auxiliary integrated devices, integrated components
- B01L2300/0627—Sensor or part of a sensor is integrated
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/30—Against vector-borne diseases, e.g. mosquito-borne, fly-borne, tick-borne or waterborne diseases whose impact is exacerbated by climate change
Abstract
The invention relates to the technical field of pathogen detection, and discloses a method for detecting food-borne disease pathogens based on microfluidics, which comprises the following steps: sequentially carrying out pathogen enrichment operation on each food sample in the sampled food sample set to obtain an enriched pathogen set, carrying out fluorescence detection on the enriched pathogen set to obtain a pathogen quantitative semantic set, and carrying out mass spectrum sampling on the enriched pathogen set to obtain a pathogen mass spectrum atlas; extracting a pathogen coding group set from the pathogen mass spectrogram set; training a self-attention pathogen model by using a pathogen encoding set and a pathogen quantitative semantic set to obtain a pathogen mass spectrum analysis model; extracting a pathogen to be detected from a sample to be detected by utilizing the microfluid, and analyzing pathogen components of a mass spectrum picture to be detected of the pathogen to be detected by utilizing a pathogen mass spectrum analysis model to obtain a pathogen detection result. The invention also provides a detection system for realizing food-borne disease pathogens based on microfluidics. The invention can improve the efficiency of detecting food-borne pathogens.
Description
Technical Field
The invention relates to the technical field of pathogen detection, in particular to a method and a system for detecting food-borne disease pathogens based on microfluidics.
Background
Pathogenic microorganisms in foods can cause human infection and food poisoning and other health problems, food is required to be subjected to food-borne pathogen detection in order to ensure food safety, the food-borne pathogen detection refers to the process of detecting potential pathogenic microorganisms collected from foods or environments, and the food-borne pathogen detection plays an important role in food safety control and public health, can help ensure food safety, and prevents outbreaks and transmission of food-borne diseases.
The existing food source pathogen detection method is mainly based on the traditional food source pathogen detection method, and the food source pathogen detection is realized by utilizing a culture method, a molecular biology technology and a biosensor technology.
Disclosure of Invention
The invention provides a method and a system for detecting food-borne disease pathogens based on microfluidics, and mainly aims to solve the problem of low efficiency in food-borne disease pathogen detection.
In order to achieve the above object, the present invention provides a method for detecting a pathogen of food-borne diseases based on microfluidics, comprising:
sampling a plurality of food sources to obtain a food source sample set, sequentially carrying out sample impurity removal and sample concentration on each food source sample in the food source sample set to obtain a concentrated sample set, and carrying out pathogen capture on the concentrated sample set by utilizing a surface modification layer of microfluid to obtain a captured pathogen set;
performing pathogen enrichment operation on the captured pathogen set by utilizing the separation layer of the microfluid to obtain an enriched pathogen set, performing fluorescence detection on the enriched pathogen set to obtain a pathogen distribution data set, and performing mass spectrum sampling on the enriched pathogen set to obtain a pathogen mass spectrum atlas;
performing image enhancement and image calibration operations on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas, performing frequency domain transformation and multiple feature extraction operations on the calibrated pathogen atlas one by one to obtain a pathogen feature set, wherein the performing image enhancement and image calibration operations on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas comprises: selecting pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one as target pathogen pictures, and performing Gaussian filtering on the target pathogen pictures to obtain denoising pathogen pictures; generating a gray level histogram of the denoising pathogen picture, and carrying out gray level equalization on the denoising pathogen picture according to the gray level histogram to obtain an equalized pathogen picture; and carrying out image enhancement on the balanced pathogen image by using the following gray enhancement algorithm to obtain an enhanced pathogen image:
Wherein f (x, y) is the gray value of the pixel point with coordinates of (x, y) in the enhanced pathogen image, x is the abscissa of the pixel, y is the ordinate of the pixel, a is the preset enhancement coefficient, exp is an exponential function, b is the preset translation coefficient, z max Is the maximum gray value, z, in the equalized pathogen picture min Is the minimum gray value in the balanced pathogen picture, L is the gray level of the balanced pathogen picture, and g (x, y) is the gray value of the pixel point with the coordinates of (x, y) in the balanced pathogen picture; sequentially carrying out baseline correction and wavelength calibration on the enhanced pathogen pictures to obtain calibrated pathogen pictures, and collecting all the calibrated pathogen pictures into a calibrated pathogen atlas;
extracting a pathogen quantitative semantic group set from the pathogen distribution data group set, performing structural transcoding on each pathogen feature in the pathogen feature group set to obtain a pathogen encoding group set, and training a preset self-attention pathogen model by using the pathogen encoding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model;
extracting a sample to be detected from food to be detected, extracting a pathogen to be detected from the sample to be detected by utilizing the microfluid, carrying out mass spectrum sampling on the pathogen to be detected to obtain a mass spectrum picture to be detected, and carrying out pathogen component analysis on the mass spectrum picture to be detected by utilizing the pathogen mass spectrum analysis model to obtain a pathogen detection result.
Optionally, the sequentially performing sample impurity removal and sample concentration operations on each food sample in the food sample set to obtain a concentrated sample set, including:
selecting food samples in the food sample set one by one as target food samples, and performing sample crushing operation on the target food samples to obtain crushed food samples;
sequentially carrying out sample dilution and sample soaking operation on the crushed food source sample to obtain a dissolved food source sample;
performing primary filtering operation on the dissolved food source sample by using a filter to obtain a filtered food source sample;
performing sample centrifugation on the dissolved food sample to obtain a centrifuged food sample;
and performing secondary filtering operation on the centrifugal food source sample by using an ultrafiltration membrane to obtain a concentrated sample, and collecting all the concentrated samples into a concentrated sample set.
Optionally, the capturing the pathogen of the concentrated sample set by using the surface modification layer of the microfluid to obtain a captured pathogen set includes:
selecting concentrated samples in the concentrated sample set one by one as target concentrated samples, and injecting the target concentrated solution into corresponding microfluid;
utilizing chemical modification molecules on a surface modification layer inside the microfluid to specifically capture pathogens in the target concentrated solution to obtain captured pathogens;
All captured pathogens corresponding to the concentrated sample set are pooled into a captured pathogen set.
Optionally, the performing a pathogen enrichment operation on the captured pathogen set using the microfluidic separation layer to obtain an enriched pathogen set comprises:
selecting the capture pathogens in the capture pathogen set one by one as target capture pathogens, and performing cell lysis on the target capture pathogens to obtain target lysis pathogens;
complementary binding is carried out on the target cracking pathogen by using a primer to obtain a target complementary pathogen;
performing directional amplification on the target complementary pathogen by using polymerase to obtain a target amplified pathogen;
annealing, extending, regenerating and the like are sequentially carried out on the target amplification pathogen to obtain a target denaturation pathogen;
and (3) separating the target denatured pathogen by utilizing the microfluidic separation layer to obtain target enriched pathogen, and collecting all the target enriched pathogen into an enriched pathogen set.
Optionally, the fluorescence detection is performed on the enriched pathogen set to obtain a pathogen distribution data set, including:
selecting the concentrated pathogens in the concentrated pathogen set one by one as target concentrated pathogens, and performing fluorescent hybridization on the target concentrated pathogens by using a preset fluorescent probe set to obtain target fluorescent pathogens;
Measuring a fluorescence signal of the target fluorescent pathogen by using a fluorescence detector to obtain a fluorescence signal data set;
and performing pathogen labeling on the fluorescent signal data set to obtain a pathogen distribution data set, and collecting all pathogen distribution data sets into a pathogen distribution data set.
Optionally, the sequentially performing baseline correction and wavelength calibration on the enhanced pathogen image to obtain a calibrated pathogen image, including:
screening a baseline region from the enhanced pathogen picture according to the mass spectrum peak of the enhanced pathogen picture;
fitting a baseline curve from the baseline region, and removing the baseline curve from the enhanced pathogen picture to obtain a corrected pathogen picture;
calculating the offset of the mass spectrum peak of the corrected pathogen image, and carrying out wavelength calibration on the corrected pathogen image according to the offset to obtain a calibrated pathogen image.
Optionally, the performing frequency domain transformation and multiple feature extraction operations on the calibration pathogen atlas one by one to obtain a pathogen feature set, including:
selecting calibration pathogen pictures in the calibration pathogen image set one by one as target calibration pictures, and performing frequency domain transformation on the target calibration pictures by using the following multi-layer frequency domain transformation algorithm to obtain a frequency domain coefficient set:
Wherein t is j,k Refers to the kth decomposition coefficient of the decomposition frequency domain of the jth layer in the frequency domain coefficient set, s j Refers to the scale factor of the j-th layer decomposition frequency domain, N refers to the signal scale sequence number of the target calibration picture, N refers to the signal scale size of the target calibration picture, and h n Refers to a first filter coefficient, d, of the target calibration picture on the nth signal scale j Refer to detail coefficients of the j-th layer decomposition frequency domain, f n Means that the target calibration picture is a second filter coefficient on the nth signal scale
Extracting distribution characteristics, position characteristics and phase characteristics from the frequency domain coefficient set in sequence;
and collecting the distribution characteristics, the position characteristics and the phase characteristics into pathogen characteristic groups, and collecting all pathogen characteristic groups into pathogen characteristic group sets.
Optionally, the performing structural transcoding on each pathogen feature in the pathogen feature set to obtain a pathogen encoding set includes:
selecting the pathogen feature groups in the pathogen feature group one by one as target pathogen feature groups, and adding position vectors for the target pathogen feature groups to obtain position pathogen feature groups;
performing attention transcoding on the position pathogen feature set by using an attention matrix to obtain an attention pathogen feature set;
Carrying out full-connection pooling operation on the attention pathogenic characteristic group to obtain a pooled pathogenic characteristic group;
and linearly activating the pooled pathogen feature groups to obtain pathogen code groups, and converging all pathogen code groups into pathogen code group sets.
Optionally, training a preset self-attention pathogen model by using the pathogen encoding set and the pathogen quantitative semantic set to obtain a pathogen mass spectrometry model, including:
generating a predicted pathogen semantic group set corresponding to the pathogen encoding group set by using a preset self-attention pathogen model;
calculating a model loss value of the self-attention pathogen model according to the predicted pathogen semantic group set and the pathogen quantitative semantic group set;
and iteratively updating the model parameters of the self-attention pathogen model according to the model loss value until the model loss value is smaller than a preset loss value threshold, and taking the updated self-attention pathogen model as a pathogen mass spectrum analysis model.
In order to solve the above problems, the present invention also provides a detection system for realizing food-borne disease pathogens based on microfluidics, the system comprising:
the pathogen capturing module is used for sampling various food sources to obtain a food source sample set, sequentially carrying out sample impurity removal and sample concentration operation on each food source sample in the food source sample set to obtain a concentrated sample set, and carrying out pathogen capturing on the concentrated sample set by utilizing a surface modification layer of a microfluid to obtain a captured pathogen set;
The fluorescence detection module is used for carrying out pathogen enrichment operation on the captured pathogen set by utilizing the separation layer of the microfluid to obtain an enriched pathogen set, carrying out fluorescence detection on the enriched pathogen set to obtain a pathogen distribution data set, and carrying out mass spectrum sampling on the enriched pathogen set to obtain a pathogen mass spectrum atlas;
the feature extraction module is used for carrying out image enhancement and image calibration operation on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas, carrying out frequency domain transformation and multiple feature extraction operation on the calibrated pathogen atlas one by one to obtain a pathogen feature set, wherein the step of carrying out image enhancement and image calibration operation on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas comprises the following steps: selecting pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one as target pathogen pictures, and performing Gaussian filtering on the target pathogen pictures to obtain denoising pathogen pictures; generating a gray level histogram of the denoising pathogen picture, and carrying out gray level equalization on the denoising pathogen picture according to the gray level histogram to obtain an equalized pathogen picture; and carrying out image enhancement on the balanced pathogen image by using the following gray enhancement algorithm to obtain an enhanced pathogen image:
Wherein f (x, y) is the gray value of the pixel point with coordinates of (x, y) in the enhanced pathogen image, x is the abscissa of the pixel, y is the ordinate of the pixel, a is the preset enhancement coefficient, exp is an exponential function, b is the preset translation coefficient, z max Is the maximum gray value, z, in the equalized pathogen picture min Is the minimum gray value in the balanced pathogen picture, L is the gray level of the balanced pathogen picture, and g (x, y) is the gray value of the pixel point with the coordinates of (x, y) in the balanced pathogen picture; sequentially carrying out baseline correction and wavelength calibration on the enhanced pathogen pictures to obtain calibrated pathogen pictures, and collecting all the calibrated pathogen pictures into a calibrated pathogen atlas;
the model training module is used for extracting a pathogen quantitative semantic group set from the pathogen distribution data group set, performing structural transcoding on each pathogen feature in the pathogen feature group set to obtain a pathogen encoding group set, and training a preset self-attention pathogen model by using the pathogen encoding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model;
the mass spectrum detection module is used for extracting a sample to be detected from food to be detected, extracting a pathogen to be detected from the sample to be detected by utilizing the microfluid, carrying out mass spectrum sampling on the pathogen to be detected to obtain a mass spectrum picture to be detected, and carrying out pathogen component analysis on the mass spectrum picture to be detected by utilizing the pathogen mass spectrum analysis model to obtain a pathogen detection result.
According to the embodiment of the invention, the pathogen data of various food sources can be obtained by sampling various food sources to obtain the food source sample set, so that the accuracy of subsequent pathogen detection is improved, the concentrated sample set can be obtained by sequentially carrying out sample impurity removal and sample concentration operation on each food source sample in the food source sample set, impurities in the sample can be removed, so that the accuracy of pathogen detection is improved, the concentrated sample set is subjected to pathogen capture by utilizing a surface modification layer of a microfluid to obtain a captured pathogen set, the pathogen to be detected can be obtained, the subsequent direct detection and the acquisition of pathogen data are facilitated, the pathogen enrichment operation is carried out on the captured pathogen set by utilizing a separation layer of the microfluid to obtain an enriched pathogen set, the pathogen concentration can be improved, the accuracy of pathogen detection is improved, the pathogen distribution data set can be obtained by carrying out fluorescent detection on the enriched pathogen set, the data set marked with pathogen content and pathogen type can be used as a training set, the subsequent model is convenient to carry out training on the model, the pathogen image is obtained by utilizing a mass spectrum sample, the pathogen image can be conveniently extracted by utilizing a machine vision detection method, the characteristic of the pathogen can be more accurately calibrated, the characteristic of the pathogen can be more accurately corrected, and the characteristic of the pathogen can be more accurately calibrated by means of the mass spectrum image is more, and the characteristic of the pathogen can be more accurately calibrated.
The pathogen quantitative semantic group set is extracted from the pathogen distribution data group set, each pathogen feature in the pathogen feature group set is subjected to structural transcoding to obtain a pathogen coding group set, a preset self-attention pathogen model is trained by using the pathogen coding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model, a relation model between the mass spectrum coding feature and the pathogen distribution semantic can be established, so that a more visual detection result is obtained, a sample to be detected is extracted from food to be detected by using the microfluid, the pathogen to be detected is extracted from the sample to be detected, mass spectrum sampling is carried out on the pathogen to be detected to obtain a mass spectrum picture to be detected, pathogen component analysis is carried out on the mass spectrum picture to be detected by using the pathogen mass spectrum analysis model to obtain a pathogen detection result, a visual pathogen detection result can be quickly and accurately generated, a step of manual labeling and manual measurement is omitted, and the pathogen detection efficiency is improved. Therefore, the method and the system for detecting the food-borne disease pathogens based on the microfluid can solve the problem of low efficiency in detecting the food-borne disease pathogens.
Drawings
Fig. 1 is a schematic flow chart of a method for detecting a pathogen of food-borne disease based on a micro-fluid according to an embodiment of the invention;
FIG. 2 is a schematic flow chart of an embodiment of the invention for extracting an enriched pathogen set;
FIG. 3 is a flow chart of generating a pathogen encoding set according to an embodiment of the invention;
FIG. 4 is a functional block diagram of a detection system for detecting a food-borne disease pathogen based on a microfluidic device according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a detection method for realizing food-borne disease pathogens based on microfluidics. The execution subject of the microfluidic-based detection method for detecting food-borne disease pathogens includes, but is not limited to, at least one of a server, a terminal, etc. capable of being configured to execute the method provided by the embodiments of the present application. In other words, the method for detecting the food-borne disease pathogen based on the microfluid implementation may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a method for detecting a pathogen of a food-borne disease based on a micro-fluid according to an embodiment of the invention is shown. In this embodiment, the method for detecting a pathogen of food-borne disease based on microfluidics includes:
s1, sampling a plurality of food sources to obtain a food source sample set, sequentially carrying out sample impurity removal and sample concentration operation on each food source sample in the food source sample set to obtain a concentrated sample set, and carrying out pathogen capture on the concentrated sample set by utilizing a surface modification layer of microfluid to obtain a captured pathogen set.
In the embodiment of the invention, the food source refers to foods such as meat, dairy products, vegetables, fruits, seafood or water, and the food source sample set comprises a plurality of food source samples, wherein the food source samples are part of samples from one food source; the step of sampling a plurality of food sources to obtain a food source sample set refers to that part of samples are collected from each food source to serve as food source samples of the food source.
In the embodiment of the present invention, the sequentially performing sample impurity removal and sample concentration operations on each food sample in the food sample set to obtain a concentrated sample set includes:
Selecting food samples in the food sample set one by one as target food samples, and performing sample crushing operation on the target food samples to obtain crushed food samples;
sequentially carrying out sample dilution and sample soaking operation on the crushed food source sample to obtain a dissolved food source sample;
performing primary filtering operation on the dissolved food source sample by using a filter to obtain a filtered food source sample;
performing sample centrifugation on the dissolved food sample to obtain a centrifuged food sample;
and performing secondary filtering operation on the centrifugal food source sample by using an ultrafiltration membrane to obtain a concentrated sample, and collecting all the concentrated samples into a concentrated sample set.
In detail, the sample crushing operation can be performed on the target food sample by using a stirring method, an ultrasonic method, a high-pressure method or an enzymolysis method to obtain a crushed food sample; the crushed food sample may be subjected to sample dilution and sample soaking operations sequentially using phosphate buffered saline (PBS buffer), tris-HCl buffer, tris-EDTA buffer (TE buffer), and the like, to obtain a dissolved food sample.
Specifically, the dissolved food source sample may be subjected to a primary filtration operation using a filter such as a cellulose filter, a polyamide filter, or a glass fiber filter, to obtain a filtered food source sample, and the filter has a pore size of between 0.2 micrometers and 1 micrometer.
In detail, the dissolved food sample may be subjected to a sample centrifugation operation using a conventional centrifuge or ultracentrifuge to obtain a centrifuged food sample, and the ultrafiltration membrane may be a membrane such as a polypropylene membrane (Polypropylene membrane), a polyamide membrane (Polyamide membrane), a starch ether membrane (Cellulose ester membrane), a polythioether membrane (Polysulfone membrane), or a polyether sulfone membrane (Polyethersulfone membrane).
Specifically, the micro-fluid is a micro-scale fluid system, and is generally composed of micro-channels, micro-valves, micro-mixers and other micro-structures, and is used for controlling and operating the flow and mixing of fluids, the surface modification layer is a chemical substance attached to the surface of a micro-fluid chip, so that the surface of the chip can have specific properties, such as hydrophilicity, electric charge and the like, and the purpose of separating and enriching samples is achieved, and the surface modification layer can be prepared by introducing chemical modification molecules, polymers or coatings and the like on the surface of the micro-fluid chip.
In detail, the set of capture pathogens is a collection of a plurality of capture pathogens, and each of the capture pathogens is all pathogens captured by a concentrated sample in the concentrated sample set, the pathogens being food-borne pathogens, such as bacteria, viruses, parasites, fungi or toxins, etc., wherein the bacteria, such as salmonella, escherichia coli, staphylococcus aureus, staphylococci, etc., the viruses, such as norovirus, adenovirus, rotavirus, etc., the parasites, such as toxoplasma, trichomonas enterica, cryptosporidium, etc., the fungi, such as mold, aspergillus, etc., the toxins, such as fish toxins, shellfish toxins, mycotoxins, etc.
In detail, the capturing the pathogen of the concentrated sample set by using the surface modification layer of the microfluid to obtain a captured pathogen set comprises the following steps:
selecting concentrated samples in the concentrated sample set one by one as target concentrated samples, and injecting the target concentrated solution into corresponding microfluid;
utilizing chemical modification molecules on a surface modification layer inside the microfluid to specifically capture pathogens in the target concentrated solution to obtain captured pathogens;
all captured pathogens corresponding to the concentrated sample set are pooled into a captured pathogen set.
In detail, the target concentrate may be injected into a predetermined microfluidic by means of external injection or automatic pump, and the chemical modification molecule may be an antibody, DNA, RNA, or oligonucleotide molecule having chemical specificity to a pathogen.
According to the embodiment of the invention, the pathogen data of various food sources can be obtained by sampling various food sources to obtain the food source sample set, so that the accuracy of subsequent pathogen detection is improved, the impurities in the sample can be removed by sequentially carrying out sample impurity removal and sample concentration operation on each food source sample in the food source sample set to obtain the concentrated sample set, so that the pathogen detection accuracy is improved, and the pathogen to be detected can be acquired by carrying out pathogen capture on the concentrated sample set by utilizing the surface modification layer of the microfluid to obtain the pathogen capture set, so that the subsequent direct detection and the pathogen data acquisition are convenient.
S2, performing pathogen enrichment operation on the captured pathogen set by utilizing the separation layer of the microfluid to obtain an enriched pathogen set, performing fluorescence detection on the enriched pathogen set to obtain a pathogen distribution data set, and performing mass spectrum sampling on the enriched pathogen set to obtain a pathogen mass spectrum atlas.
In the embodiment of the invention, the separation layer is a microstructure layer for separating different components in a sample in the microfluid, the enriched pathogen set is a set consisting of enriched pathogens, and each enriched pathogen is a pathogen obtained by enriching one captured pathogen in the captured pathogen set.
In an embodiment of the present invention, referring to fig. 2, the performing a pathogen enrichment operation on the captured pathogen set by using the separation layer of the microfluidic device to obtain an enriched pathogen set includes:
s21, selecting the capture pathogens in the capture pathogen set one by one as target capture pathogens, and performing cell lysis on the target capture pathogens to obtain target lysis pathogens;
s22, carrying out complementary binding on the target cracking pathogen by using a primer to obtain a target complementary pathogen;
s23, directionally amplifying the target complementary pathogen by utilizing polymerase to obtain a target amplified pathogen;
S24, annealing, extending, regenerating and the like are sequentially carried out on the target amplification pathogen, so that a target denaturation pathogen is obtained;
s25, separating the target denatured pathogen by utilizing the microfluidic separation layer to obtain target enriched pathogen, and collecting all the target enriched pathogen into an enriched pathogen set.
Specifically, the target capture pathogen can be subjected to cell lysis by using a phenol imitation method, a chloroform method or a magnetic bead method to obtain the target lysis pathogen, the primers are two short single-stranded DNAs for amplifying the capture pathogen DNA, and the polymerase can be a polymerase such as Taq polymerase Pfu polymerase, phusion polymerase and Q5 polymerase.
Specifically, annealing, extending, regenerating and other operations can be sequentially performed on the target amplification pathogen by using a denaturation temperature to obtain a target denaturation pathogen, the denaturation temperature is between 94 ℃ and 96 ℃, and separation operations can be performed on the target denaturation pathogen by using methods such as a filtration method, a washing method, a centrifugation method and the like to obtain a target enrichment pathogen.
In detail, the fluorescence detection is performed on the enriched pathogen set to obtain a pathogen distribution data set, which comprises the following steps:
Selecting the concentrated pathogens in the concentrated pathogen set one by one as target concentrated pathogens, and performing fluorescent hybridization on the target concentrated pathogens by using a preset fluorescent probe set to obtain target fluorescent pathogens;
measuring a fluorescence signal of the target fluorescent pathogen by using a fluorescence detector to obtain a fluorescence signal data set;
and performing pathogen labeling on the fluorescent signal data set to obtain a pathogen distribution data set, and collecting all pathogen distribution data sets into a pathogen distribution data set.
In detail, the fluorescent probe set is a molecular probe which is set according to the DNA of the food-borne pathogen, has a specific length and a specific chemical modification method, and can emit a fluorescent signal, and the fluorescent detector comprises a fluorescent microscope, a laser confocal microscope, a fluorescent spectrophotometer and the like.
Specifically, the pathogen marking is performed on the fluorescent signal data set to obtain a pathogen distribution data set, namely, pathogen marking is performed on the fluorescent signal data set according to the information such as the signal intensity, the peak time and the like of each fluorescent signal in the fluorescent signal data set to obtain a data set containing pathogen types and pathogen ratios of various pathogens in the target enriched pathogen.
Specifically, the method can utilize methods such as atomic force microscope (Atomic Force Microscope, abbreviated as AFM) and scanning electron microscope (Scanning Electron Microscope, abbreviated as SEM) to sample the enriched pathogen set in a mass spectrum manner, so as to obtain a pathogen mass spectrum atlas.
In the embodiment of the invention, the pathogen concentration can be improved by carrying out pathogen enrichment operation on the captured pathogen set by utilizing the separation layer of the microfluid to obtain an enriched pathogen set, so that the accuracy of pathogen detection is improved, the pathogen distribution data set is obtained by carrying out fluorescence detection on the enriched pathogen set, and the data set marked with the pathogen content and the pathogen type can be obtained as a training set, so that the subsequent training of a model is facilitated, and the pathogen mass spectrum image set is obtained by carrying out mass spectrum sampling on the enriched pathogen set, so that the pathogen detection can be realized by a machine vision method conveniently.
And S3, carrying out image enhancement and image calibration operation on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas, and carrying out frequency domain transformation and multi-feature extraction operation on the calibrated pathogen atlas one by one to obtain a pathogen feature set.
In the embodiment of the invention, the calibration pathogen atlas is an atlas formed by pathogen mass spectrum pictures in the calibrated pathogen mass spectrum set.
In the embodiment of the present invention, the performing image enhancement and image calibration operations on the pathogen mass spectrum pictures in the pathogen mass spectrum set one by one to obtain a calibrated pathogen atlas includes:
selecting pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one as target pathogen pictures, and performing Gaussian filtering on the target pathogen pictures to obtain denoising pathogen pictures;
generating a gray level histogram of the denoising pathogen picture, and carrying out gray level equalization on the denoising pathogen picture according to the gray level histogram to obtain an equalized pathogen picture;
and carrying out image enhancement on the balanced pathogen image by using the following gray enhancement algorithm to obtain an enhanced pathogen image:
wherein f (x, y) is the gray value of the pixel point with coordinates of (x, y) in the enhanced pathogen image, x is the abscissa of the pixel, y is the ordinate of the pixel, a is the preset enhancement coefficient, exp is an exponential function, b is the preset translation coefficient, z max Is the maximum gray value, z, in the equalized pathogen picture min Is the minimum gray value in the balanced pathogen picture, L is the gray level of the balanced pathogen picture, and g (x, y) is the gray value of the pixel point with the coordinates of (x, y) in the balanced pathogen picture;
And sequentially carrying out baseline correction and wavelength calibration on the enhanced pathogen pictures to obtain calibrated pathogen pictures, and collecting all the calibrated pathogen pictures into a calibrated pathogen atlas.
In detail, the balanced pathogen image is subjected to image enhancement by using the gray enhancement algorithm to obtain an enhanced pathogen image, and image details can be improved according to gray level contrast of the image, so that more image features are reserved.
Specifically, the sequentially performing baseline correction and wavelength calibration on the enhanced pathogen image to obtain a calibrated pathogen image, including:
screening a baseline region from the enhanced pathogen picture according to the mass spectrum peak of the enhanced pathogen picture;
fitting a baseline curve from the baseline region, and removing the baseline curve from the enhanced pathogen picture to obtain a corrected pathogen picture;
calculating the offset of the mass spectrum peak of the corrected pathogen image, and carrying out wavelength calibration on the corrected pathogen image according to the offset to obtain a calibrated pathogen image.
In detail, the screening the baseline region from the enhanced pathogenic image according to the mass spectrum peak of the enhanced pathogenic image refers to taking the region without the mass spectrum peak in the enhanced pathogenic image as the baseline region, and generally selecting the regions at two ends of the mass spectrum or near the mass spectrum peak, and fitting a baseline curve from the baseline region by using a polynomial fitting method or a cubic spline fitting method.
Specifically, calculating the offset of the mass spectrum peak of the corrected pathogenic image refers to comparing the position of the mass spectrum peak of the internal standard substance with the known mass-to-charge ratio value of the internal standard substance, and performing wavelength calibration on the corrected pathogenic image according to the offset to obtain a calibrated pathogenic image refers to adjusting the position of the mass spectrum peak to be consistent with the mass-to-charge ratio value.
Specifically, the performing frequency domain transformation and multiple feature extraction operations on the calibration pathogen atlas one by one to obtain a pathogen feature set, including:
selecting calibration pathogen pictures in the calibration pathogen image set one by one as target calibration pictures, and performing frequency domain transformation on the target calibration pictures by using the following multi-layer frequency domain transformation algorithm to obtain a frequency domain coefficient set:
wherein t is j,k Refers to the kth decomposition coefficient of the decomposition frequency domain of the jth layer in the frequency domain coefficient set, s j Refers to the scale factor of the j-th layer decomposition frequency domain, N refers to the signal scale sequence number of the target calibration picture, N refers to the signal scale size of the target calibration picture, and h n Refers to a first filter coefficient, d, of the target calibration picture on the nth signal scale j Refer to detail coefficients of the j-th layer decomposition frequency domain, f n Means that the target calibration picture is a second filter coefficient on the nth signal scale
Extracting distribution characteristics, position characteristics and phase characteristics from the frequency domain coefficient set in sequence;
and collecting the distribution characteristics, the position characteristics and the phase characteristics into pathogen characteristic groups, and collecting all pathogen characteristic groups into pathogen characteristic group sets.
In detail, the multi-layer frequency domain transformation algorithm is utilized to perform frequency domain transformation on the target calibration picture to obtain a frequency domain coefficient set, so that frequency domain feature separation of the mass spectrum picture can be realized, feature clustering is realized, and more remarkable pathogenic features are obtained.
Specifically, the distribution characteristic refers to frequency distribution and intensity of each layer of decomposition frequency domain in the frequency domain coefficient set, the position characteristic refers to peak position and peak width of each layer of decomposition frequency domain in the frequency domain coefficient set, and the phase characteristic refers to frequency, phase, amplitude and other characteristics of each layer of decomposition frequency domain in the frequency domain coefficient set.
In the embodiment of the invention, the pathogen mass spectrum images in the pathogen mass spectrogram set are subjected to image enhancement and image calibration operation one by one to obtain the calibrated pathogen spectrogram set, so that the details of the mass spectrum images can be enhanced, more accurate pathogen characteristics are obtained, and the pathogen characteristic set is obtained by carrying out frequency domain transformation and multiple characteristic extraction operation one by one on the calibrated pathogen spectrogram set, so that the mass spectrum characteristics can be extracted more accurately, and the precision of a subsequent model is improved.
S4, extracting a pathogen quantitative semantic group set from the pathogen distribution data group set, performing structural transcoding on each pathogen feature in the pathogen feature group set to obtain a pathogen encoding group set, and training a preset self-attention pathogen model by using the pathogen encoding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model.
In the embodiment of the invention, the pathogen quantitative semantic group set refers to a normalized pathogen distribution data group set, and the pathogen quantitative semantic group set extracted from the pathogen distribution data group set refers to semantic normalization of the pathogen distribution data group, so that pathogen semantics in the pathogen distribution data group set are converted into normalized pathogen semantics according to a word vector distance formula.
In the embodiment of the present invention, referring to fig. 3, the performing structural transcoding on each pathogenic feature in the pathogenic feature set to obtain a pathogenic code set includes:
s31, selecting pathogen feature groups in the pathogen feature group one by one as target pathogen feature groups, and adding position vectors for the target pathogen feature groups to obtain position pathogen feature groups;
s32, performing attention transcoding on the position pathogen feature set by using an attention matrix to obtain an attention pathogen feature set;
S33, carrying out full-connection pooling operation on the attention pathogen feature set to obtain a pooled pathogen feature set;
s34, carrying out linear activation on the pooled pathogen feature groups to obtain pathogen code groups, and collecting all pathogen code groups into pathogen code group sets.
Specifically, adding a position vector to the target pathogen feature set to obtain a position pathogen feature set refers to splicing the position vector of each pathogen feature in the target feature set to a corresponding pathogen feature to obtain a position pathogen feature, wherein the attention matrix is a QKV matrix of a bert model or a transformer model, and the pooled pathogen feature set can be linearly activated by using a softmax function or a ReLU function to obtain a pathogen coding set.
In detail, the training of the preset self-attention pathogen model by using the pathogen encoding set and the pathogen quantitative semantic set to obtain a pathogen mass spectrum analysis model comprises the following steps:
generating a predicted pathogen semantic group set corresponding to the pathogen encoding group set by using a preset self-attention pathogen model;
calculating a model loss value of the self-attention pathogen model according to the predicted pathogen semantic group set and the pathogen quantitative semantic group set;
And iteratively updating the model parameters of the self-attention pathogen model according to the model loss value until the model loss value is smaller than a preset loss value threshold, and taking the updated self-attention pathogen model as a pathogen mass spectrum analysis model.
In detail, the self-attention pathogen model may be a bi-directional encoder model (Bidirectional Encoder Representations from Transformers, BERT for short) or other transducer network model.
Specifically, a model loss value of the self-attention pathogen model may be calculated according to the predicted pathogen semantic group set and the pathogen quantitative semantic group set using a loss value calculation formula such as a mean square error loss value or a cross entropy loss value.
In detail, the model parameters of the self-attention pathogen model may be iteratively updated according to the model loss values using a batch gradient descent algorithm, a stochastic gradient descent algorithm, or a rapid gradient descent algorithm.
In the embodiment of the invention, the pathogen coding set is obtained by extracting the pathogen quantitative semantic set from the pathogen distribution data set, carrying out structural transcoding on each pathogen feature in the pathogen feature set, and the pathogen coding set and the pathogen quantitative semantic set are utilized to train a preset self-attention pathogen model to obtain a pathogen mass spectrum analysis model, so that a relation model between the mass spectrum coding feature and the pathogen distribution semantic can be established, and a more visual detection result is obtained.
S5, extracting a sample to be detected from food to be detected, extracting a pathogen to be detected from the sample to be detected by utilizing the microfluid, carrying out mass spectrum sampling on the pathogen to be detected to obtain a mass spectrum picture to be detected, and carrying out pathogen component analysis on the mass spectrum picture to be detected by utilizing the pathogen mass spectrum analysis model to obtain a pathogen detection result.
In the embodiment of the invention, the food to be detected is food for detecting food-borne pathogens, and the sample to be detected is a part of the sample of the food to be detected.
In the embodiment of the present invention, the method for extracting the pathogen to be detected from the sample to be detected by using the micro-fluid is consistent with the method for sequentially performing sample impurity removal and sample concentration operations on each food sample in the food sample set in the step S1 to obtain a concentrated sample set, performing pathogen capturing on the concentrated sample set by using a surface modification layer of the micro-fluid to obtain a captured pathogen set, and performing pathogen enrichment operation on the captured pathogen set by using a separation layer of the micro-fluid in the step S2 to obtain an enriched pathogen set, which is not described herein.
Specifically, the method for performing mass spectrum sampling on the pathogen to be detected to obtain a mass spectrum picture is consistent with the method for performing mass spectrum sampling on the enriched pathogen set in the step S2 to obtain a pathogen mass spectrum atlas, which is not described herein.
In detail, the method for performing feature encoding on the mass spectrum image to be detected before performing the pathogen component analysis on the mass spectrum image to be detected by using the pathogen mass spectrum analysis model to obtain a pathogen detection result is consistent with the method for performing image enhancement and image calibration operation on the mass spectrum images in the pathogen mass spectrogram set one by one in the step S3 to obtain a calibrated pathogen atlas, performing frequency domain transformation and multiple feature extraction operation on the calibrated pathogen atlas one by one to obtain a pathogen feature set, and performing structural transcoding on each pathogen feature in the pathogen feature set in the step S4 to obtain a pathogen encoding set, which is not repeated herein.
Specifically, the pathogen detection result comprises the types and the ratio condition descriptions of various food-borne pathogens in the food to be detected.
In the embodiment of the invention, the sample to be detected is extracted from the food to be detected, the micro-fluid is utilized to extract the pathogen to be detected from the sample to be detected, the mass spectrum sampling is carried out on the pathogen to be detected, the mass spectrum picture to be detected is obtained, and the pathogen component analysis is carried out on the mass spectrum picture to be detected by utilizing the pathogen mass spectrum analysis model, so that the pathogen detection result is obtained, the intuitive pathogen detection result can be quickly and accurately generated, the step of manually marking and manually measuring is omitted, and the pathogen detection efficiency is improved.
According to the embodiment of the invention, the pathogen data of various food sources can be obtained by sampling various food sources to obtain the food source sample set, so that the accuracy of subsequent pathogen detection is improved, the concentrated sample set can be obtained by sequentially carrying out sample impurity removal and sample concentration operation on each food source sample in the food source sample set, impurities in the sample can be removed, so that the accuracy of pathogen detection is improved, the concentrated sample set is subjected to pathogen capture by utilizing a surface modification layer of a microfluid to obtain a captured pathogen set, the pathogen to be detected can be obtained, the subsequent direct detection and the acquisition of pathogen data are facilitated, the pathogen enrichment operation is carried out on the captured pathogen set by utilizing a separation layer of the microfluid to obtain an enriched pathogen set, the pathogen concentration can be improved, the accuracy of pathogen detection is improved, the pathogen distribution data set can be obtained by carrying out fluorescent detection on the enriched pathogen set, the data set marked with pathogen content and pathogen type can be used as a training set, the subsequent model is convenient to carry out training on the model, the pathogen image is obtained by utilizing a mass spectrum sample, the pathogen image can be conveniently extracted by utilizing a machine vision detection method, the characteristic of the pathogen can be more accurately calibrated, the characteristic of the pathogen can be more accurately corrected, and the characteristic of the pathogen can be more accurately calibrated by means of the mass spectrum image is more, and the characteristic of the pathogen can be more accurately calibrated.
The pathogen quantitative semantic group set is extracted from the pathogen distribution data group set, each pathogen feature in the pathogen feature group set is subjected to structural transcoding to obtain a pathogen coding group set, a preset self-attention pathogen model is trained by using the pathogen coding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model, a relation model between the mass spectrum coding feature and the pathogen distribution semantic can be established, so that a more visual detection result is obtained, a sample to be detected is extracted from food to be detected by using the microfluid, the pathogen to be detected is extracted from the sample to be detected, mass spectrum sampling is carried out on the pathogen to be detected to obtain a mass spectrum picture to be detected, pathogen component analysis is carried out on the mass spectrum picture to be detected by using the pathogen mass spectrum analysis model to obtain a pathogen detection result, a visual pathogen detection result can be quickly and accurately generated, a step of manual labeling and manual measurement is omitted, and the pathogen detection efficiency is improved. Therefore, the method for detecting the food-borne disease pathogens based on the microfluid can solve the problem of low efficiency in detecting the food-borne disease pathogens.
Fig. 4 is a functional block diagram of a detection system for detecting a pathogen of a food-borne disease based on a microfluidic device according to an embodiment of the present invention.
The microfluidic-based detection system 100 for food-borne disease pathogens according to the present invention may be installed in an electronic device. Depending on the functions implemented, the microfluidic-based detection system 100 for food-borne disease pathogens may include a pathogen capture module 101, a fluorescence detection module 102, a feature extraction module 103, a model training module 104, and a mass spectrometry detection module 105. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the pathogen capturing module 101 is configured to sample a plurality of food sources to obtain a food source sample set, sequentially perform sample impurity removal and sample concentration operations on each food source sample in the food source sample set to obtain a concentrated sample set, and perform pathogen capturing on the concentrated sample set by using a surface modification layer of a microfluid to obtain a captured pathogen set;
The fluorescence detection module 102 is configured to perform pathogen enrichment operation on the captured pathogen set by using the microfluidic separation layer to obtain an enriched pathogen set, perform fluorescence detection on the enriched pathogen set to obtain a pathogen distribution data set, and perform mass spectrum sampling on the enriched pathogen set to obtain a pathogen mass spectrum atlas;
the feature extraction module 103 is configured to perform image enhancement and image calibration operations on the pathogenic mass spectrum pictures in the pathogenic mass spectrogram set one by one to obtain a calibrated pathogenic atlas, perform frequency domain transformation and multiple feature extraction operations on the calibrated pathogenic atlas one by one to obtain a pathogenic feature set, where the performing image enhancement and image calibration operations on the pathogenic mass spectrum pictures in the pathogenic mass spectrogram set one by one to obtain a calibrated pathogenic atlas includes: selecting pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one as target pathogen pictures, and performing Gaussian filtering on the target pathogen pictures to obtain denoising pathogen pictures; generating a gray level histogram of the denoising pathogen picture, and carrying out gray level equalization on the denoising pathogen picture according to the gray level histogram to obtain an equalized pathogen picture; and carrying out image enhancement on the balanced pathogen image by using the following gray enhancement algorithm to obtain an enhanced pathogen image:
Wherein f (x, y) is the gray value of the pixel point with coordinates of (x, y) in the enhanced pathogen image, x is the abscissa of the pixel, y is the ordinate of the pixel, a is the preset enhancement coefficient, exp is an exponential function, b is the preset translation coefficient, z max Is the maximum gray value, z, in the equalized pathogen picture min Is the minimum gray value in the balanced pathogen picture, L is the gray level of the balanced pathogen picture, and g (x, y) is the gray value of the pixel point with the coordinates of (x, y) in the balanced pathogen picture; sequentially carrying out baseline correction and wavelength calibration on the enhanced pathogen pictures to obtain calibrated pathogen pictures, and collecting all the calibrated pathogen pictures into a calibrated pathogen atlas;
the model training module 104 is configured to extract a pathogen quantitative semantic group set from the pathogen distribution data set, perform structural transcoding on each pathogen feature in the pathogen feature set to obtain a pathogen encoding group set, and train a preset self-attention pathogen model by using the pathogen encoding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model;
the mass spectrum detection module 105 is configured to extract a sample to be detected from a food to be detected, extract a pathogen to be detected from the sample to be detected by using the microfluidic, sample the pathogen to be detected by mass spectrum, obtain a mass spectrum picture to be detected, and analyze a pathogen component of the mass spectrum picture to be detected by using the pathogen mass spectrum analysis model, so as to obtain a pathogen detection result.
In detail, each module in the detection system 100 for implementing a food-borne disease pathogen based on a micro-fluid according to the embodiment of the present invention adopts the same technical means as the detection method for implementing a food-borne disease pathogen based on a micro-fluid described in fig. 1 to 3, and can produce the same technical effects, which are not described herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Multiple units or systems set forth in the system embodiments may also be implemented by one unit or system in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A method for detecting a food-borne disease pathogen based on microfluidics, the method comprising:
s1: sampling a plurality of food sources to obtain a food source sample set, sequentially carrying out sample impurity removal and sample concentration on each food source sample in the food source sample set to obtain a concentrated sample set, and carrying out pathogen capture on the concentrated sample set by utilizing a surface modification layer of microfluid to obtain a captured pathogen set;
s2: performing pathogen enrichment operation on the captured pathogen set by utilizing the separation layer of the microfluid to obtain an enriched pathogen set, performing fluorescence detection on the enriched pathogen set to obtain a pathogen distribution data set, and performing mass spectrum sampling on the enriched pathogen set to obtain a pathogen mass spectrum atlas;
s3: performing image enhancement and image calibration operations on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas, performing frequency domain transformation and multiple feature extraction operations on the calibrated pathogen atlas one by one to obtain a pathogen feature set, wherein the performing image enhancement and image calibration operations on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas comprises:
S31: selecting pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one as target pathogen pictures, and performing Gaussian filtering on the target pathogen pictures to obtain denoising pathogen pictures;
s32: generating a gray level histogram of the denoising pathogen picture, and carrying out gray level equalization on the denoising pathogen picture according to the gray level histogram to obtain an equalized pathogen picture;
s33: and carrying out image enhancement on the balanced pathogen image by using the following gray enhancement algorithm to obtain an enhanced pathogen image:
wherein f (x, y) is the gray value of the pixel point with coordinates of (x, y) in the enhanced pathogen image, x is the abscissa of the pixel, y is the ordinate of the pixel, a is the preset enhancement coefficient, exp is an exponential function, b is the preset translation coefficient, z max Is the maximum gray value, z, in the equalized pathogen picture min Is the minimum gray value in the balanced pathogen picture, L is the gray level of the balanced pathogen picture, and g (x, y) is the gray value of the pixel point with the coordinates of (x, y) in the balanced pathogen picture;
s34: sequentially carrying out baseline correction and wavelength calibration on the enhanced pathogen pictures to obtain calibrated pathogen pictures, and collecting all the calibrated pathogen pictures into a calibrated pathogen atlas;
S4: extracting a pathogen quantitative semantic group set from the pathogen distribution data group set, performing structural transcoding on each pathogen feature in the pathogen feature group set to obtain a pathogen encoding group set, and training a preset self-attention pathogen model by using the pathogen encoding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model;
s5: extracting a sample to be detected from food to be detected, extracting a pathogen to be detected from the sample to be detected by utilizing the microfluid, carrying out mass spectrum sampling on the pathogen to be detected to obtain a mass spectrum picture to be detected, and carrying out pathogen component analysis on the mass spectrum picture to be detected by utilizing the pathogen mass spectrum analysis model to obtain a pathogen detection result.
2. The method for detecting a pathogen of a food-borne disease based on a microfluidics device according to claim 1, wherein the sequentially performing sample impurity removal and sample concentration operations on each food-borne sample in the food-borne sample set to obtain a concentrated sample set comprises:
selecting food samples in the food sample set one by one as target food samples, and performing sample crushing operation on the target food samples to obtain crushed food samples;
Sequentially carrying out sample dilution and sample soaking operation on the crushed food source sample to obtain a dissolved food source sample;
performing primary filtering operation on the dissolved food source sample by using a filter to obtain a filtered food source sample;
performing sample centrifugation on the dissolved food sample to obtain a centrifuged food sample;
and performing secondary filtering operation on the centrifugal food source sample by using an ultrafiltration membrane to obtain a concentrated sample, and collecting all the concentrated samples into a concentrated sample set.
3. The microfluidic-based detection method of food-borne disease pathogens according to claim 1, wherein the pathogen capture of the concentrated sample set using a surface modification layer of the microfluidic comprises:
selecting concentrated samples in the concentrated sample set one by one as target concentrated samples, and injecting the target concentrated solution into corresponding microfluid;
utilizing chemical modification molecules on a surface modification layer inside the microfluid to specifically capture pathogens in the target concentrated solution to obtain captured pathogens;
all captured pathogens corresponding to the concentrated sample set are pooled into a captured pathogen set.
4. The method for detecting a pathogen of food-borne disease based on a micro-fluid according to claim 1, wherein the pathogen enrichment operation of the captured pathogen set by using the separation layer of the micro-fluid to obtain an enriched pathogen set comprises:
Selecting the capture pathogens in the capture pathogen set one by one as target capture pathogens, and performing cell lysis on the target capture pathogens to obtain target lysis pathogens;
complementary binding is carried out on the target cracking pathogen by using a primer to obtain a target complementary pathogen;
performing directional amplification on the target complementary pathogen by using polymerase to obtain a target amplified pathogen;
annealing, extending, regenerating and the like are sequentially carried out on the target amplification pathogen to obtain a target denaturation pathogen;
and (3) separating the target denatured pathogen by utilizing the microfluidic separation layer to obtain target enriched pathogen, and collecting all the target enriched pathogen into an enriched pathogen set.
5. The method for detecting a pathogen of food-borne diseases based on microfluidics according to claim 1, wherein the performing fluorescent detection on the enriched pathogen set to obtain a pathogen distribution dataset comprises:
selecting the concentrated pathogens in the concentrated pathogen set one by one as target concentrated pathogens, and performing fluorescent hybridization on the target concentrated pathogens by using a preset fluorescent probe set to obtain target fluorescent pathogens;
measuring a fluorescence signal of the target fluorescent pathogen by using a fluorescence detector to obtain a fluorescence signal data set;
And performing pathogen labeling on the fluorescent signal data set to obtain a pathogen distribution data set, and collecting all pathogen distribution data sets into a pathogen distribution data set.
6. The microfluidic-based detection method of food-borne disease pathogens according to claim 1, wherein the sequentially performing baseline correction and wavelength calibration on the enhanced pathogen image to obtain a calibrated pathogen image comprises:
screening a baseline region from the enhanced pathogen picture according to the mass spectrum peak of the enhanced pathogen picture;
fitting a baseline curve from the baseline region, and removing the baseline curve from the enhanced pathogen picture to obtain a corrected pathogen picture;
calculating the offset of the mass spectrum peak of the corrected pathogen image, and carrying out wavelength calibration on the corrected pathogen image according to the offset to obtain a calibrated pathogen image.
7. The method for detecting a pathogen of a food-borne disease based on microfluidics according to claim 1, wherein the performing frequency domain transformation and multiple feature extraction operations on the calibration pathogen atlas one by one to obtain a pathogen feature set includes:
selecting calibration pathogen pictures in the calibration pathogen image set one by one as target calibration pictures, and performing frequency domain transformation on the target calibration pictures by using the following multi-layer frequency domain transformation algorithm to obtain a frequency domain coefficient set:
Wherein t is j,k Refers to the kth decomposition coefficient of the decomposition frequency domain of the jth layer in the frequency domain coefficient set, s j Refers to the scale factor of the j-th layer decomposition frequency domain, N refers to the signal scale sequence number of the target calibration picture, N refers to the signal scale size of the target calibration picture, and h n Refers to a first filter coefficient, d, of the target calibration picture on the nth signal scale j Refer to detail coefficients of the j-th layer decomposition frequency domain, f n Means that the target calibration picture is a second filter coefficient on the nth signal scale
Extracting distribution characteristics, position characteristics and phase characteristics from the frequency domain coefficient set in sequence;
and collecting the distribution characteristics, the position characteristics and the phase characteristics into pathogen characteristic groups, and collecting all pathogen characteristic groups into pathogen characteristic group sets.
8. The method for detecting a pathogen of a food-borne disease based on microfluidics according to claim 1, wherein the step of performing structural transcoding on each pathogen feature in the pathogen feature set to obtain a pathogen encoding set comprises:
selecting the pathogen feature groups in the pathogen feature group one by one as target pathogen feature groups, and adding position vectors for the target pathogen feature groups to obtain position pathogen feature groups;
Performing attention transcoding on the position pathogen feature set by using an attention matrix to obtain an attention pathogen feature set;
carrying out full-connection pooling operation on the attention pathogenic characteristic group to obtain a pooled pathogenic characteristic group;
and linearly activating the pooled pathogen feature groups to obtain pathogen code groups, and converging all pathogen code groups into pathogen code group sets.
9. The method for detecting a pathogen of a food-borne disease based on microfluidics according to claim 1, wherein training a preset self-attention pathogen model by using the pathogen encoding set and the pathogen quantitative semantic set to obtain a pathogen mass spectrometry model comprises:
generating a predicted pathogen semantic group set corresponding to the pathogen encoding group set by using a preset self-attention pathogen model;
calculating a model loss value of the self-attention pathogen model according to the predicted pathogen semantic group set and the pathogen quantitative semantic group set;
and iteratively updating the model parameters of the self-attention pathogen model according to the model loss value until the model loss value is smaller than a preset loss value threshold, and taking the updated self-attention pathogen model as a pathogen mass spectrum analysis model.
10. A microfluidic-based detection system for implementing a food-borne disease pathogen, the system comprising:
the pathogen capturing module is used for sampling various food sources to obtain a food source sample set, sequentially carrying out sample impurity removal and sample concentration operation on each food source sample in the food source sample set to obtain a concentrated sample set, and carrying out pathogen capturing on the concentrated sample set by utilizing a surface modification layer of a microfluid to obtain a captured pathogen set;
the fluorescence detection module is used for carrying out pathogen enrichment operation on the captured pathogen set by utilizing the separation layer of the microfluid to obtain an enriched pathogen set, carrying out fluorescence detection on the enriched pathogen set to obtain a pathogen distribution data set, and carrying out mass spectrum sampling on the enriched pathogen set to obtain a pathogen mass spectrum atlas;
the feature extraction module is used for carrying out image enhancement and image calibration operation on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas, carrying out frequency domain transformation and multiple feature extraction operation on the calibrated pathogen atlas one by one to obtain a pathogen feature set, wherein the step of carrying out image enhancement and image calibration operation on the pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one to obtain a calibrated pathogen atlas comprises the following steps: selecting pathogen mass spectrum pictures in the pathogen mass spectrogram set one by one as target pathogen pictures, and performing Gaussian filtering on the target pathogen pictures to obtain denoising pathogen pictures; generating a gray level histogram of the denoising pathogen picture, and carrying out gray level equalization on the denoising pathogen picture according to the gray level histogram to obtain an equalized pathogen picture; and carrying out image enhancement on the balanced pathogen image by using the following gray enhancement algorithm to obtain an enhanced pathogen image:
Wherein f (x, y) is the gray value of the pixel point with coordinates of (x, y) in the enhanced pathogen image, x is the abscissa of the pixel, y is the ordinate of the pixel, a is the preset enhancement coefficient, exp is an exponential function, b is the preset translation coefficient, z max Is the maximum gray value, z, in the equalized pathogen picture min Is the minimum gray value in the balanced pathogen picture, L is the gray level of the balanced pathogen picture, and g (x, y) is the gray value of the pixel point with the coordinates of (x, y) in the balanced pathogen picture; sequentially carrying out baseline correction and wavelength calibration on the enhanced pathogen pictures to obtain calibrated pathogen pictures, and collecting all the calibrated pathogen pictures into a calibrated pathogen atlas;
the model training module is used for extracting a pathogen quantitative semantic group set from the pathogen distribution data group set, performing structural transcoding on each pathogen feature in the pathogen feature group set to obtain a pathogen encoding group set, and training a preset self-attention pathogen model by using the pathogen encoding group set and the pathogen quantitative semantic group set to obtain a pathogen mass spectrum analysis model;
the mass spectrum detection module is used for extracting a sample to be detected from food to be detected, extracting a pathogen to be detected from the sample to be detected by utilizing the microfluid, carrying out mass spectrum sampling on the pathogen to be detected to obtain a mass spectrum picture to be detected, and carrying out pathogen component analysis on the mass spectrum picture to be detected by utilizing the pathogen mass spectrum analysis model to obtain a pathogen detection result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310511188.5A CN116500263A (en) | 2023-05-08 | 2023-05-08 | Method and system for detecting food-borne disease pathogens based on microfluidics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310511188.5A CN116500263A (en) | 2023-05-08 | 2023-05-08 | Method and system for detecting food-borne disease pathogens based on microfluidics |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116500263A true CN116500263A (en) | 2023-07-28 |
Family
ID=87319962
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310511188.5A Pending CN116500263A (en) | 2023-05-08 | 2023-05-08 | Method and system for detecting food-borne disease pathogens based on microfluidics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116500263A (en) |
-
2023
- 2023-05-08 CN CN202310511188.5A patent/CN116500263A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Microbial community analyses associated with nine varieties of wine grape carposphere based on high-throughput sequencing | |
CN108280320B (en) | Rapid and accurate high-flux drug screening system based on deep learning | |
CN109863239A (en) | The spectroscopy system and method for identification and quantification for pathogen | |
EP3171172B1 (en) | Method and device for detecting bacteria | |
CN107850540A (en) | Prepare the method that fluid sample carries out LIBS and imaging analysis | |
Steward | Fingerprinting viral assemblages by pulsed field gel electrophoresis (PFGE) | |
US10415031B2 (en) | Method, apparatus and kit for human identification using polymer filter means for separation of sperm cells from biological samples that include other cell types | |
CN114399763B (en) | Single-sample and small-sample micro-body paleobiological fossil image identification method and system | |
Barboux et al. | FTIR spectroscopy for identification and intra-species characterization of Serpula lacrymans | |
CN116500263A (en) | Method and system for detecting food-borne disease pathogens based on microfluidics | |
CN105132588A (en) | Method for detecting sweet potato leaf curl viruses and special primer set thereof | |
CN112560597B (en) | Microscopic hyperspectral based COVID-19 detection and identification method | |
CN116287138B (en) | FISH-based cell detection system and method thereof | |
US20190362491A1 (en) | Computer-implemented apparatus and method for performing a genetic toxicity assay | |
EP3617916A1 (en) | Integration system and integration method | |
Nijssen et al. | Axon-seq for in depth analysis of the RNA content of neuronal processes | |
CN107746884B (en) | AFLP primer combination product, kit and method for identifying individual and variety of beef cattle | |
CN113744806B (en) | Fungus sequencing data identification method based on nanopore sequencer | |
CN113470752B (en) | Bacterial sequencing data identification method based on nanopore sequencer | |
Kim et al. | A novel pathogen capturing device for removal and detection | |
WO2021155221A3 (en) | Apparatus and method for collecting liquid samples | |
CN110408722B (en) | Specific DNA segment and primer for mulberry species identification | |
KR20230167028A (en) | Machine-learning model for detecting bubbles in nucleotide sample slides for sequencing | |
Gai et al. | Effective classification of melting curve in real-time PCR based on dynamic filter-based convolutional neural network | |
Bao et al. | Real-time, direct classification of nanopore signals with squigglenet |
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 |