CN113945539A - GWAS (glow wire optical network analysis) -based method and system for predicting quality of near infrared spectrum characteristic waveband after screening - Google Patents
GWAS (glow wire optical network analysis) -based method and system for predicting quality of near infrared spectrum characteristic waveband after screening Download PDFInfo
- Publication number
- CN113945539A CN113945539A CN202111209987.4A CN202111209987A CN113945539A CN 113945539 A CN113945539 A CN 113945539A CN 202111209987 A CN202111209987 A CN 202111209987A CN 113945539 A CN113945539 A CN 113945539A
- Authority
- CN
- China
- Prior art keywords
- near infrared
- infrared spectrum
- sample
- gwas
- characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 103
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 76
- 238000012216 screening Methods 0.000 title claims abstract description 54
- 238000003012 network analysis Methods 0.000 title description 2
- 230000003287 optical effect Effects 0.000 title description 2
- 235000013372 meat Nutrition 0.000 claims abstract description 79
- 238000004458 analytical method Methods 0.000 claims abstract description 64
- 238000010586 diagram Methods 0.000 claims abstract description 30
- 230000003595 spectral effect Effects 0.000 claims abstract description 27
- 238000005516 engineering process Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims description 27
- 238000001228 spectrum Methods 0.000 claims description 25
- 238000012937 correction Methods 0.000 claims description 14
- 238000002790 cross-validation Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 11
- 238000002360 preparation method Methods 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 9
- 102000004169 proteins and genes Human genes 0.000 claims description 8
- 108090000623 proteins and genes Proteins 0.000 claims description 8
- 238000012417 linear regression Methods 0.000 claims description 7
- 102000008186 Collagen Human genes 0.000 claims description 6
- 108010035532 Collagen Proteins 0.000 claims description 6
- 229920001436 collagen Polymers 0.000 claims description 6
- 238000012850 discrimination method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 210000003195 fascia Anatomy 0.000 claims description 5
- 239000011521 glass Substances 0.000 claims description 5
- 235000020997 lean meat Nutrition 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 150000003839 salts Chemical class 0.000 claims description 5
- 150000004671 saturated fatty acids Chemical class 0.000 claims description 5
- 159000000000 sodium salts Chemical class 0.000 claims description 5
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 235000003441 saturated fatty acids Nutrition 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims 1
- 239000000523 sample Substances 0.000 description 59
- 230000000875 corresponding effect Effects 0.000 description 25
- 235000015277 pork Nutrition 0.000 description 9
- 235000013622 meat product Nutrition 0.000 description 7
- 238000012098 association analyses Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 6
- 238000009395 breeding Methods 0.000 description 5
- 230000001488 breeding effect Effects 0.000 description 5
- 230000002068 genetic effect Effects 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 241000282887 Suidae Species 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 241000726221 Gemma Species 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- 238000000342 Monte Carlo simulation Methods 0.000 description 2
- 238000004497 NIR spectroscopy Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 235000014113 dietary fatty acids Nutrition 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000009313 farming Methods 0.000 description 2
- 229930195729 fatty acid Natural products 0.000 description 2
- 239000000194 fatty acid Substances 0.000 description 2
- 150000004665 fatty acids Chemical class 0.000 description 2
- 238000002373 gas-phase electrophoretic mobility molecular analysis Methods 0.000 description 2
- 230000007614 genetic variation Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004566 IR spectroscopy Methods 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012252 genetic analysis Methods 0.000 description 1
- 238000003205 genotyping method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002773 nucleotide Substances 0.000 description 1
- 125000003729 nucleotide group Chemical group 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000003307 slaughter Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B20/20—Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Analytical Chemistry (AREA)
- Genetics & Genomics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Medical Informatics (AREA)
- Biotechnology (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Biochemistry (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a method and a system for predicting quality based on near infrared spectrum characteristic bands after GWAS screening, which apply a special near infrared spectrum characteristic band screening strategy, firstly scan a configured original sample by using near infrared spectrum acquisition equipment to obtain spectral data of the sample, determine various meat quality property physicochemical indexes of the sample, then introduce the two data into a corresponding system according to a set mode for GWAS analysis, further draw a matched Manhattan diagram according to an analysis result and a set threshold line, screen out a plurality of matching bands which exceed a threshold value and correspond to various meat property indexes based on information in the diagram, finally realize meat quality prediction by using a near infrared spectrum technology based on the screened bands, on one hand, the problems of equipment performance overflow and high cost in the traditional prediction process are overcome, and the prediction cost is controlled at a reasonable level, on the other hand, the data processing flow is simplified, the prediction timeliness is optimized, and the accuracy of the prediction result is improved.
Description
Technical Field
The invention relates to the technical field of nondestructive reliability testing and detection monitoring of quality, in particular to a GWAS (glow-wire-optical-spectrum) screening-based method and a GWAS screening-based system for predicting quality of near infrared spectrum characteristic bands, which can be used for nondestructive detection and monitoring of meat products.
Background
In recent years, with the improvement of living standard of people, the demand of consumers for high-quality meat products with delicious taste and rich nutrition is continuously increased, the market consumption structure is changed, pork is taken as main consumption meat in the market, and more breeding companies take the long-term aim of checking and improving the pork quality as pig breeding. There are many indicators that are commonly used to assess the quality of pork, including fat, moisture, protein, fatty acid content, PH, flesh color, etc. In addition to conventional physicochemical analysis, the evaluation methods for the pork quality indexes in food and farming and animal husbandry industries all over the world are also gradually favored by researchers or related industrial personnel by nondestructive, rapid and convenient meat product component determination methods based on visible light/near infrared spectroscopy.
However, in the industrial practical application process of the near infrared spectrum analysis technology, the cost of the available near infrared spectrum measuring instrument is not high, and especially the measuring probes matched with different wave band configurations and matched with the instrument are often expensive, which may be a huge expense for scientific research workers or related practitioners, so that the application of the meat product component measuring technology which is nondestructive, rapid and convenient for the visible light/near infrared spectrum technology is obviously limited, and the practicability is limited; in addition, the meat quality character prediction is realized by utilizing a visible light/near infrared spectrum instrument based on full-wave band configuration, the pertinence is insufficient, the reliability of a prediction result is insufficient, and the market and the demand of meat quality cultivation cannot be realized.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
In order to solve the above problem, the present invention provides a method for predicting quality of a near infrared spectrum characteristic band after GWAS screening, and in one embodiment, the method includes:
a sample configuration step, configuring original meat samples of a set scale based on comprehensive meat quality traits to be detected, performing sample preparation processing according to a set processing strategy, and numbering prepared target samples;
the method comprises the following steps of measuring data, scanning each target sample through near infrared spectrum acquisition equipment to obtain near infrared spectrum data, obtaining meat quality property data of each target sample by utilizing a measurement function module attached to the near infrared equipment or a matched physical and chemical measurement means, and recording the two data in a correlation manner;
GWAS analysis, namely calling a linear mixing model by utilizing GEMMA software to carry out GWAS analysis on the two to obtain a corresponding analysis result;
drawing a characteristic diagram, and drawing a corresponding Manhattan diagram based on a result file after GWAS analysis in cooperation with a set significance threshold line;
a characteristic screening step, namely screening and determining effective spectral bands corresponding to all meat quality characteristic indexes according to the distribution condition of each meat quality characteristic index representation information relative to spectral band representation information in a Manhattan diagram;
and (3) forecasting the application steps, and forecasting the meat quality character based on the effective spectrum band obtained by screening by utilizing the near infrared spectrum technology.
In an optional embodiment, in the sample configuration step, the meat quality trait to be measured includes the following indexes: fat, moisture, protein, lean meat percentage, collagen, salt, ash, saturated fatty acids, energy kJ/100g, energy kcal/100g, sodium salt, pH, L, a, and b.
Further, in one embodiment, in the sample configuration step, the process of performing the sample preparation process according to the set processing strategy includes:
the fat and fascia visible on the surface of each original sample were removed, and each sample was crushed using a crushing apparatus so that the crushed samples could be sampled and filled uniformly into round glass plates.
In one embodiment, in the data determining step, after scanning to obtain the near infrared spectrum data, the method further includes:
and eliminating the samples exceeding the Mahalanobis distance threshold value by using a Mahalanobis distance discrimination method, and putting the rest samples serving as effective samples into the meat quality character data acquisition and subsequent steps.
In a preferred embodiment, in the GWAS analyzing step, the GWAS analyzing step includes: and (3) taking the meat quality character data as a phenotype file, taking the near infrared spectrum data as a genotype file, inputting the phenotype file and the near infrared spectrum data into corresponding GEMMA software or a platform, and calling a linear mixing model to perform GWAS analysis so as to effectively eliminate the influence of multiple collinearity existing among spectrum bands on an analysis result.
Further, in an embodiment, in the GWAS analyzing step, a linear mixture model shown in the following formula is called:
Y＝Xb+Zu+ε
y is a phenotype vector corresponding to the sample, X is a fixed effect matrix generated by covariates, Z is a random effect matrix aggregating all sample spectrum information, b and u respectively represent weight coefficients of the fixed effect and the random effect, and epsilon is a residual error.
Specifically, in one embodiment, in the step of drawing the feature map, the spectral band is taken as an abscissa, the significance p value is subjected to-log 10 conversion and then taken as an ordinate to draw a scatter diagram, and a significant threshold line is set by using a Bonferroni correction method.
In an optional embodiment, in the feature screening step, for each meat quality trait index, each peak of each index exceeding a threshold value in the feature map and 5 bands around the peak are selected, and the bands are used as matching near-infrared feature bands corresponding to a single meat quality trait index.
Further, in one embodiment, the method further comprisesThe method comprises the steps of analyzing and verifying, wherein before the step of predicting and applying, the selected characteristic wave bands are verified relative to the full wave bands by applying a multiple linear regression model, and the following parameters are calculated: correction set decision coefficient
Cross validation set decision coefficient
The root mean square error of the correction set (RMSEC) and the root mean square error of the cross validation set (RMSECV) are compared and measured with the prediction result of the screened characteristic wave band relative to the full wave band.
Based on other aspects of the method in any one or more of the above embodiments, the present invention further provides a system for predicting quality of near infrared spectrum characteristic band after GWAS screening, where the system performs the method in any one or more of the above embodiments.
Compared with the closest prior art, the invention also has the following beneficial effects:
the invention provides a method and a system for predicting quality based on near infrared spectrum characteristic wave bands after GWAS screening, wherein the method applies a special near infrared spectrum characteristic wave band screening strategy, firstly, near infrared spectrum acquisition equipment is utilized to scan a configured original sample to obtain the spectral data of the sample, various meat quality property physicochemical indexes of the sample are measured, then, the two data are led into a corresponding system according to a set mode to carry out GWAS analysis, a matched Manhattan graph is drawn according to an analysis result and a set threshold line, a plurality of matching wave bands which exceed a threshold value and correspond to various meat quality property indexes are screened out based on the information in the graph, finally, the meat quality prediction is realized based on the screened wave bands by utilizing a near infrared spectrum technology, on one hand, the input cost in the future near infrared equipment and the purchase stage is effectively controlled, on the other hand, the data processing flow is simplified, the prediction timeliness is optimized, and meanwhile the accuracy of the prediction result is improved.
Furthermore, in the invention, the correlation result of the spectrum and the sample index is displayed in a visual form in a manhattan diagram mode, so that the visual feeling is provided for researchers or related industrial personnel;
in addition, the researchers of the present invention consider that in GWAS analysis taking genetics as a background, each independent data individual has characteristics of high dimensionality, and besides, a great degree of collinearity exists among all the dimensionalities, which is called linkage disequilibrium among SNP loci in genetic analysis. And a linear mixed model is called in the GWAS analysis step to realize analysis, so that the method not only contains a fixed effect, but also contains a random effect, the influence of multiple collinearity on an analysis result can be effectively eliminated, and the reliability of the analysis result is ensured.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic flowchart of a method for predicting quality of a near infrared spectrum characteristic band after GWAS-based screening according to an embodiment of the present invention;
figure 2 is a schematic diagram of the principle of GWAS-based near infrared spectrum characteristic band screening in the method for predicting quality provided by the embodiment of the invention;
fig. 3 is a schematic flow chart of configuring a sample in a method for predicting quality of near infrared spectrum characteristic band after GWAS-based screening according to another embodiment of the present invention;
fig. 4 is an example of a near infrared spectrum before outliers are removed in the method for predicting quality of near infrared spectrum characteristic bands after GWAS screening according to the embodiment of the present invention;
fig. 5 is an example of a near infrared spectrum after outliers are removed in the method for predicting quality of near infrared spectrum characteristic bands after GWAS-based screening according to the embodiment of the present invention;
fig. 6 is a manhattan diagram example of a method for predicting quality of near infrared spectrum characteristic bands after GWAS-based screening according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a system for predicting quality of near infrared spectrum characteristic bands after GWAS-based screening according to another embodiment of the present invention.
Detailed Description
The following detailed description will be provided for the embodiments of the present invention with reference to the accompanying drawings and examples, so that the practitioner of the present invention can fully understand how to apply the technical means to solve the technical problems, achieve the technical effects, and implement the present invention according to the implementation procedures. It should be noted that, unless otherwise conflicting, the embodiments and features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are all within the scope of the present invention.
Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel, concurrently, or simultaneously. The order of the operations may be rearranged. A process may be terminated when its operations are completed, but may have additional steps not included in the figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.
The computer equipment comprises user equipment and network equipment. The user equipment or the client includes but is not limited to a computer, a smart phone, a PDA, and the like; network devices include, but are not limited to, a single network server, a server group of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. The computer devices may operate individually to implement the present invention or may be networked and interoperate with other computer devices in the network to implement the present invention. The network in which the computer device is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Pork is the main consumer meat in the market, and more breeding companies are taking the inspection and improvement of pork quality as a long-term goal of pig breeding. There are many indicators that are commonly used to assess the quality of pork, including fat, moisture, protein, fatty acid content, PH, flesh color, etc. In addition to conventional physicochemical analysis, the evaluation methods for the pork quality indexes in food and farming and animal husbandry industries all over the world are also gradually favored by researchers or related industrial personnel by nondestructive, rapid and convenient meat product component determination methods based on visible light/near infrared spectroscopy.
However, in the industrial practical application process of the near infrared spectrum analysis technology, the cost of the available near infrared spectrum measuring instrument is not high, and especially the measuring probes matched with different wave band configurations and matched with the instrument are often expensive, which may be a huge expense for scientific research workers or related practitioners, so that the application of the meat product component measuring technology which is nondestructive, rapid and convenient for the visible light/near infrared spectrum technology is obviously limited, and the practicability is limited; in addition, the meat quality character prediction is realized by utilizing a visible light/near infrared spectrum instrument based on full-wave band configuration, the pertinence is insufficient, the reliability of a prediction result is insufficient, and the market and the demand of meat quality cultivation cannot be realized.
Based on the consideration of the near infrared detection technology, researchers of the invention can screen out the near infrared band or band range really needed in the prediction work in a targeted manner, and bring the near infrared band or band range into the research, development and purchase stages of the near infrared equipment, thereby effectively reducing the overflow of the hardware equipment performance in the using process, and effectively achieving the purposes of reducing the use cost and promoting the industrialized application of the near infrared detection technology.
Common screening methods for spectral characteristic bands are roughly divided into two categories, the first category is screening based on mathematical statistics and comprises a continuous projection algorithm (SPA), a correlation coefficient method (CC), a Monte Carlo Method (MC) and the like. The second category is feature robot optimization based on artificial intelligence, such as Genetic Algorithm (GA), Ant Colony Algorithm (ACA), random frog-leaping algorithm (RF), etc. In related reports at home and abroad, the methods have achieved good results on characteristic band screening of spectra. However, in specific applications, the methods require users to have a certain degree of mathematical modeling and program compiling basis, so that low thresholds are set for common workers, and the popularization and the promotion of the methods in the industrial practical application process of the near infrared technology are limited. Therefore, the research project group develops a novel, efficient and convenient near infrared spectrum characteristic waveband screening method based on GWAS (whole genome association analysis), and applies the method to the meat quality prediction technology.
Specifically, in order to solve the above problems, the invention provides a method and a system for predicting quality based on near infrared spectrum characteristic bands after GWAS screening, the scheme is based on the technical knowledge base of genetics, by establishing the relevance between the spectrum bands and various physical and chemical indexes of a sample, presenting the relevance result in a visual mode, and performing reliable modeling verification on the screened characteristic bands, so that the improvement of prediction potential of various physical and chemical indexes is realized, and assistance is provided for the near infrared technology on an industrial application road.
The detailed flow of the method of the embodiments of the present invention is described in detail below based on the accompanying drawings, and the steps shown in the flow chart of the drawings can be executed in a computer system containing a computer-executable instruction such as a set of computer-executable instructions. Although a logical order of steps is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Example one
Fig. 1 is a schematic flow chart illustrating a method for predicting quality of a near infrared spectrum characteristic band after GWAS-based screening according to an embodiment of the present invention, and as can be seen from fig. 1, the method includes the following steps.
A sample configuration step, configuring original meat samples of a set scale based on comprehensive meat quality traits to be detected, performing sample preparation processing according to a set processing strategy, and numbering prepared target samples;
the method comprises the following steps of measuring data, scanning each target sample through near infrared spectrum acquisition equipment to obtain near infrared spectrum data, obtaining meat quality property data of each target sample by utilizing a measurement function module attached to the near infrared equipment or a matched physical and chemical measurement means, and recording the two data in a correlation manner;
GWAS analysis, namely calling a linear mixing model by utilizing GEMMA software to carry out GWAS analysis on the two to obtain a corresponding analysis result;
drawing a characteristic diagram, and drawing a corresponding Manhattan diagram based on a result file after GWAS analysis in cooperation with a set significance threshold line;
a characteristic screening step, namely screening and determining effective spectral bands corresponding to all meat quality characteristic indexes according to the distribution condition of each meat quality characteristic index representation information relative to spectral band representation information in a Manhattan diagram;
and (3) forecasting the application steps, and forecasting the meat quality character based on the effective spectrum band obtained by screening by utilizing the near infrared spectrum technology.
By adopting the operation logic in the embodiment, aiming at the problems that the surplus of the modeling waveband causes the overflow of the hardware equipment performance and the industrialization popularization cost is high in the actual production and application process of the current near infrared technology, and the realization difficulty and the threshold of most of the existing characteristic waveband screening methods are high, the GWAS (global warming function analysis) -based near infrared spectrum characteristic waveband screening strategy is specially applied, and the method is rapid, convenient and effective. On the basis of the background of genetic knowledge, the method realizes the improvement of the prediction potential of multiple physical and chemical indexes by establishing the relevance between the spectral band and each physical and chemical index of the sample, presenting the relevance result in a visual mode and carrying out modeling verification on the screened characteristic band, and provides assistance for the near infrared technology on an industrial application road.
In practical application, the adopted screening strategy of the near infrared spectrum characteristic wave band comprises the following ideas: step (1), measuring and collecting sample data; step (2): GWAS analysis is carried out by utilizing GEMMA; step (3), utilizing R software to draw a Manhattan diagram; and (4) extracting a target characteristic wave band according to the information in the Manhattan graph.
The method comprises the following steps that (1) a plurality of fresh pork samples are numbered and scanned through near infrared spectrum acquisition equipment, and meanwhile, various meat quality characters of the corresponding samples are measured by using a traditional method or a measuring module attached to the near infrared spectrum acquisition equipment;
and (2) respectively recording the meat quality and the near infrared spectrum data in a text format, wherein the meat quality is used as a phenotype file, the near infrared spectrum data is used as a genotype file and is input into GEMMA software, and calling a linear mixing model for GWAS analysis.
And (3) inputting a result file after GWAS analysis into R software, and setting a significance threshold line to draw a Manhattan graph.
And (4) observing a Manhattan diagram, and screening characteristic spectrum wave bands according to the peak valley formed by scatter point formation, as shown in figure 2.
The near infrared band screened by the process is the characteristic band corresponding to the physicochemical components of the sample. The method is an unprecedented spectrum band screening method, all near infrared spectrum bands are associated with physicochemical components needing to be predicted, the method has the advantages of simple process, strong repeatability, low technical threshold and the like, meanwhile, the visualization of the association result provides the most intuitive feeling for researchers or related practitioners, and effective assistance is provided for the industrial application of the near infrared spectrum analysis technology.
GWAS (whole genome association analysis) is a genetic statistical analysis technology which is established on the basis of association analysis, fully utilizes linkage disequilibrium at a population level, takes single nucleotide polymorphic Sites (SNP) in a genome as molecular genetic markers and locates genetic factors influencing complex phenotypic traits. The basic principle is to select genetic variation in the whole genome range for genotyping, compare the frequency difference of each genetic variation between abnormal individuals and a control group, and statistically analyze the strength of the association between each variation and target traits.
In the invention, the reliable relevance between the spectrum band and each physical and chemical property of a sample is established mainly by combining the related background of genetics and adopting the thought and flow of genome wide association analysis (GWAS), thereby realizing the screening of the characteristic band.
In order to ensure that the characteristic bands obtained after screening can fully cover various meat quality trait indexes, the meat quality trait indexes to be measured need to be fully considered in the process of preparing the sample, and specifically, in one embodiment, in the step of configuring the sample, the meat quality traits to be measured which need to be considered include the following indexes: fat, moisture, protein, lean meat percentage, collagen, salt, ash, saturated fatty acids, energy kJ/100g, energy kcal/100g, sodium salt, pH, L, a, and b.
Further, reasonable samples need to be configured before data measurement, and in practical application, the individual original samples for calibration modeling in the experiment of the invention are respectively obtained from slaughtering of three pig breeding companies in Guangdong, Jiangxi and Guangxi. Wherein 90 percent of individuals are Changbai pigs, big white pigs and filial generations thereof, and 10 percent of local pigs are slaughtered after reaching the uniform marketing day age (average 200 days of age). Acid discharging is carried out on the slaughtered carcass in a refrigeration house at the temperature of 0-4 ℃ for 24 hours, then the carcass is cut, and the longissimus dorsi at the position of 5-6 ribs of the left half carcass is sampled and measured.
In a preferred embodiment, in the sample configuration step, the process of performing the sample preparation process according to the set processing strategy includes:
the fat and fascia visible on the surface of each original sample were removed, and each sample was crushed using a crushing apparatus so that the crushed samples could be sampled and filled uniformly into round glass plates.
In practical application, all samples can be thawed at room temperature (20 ℃), sampled according to the method specified in the Chinese GB/T9695.19-2008 meat and meat product sampling method, fat, fascia and the like visible on the surface of the samples are removed and numbered, each sample is respectively crushed by a small electric table-type meat grinder (Skyworth-P407, 50HZ, 300w and 28000r/min), and the samples are filled into a round glass plate (the diameter is 80mm and the depth is 13mm) after the uniform crushing is ensured, as shown in FIG. 3. The near infrared spectrum wavelength collected by the FoodScan2 spectrum analyzer used in the experiment was 400 to 1099.5 nm. The near infrared spectral data for each sample, taken as the average of 18 spectral subsets recorded at 18 different points on an autorotating plate in the analyzer, is stored as log (1/R), R representing reflectance.
Further, FoodScan was used according to the American Association of Analytical chemists AOAC (Association of Official Analytical chemists) approved Official methodTM2, a food analyzer (Denmark) instrument for measuring 15 Meat quality characters such as fat, protein, water, collagen content and the like of the longissimus dorsi of pigs in a transmission mode, and detailed data are shown in the following table 1);
TABLE 1 meat quality determination (15 items in total)
Furthermore, in consideration of the fact that random errors may exist in the measurement process and factors such as environment and batch influence subsequent modeling, researchers of the invention design to correct the acquired sample data by using a mahalanobis distance discrimination method according to the standard described in (NY/T2797-2015) in order to avoid interference of basic data sample errors (or outlier sample information) on the analysis result.
Therefore, in a preferred embodiment, in the data determining step, after scanning to obtain the near infrared spectrum data, the method further includes:
and eliminating the samples exceeding the Mahalanobis distance threshold value by using a Mahalanobis distance discrimination method, and putting the rest samples serving as effective samples into the meat quality character data acquisition and subsequent steps.
In the experiment, the spectrum range collected by Foodscan is between 400 nm and 1099.5nm, the interval is 0.5nm, samples exceeding the Mahalanobis distance threshold are removed by using the Mahalanobis distance discrimination method, and finally 1206 samples are obtained by screening. Fig. 4 and 5 show near-infrared diffuse reflection spectrograms before and after the abnormal individual is removed, respectively.
In practical application, the mahalanobis distance discrimination principle shown in the following formula can be adopted:
wherein, MDiMahalanobis distance, x, for the ith samplei＝(xi1，...，xik)TFor the ith sample xiScore in k dimensions, μ ═ μ (μ)1，...，μk)TExpectation of x, S is the covariance matrix of x, MDLIs a mahalanobis distance threshold value,
mean value obtained for the Mahalanobis distance of the samples, SDMDIs the standard deviation of the mahalanobis distance of the sample.
Based on the scheme in the embodiment, the error samples exceeding the Mahalanobis distance threshold are removed, and the rest samples are put into the meat quality character data acquisition operation and the subsequent operation, so that the consumption of computing resources can be saved, the analysis timeliness is improved, the influence of the error samples on the analysis result can be overcome, and the accuracy of the analysis result is improved.
Further utilizing GEMMA software to call a linear mixing model to carry out GWAS analysis on the obtained meat quality character data and the obtained near infrared spectrum data, and obtaining corresponding analysis results; in an embodiment, the GWAS analyzing step includes: and inputting the meat quality character data serving as a phenotype file and the near infrared spectrum data serving as a genotype file into corresponding GEMMA software or a platform to obtain a corresponding analysis result.
Respectively inputting the obtained 15 meat quality traits and the near infrared spectrum information into a text file, wherein the obtained trait file presents a matrix of n x 15, the spectrum file presents a matrix of p x (3+ n), wherein n represents the total number of samples, p represents the total number of spectrum wave bands, the meat quality trait file does not need to be added with row names and column names, the first column of the spectrum information file is a wave band serial number (400-1099.5), and the second column and the third column are filled in the same base type, namely any one of A, T, C, G. Then, the meat quality character file is used as a phenotype file, a parameter '-p' is used for calling, the spectrum information file is used as a genotype file, and a parameter '-g' is used for calling. Meanwhile, as the call of the 'g' is not a real genotype file, a parameter of 'notsrnp' needs to be added to ensure the normal running of the program. And finally calling the parameter "-1 mm 1" to perform GWAS analysis.
The genotype data used in the GWAS analysis has a high similarity to the near infrared spectrum data. In addition to having a population size and the high dimensional nature of each individual in the population, there is a large degree of co-linearity between the dimensions, referred to as linkage disequilibrium between SNP sites in the genotype data. Therefore, to eliminate the effect of multiple collinearity on the analysis results, the linear mixture model was called in GEMMA for GWAS analysis.
The linear mixture model is a variance component model that includes both fixed and random effects. When a parameter can be considered constant, the effect produced is a fixed effect. But the parameters are also characterized by random variables, we call the random effect, which is generally of the form:
Y＝Xb+Zu+ε
wherein Y is a phenotype vector corresponding to the sample; x is a fixed effect matrix (covariates such as sample types, sampling time and the like); z is a random effect matrix, which is a correlation matrix aggregating all sample spectral information in the research; b and u represent coefficients of fixed and random effects, respectively, to measure the weight between different effects; ε is the residual error.
After completing GWAS analysis using GEMMA software, a text file with the suffix assoc. Only the "rs" of column 2 and the "p _ wald" information of column 11 are used in this item. The text file is imported into R software, the information of rs in the 2 nd column is used as an abscissa, the information of p _ wald in the 11 th column is subjected to-log 10 conversion and then used as an ordinate to draw a scatter diagram,
further, in one embodiment, in the step of drawing the feature map, the spectral band is taken as an abscissa, the significance p value is subjected to-log 10 conversion and then taken as an ordinate to draw a scatter diagram, a Bonferroni correction method is adopted to set a significance threshold line, such as 0.05/p or 0.01/p, p represents the total number of the spectral bands, and in this item, is 1400, and the drawn scatter diagram is a "manhattan diagram".
In a preferred embodiment, in the characteristic screening step, for each meat quality trait index, each peak of each index exceeding a threshold value in the characteristic map and a plurality of bands around the peak are selected, and the bands are used as matching near-infrared characteristic bands corresponding to a single meat quality trait index.
In specific application, each peak wavelength and five bands around the peak wavelength, which exceed a threshold value in correlation analysis, of all meat quality indexes are selected, the bands are used as near-infrared characteristic bands of the meat quality indexes, and specific data are shown in the following table 2.
TABLE 2 number and location of characteristic peaks
Based on GWAS basic principle, association analysis is carried out on 15 meat quality traits in a full spectrum band, and the threshold values are set to be p-0.05/1400 and p-0.05/1400. Each point in fig. 6 represents a wavelength and the orange point represents a point above the threshold, indicating that this wavelength contributes to the prediction of the meat quality trait. For example, by observing manhattan, the three indexes of salt (%), PH and L do not exceed the wavelength of the threshold, which indicates that there is substantially no valid information in the spectral wavelengths of 400 to 1099.5; the ash content, a and b indexes exceed the threshold wavelength less, which indicates that the effective information is less in the spectral wavelengths of 400 to 1099.5; the effective information of other indexes in the spectrum wavelength from 400 to 1099.5 is rich, which shows that the indexes have good prediction potential in the wavelength range, and based on the same strategy, matching characteristic wave bands corresponding to the meat quality character indexes are selected.
Further, in one embodiment, the method further comprises an analysis and verification step, and before the prediction application step, the selected characteristic wave band is verified relative to the full wave band by applying a multiple linear regression model, and the following parameters are calculated: and comparing and measuring the prediction results of the screened characteristic bands relative to the full bands by using the correction set decision coefficient, the cross validation set decision coefficient, the correction set root mean square error and the cross validation set root mean square error.
The characteristic wavelengths obtained by screening are predicted by using a multiple linear regression model, and theoretically, the problem of multiple collinearity of spectral data at the moment is greatly improved. The main parameters for measuring the model quality in this study include the calibration set decision coefficient
Cross validation set decision coefficient
Correction set Root Mean Square Error (RMSEC) and cross validation set Root Mean Square Error (RMSECV). A good model should have a high height
And
coefficients, and lower RMSEC and RMSECV values, with smaller differences between RMSEC and RMSECV being better.
The calculation results are specifically shown in table 3 below, and the results show that a severe overfitting phenomenon exists in the process of performing multiple linear regression prediction by using full-waveband information, and the correction set results are obviously superior to the cross validation set, which may be caused by the characteristics of multiple dimensionality and strong collinearity of spectral data. When the characteristic wave band screened by the novel research method is used for predicting again, the prediction results of fat (%), water (%), protein (%), lean meat percentage (%), collagen (%), saturated fatty acid (%), energy kJ/100g, energy kcal/100g and sodium salt (%) are all greatly improved.
TABLE 3 comparison of full band and eigenband prediction effects under multiple linear regression model
Meanwhile, the prediction result is basically consistent with the Manhattan graph presentation result in the whole view, namely the prediction effect is positively correlated with the number of the wavelengths exceeding the threshold value.
In conclusion, the method for selecting the characteristic wavelength of the meat quality character by using the near infrared spectrum for correlation analysis is feasible, and the prediction result shows that the method is a very reliable screening method after the characteristic wave band screened by the method is used for modeling prediction analysis.
The method establishes the association between the spectral band and the multiple physicochemical properties of the sample based on the thought and the process of genome-wide association analysis (GWAS), and the subsequent modeling cross validation proves that the characteristic band screened by the method can improve the prediction accuracy of the multiple physicochemical indexes, so that the meat quality prediction is further realized based on a feasible near infrared spectrum characteristic band screening strategy, the input cost of near infrared equipment in the research and development and purchase stages during the prediction operation is effectively controlled, and the reliability and the accuracy of the prediction result are improved.
In addition, compared with the traditional characteristic wave band screening method, the data processing flow is simple to operate, strong in repeatability and low in technical threshold, and meanwhile, the correlation result of the spectrum and the sample index is displayed in a visual mode in a manhattan diagram mode, so that the visual feeling is provided for researchers or related industrial personnel, and substantial help is provided for industrial popularization and application of the near infrared spectrum analysis technology.
While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present invention is not limited by the illustrated ordering of acts, as some steps may occur in other orders or concurrently with other steps in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
It should be noted that in other embodiments of the present invention, the method may further combine one or more of the above embodiments to obtain a new data processing and analysis prediction application method, so as to optimize the application of the infrared spectroscopy technology.
It should be noted that, based on the method in any one or more of the above embodiments of the present invention, the present invention further provides a storage medium, which stores program codes for implementing the method in any one or more of the above embodiments, and when the program codes are executed by an operating system, the method for predicting the quality of the GWAS-based filtered near infrared spectrum eigenband can be implemented.
Example two
The method is described in detail in the embodiments disclosed in the present invention, and the method of the present invention can be implemented by using various types of apparatuses or systems, so based on other aspects of the method described in any one or more embodiments, the present invention further provides a system for predicting quality of near infrared spectrum characteristic band after GWAS-based screening, where the system is configured to perform the method for predicting quality of near infrared spectrum characteristic band after GWAS-based screening described in any one or more embodiments. Specific examples are given below for a detailed description.
Specifically, fig. 7 is a schematic structural diagram of a system for predicting quality based on a near infrared spectrum characteristic band after GWAS screening, which is provided in an embodiment of the present invention, and as shown in fig. 7, the system includes:
the sample configuration module is configured to configure original meat samples of a set scale based on comprehensive meat quality traits to be detected, perform sample preparation processing according to a set processing strategy, and number each prepared target sample;
the data measurement module is configured to scan each target sample through the near infrared spectrum acquisition equipment to obtain near infrared spectrum data, obtain meat quality property data of each target sample by using a measurement function module attached to the near infrared equipment or a matched physical and chemical measurement means, and record the two data in a correlation manner;
the GWAS analysis module is configured to call the linear mixing model by utilizing GEMMA software to perform GWAS analysis on the linear mixing model and the GWAS analysis module so as to obtain a corresponding analysis result;
the characteristic diagram drawing module is configured to draw a corresponding Manhattan diagram based on a result file after GWAS analysis in cooperation with a set significance threshold line;
the characteristic screening module is configured to screen and determine effective spectral bands corresponding to all meat quality characteristic indexes according to the distribution condition of each piece of meat quality characteristic index representation information relative to the spectral band representation information in the Manhattan diagram;
and the prediction application module is configured to realize the prediction of the meat quality character based on the effective spectrum band obtained by screening by utilizing the near infrared spectrum technology.
In a preferred embodiment, when the sample configuration module configures an original meat sample of a set size, the meat quality traits to be measured include the following indexes: fat, moisture, protein, lean meat percentage, collagen, salt, ash, saturated fatty acids, energy kJ/100g, energy kcal/100g, sodium salt, pH, L, a, and b.
Further, in one embodiment, the sample configuration module performs the sample preparation process according to the set processing strategy based on the following operations:
the fat and fascia visible on the surface of each original sample were removed, and each sample was crushed using a crushing apparatus so that the crushed samples could be sampled and filled uniformly into round glass plates.
In a specific embodiment, after scanning to obtain the near infrared spectrum data, the data determination module is further configured to perform the following operations:
and eliminating the samples exceeding the Mahalanobis distance threshold value by using a Mahalanobis distance discrimination method, and putting the rest samples serving as effective samples into the meat quality character data acquisition and subsequent steps.
Further, in an embodiment, the GWAS analysis module is configured to: and inputting the meat quality character data serving as a phenotype file and the near infrared spectrum data serving as a genotype file into corresponding GEMMA software or a platform, and calling a linear mixing model to perform GWAS analysis so as to avoid the influence of similarity between the genotype data used in the GWAS analysis and the near infrared spectrum data.
Specifically, in one embodiment, the GWAS analysis module invokes a linear mixture model shown by the following formula to implement the analysis:
Y＝Xb+Zu+ε
y is a phenotype vector corresponding to the sample, X is a fixed effect matrix generated by covariates, Z is a random effect matrix aggregating all sample spectrum information, b and u respectively represent weight coefficients of the fixed effect and the random effect, and epsilon is a residual error.
In an optional embodiment, the feature map drawing module is specifically configured to: and (3) taking the spectral band as an abscissa, carrying out-log 10 conversion on the significance p value, then taking the converted value as an ordinate to draw a scatter diagram, and setting a significance threshold line by adopting a Bonferroni correction method.
Further, in an embodiment, the feature filtering module is specifically configured to: and aiming at each meat quality character index, selecting each peak of each index exceeding a threshold value in the characteristic diagram and wave bands with set quantity around the peak, and taking the wave bands as matched near-infrared characteristic wave bands corresponding to the single meat quality character index.
In addition, it should be noted that, in a preferred embodiment, the system further includes an analysis and verification module configured to, before the step of predicting and applying, perform verification on the selected characteristic bands with respect to the full band by applying a multiple linear regression model, by calculating the following parameters: and comparing and measuring the prediction results of the screened characteristic bands relative to the full bands by using the correction set decision coefficient, the cross validation set decision coefficient, the correction set root mean square error and the cross validation set root mean square error.
In the GWAS-screened near infrared spectrum characteristic band quality prediction system provided by the embodiment of the invention, each module or unit structure can be independently operated or operated in a combined mode according to actual analysis and operation requirements so as to achieve corresponding technical effects.
It is to be understood that the disclosed embodiments of the invention are not limited to the particular structures, process steps, or materials disclosed herein but are extended to equivalents thereof as would be understood by those ordinarily skilled in the relevant arts. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting.
Reference in the specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Thus, appearances of the phrase "an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment.
Although the embodiments of the present invention have been described above, the above descriptions are only for the convenience of understanding the present invention, and are not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for predicting quality of near infrared spectrum characteristic waveband after GWAS screening is characterized by comprising the following steps:
a sample configuration step, configuring original meat samples of a set scale based on comprehensive meat quality traits to be detected, performing sample preparation processing according to a set processing strategy, and numbering prepared target samples;
the method comprises the following steps of measuring data, scanning each target sample through near infrared spectrum acquisition equipment to obtain near infrared spectrum data, obtaining meat quality property data of each target sample by utilizing a measurement function module attached to the near infrared equipment or a matched physical and chemical measurement means, and recording the two data in a correlation manner;
GWAS analysis, namely calling a linear mixing model by utilizing GEMMA software to carry out GWAS analysis on the two to obtain a corresponding analysis result;
drawing a characteristic diagram, and drawing a corresponding Manhattan diagram based on a result file after GWAS analysis in cooperation with a set significance threshold line;
a characteristic screening step, namely screening and determining effective spectral bands corresponding to all meat quality characteristic indexes according to the distribution condition of each meat quality characteristic index representation information relative to spectral band representation information in a Manhattan diagram;
and (3) forecasting the application steps, and forecasting the meat quality character based on the effective spectrum band obtained by screening by utilizing the near infrared spectrum technology.
2. The method of claim 1, wherein in the sample preparation step, the meat quality trait to be measured comprises the following indices: fat, moisture, protein, lean meat percentage, collagen, salt, ash, saturated fatty acids, energy kJ/100g, energy kcal/100g, sodium salt, pH, L, a, and b.
3. The method of claim 1, wherein in the sample configuration step, the performing of the sample preparation process according to the set process strategy comprises:
the fat and fascia visible on the surface of each original sample were removed, and each sample was crushed using a crushing apparatus so that the crushed samples could be sampled and filled uniformly into round glass plates.
4. The method of claim 1, wherein, in the data determining step, scanning the near infrared spectral data further comprises:
and eliminating the samples exceeding the Mahalanobis distance threshold value by using a Mahalanobis distance discrimination method, and putting the rest samples serving as effective samples into the meat quality character data acquisition and subsequent steps.
5. The method of claim 1, wherein in the GWAS analysis step, comprising: and (3) taking the meat quality character data as a phenotype file, taking the near infrared spectrum data as a genotype file, inputting the phenotype file and the near infrared spectrum data into corresponding GEMMA software or a platform, and calling a linear mixing model to perform GWAS analysis so as to effectively eliminate the influence of multiple collinearity existing among spectrum bands on an analysis result.
6. The method of claim 5, wherein said GWAS analysis step calls a linear mixture model represented by the following formula:
Y＝Xb+Zu+ε
y is a phenotype vector corresponding to the sample, X is a fixed effect matrix generated by covariates, Z is a random effect matrix aggregating all sample spectrum information, b and u respectively represent weight coefficients of the fixed effect and the random effect, and epsilon is a residual error.
7. The method according to claim 1, wherein in the characteristic map plotting step, a scatter diagram is plotted with the spectral band as abscissa and the p-value of significance subjected to-log 10 conversion as ordinate, and a threshold line of significance is set by a Bonferroni correction method.
8. The method of claim 1, wherein in the characteristic screening step, for each of the meat quality trait indexes, each peak exceeding a threshold value in the characteristic map and a set number of bands around the peak are selected, and the bands are used as matching near-infrared characteristic bands corresponding to the individual meat quality trait indexes.
9. The method of claim 1, further comprising the steps of analyzing the validation, and applying the predictionBefore the step, the selected characteristic wave band is verified relative to the full wave band by applying a multiple linear regression model, and the following parameters are calculated: correction set decision coefficient
Cross validation set decision coefficient
The root mean square error of the correction set (RMSEC) and the root mean square error of the cross validation set (RMSECV) are compared and measured with the prediction result of the screened characteristic wave band relative to the full wave band.
10. A system for predicting quality based on a near infrared spectral signature band after GWAS screening, the system performing the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111209987.4A CN113945539B (en) | 2021-10-18 | 2021-10-18 | Method and system for predicting quality of near infrared spectrum characteristic wave band based on GWAS (Global positioning System) screening |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111209987.4A CN113945539B (en) | 2021-10-18 | 2021-10-18 | Method and system for predicting quality of near infrared spectrum characteristic wave band based on GWAS (Global positioning System) screening |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113945539A true CN113945539A (en) | 2022-01-18 |
| CN113945539B CN113945539B (en) | 2023-07-04 |
Family
ID=79330993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111209987.4A Active CN113945539B (en) | 2021-10-18 | 2021-10-18 | Method and system for predicting quality of near infrared spectrum characteristic wave band based on GWAS (Global positioning System) screening |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113945539B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
| CN107860740A (en) * | 2017-12-08 | 2018-03-30 | 中国农业科学院茶叶研究所 | A kind of evaluation method of the fermentation of black tea quality based on near-infrared spectrum technique |
| CN107917897A (en) * | 2017-12-28 | 2018-04-17 | 福建医科大学 | The method of the special doctor's food multicomponent content of near infrared ray |
| CN109799207A (en) * | 2019-01-15 | 2019-05-24 | 上海交通大学 | The quantitative detecting method of talcum powder is mixed in the root of Dahurain angelica based on near-infrared spectrum analysis |
-
2021
- 2021-10-18 CN CN202111209987.4A patent/CN113945539B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018010352A1 (en) * | 2016-07-11 | 2018-01-18 | 上海创和亿电子科技发展有限公司 | Qualitative and quantitative combined method for constructing near infrared quantitative model |
| CN107860740A (en) * | 2017-12-08 | 2018-03-30 | 中国农业科学院茶叶研究所 | A kind of evaluation method of the fermentation of black tea quality based on near-infrared spectrum technique |
| CN107917897A (en) * | 2017-12-28 | 2018-04-17 | 福建医科大学 | The method of the special doctor's food multicomponent content of near infrared ray |
| CN109799207A (en) * | 2019-01-15 | 2019-05-24 | 上海交通大学 | The quantitative detecting method of talcum powder is mixed in the root of Dahurain angelica based on near-infrared spectrum analysis |
Non-Patent Citations (1)
| Title |
|---|
| 田潇瑜;唐鸣;白竣文;: "基于反射光谱特征的牛肉嫩度预测模型研究", 食品科技, no. 09 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113945539B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hu et al. | Rapid detection of three quality parameters and classification of wine based on Vis-NIR spectroscopy with wavelength selection by ACO and CARS algorithms | |
| Li et al. | Nondestructive detection of total volatile basic nitrogen (TVB-N) content in pork meat by integrating hyperspectral imaging and colorimetric sensor combined with a nonlinear data fusion | |
| CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
| Jiang et al. | Application of hyperspectral imaging for detecting and visualizing leaf lard adulteration in minced pork | |
| Qu et al. | Predicting pork freshness using multi-index statistical information fusion method based on near infrared spectroscopy | |
| Horcada et al. | Authentication of Iberian pork official quality categories using a portable near infrared spectroscopy (NIRS) instrument | |
| Song et al. | Smartphone detection of minced beef adulteration | |
| Fowler et al. | Preliminary investigation for the prediction of intramuscular fat content of lamb in-situ using a hand-held NIR spectroscopic device | |
| Chen et al. | A novel variable selection method based on stability and variable permutation for multivariate calibration | |
| Aheto et al. | Combination of spectra and image information of hyperspectral imaging data for fast prediction of lipid oxidation attributes in pork meat | |
| Li et al. | Hyperspectral imaging combined with convolutional neural network for accurately detecting adulteration in Atlantic salmon | |
| Tang et al. | Quantification and visualization of meat quality traits in pork using hyperspectral imaging | |
| Guo et al. | Method and system for nondestructive detection of freshness in Penaeus vannamei based on hyperspectral technology | |
| CN111693487A (en) | Fruit sugar degree detection method and system based on genetic algorithm and extreme learning machine | |
| Li et al. | Fourier transform near-infrared spectroscopy coupled with variable selection methods for fast determination of salmon fillets storage time | |
| Serva et al. | Testing two NIRs instruments to predict chicken breast meat quality and exploiting machine learning approaches to discriminate among genotypes and presence of myopathies | |
| CN113945539B (en) | Method and system for predicting quality of near infrared spectrum characteristic wave band based on GWAS (Global positioning System) screening | |
| Shen et al. | Discrimination of blended Chinese rice wine ages based on near-infrared spectroscopy | |
| Tang et al. | Extensive evaluation of prediction performance for 15 pork quality traits using large scale VIS/NIRS data | |
| CN107356536B (en) | Wine quality detection method, server and spectral measurement equipment | |
| CN113866122A (en) | Method for rapidly identifying chicken varieties and application thereof | |
| CN111122492B (en) | Near-infrared detection-based fast water-injected meat screening method | |
| Ren et al. | Intelligent Evaluation of the Appearance Modality of Black Tea Based on Machine Vision and Hyperspectral Imaging | |
| CN113866119A (en) | Water-injected chicken rapid identification method and application | |
| CN106501212A (en) | Based on the method that the ripe rear quality of beef is roasted in the information prediction of raw meat near infrared spectrum |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |