CN117368146B - Rapid detection method for mycelium protein content - Google Patents
Rapid detection method for mycelium protein content Download PDFInfo
- Publication number
- CN117368146B CN117368146B CN202311679452.2A CN202311679452A CN117368146B CN 117368146 B CN117368146 B CN 117368146B CN 202311679452 A CN202311679452 A CN 202311679452A CN 117368146 B CN117368146 B CN 117368146B
- Authority
- CN
- China
- Prior art keywords
- mycelium
- protein content
- model
- sample
- wet
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 239000000126 substance Substances 0.000 claims abstract description 93
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 44
- 238000001228 spectrum Methods 0.000 claims abstract description 43
- 230000003595 spectral effect Effects 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000010200 validation analysis Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 230000009467 reduction Effects 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 48
- 238000000855 fermentation Methods 0.000 claims description 21
- 230000004151 fermentation Effects 0.000 claims description 21
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000007637 random forest analysis Methods 0.000 claims description 20
- 241000233866 Fungi Species 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 15
- 239000001963 growth medium Substances 0.000 claims description 12
- 238000002329 infrared spectrum Methods 0.000 claims description 11
- 238000000513 principal component analysis Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 9
- 241000235402 Rhizomucor Species 0.000 claims description 8
- 230000001419 dependent effect Effects 0.000 claims description 7
- 239000012528 membrane Substances 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000000967 suction filtration Methods 0.000 claims description 4
- 238000001035 drying Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000010561 standard procedure Methods 0.000 claims description 3
- 241000228212 Aspergillus Species 0.000 claims description 2
- 241000235395 Mucor Species 0.000 claims description 2
- 241000235527 Rhizopus Species 0.000 claims description 2
- 241000223259 Trichoderma Species 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000004140 cleaning Methods 0.000 claims description 2
- 238000009630 liquid culture Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 239000008223 sterile water Substances 0.000 claims description 2
- 230000014616 translation Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 claims 1
- 238000010998 test method Methods 0.000 claims 1
- 239000003153 chemical reaction reagent Substances 0.000 abstract description 4
- 108090000623 proteins and genes Proteins 0.000 description 7
- 102000004169 proteins and genes Human genes 0.000 description 7
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 6
- 239000008103 glucose Substances 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 241000221960 Neurospora Species 0.000 description 5
- 229940041514 candida albicans extract Drugs 0.000 description 4
- 238000009841 combustion method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 235000013305 food Nutrition 0.000 description 4
- WRUGWIBCXHJTDG-UHFFFAOYSA-L magnesium sulfate heptahydrate Chemical compound O.O.O.O.O.O.O.[Mg+2].[O-]S([O-])(=O)=O WRUGWIBCXHJTDG-UHFFFAOYSA-L 0.000 description 4
- 229940061634 magnesium sulfate heptahydrate Drugs 0.000 description 4
- 229910000402 monopotassium phosphate Inorganic materials 0.000 description 4
- 235000019796 monopotassium phosphate Nutrition 0.000 description 4
- GNSKLFRGEWLPPA-UHFFFAOYSA-M potassium dihydrogen phosphate Chemical compound [K+].OP(O)([O-])=O GNSKLFRGEWLPPA-UHFFFAOYSA-M 0.000 description 4
- LWIHDJKSTIGBAC-UHFFFAOYSA-K potassium phosphate Substances [K+].[K+].[K+].[O-]P([O-])([O-])=O LWIHDJKSTIGBAC-UHFFFAOYSA-K 0.000 description 4
- 239000012138 yeast extract Substances 0.000 description 4
- 238000001599 direct drying Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 239000007788 liquid Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 108010058643 Fungal Proteins Proteins 0.000 description 2
- LFVGISIMTYGQHF-UHFFFAOYSA-N ammonium dihydrogen phosphate Chemical compound [NH4+].OP(O)([O-])=O LFVGISIMTYGQHF-UHFFFAOYSA-N 0.000 description 2
- 229910000387 ammonium dihydrogen phosphate Inorganic materials 0.000 description 2
- BFNBIHQBYMNNAN-UHFFFAOYSA-N ammonium sulfate Chemical compound N.N.OS(O)(=O)=O BFNBIHQBYMNNAN-UHFFFAOYSA-N 0.000 description 2
- 229910052921 ammonium sulfate Inorganic materials 0.000 description 2
- 235000011130 ammonium sulphate Nutrition 0.000 description 2
- LLSDKQJKOVVTOJ-UHFFFAOYSA-L calcium chloride dihydrate Chemical compound O.O.[Cl-].[Cl-].[Ca+2] LLSDKQJKOVVTOJ-UHFFFAOYSA-L 0.000 description 2
- 229940052299 calcium chloride dihydrate Drugs 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- BNIILDVGGAEEIG-UHFFFAOYSA-L disodium hydrogen phosphate Chemical compound [Na+].[Na+].OP([O-])([O-])=O BNIILDVGGAEEIG-UHFFFAOYSA-L 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000005417 food ingredient Substances 0.000 description 2
- 235000019837 monoammonium phosphate Nutrition 0.000 description 2
- 108010082495 Dietary Plant Proteins Proteins 0.000 description 1
- 108010070551 Meat Proteins Proteins 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000221961 Neurospora crassa Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003176 fibrotic effect Effects 0.000 description 1
- 235000012041 food component Nutrition 0.000 description 1
- 230000002538 fungal effect Effects 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 239000002609 medium Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 235000021568 protein beverage Nutrition 0.000 description 1
- HYISVWRHTUCNCS-UHFFFAOYSA-N pyrene-1-carboxylic acid Chemical compound C1=C2C(C(=O)O)=CC=C(C=C3)C2=C2C3=CC=CC2=C1 HYISVWRHTUCNCS-UHFFFAOYSA-N 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000002798 spectrophotometry method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 229910021654 trace metal Inorganic materials 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
- 235000021404 traditional food Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—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
- 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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
- G01N2021/3572—Preparation of samples, e.g. salt matrices
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a rapid detection method for mycelium protein content, which is realized by establishing a detection model. The model building step comprises the following steps: obtaining spectrum data of a mycelium wet substance sample, and detecting the water content and the protein content of the mycelium wet substance sample; corresponding the spectrum data with the measured water content and protein content, and establishing a database; preprocessing the spectrum data, and extracting dimension reduction and characteristics; the samples were divided into training and validation sets: based on the spectral data and the water content data of the training set sample, a model A for detecting the water content of the mycelium wet substance is established; establishing a model B for detecting the protein content in the mycelium wet substance based on the spectral data and the protein content data of the training set sample; based on the moisture content of the wet matter, the protein content of the wet matter and the protein content detection value of the dry matter, a model C for detecting the protein content in the dry matter of the mycelium is established. The invention has simple operation, high efficiency, no damage to samples, no use of chemical reagents, no need of expensive instruments and good application prospect.
Description
Technical Field
The invention belongs to the field of near infrared spectrum nondestructive detection, and particularly relates to a rapid detection method for mycelium protein content.
Background
Fungal proteins have the potential to replace part of traditional meat and vegetable proteins as a sustainable protein source. Has important significance for relieving the resource requirement of the traditional animal husbandry, reducing the emission of greenhouse gases and improving the safety of food models. The use of fungal proteins can be used to develop a variety of novel foods and food ingredients, such as high quality protein-rich products, protein beverages, etc., which contribute to the innovation and diversity of the food industry. Therefore, the mycoprotein is reasonably utilized, and the problem of protein shortage faced by China can be effectively relieved. Among them, filamentous fungi have great potential for use in foods due to their high protein conversion efficiency, high protein content, and fibrotic structure.
At present, a plurality of methods for detecting the protein content of the mycelium of the filamentous fungi, such as a Kjeldahl nitrogen determination method, a combustion method, a spectrophotometry method and the like, have the problems of long time consumption, environmental pollution caused by using chemical reagents and the like although the detection results of the methods are reliable, and cannot meet the requirements of rapid and nondestructive detection of the protein content of the mycelium. The near infrared spectrum technology is widely applied to the traditional food ingredient detection field because of the advantages of no damage to samples, high efficiency, low cost and the like.
Disclosure of Invention
Aiming at the problems that the traditional method for detecting the protein content of the mycelium consumes long time, damages a sample, pollutes the environment by using a chemical reagent and the like, the invention establishes a method for rapidly and nondestructively detecting the protein content of the mycelium based on a near infrared spectrum technology.
The invention provides a method for establishing a rapid detection model of mycelium protein content, which comprises the following steps:
s1, preparing a liquid culture medium, inoculating filamentous fungi, performing suction filtration after fermentation to collect mycelia, and simultaneously cleaning with sterile water; measuring the water content of the mycelium wet substance sample and the protein content of the dried mycelium dry substance according to a national standard method, and converting the protein content of the mycelium wet substance;
s2, scanning a sample by using a near infrared spectrometer to obtain original spectrum data of the sample; then, the near infrared spectrum data of the sample are corresponding to the water content and the protein content measured in the step S1, and a database is established;
s3, preprocessing the original spectrum data, and performing dimension reduction and feature extraction;
s4, randomly dividing the sample into a training set and a verification set: based on near infrared spectrum data and water content data of a training set sample, a model A for detecting the water content in mycelium is established, and then the accuracy and stability of the model are verified according to the spectrum data and the water content data of a verification set sample;
s5, based on near infrared spectrum data and protein content data of the training set sample, establishing a model B for detecting the protein content in the mycelium wet substance, and verifying the accuracy and stability of the model according to the spectrum data and the protein content data of the verification set sample;
s6, based on the moisture content of the wet substance, the protein content of the wet substance and the protein content detection value of the dry substance predicted by the models in the steps S4 and S5, a model C for detecting the protein content in the dry substance of the mycelium is established, and the method can be used for rapidly detecting the protein content in the dry substance of the mycelium after verification of accuracy and stability.
In the step S2, the spectrum scanning range of the near infrared spectrometer is 10000-6250 cm -1 Spectral data were collected once at three different locations for each sample and the average was taken as the original spectral data for the sample.
And S3, preprocessing the acquired original spectrum data by adopting one or more methods of multi-element scattering correction, standard normal transformation, trend correction, first derivative, second derivative, wavelet transformation, SG smoothing and vector normalization, then carrying out data dimension reduction by using principal component analysis and random forest algorithm, and selecting characteristics.
S3, specifically, preprocessing spectrum data of the sample under different wave bands by adopting standard forward transform and wavelet transform, analyzing and calculating the contribution rate of main components corresponding to the number of the wave bands by using the main components, and obtaining the main components corresponding to the number of the wave bands when the accumulated contribution rate reaches 0.9999;
calculating the importance of the main component to the predicted water content by using a random forest algorithm, sequencing the main component according to a descending order, and taking the main component arranged in front as a characteristic when the accumulated importance reaches 0.95 so as to extract the characteristic related to the water content;
the importance of the principal components to the predicted protein content is calculated by using a random forest algorithm and sorted in descending order, and when the cumulative importance reaches 0.95, the principal components arranged in front are used as features to extract the features related to the protein content.
And S4, randomly dividing the sample into a training set and a verification set by using an SPXY algorithm. Preferably, in the step S4, a partial least square method is adopted to fit the spectral data and the water content data of the training set sample, and a water content model for detecting the mycelium wet substance is constructed; and fitting spectral data and protein content data of the training set sample by adopting a partial least square method, and constructing a model for detecting the protein content in the mycelium wet substance.
More preferably, in step S4, the moisture content of the training set sample is used as a dependent variable by using a partial least square method, spectral data of features extracted by principal component analysis and random forest algorithm is used as an independent variable to perform fitting, a model A for detecting the moisture content of the mycelium wet substance is established, the accuracy and stability of the model are verified by using the spectral data and the moisture content data of the verification set sample, and if the coefficient R is determined 2 >0.9 root mean square error RMSE<0.1, the model meets the requirements;
using partial least square method to take protein content of training set sample as dependent variable, extracting characteristic spectrum data as independent variable by principal component analysis and random forest algorithm, fitting, and establishing and detecting mycelium wetModel B of protein content in the substance, and then verifying the accuracy and stability of the model by using the spectral data and the protein content data of the verification set sample, if the coefficient R is determined 2 >0.9 root mean square error RMSE<0.1, the model meets the requirements;
the construction method of the model C in the step S6 is as follows: and taking the predicted result of the water content model A in the mycelium wet substance and the predicted result of the protein content model B in the mycelium wet substance as independent variables, taking the protein content in the dried mycelium dry substance as the dependent variables, and fitting by using a random forest algorithm to establish a model C for predicting the protein content in the mycelium dry substance.
Based on the detection result of the model A for detecting the moisture content of the mycelium wet substance and the detection result of the model B for detecting the protein content of the mycelium wet substance, selecting samples with the moisture content of 0.4-0.65 and the protein content of 0.15-0.29 of the mycelium wet substance and corresponding protein content of the dried mycelium dry substance, and establishing a model C for predicting the protein content of the mycelium dry substance. If model C determines coefficient R 2 >0.85, which can be used for detecting the protein content in the mycelium dry substance.
In particular, the filamentous fungus is Mucor, rhizopus, rhizomucor, trichoderma or Aspergillus.
The invention also provides a model A for detecting the water content in the mycelium wet substance, a model B for detecting the protein content in the mycelium wet substance or a model C for detecting the protein content in the mycelium dry substance, which are obtained by the establishment method.
The invention provides a rapid detection method for mycelium protein content, which utilizes the model to detect, and obtains a detection result, namely the protein content in mycelium dry matters.
Specifically, the method comprises the following steps:
first, mycelia are prepared: collecting mycelium by filtering fermented filamentous fungus fermentation liquor with a filter membrane, compacting the mycelium, and making the thickness uniform;
secondly, obtaining original spectrum data;
thirdly, inputting the original spectrum data into the model A for detecting the moisture content of the mycelium wet substance, and outputting a result to obtain a predicted value of the moisture content of the mycelium wet substance; inputting the original spectrum data into the model B for detecting the protein content in the wet mycelium substance, and outputting a result to obtain a predicted value of the protein content in the wet mycelium substance;
and fourthly, inputting the detection value of the moisture content and protein content model in the mycelium wet substance into the model C to output the protein content in the mycelium dry substance.
Preferably, in the second step, the near infrared spectrometer is set to have a mode width of 8.2 and an average scanning frequency of 5-10 times, spectrum data are collected in an environment with a relative humidity of 45% at 26 ℃, spectrum data are collected at three different positions of each sample, and an average value is taken as original spectrum data of the sample.
Based on mycelium obtained by fermenting the same filamentous fungus in different culture mediums in the step S1, finally evaluating the protein content of the mycelium in different culture mediums in the step S6, and screening the optimal culture mediums; based on mycelium obtained by fermenting different filamentous fungi in the same culture medium in the step S1, the protein production capacity of different strains under the same culture medium is finally evaluated in the step S6 and used for screening high-protein-yield strains.
The invention has the technical effects that:
the invention establishes a method for rapidly and nondestructively detecting the protein content of mycelium based on a near infrared spectrum technology. The method comprises the steps of measuring the moisture content and the protein content of 300 samples in a corresponding state, collecting near infrared spectrum data of the samples by a near infrared spectrometer, preprocessing the collected original spectrum data by one or more methods of multi-element scattering correction, standard normal transformation, trend correction, first derivative, second derivative, wavelet transformation, SG smoothing and vector normalization, then carrying out data dimension reduction by using principal component analysis, extracting characteristic wave bands by a random forest algorithm, fitting the spectrum data with the moisture content and the protein content by a partial least square method, establishing a method for detecting the moisture content and the protein content in wet mycelium matters, and establishing a method for detecting the protein content in mycelium by combining the protein content data in dry mycelium matters.
Compared with the traditional method for detecting the protein content of mycelium, the invention has the following advantages: the operation is simple, sample pretreatment is not needed, no professional detection personnel are needed, and the sample is only needed to be placed on a near infrared spectrometer lens to obtain spectral data of the sample and input the spectral data into the model; the time is saved, the detection time of one sample is only 5-20s, 800 samples can be detected every day, and the detection time is more than 30 times of that of the traditional chemical detection method; providing real-time or near real-time data during fermentation to take timely action to correct problems or optimize the filamentous fungal fermentation process, thereby reducing risk and loss; no expensive detection instrument is needed, no chemical reagent is used, the detection cost is low, and the environment is not polluted.
Drawings
Fig. 1 is a flow chart of the present invention.
Fig. 2 is an original spectral image of 300 samples in example 1.
FIG. 3 is a scatter plot of the national standard test values for moisture content and the predicted values for the test model for the training set mycelium wet substance samples of example 1.
FIG. 4 is a scatter plot of national standard test values and test model predicted values for the moisture content of a sample of the calibration collection mycelium wet substance in example 1.
FIG. 5 is a scatter plot of the national standard detection values of protein content and the predicted values of the detection model for the training set mycelium wet substance samples in example 1.
FIG. 6 is a scatter plot of the national standard test values and the predicted values of the test model for the protein content of the samples of the calibration collection mycelium wet substance in example 1.
FIG. 7 is a scatter plot of national standard detection values of protein content and prediction values of a prediction model of a training set mycelium wet substance sample after drying in example 1.
FIG. 8 is a scatter plot of national standard detection values of protein content and prediction values of a prediction model after the mycelium wet substance sample is dried in example 1.
FIG. 9 is a scatter plot of national standard detection values of protein content and prediction values of prediction models after 12 mycelium wet substance samples were dried in example 2.
FIG. 10 is a scatter plot of national standard detection values of protein content and prediction values of prediction models after 12 mycelium wet substance samples were dried in example 3.
Detailed Description
In order to make the objects and technical steps of the present invention clearer, the present invention will be further described with reference to the accompanying drawings and detailed description, examples are only for illustrating the present invention, but not limited to the present invention, and the methods in the examples are conventional methods unless specifically described.
As shown in fig. 1, the present application provides a method for establishing a rapid detection model of mycelium protein content, which includes:
s1: inoculating spore or seed liquid of filamentous fungi into different culture mediums for liquid fermentation, and filtering and collecting mycelium samples and numbers for later use after fermentation is finished; the moisture content and protein content of the mycelium wet substance samples were measured according to the national standard method. S2: collecting near infrared spectrum data of mycelium samples, and establishing a database by corresponding the spectrum data with water content and protein content data.
S3: preprocessing the original spectrum data of a sample, then carrying out data dimension reduction by using a principal component analysis method, and extracting characteristic wavelengths by using a random forest algorithm; the samples were randomly divided into training and validation sets using the SPXY algorithm.
S4: fitting spectral data and water content data of a training set sample by using a partial least square method, and establishing a model A for detecting the water content of wet mycelium matters; and fitting spectral data and protein content data of the training set sample by using a partial least square method, and establishing a model B for detecting the protein content of the mycelium wet substance.
S5: using spectrum data and water content data of a verification set sample to verify the accuracy and stability of a mycelium wet substance water content detection model; and verifying the accuracy and stability of the mycelium wet substance protein content detection model by utilizing the spectral data and the protein content data of the verification set sample.
S6: based on the moisture content of wet matters, the protein content of the wet matters and the protein content detection value of the dry matters predicted by the S4 and S5 step models, a model C for detecting the protein content in the dry matters of the mycelium is established, and the method can be used for rapidly detecting the protein content in the dry matters of the mycelium after verification of accuracy and stability.
Example 1
In this embodiment, a process for establishing a model for detecting the moisture content and the protein content in wet mycelium substances and a process for establishing a model for detecting the protein content in dry mycelium substances are provided. Wherein the model is implemented by a computer program which can be programmed in a known computer program language to obtain corresponding computer program software, the program being executed by a processor of a computer.
The process specifically comprises the following steps:
different culture mediums suitable for the growth of the filamentous fungi are prepared by adjusting parameters such as the composition, the content, the fermentation condition and the like of the culture medium. The rhizomucor parvus culture medium mainly comprises 10-40 g/L of glucose, 14-50 g/L of ammonium dihydrogen phosphate, 1-6 g/L of yeast extract, 8-30 g/L of monopotassium phosphate, 1-6 g/L of magnesium sulfate heptahydrate, 0.1-0.4 g/L of calcium chloride dihydrate, 2-8 g/L of disodium hydrogen phosphate and pH range of 4-6. Main components of the culture medium for the Neurospora crassa comprise 10-40 g/L of glucose, 7-20 g/L of yeast extract, 10-30 g/L of ammonium sulfate, 5-16 g/L of monopotassium phosphate, 1-7 g/L of magnesium sulfate heptahydrate and pH range of 4-7. Inoculating spores or seed liquid of the filamentous fungi into the culture medium, and fermenting at 35 ℃ and 220rpm for 24-48 hours. After fermentation, a mycelium sample is collected by suction filtration through a5 mu m filter membrane and numbered for standby. The mycelium should be compacted during suction filtration, the thickness is uniform, and gaps are avoided. A total of 300 mycelium samples were collected by fermentation.
Near infrared spectrum data of a sample are collected by using a near infrared spectrometer, and the scanned spectrum range is 10000-6250 cm -1 Setting the mode width as 8.2, preheating the spectrometer for 15min before scanning for 8 times, collecting spectrum data in an environment with the relative humidity of 45% at 26 ℃, collecting spectrum data at three different positions of each sample, and taking the average value as the original spectrum data of the sample. The raw spectral patterns of 300 mycelium wet substance samples are shown in FIG. 2.
According to the direct drying method in GB 5009.3-2016, a sample of the wet mycelium material from which the spectral data has been collected is dried and the moisture content of the sample is calculated. The protein content in the dried mycelium dry matter sample was determined according to the combustion method in GB 5009.5-2010 and converted to the protein content in the mycelium wet matter sample. And (5) corresponding the spectrum data, the water content data and the protein content data, and establishing a database. Wherein, the calculation formula of the protein content in the wet substance is as follows:
in the middle ofPC d : protein content in dry matter;PC w : protein content in the wet material;MC：water content.
Spectral data of 300 samples under 118 different wavebands are preprocessed by standard forward transform and wavelet transform, contribution rates of 118 main components are calculated by using a Principal Component Analysis (PCA), and when the cumulative contribution rate reaches 0.9999, 50 main components are corresponding, and the contribution rates are named PCA 1-PCA 50.
The importance of 50 main components for predicting the water content is calculated by using a Random Forest (RF) algorithm and is ordered according to a descending order, when the accumulated importance reaches 0.95, the first 30 main components are used as characteristics, and the extracted characteristics related to the water content comprise pca 1-pca 18, pca 20-pca 22, pca26, pca27, pca34, pca36, pca39, pca41, pca42 and pca44. The 300 mycelium samples were randomly divided into training and validation sets using the SPXY algorithm, with 210 samples of the training set and 90 samples of the validation set. Using partial least square method to take the water content of training set sample as dependent variable, using spectral data of main component analysis and random forest extraction characteristics as independent variable, fitting, building model A for detecting water content in mycelium, using spectral data and water content data of verification set sample to verify accuracy and stability of model, if coefficient R is determined 2 >0.9 root mean square error RMSE<0.1, the model meets the requirements. In a specific experiment, as shown in fig. 3, the determination coefficient of the real value of the water content of the training set and the model predicted value is 0.9514, and the root mean square error is 0.0286; as shown in fig. 4, the validation set sample water cut true value and model predictive value determined coefficient was 0.9477 and root mean square error was 0.0258.
Calculation 50 using Random Forest (RF) algorithmThe importance of each main component to the predicted protein content is ordered in descending order, when the cumulative importance reaches 0.95, the first 30 main components are used as characteristics, and the extracted characteristics related to the protein content comprise pca 1-pca 13, pca 15-pca 17, pca19, pca 20-pca 22, pca25, pca32, pca33, pca38, pca39, pca42, pca44, pca46 and pca48. The 300 samples were randomly divided into training and validation sets using the SPXY algorithm, with 210 samples for the training set and 90 samples for the validation set. Using partial least square method to take protein content of training set sample as dependent variable, performing principal component analysis and random forest extraction characteristic spectral data as independent variable, fitting, establishing model B for detecting protein content in mycelium wet substance, verifying accuracy and stability of model by using spectral data and protein content data of verification set sample, and determining coefficient R 2 >0.9 root mean square error RMSE<0.1, the model meets the requirements. In a specific experiment, as shown in fig. 5, the determination coefficient of the real value of the protein content of the training set sample and the model predicted value is 0.9606, and the root mean square error is 0.0131; as shown in fig. 6, the determination coefficient of the true value and the model predicted value of the protein content of the validation set sample is 0.9473, and the root mean square error is 0.0123.
Based on the detection result of the moisture content model in the mycelium wet substance and the detection result of the protein content model in the mycelium wet substance, selecting samples with the moisture content of 0.4-0.65 and the protein content of 0.15-0.29 of the mycelium wet substance and the protein content of the mycelium dry substance after corresponding drying, and establishing a model for predicting the protein content of the mycelium dry substance. A total of 99 samples were selected, 79 of which were randomly selected for modeling the protein content in the mycelium dry substance, and 20 samples were used for verifying the accuracy and stability of modeling. As shown in fig. 7, the determination coefficient of the real value of the dry matter protein content and the model predictive value of 79 samples was 0.9511. As shown in FIG. 8, the dry matter protein content of 20 samples was truly a value and model predictive value determination factor of 0.888.
Example 2
This example serves to verify the accuracy and stability of the method of example 1 in predicting the amount of mycelium protein obtained under different fermentation conditions for the same strain.
6 different rhizomucor minutissimum culture mediums are prepared by adjusting different combinations of glucose concentration of 20-100g/L and pH range of 3.5-4.5. Inoculating rhizomucor parvulus CGMCC No. 40441, fermenting at 35 ℃ and 220rpm for 48 hours, and filtering and collecting 6 mycelium samples from fermentation broth by using a filter membrane with the size of 5 mu m. The mycelium should be compacted and the thickness is uniform during filtration.
The concentration of glucose is regulated to be 20-100g/L, and 6 different m-type Neurospora culture mediums are prepared by different combinations of pH ranges of 5.0-6.0. Inoculating Neurospora CGMCC No. 40496, fermenting at 35deg.C and 220rpm for 48 hr, and filtering and collecting 6 mycelium samples from the fermentation broth with 5 μm filter membrane. The mycelium should be compacted and the thickness is uniform during filtration.
The near infrared spectrometer is preheated for 15min, the mode width is set to be 8.2, the average scanning times are set to be 8, spectrum data are collected in an environment with the temperature of 26 ℃ and the relative humidity of 45%, spectrum data are collected at three different positions of each sample, and the average value is taken as the original spectrum data of the sample.
According to the direct drying method in GB 5009.3-2016, a sample of the wet mycelium material from which the spectral data has been collected is dried and the moisture content of the sample is calculated. The protein content in the dried mycelium dry matter sample was determined according to the combustion method in GB 5009.5-2010 and converted to the protein content in the mycelium wet matter sample.
The original spectrum data of 12 samples are respectively input into a mycelium wet substance water content detection model A and a mycelium wet substance protein content detection model B established in the example 1, so that a water content model predicted value and a protein content model predicted value of the 12 mycelium wet substance samples can be obtained, and then input into a mycelium dry substance protein content prediction model C established in the example 1, so that a mycelium dry substance protein content predicted value after the 12 mycelium wet substance samples are dried can be obtained (table 1). As shown in fig. 9, the national standard detection value and model predictive value of protein content after 12 wet matter mycelium samples were dried had a coefficient of determination of 0.8804. The protein content in the mycelium dry substance predicted according to the model can provide a reference for rapidly evaluating the fermentation medium of high-yield protein.
Table 1 predicted and measured values of protein content in mycelium dry substance under different fermentation conditions.
Example 3
This example serves to verify the accuracy and stability of the method of example 1 in predicting the amount of mycelium protein obtained under the same fermentation conditions for different strains.
The rhizomucor parvus culture medium is prepared, and the main components comprise 10g/L of glucose, 12.33g/L of ammonium dihydrogen phosphate, 1.5g/L of yeast extract, 7g/L of monopotassium phosphate, 1.5g/L of magnesium sulfate heptahydrate, 0.1g/L of calcium chloride dihydrate, 2g/L of disodium hydrogen phosphate and trace metal solution, wherein the pH value is 4.0. 6 different Rhizomucor parvum strains (see 6 Rhizomucor parvum strains screened in China patent CN 115851458A) were inoculated under the above conditions, and fermented at 220rpm for 48 hours at 35 ℃.6 mycelium samples are filtered and collected from fermentation broth by using a5 mu m filter membrane, and mycelium is compacted during filtration and has uniform thickness (corresponding to sample numbers 1-6).
The preparation method comprises preparing a culture medium of Neurospora, wherein the main components comprise 10g/L glucose, 5g/L yeast extract, 10.62 g/L ammonium sulfate, 3.5 g/L monopotassium phosphate, 0.75 g/L magnesium sulfate heptahydrate, trace elements and pH 7.0. 6 different strains of Neurospora are inoculated (see 6 strains of Neurospora in China patent CN 116162554A), and fermentation is carried out at 35℃and 220rpm for 36 hours. 6 mycelium samples are filtered and collected from fermentation broth by using a5 mu m filter membrane, and mycelium is compacted during filtration and has uniform thickness (corresponding to sample numbers 7-12).
The spectrometer is preheated for 15min, the mode width is set to be 8.2, the average scanning times are set to be 8, spectrum data are collected in an environment with the relative humidity of 45% at 26 ℃, spectrum data are collected at three different positions of each sample, and the average value is taken as the original spectrum data of the sample.
According to the direct drying method in GB 5009.3-2016, the sample after the spectral data acquisition is dried in an oven at 70 ℃ to calculate the water content of the sample. The protein content in the dried mycelium dry matter sample was determined according to the combustion method in GB 5009.5-2010 and converted to the protein content in the mycelium wet matter sample.
The raw spectral data of the 12 samples are respectively input into a mycelium wet substance water content detection model and a mycelium wet substance protein content detection model established in example 1, so that a water content prediction model predicted value and a protein content prediction value of the 12 mycelium wet substance samples can be obtained, and then input into a mycelium dry substance protein content prediction model established in example 1, so that a mycelium dry substance protein content prediction value after the 12 mycelium wet substance samples are dried can be obtained (table 2). As shown in fig. 10, the national standard detection value and model predictive value of protein content after 12 wet matter mycelium samples were dried have a coefficient of 0.8694. The protein content in the mycelium dry substance predicted according to the model can provide a reference for rapidly screening the high-protein-yield filamentous fungi.
TABLE 2 predicted and detected protein content in mycelium dry substance for different strains under the same fermentation conditions
The foregoing description is representative of the preferred embodiments of the present application and is not intended to be limiting. Any changes or substitutions that would be readily apparent to one of ordinary skill in the art, within the scope of the technology disclosed in this application, are intended to be included within the scope of this application. The scope of the claims should, therefore, be determined with reference to the appended claims.
Claims (10)
1. The method for establishing the rapid detection model of the mycelium protein content is characterized by comprising the following steps of:
s1, preparing a liquid culture medium, inoculating filamentous fungi, performing suction filtration after fermentation to collect mycelia, and simultaneously cleaning with sterile water; measuring the water content of the mycelium wet substance sample and the protein content of the dried mycelium dry substance according to a national standard method, and converting the protein content of the mycelium wet substance;
s2, scanning a sample by using a near infrared spectrometer to obtain original spectrum data of the sample; then, the near infrared spectrum data of the sample are corresponding to the water content and the protein content measured in the step S1, and a database is established; wherein the spectrum scanning range of the near infrared spectrometer is 10000-6250 cm -1 ；
S3, preprocessing the collected original spectrum data by adopting one or more methods of multi-element scattering correction, standard normal transformation, trend correction, first derivative, second derivative, wavelet transformation, SG smoothing and vector normalization, then carrying out data dimension reduction by using principal component analysis and random forest algorithm, and selecting characteristics;
s4, randomly dividing the sample into a training set and a verification set: the method comprises the steps of using the partial least square method to take the water content of a training set sample as a dependent variable, taking spectral data of features extracted through principal component analysis and random forest algorithm as the independent variable, fitting, establishing a model A for detecting the water content of mycelium wet substances, verifying the accuracy and stability of the model by using the spectral data and the water content data of a verification set sample, and determining a coefficient R if 2 >0.9 root mean square error RMSE<0.1, the model meets the requirements;
s5, using a partial least square method to take the protein content of the training set sample as a dependent variable, taking spectral data of the extracted characteristics of the training set sample as the independent variable through principal component analysis and random forest algorithm, fitting, establishing a model B for detecting the protein content in the mycelium wet substance, verifying the accuracy and stability of the model through the spectral data and the protein content data of the verification set sample, and determining a coefficient R if 2 >0.9 root mean square error RMSE<0.1, the model meets the requirements;
s6, taking a prediction result of the moisture content model A in the mycelium wet substance and a prediction result of the protein content model B in the mycelium wet substance as independent variables, taking the protein content in the mycelium dry substance after drying as the independent variables, fitting by using a random forest algorithm, establishing a model C for detecting the protein content in the mycelium dry substance, and rapidly detecting the protein content in the mycelium dry substance after verifying the accuracy and stability.
2. The method according to claim 1, wherein in step S2, spectrum data is collected once at three different positions for each sample, and an average value is taken as the original spectrum data of the sample.
3. The method according to claim 1, wherein in step S3, specifically, spectrum data of the sample under different wavebands is preprocessed by standard forward transform and wavelet transform, the contribution rate of the main components corresponding to the number of wavebands is calculated by using main component analysis, and when the cumulative contribution rate reaches 0.9999, the main components corresponding to the number of wavebands are obtained;
calculating the importance of the main component to the predicted water content by using a random forest algorithm, sequencing the main component according to a descending order, and taking the main component arranged in front as a characteristic when the accumulated importance reaches 0.95 so as to extract the characteristic related to the water content;
the importance of the principal components to the predicted protein content is calculated by using a random forest algorithm and sorted in descending order, and when the cumulative importance reaches 0.95, the principal components arranged in front are used as features to extract the features related to the protein content.
4. The method according to claim 1, wherein in step S4, the sample is randomly divided into a training set and a validation set using the SPXY algorithm.
5. The method of claim 1 to 4, wherein the filamentous fungus is Mucor, rhizopus, rhizomucor, trichoderma or Aspergillus.
6. The method according to any one of claims 1 to 5, wherein the model A for detecting the water content in the wet mycelium material, the model B for detecting the protein content in the wet mycelium material or the model C for detecting the protein content in the dry mycelium material are obtained.
7. A rapid detection method of mycelium protein content, characterized in that the detection is carried out by using the model as claimed in claim 6 to obtain the detection result, namely the protein content in mycelium dry substance.
8. The method for rapid detection of protein content of mycelium according to claim 7,
first, mycelia are prepared: collecting mycelium by filtering fermented filamentous fungus fermentation liquor with a filter membrane, compacting the mycelium, and making the thickness uniform;
secondly, obtaining original spectrum data;
thirdly, inputting the original spectrum data into the model A for detecting the moisture content of the mycelium wet substance, and outputting a result to obtain a predicted value of the moisture content of the mycelium wet substance; inputting the original spectrum data into the model B for detecting the protein content in the wet mycelium substance, and outputting a result to obtain a predicted value of the protein content in the wet mycelium substance;
and fourthly, inputting the detection value of the moisture content and protein content model in the mycelium wet substance into the model C to output the protein content in the mycelium dry substance.
9. The rapid inspection method according to claim 8, wherein in the second step, the near infrared spectrometer is set to have a mode width of 8.2 and an average scanning number of 5-10 times, spectral data is collected under an environment with a relative humidity of 45% at 26 ℃, spectral data is collected once at three different positions of each sample, and an average value is taken as raw spectral data of the sample.
10. The rapid test method of claim 9 wherein,
based on mycelium obtained by fermenting the same filamentous fungus in different culture mediums in the step S1, finally evaluating the protein content of the mycelium in different culture mediums in the step S6, and screening the optimal culture mediums; based on mycelium obtained by fermenting different filamentous fungi in the same culture medium in the step S1, the protein production capacity of different strains under the same culture medium is finally evaluated in the step S6 and used for screening high-protein-yield strains.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311679452.2A CN117368146B (en) | 2023-12-08 | 2023-12-08 | Rapid detection method for mycelium protein content |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311679452.2A CN117368146B (en) | 2023-12-08 | 2023-12-08 | Rapid detection method for mycelium protein content |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117368146A CN117368146A (en) | 2024-01-09 |
| CN117368146B true CN117368146B (en) | 2024-03-12 |
Family
ID=89391471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311679452.2A Active CN117368146B (en) | 2023-12-08 | 2023-12-08 | Rapid detection method for mycelium protein content |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117368146B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2025329A1 (en) * | 1989-09-18 | 1991-03-19 | James Bertram Callis | Characterizing matter of biological origin using near infrared spectroscopy |
| WO2006131546A1 (en) * | 2005-06-09 | 2006-12-14 | Bayer Cropscience Sa | Method for identification of novel fungicides |
| CN101419165A (en) * | 2008-11-17 | 2009-04-29 | 江苏科技大学 | Mequindox content detecting method in veterinary drugs |
| WO2009059176A2 (en) * | 2007-11-02 | 2009-05-07 | Ceres, Inc. | Materials and methods for use in biomass processing |
| CH708057A2 (en) * | 2013-05-06 | 2014-11-14 | Univ Jiangnan | Near-infrared method for determining the constituents of the lotus root. |
| CA2839027A1 (en) * | 2014-01-02 | 2015-07-02 | Alltech, Inc. | Systems and methods for estimating feed efficiency and carbon footprint for milk producing animal |
| CN106970041A (en) * | 2017-04-12 | 2017-07-21 | 江苏省农业科学院 | A kind of near-infrared assay method of the big aggressiveness content of wheat flour Insoluble glutenin |
| CN107255624A (en) * | 2017-05-12 | 2017-10-17 | 华南农业大学 | A kind of fast and convenient method for determining protein content in fan's power mushroom entity |
| CN107389592A (en) * | 2017-07-10 | 2017-11-24 | 天津工业大学 | A kind of complex sample spectral signal selective ensemble pre-processes modeling method |
| CN107884361A (en) * | 2017-11-03 | 2018-04-06 | 云南农业大学 | A kind of Yunnan local chicken muscle freeze-dried powder gross protein value near infrared detection method |
| CN111024647A (en) * | 2020-01-08 | 2020-04-17 | 山东金璋隆祥智能科技有限责任公司 | Method for detecting moisture and protein content in dry starch based on GSA near infrared technology |
| CN112986174A (en) * | 2021-02-03 | 2021-06-18 | 佛山一本农业科技有限公司 | Near infrared spectrum-based fruit and vegetable optimal sorting method and system and readable storage medium |
| CN113310929A (en) * | 2021-05-10 | 2021-08-27 | 华中农业大学 | Soybean powder doped in high-temperature sterilized milk and spectral identification method of doping proportion thereof |
| CN114518339A (en) * | 2022-02-23 | 2022-05-20 | 新希望六和股份有限公司 | Method for establishing near-infrared prediction model of wet-based fermented soybean meal and application |
| CN115561223A (en) * | 2022-09-27 | 2023-01-03 | 正大青春宝药业有限公司 | Method for detecting content of perhexiline aqueous extract based on Raman spectrum and application |
-
2023
- 2023-12-08 CN CN202311679452.2A patent/CN117368146B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2025329A1 (en) * | 1989-09-18 | 1991-03-19 | James Bertram Callis | Characterizing matter of biological origin using near infrared spectroscopy |
| WO2006131546A1 (en) * | 2005-06-09 | 2006-12-14 | Bayer Cropscience Sa | Method for identification of novel fungicides |
| WO2009059176A2 (en) * | 2007-11-02 | 2009-05-07 | Ceres, Inc. | Materials and methods for use in biomass processing |
| CN101918815A (en) * | 2007-11-02 | 2010-12-15 | 赛乐斯股份有限公司 | Materials and methods for use in biomass processing |
| CN101419165A (en) * | 2008-11-17 | 2009-04-29 | 江苏科技大学 | Mequindox content detecting method in veterinary drugs |
| CH708057A2 (en) * | 2013-05-06 | 2014-11-14 | Univ Jiangnan | Near-infrared method for determining the constituents of the lotus root. |
| CA2839027A1 (en) * | 2014-01-02 | 2015-07-02 | Alltech, Inc. | Systems and methods for estimating feed efficiency and carbon footprint for milk producing animal |
| CN106970041A (en) * | 2017-04-12 | 2017-07-21 | 江苏省农业科学院 | A kind of near-infrared assay method of the big aggressiveness content of wheat flour Insoluble glutenin |
| CN107255624A (en) * | 2017-05-12 | 2017-10-17 | 华南农业大学 | A kind of fast and convenient method for determining protein content in fan's power mushroom entity |
| CN107389592A (en) * | 2017-07-10 | 2017-11-24 | 天津工业大学 | A kind of complex sample spectral signal selective ensemble pre-processes modeling method |
| CN107884361A (en) * | 2017-11-03 | 2018-04-06 | 云南农业大学 | A kind of Yunnan local chicken muscle freeze-dried powder gross protein value near infrared detection method |
| CN111024647A (en) * | 2020-01-08 | 2020-04-17 | 山东金璋隆祥智能科技有限责任公司 | Method for detecting moisture and protein content in dry starch based on GSA near infrared technology |
| CN112986174A (en) * | 2021-02-03 | 2021-06-18 | 佛山一本农业科技有限公司 | Near infrared spectrum-based fruit and vegetable optimal sorting method and system and readable storage medium |
| CN113310929A (en) * | 2021-05-10 | 2021-08-27 | 华中农业大学 | Soybean powder doped in high-temperature sterilized milk and spectral identification method of doping proportion thereof |
| CN114518339A (en) * | 2022-02-23 | 2022-05-20 | 新希望六和股份有限公司 | Method for establishing near-infrared prediction model of wet-based fermented soybean meal and application |
| CN115561223A (en) * | 2022-09-27 | 2023-01-03 | 正大青春宝药业有限公司 | Method for detecting content of perhexiline aqueous extract based on Raman spectrum and application |
Non-Patent Citations (2)
| Title |
|---|
| Prediction of protein content in rice using a near-infrared imaging system as diagnostic technique;Lin, LH 等;INTERNATIONAL JOURNAL OF AGRICULTURAL AND BIOLOGICAL ENGINEERING;第12卷(第2期);195-200 * |
| 大蒜真空脉动干燥工艺参数优化;乔宏柱;高振江;王军;郑志安;魏青;李高飞;;农业工程学报(第05期);第256-263页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117368146A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110441248B (en) | Method for building pit mud moisture prediction model based on hyperspectral image technology | |
| CN107796782B (en) | Redrying quality stability evaluation method based on tobacco leaf characteristic spectrum consistency measurement | |
| CN102539375A (en) | Straw solid-state fermentation process parameter soft measurement method and device based on near infrared spectrum | |
| CN103278473B (en) | The mensuration of pipering and moisture and method for evaluating quality in white pepper | |
| CN108680515B (en) | Single-grain rice amylose quantitative analysis model construction and detection method thereof | |
| CN101210875A (en) | Damage-free measurement method for soil nutrient content based on near infrared spectra technology | |
| CN103344597B (en) | Anti-flavored-interference near infrared non-destructive testing method for internal components of lotus roots | |
| CN109374548A (en) | A method of quickly measuring nutritional ingredient in rice using near-infrared | |
| CN107505179A (en) | A kind of soil pretreatment and nutrient near infrared spectrum detection method | |
| CN111795943A (en) | Method for nondestructive detection of exogenous doped sucrose in tea based on near infrared spectrum technology | |
| CN110308111B (en) | Method for rapidly predicting time for smoldering yellow tea by using near infrared spectrum technology | |
| CN109164069B (en) | Identification method for leaf surface disease grade of fruit tree | |
| CN102288569A (en) | Method for rapidly analyzing fiber biomass | |
| CN106338488A (en) | Method for fast undamaged determination of transgenic soybean milk powder | |
| CN117368146B (en) | Rapid detection method for mycelium protein content | |
| CN108007917B (en) | Method for establishing Raman spectrum measurement model of nitrogen content in rice plant by Hilbert method | |
| CN105675538A (en) | Method for detection of linseed cake nutrients | |
| CN107796779A (en) | The near infrared spectrum diagnostic method of rubber tree LTN content | |
| CN113049526B (en) | Corn seed moisture content determination method based on terahertz attenuated total reflection | |
| CN108007916B (en) | Confocal micro-Raman measurement model for establishing nitrogen content of rice plant by Hilbert-Huang method | |
| CN110320174B (en) | Method for rapidly predicting time for smoldering yellow tea by applying polynomial net structure artificial neural network | |
| CN112763448A (en) | ATR-FTIR technology-based method for rapidly detecting content of polysaccharides in rice bran | |
| CN112697745A (en) | Method for measuring alcohol content of white spirit | |
| CN113418889A (en) | Real-time detection method for water content and total number of bacterial colonies of dried vegetables based on deep learning | |
| CN111259970A (en) | Intelligent monitoring method for dough fermentation state in steamed bun processing process |
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 |