CN116959628A - Method and device for analyzing substance components in whole cell culture process - Google Patents
Method and device for analyzing substance components in whole cell culture process Download PDFInfo
- Publication number
- CN116959628A CN116959628A CN202310912458.3A CN202310912458A CN116959628A CN 116959628 A CN116959628 A CN 116959628A CN 202310912458 A CN202310912458 A CN 202310912458A CN 116959628 A CN116959628 A CN 116959628A
- Authority
- CN
- China
- Prior art keywords
- matrix
- component
- concentration
- spectrum
- spectrum matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000126 substance Substances 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004113 cell culture Methods 0.000 title claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims abstract description 94
- 238000001228 spectrum Methods 0.000 claims abstract description 81
- 238000004458 analytical method Methods 0.000 claims abstract description 53
- 239000013076 target substance Substances 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000001237 Raman spectrum Methods 0.000 claims abstract description 5
- 238000000855 fermentation Methods 0.000 claims abstract description 5
- 230000004151 fermentation Effects 0.000 claims abstract description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000001069 Raman spectroscopy Methods 0.000 description 10
- 230000003595 spectral effect Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000013211 curve analysis Methods 0.000 description 4
- 238000010238 partial least squares regression Methods 0.000 description 4
- QTBSBXVTEAMEQO-UHFFFAOYSA-N Acetic acid Chemical compound CC(O)=O QTBSBXVTEAMEQO-UHFFFAOYSA-N 0.000 description 3
- 238000005315 distribution function Methods 0.000 description 3
- JVTAAEKCZFNVCJ-UHFFFAOYSA-N lactic acid Chemical compound CC(O)C(O)=O JVTAAEKCZFNVCJ-UHFFFAOYSA-N 0.000 description 2
- 238000004949 mass spectrometry Methods 0.000 description 2
- 239000000758 substrate Substances 0.000 description 2
- GUBGYTABKSRVRQ-XLOQQCSPSA-N Alpha-Lactose Chemical compound O[C@@H]1[C@@H](O)[C@@H](O)[C@@H](CO)O[C@H]1O[C@@H]1[C@@H](CO)O[C@H](O)[C@H](O)[C@H]1O GUBGYTABKSRVRQ-XLOQQCSPSA-N 0.000 description 1
- 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 1
- ZDXPYRJPNDTMRX-VKHMYHEASA-N L-glutamine Chemical compound OC(=O)[C@@H](N)CCC(N)=O ZDXPYRJPNDTMRX-VKHMYHEASA-N 0.000 description 1
- GUBGYTABKSRVRQ-QKKXKWKRSA-N Lactose Natural products OC[C@H]1O[C@@H](O[C@H]2[C@H](O)[C@@H](O)C(O)O[C@@H]2CO)[C@H](O)[C@@H](O)[C@H]1O GUBGYTABKSRVRQ-QKKXKWKRSA-N 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- WQZGKKKJIJFFOK-VFUOTHLCSA-N beta-D-glucose Chemical compound OC[C@H]1O[C@@H](O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-VFUOTHLCSA-N 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- ZDXPYRJPNDTMRX-UHFFFAOYSA-N glutamine Natural products OC(=O)C(N)CCC(N)=O ZDXPYRJPNDTMRX-UHFFFAOYSA-N 0.000 description 1
- 239000004310 lactic acid Substances 0.000 description 1
- 235000014655 lactic acid Nutrition 0.000 description 1
- 239000008101 lactose Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
-
- 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
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Crystallography & Structural Chemistry (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention relates to a substance component analysis method and a device for the whole cell culture process, wherein the method comprises the following steps: pre-training to obtain a concentration regression model; an acquisition step of acquiring a plurality of Raman spectrums in real time for a culture solution in fermentation so as to obtain an original spectrum matrix; analyzing to obtain a main component matrix; an extraction step, namely performing feature extraction on the main component matrix to obtain a concentration spectrum matrix and a component spectrum matrix; a correlation step of obtaining an optimal component spectrum matrix of a plurality of target substances; comparing the optimal component spectrum matrixes of the target substances, and obtaining an actual spectrum matrix according to the concentration spectrum matrix and the component spectrum matrix; and a prediction step, carrying out concentration regression prediction according to the actual spectrum matrix and the concentration regression model to obtain a predicted concentration matrix. According to the invention, the technical problem that the substance components cannot be analyzed correctly is solved, and the stability and accuracy of the substance component analysis are improved.
Description
Technical Field
The invention relates to the field of substance analysis, in particular to a substance component analysis method and a device for the whole cell culture process.
Background
During cell culture, a constant concern over the content of various substances within the tank is extremely important for the growth of microorganisms and the formation of products. The usual method is to use various detectors, off-line sampling analysis, etc., and there are also methods using raman spectroscopy for on-line analysis. In the conventional raman spectrum analysis method, after spectrum acquisition, pretreatment is performed through baseline calibration, normalization and the like, and concentration regression is performed to obtain a corresponding substance concentration value.
In the actual biological fermentation process, the substances are not clear, namely the types and the amounts of the source substances are not clear, namely the raman peak intensities of part of the substances are not obvious, so that after concentration regression is directly performed by the prior art, an accurate concentration value matrix cannot be derived, and the components of the substances cannot be analyzed correctly.
It can be seen that the provision of an improved method and apparatus for analyzing the composition of matter for the whole cell culture process, based on the shortcomings of the prior art, is a technical problem to be solved by those skilled in the art.
Disclosure of Invention
Problems to be solved by the invention
The object of the present invention is to overcome the drawbacks of the prior art and to provide an improved method and device for analysing the composition of matter for the whole process of cell culture. According to the improved substance component analysis method and device provided by the invention, the technical problem that the substance component cannot be accurately analyzed is solved, and the stability and accuracy of the substance component analysis are improved.
Means for solving the problems
The first aspect of the present invention relates to a method for analyzing a substance component for a whole cell culture process, comprising the steps of:
a pre-training step, namely respectively carrying out spectrum acquisition on a plurality of target substances in a microorganism-free environment to obtain a multidimensional matrix, and recording concentration matrixes of the plurality of target substances to obtain a concentration regression model;
an acquisition step of acquiring a plurality of Raman spectrums in real time for a culture solution in fermentation so as to obtain an original spectrum matrix;
an analysis step of performing ICA on the original spectrum matrix, and substituting a plurality of main components respectively to obtain a main component matrix;
an extraction step, namely performing feature extraction on the main component matrix to obtain a concentration spectrum matrix and a component spectrum matrix;
a correlation step of performing correlation analysis on the component spectrum matrix and the multidimensional matrix, thereby obtaining an optimal component spectrum matrix of a plurality of target substances;
comparing the optimal component spectrum matrixes of the target substances, and obtaining an actual spectrum matrix according to the concentration spectrum matrix and the component spectrum matrix;
and a prediction step, carrying out concentration regression prediction according to the actual spectrum matrix and the concentration regression model to obtain a predicted concentration matrix.
Preferably, in the pre-training step, the multidimensional matrix is obtained in a linear correction manner.
Preferably, in the pre-training step, a concentration regression model is obtained in PLS-R mode.
Preferably, in the extracting step, the concentration spectrum matrix and the component spectrum matrix are obtained by a multivariate curve resolution and an alternating least squares method.
Preferably, in the comparing step, the comparison is performed by means of MSE.
The second aspect of the present invention relates to a substance component analysis apparatus for use in a whole cell culture process, the substance component analysis apparatus for performing a substance component analysis by the substance component analysis method of the first aspect of the present invention, the apparatus comprising:
the operation module is used for carrying out various operations in the analysis of the material components;
the communication module is connected with the operation module and used for communicating with the outside;
the storage module is connected with the operation module and used for storing the operated data;
the IO module is connected with the operation module and is used for receiving the input of a user and outputting an operation result;
and the display module is connected with the operation module and used for displaying the operation conditions and process.
Preferably, the operation module performs parallel processing using the GPU.
ADVANTAGEOUS EFFECTS OF INVENTION
According to the improved substance component analysis method and device provided by the invention, the technical problem that the substance component cannot be accurately analyzed is solved, and the stability and accuracy of the substance component analysis are improved.
Drawings
Fig. 1 is a flowchart of a method for analyzing a substance component according to a first embodiment of the present invention.
Fig. 2 is a spectrum corresponding to the original spectrum matrix in the analysis method of fig. 1.
Fig. 3 is a pseudo-inverse spectrum corresponding to the principal component matrix in the analysis method of fig. 1.
Fig. 4 is a spectrum corresponding to the concentration spectrum matrix in the analysis method of fig. 1.
FIG. 5 is a spectrum corresponding to the component spectrum matrix in the analysis method of FIG. 1.
Fig. 6 is a spectrum corresponding to the actual spectrum matrix in the analysis method of fig. 1.
Fig. 7 is a schematic view of a substance component analysis device according to a second embodiment of the present invention.
Detailed Description
The method and apparatus for analyzing a substance component used in the whole cell culture process according to the present invention will be described in detail below.
Fig. 1 is a flowchart of a method for analyzing a substance component according to a first embodiment of the present invention. As shown in fig. 1, the method includes: a pre-training step 101, an acquisition step 102, an analysis step 103, an extraction step 104, a correlation step 105, a comparison step 106, a prediction step 107.
Specifically, in the pre-training step 101, spectrum acquisition is performed on a plurality of target substances in a microorganism-free environment to obtain a relatively pure single standard spectrum and a spectrum in which a plurality of equivalent substances are alternately mixed, the spectra are superimposed and recorded as a multi-dimensional matrix [ Xp ], and a concentration matrix of the plurality of target substances is recorded to obtain a concentration regression model Mp.
The target substance may be selected according to the object of analysis, and may be, for example, glucose, lactose, acetic acid, glutamine, lactic acid, living cells, or the like.
Preferably, the multidimensional matrix [ Xp ] is obtained in a linear correction manner. The linear correction method may be, for example, baseline correction, savitzky-Golay filtering, or the like.
Preferably, the concentration regression model Mp is obtained in the manner of PLS-R (partial least squares regression).
Fig. 2 is a spectrum corresponding to the original spectrum matrix in the analysis method of fig. 1. In FIG. 2, the abscissa represents Raman shift in wavenumber (cm -1 ) The ordinate indicates the raman intensity in relative intensity (a.u). In the collection step 102, the culture solution in the tank is uniformly mixed under the action of the stirring paddle, a plurality of Raman spectrums are collected in real time, and after pretreatment, an original spectrum matrix [ S ] which is corresponding to FIG. 2 and eliminates noise in the fermentation process is obtained]。
Fig. 3 is a pseudo-inverse spectrum corresponding to the principal component matrix in the analysis method of fig. 1. In FIG. 3, the abscissa represents Raman shift in wavenumber (cm -1 ) The ordinate represents the value of the pseudo-inverse matrix after ICA extraction, and the value has no units. In the analysis step 103, ICA is performed on the original spectrum matrix, and a plurality of principal components are substituted into each of the spectrum matrix to obtain a principal component matrix. In this case, the number of principal components is set to n, and n may be a natural number of 3 or more and 30 or less, for example, and the principal components are substituted for the following to perform cyclic calculation. Matrix the original spectrum S]ICA (independent principal component analysis) is performed, and the principal components are substituted to obtain principal component matrix [ Si ]]The inside contains the spectral information of n principal components.
The specific ICA method is to increase a unmixed matrix [ W ], define si=w×s, establish an independent distribution function according to the property of independent distribution of the main component, and then popularize the independent distribution function into a joint distribution function, wherein W is a joint distribution parameter, and the unmixed matrix [ W ] can be calculated through maximum likelihood estimation, so as to calculate the main component matrix [ Si ].
Fig. 4 is a spectrum corresponding to the concentration spectrum matrix in the analysis method of fig. 1, and fig. 5 is a spectrum corresponding to the component spectrum matrix in the analysis method of fig. 1. In fig. 4, the abscissa represents the component spectral measurement value corresponding to the concentration spectral matrix, the value has no unit, and the ordinate represents the raman intensity in relative intensity (a.u). In FIG. 5, the abscissa represents Raman shift in wavenumber (cm -1 ) The ordinate indicates the component spectral metric values, the values being unitless. In the extraction step 104, since the superposition of spectral components follows a linear relationship, the equation is set:
S=K*St T +E,
wherein S is an original spectrum matrix [ S ], K is a concentration component of a main component matrix [ Si ], st is a component of the main component matrix [ Si ], E is a difference value between the original spectrum matrix [ S ] and the main component matrix [ Si ], namely a substrate spectrum, and the concentration spectrum matrix [ K ] and the component spectrum matrix [ St ] are obtained through calculation according to the formula.
Preferably, by a multi-curve resolution and alternating least square method, non-negative least square and L2 regularization are adopted as linear regression constraint, the optimal convergence term is calculated by iterative placement in a formula, and a concentration spectrum matrix [ K ] and a component spectrum matrix [ St ] in a real-time spectrum are obtained.
In a correlation step 105, the component spectrum matrix [ St ] is subjected to correlation analysis with the multidimensional matrix [ Xp ] to extract an optimal component spectrum matrix [ Sr ] of the target substance in the component spectrum.
Fig. 6 is a spectrum corresponding to the actual spectrum matrix in the analysis method of fig. 1. In FIG. 6, the abscissa represents Raman shift in wavenumber (cm -1 ) The ordinate indicates the raman intensity in relative intensity (a.u). In a comparison step 106, the pairComparing the results of the principal components, for example, by comparing the correlation, etc., to obtain the optimal principal component decomposition, and passing the concentration spectrum matrix [ K ] for the optimal solution set of this reasoning]And an optimal component spectral matrix [ Sr]The actual spectrum matrix [ XIN ] of the target substance with optimal matching can be obtained]。
Preferably, the comparison is made by means of MSE (MeanSquaredError).
In the prediction step 107, concentration regression prediction is performed on the actual spectrum matrix [ XIN ] by the concentration regression model Mp to obtain a predicted concentration matrix value. The final concentration matrix value is the predicted concentration of the target substance.
As described above, the first embodiment uses a blind source separation method and a PLS-R regression method to calculate the concentration. In the method, the influence problem of unknown components is solved by circularly setting the main component of ICA to obtain the optimal component spectrum, and the problem that component analysis cannot be accurately performed under the condition that the Raman peak intensity of a substance is not obvious is solved by separating out the spectrum and removing the substrate spectrum. Meanwhile, the method can also improve the stability and accuracy of detection, and when a traditional analysis method is used, MAPE (mean absolute percentage error) is 0-0.98, and after the method of the first embodiment of the invention is adopted, MAPE is greatly reduced to 0-0.14, so that the accuracy and robustness of an analysis flow are improved.
Therefore, according to the method for analyzing the substance component in the first embodiment of the invention, the technical problem that the substance component cannot be accurately analyzed is solved, and the stability and the accuracy of the analysis of the substance component are improved.
The second aspect of the present invention relates to a substance component analysis apparatus for performing substance component analysis by the substance component analysis method of the first aspect of the present invention. As shown in fig. 7, the apparatus includes: the operation module is used for carrying out various operations in the analysis of the material components; the communication module is connected with the operation module and used for communicating with the outside; the storage module is connected with the operation module and used for storing the operated data; the IO module is connected with the operation module and is used for receiving the input of a user and outputting an operation result; and the display module is connected with the operation module and used for displaying the operation conditions and process.
Specifically, the operation module may perform parallel operation on a plurality of matrix iterative operations in the substance component analysis method according to the first aspect of the present invention, such as a matrix iterative regression process of multivariate curve analysis. The operation module may be a parallel processing logic board card, such as a GPU operation card or an FPGA core card, and together with the communication module, the storage module, the IO module, and the display module, form a substance component analysis device for the whole cell culture process, where the analysis device may interact with a user through a key of the IO module.
The multi-element curve analysis process of the material component analysis method involves a large number of matrix multiplication and least square iteration, and the multi-element curve analysis operation process can be implanted into the GPU of the GPU operation card for operation, so that the matrix multiplication process is processed in parallel, and a large number of multi-element curve analysis operation time is saved by fully utilizing the parallel processing capability of the GPU.
As described above, according to the second embodiment, by using the substance component analysis device which is configured to be compatible with the first embodiment, the processing speed is greatly improved as compared with the substance component analysis technique in the related art, and thus, real-time analysis can be realized. It has been calculated that the calculation time for mass spectrometry is about 5s when the conventional analyzer is applied, whereas the calculation time for mass spectrometry is significantly reduced to about 500ms when the analyzer of the present invention is applied.
Therefore, according to the substance component analysis device of the second embodiment of the invention, the technical problem that the substance component cannot be accurately analyzed is solved, and the stability and accuracy of the substance component analysis are improved.
Industrial applicability
According to the method and the device for analyzing the substance components, the technical problem that the substance components cannot be accurately analyzed is solved, and the stability and the accuracy of the substance component analysis are improved.
While the invention has been shown and described with reference to certain preferred embodiments thereof, 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.
Claims (7)
1. A method for analyzing a substance component in a whole cell culture process, comprising the steps of:
a pre-training step, namely respectively carrying out spectrum acquisition on a plurality of target substances in a microorganism-free environment to obtain a multidimensional matrix, and recording concentration matrixes of the plurality of target substances to obtain a concentration regression model;
an acquisition step of acquiring a plurality of Raman spectrums in real time for a culture solution in fermentation so as to obtain an original spectrum matrix;
an analysis step of performing ICA on the original spectrum matrix, and substituting a plurality of main components respectively to obtain a main component matrix;
an extraction step, namely performing feature extraction on the main component matrix to obtain a concentration spectrum matrix and a component spectrum matrix;
a correlation step of performing correlation analysis on the component spectrum matrix and the multidimensional matrix, thereby obtaining an optimal component spectrum matrix of a plurality of target substances;
comparing the optimal component spectrum matrixes of the target substances, and obtaining an actual spectrum matrix according to the concentration spectrum matrix and the component spectrum matrix;
and a prediction step, carrying out concentration regression prediction according to the actual spectrum matrix and the concentration regression model to obtain a predicted concentration matrix.
2. The method for analyzing a substance component as defined in claim 1, wherein,
in the pre-training step, a multi-dimensional matrix is obtained in a linear correction manner.
3. The method for analyzing a substance component as defined in claim 1, wherein,
in the pre-training step, a concentration regression model is obtained in the PLS-R mode.
4. The method for analyzing a substance component as defined in claim 1, wherein,
in the extraction step, a concentration spectrum matrix and a component spectrum matrix are obtained through multi-curve resolution and an alternate least square method.
5. The method for analyzing a substance component as defined in claim 1, wherein,
in the comparison step, the comparison is performed by means of MSE.
6. A substance component analysis apparatus for use in a whole cell culture process, characterized by performing a substance component analysis by the substance component analysis method according to any one of claims 1 to 5, the apparatus comprising:
the operation module is used for carrying out various operations in the analysis of the material components;
the communication module is connected with the operation module and used for communicating with the outside;
the storage module is connected with the operation module and used for storing the operated data;
the IO module is connected with the operation module and is used for receiving the input of a user and outputting an operation result;
and the display module is connected with the operation module and used for displaying the operation conditions and process.
7. The device for analyzing a substance component as defined in claim 6, wherein,
the operation module performs parallel processing by using the GPU.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310912458.3A CN116959628A (en) | 2023-07-25 | 2023-07-25 | Method and device for analyzing substance components in whole cell culture process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310912458.3A CN116959628A (en) | 2023-07-25 | 2023-07-25 | Method and device for analyzing substance components in whole cell culture process |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116959628A true CN116959628A (en) | 2023-10-27 |
Family
ID=88444129
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310912458.3A Pending CN116959628A (en) | 2023-07-25 | 2023-07-25 | Method and device for analyzing substance components in whole cell culture process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116959628A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101458214A (en) * | 2008-12-15 | 2009-06-17 | 浙江大学 | Organic polymer solution concentration detecting method |
CN103175806A (en) * | 2013-03-14 | 2013-06-26 | 公安部天津消防研究所 | Method for detecting moisture content of dry powder extinguishing agents based on near infrared spectroscopy analysis |
CN104165861A (en) * | 2014-08-22 | 2014-11-26 | 云南中烟工业有限责任公司 | Near infrared spectrum quantitative model simplification method based on principal component analysis |
CN108802000A (en) * | 2018-03-16 | 2018-11-13 | 上海交通大学 | A kind of lossless quick cholecalciferol-cholesterol content quantitative method based on the full spectrum analysis of Raman |
CN110186851A (en) * | 2019-05-27 | 2019-08-30 | 生态环境部南京环境科学研究所 | It is a kind of based on the semi-supervised Hyperspectral imaging heavy metal-polluted soil concentration evaluation method from Coded Analysis |
CN110726694A (en) * | 2019-10-22 | 2020-01-24 | 常州大学 | Characteristic wavelength selection method and system of spectral variable gradient integrated genetic algorithm |
CN113030012A (en) * | 2021-04-02 | 2021-06-25 | 山东大学 | Spectrum analysis method and system based on multistage partial least square algorithm |
CN113919141A (en) * | 2021-09-22 | 2022-01-11 | 中国矿业大学 | Coal mine area storage yard soil heavy metal risk management and control system and migration inversion method |
CN114611582A (en) * | 2022-02-16 | 2022-06-10 | 温州大学 | Method and system for analyzing substance concentration based on near infrared spectrum technology |
-
2023
- 2023-07-25 CN CN202310912458.3A patent/CN116959628A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101458214A (en) * | 2008-12-15 | 2009-06-17 | 浙江大学 | Organic polymer solution concentration detecting method |
CN103175806A (en) * | 2013-03-14 | 2013-06-26 | 公安部天津消防研究所 | Method for detecting moisture content of dry powder extinguishing agents based on near infrared spectroscopy analysis |
CN104165861A (en) * | 2014-08-22 | 2014-11-26 | 云南中烟工业有限责任公司 | Near infrared spectrum quantitative model simplification method based on principal component analysis |
CN108802000A (en) * | 2018-03-16 | 2018-11-13 | 上海交通大学 | A kind of lossless quick cholecalciferol-cholesterol content quantitative method based on the full spectrum analysis of Raman |
CN110186851A (en) * | 2019-05-27 | 2019-08-30 | 生态环境部南京环境科学研究所 | It is a kind of based on the semi-supervised Hyperspectral imaging heavy metal-polluted soil concentration evaluation method from Coded Analysis |
CN110726694A (en) * | 2019-10-22 | 2020-01-24 | 常州大学 | Characteristic wavelength selection method and system of spectral variable gradient integrated genetic algorithm |
CN113030012A (en) * | 2021-04-02 | 2021-06-25 | 山东大学 | Spectrum analysis method and system based on multistage partial least square algorithm |
CN113919141A (en) * | 2021-09-22 | 2022-01-11 | 中国矿业大学 | Coal mine area storage yard soil heavy metal risk management and control system and migration inversion method |
CN114611582A (en) * | 2022-02-16 | 2022-06-10 | 温州大学 | Method and system for analyzing substance concentration based on near infrared spectrum technology |
Non-Patent Citations (1)
Title |
---|
葛东旭: "《数据挖掘原理与应用》", 30 April 2020, 北京机械工业出版社, pages: 47 - 51 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101915744B (en) | Near infrared spectrum nondestructive testing method and device for material component content | |
CN104677875B (en) | A kind of three-dimensional fluorescence spectrum combines the method that parallel factor differentiates different brands Chinese liquor | |
Jimenez-Carvelo et al. | Data mining/machine learning methods in foodomics | |
US9360421B2 (en) | Use of nuclear magnetic resonance and near infrared to analyze biological samples | |
CN111289489B (en) | Raman spectrum-based microorganism single cell growth detection method | |
CN106841083A (en) | Sesame oil quality detecting method based on near-infrared spectrum technique | |
Cozzolino et al. | The use of attenuated total reflectance as tool to monitor the time course of fermentation in wild ferments | |
CN111751376A (en) | Rice nitrogen nutrition estimation method based on canopy image feature derivation | |
CN109374548A (en) | A method of quickly measuring nutritional ingredient in rice using near-infrared | |
CN110110789A (en) | A kind of Chinese herbal medicine quality discrimination method based on multispectral figure information fusion technology | |
CN116959628A (en) | Method and device for analyzing substance components in whole cell culture process | |
CN110084420B (en) | Method for detecting total sugar, total acid and alcoholic strength of yellow water in strong aromatic Chinese spirit fermentation | |
CN115963074A (en) | Rapid detection method and system for spore and hypha ratio of microbial material | |
CN110887921A (en) | Method for efficiently and rapidly analyzing characteristic volatile components of eucommia leaves and fermentation product thereof | |
CN115950871A (en) | Method, device, system and equipment for detecting content of polyhydroxyalkanoate | |
CN105866065B (en) | Methenamine content analysis method in a kind of methenamine-acetum | |
CN111537467A (en) | Method for nondestructively measuring starch content of mung beans | |
CN111474287A (en) | Computer-aided system and method for analyzing composition components of medicine | |
CN111474134A (en) | Method for controlling butyric acid fermentation by using online near infrared | |
Bambina et al. | 1H-NMR Spectroscopy Coupled with Chemometrics to Classify Wines According to Different Grape Varieties and Different Terroirs | |
CN108956527B (en) | Method for rapidly detecting cyclic adenosine monophosphate cAMP content in red dates | |
CN117147524A (en) | Mixed solution rapid detection method based on principal component analysis | |
CN116952893B (en) | Method for near infrared detection of humification degree in pig manure composting process | |
Side | Protein concentration prediction in cell cultures: the next stage in near infrared bioprocess analysis | |
Jin et al. | Hyperspectral Inversion Modeling of Fat and Protein Content in Milk Based on XGBoost |
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 |