CN104372075A - Method for construction of discrimination model for discriminating daqu quality - Google Patents
Method for construction of discrimination model for discriminating daqu quality Download PDFInfo
- Publication number
- CN104372075A CN104372075A CN201410419220.8A CN201410419220A CN104372075A CN 104372075 A CN104372075 A CN 104372075A CN 201410419220 A CN201410419220 A CN 201410419220A CN 104372075 A CN104372075 A CN 104372075A
- Authority
- CN
- China
- Prior art keywords
- quality
- discrimination model
- discriminating
- daqu
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
- C12Q1/6869—Methods for sequencing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Organic Chemistry (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Zoology (AREA)
- General Health & Medical Sciences (AREA)
- Biotechnology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Wood Science & Technology (AREA)
- Biochemistry (AREA)
- Microbiology (AREA)
- Immunology (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention provides a method for construction of a discrimination model for discriminating daqu quality, the method comprises the following steps: 1, information extraction; 2, variable screening and optimization; 3, construction of the discrimination model; 4, verification of the model; and 5, discriminating; and the method is applied to discriminating of daqu quality in distiller's yeast. The method uses 454 high throughput sequencing technology, and solves the problem that the first generation sequencing technology cannot comprehensively and accurately reflect the composition information of daqu microbes; by use of partial least squares method for variable screening and optimization of the microbes and meanwhile combination with quadratic discriminatory analysis, the daqu quality discriminating evaluation is constructed, and is applied to discriminating of daqu quality grade, the method for discriminating finished product qu and out-taken yellow qu and white qu grade is constructed, and the method has the advantages of simple operation and use, higher discriminating accuracy rate, and the like.
Description
Technical field
The present invention relates to the technical field belonging to spirit quality and differentiate, be specifically related to application Daqu microorganism composition information, realize spirit quality mirror method for distinguishing in conjunction with multivariate statistical method.
Background technology
Daqu is the indispensable part of brewed spirit, plays 1. microbe inoculation; 2. enzyme system is produced; 3. flavour substances and precursor be provided and 4. supplement the effect of material.This first three microflora's Fauna construction of planting in function and Daqu has great cognation, and therefore Daqu microorganism composition difference can react its quality to a certain extent.
454 high-flux sequence methods are the DNA sequencing technology of new generation developed in the last few years, with its digitized signal, high data throughput, high feature such as the order-checking degree of depth, high-accuracy etc., the colony assay of extensive multiple sample can be realized, be widely used in the comparative analysis of human body and microbial population of animal intestinal tract, marine microorganism flora composition.Part result of study is published in the international top magazine such as " Nature ", " PNAS ", " GenomeRes ", " Gut ", " Gastroenterology ".
Multivariate statistical method is the branch grown up from the classical theory of statistics, is a kind of comprehensive analysis method, and it can analyze their statistical law under multiple object and the inter-related situation of multiple index.Wherein, partial least square method (PLS) is a kind of novel multivariate statistics data analysing method, its variable importance projection index VIP value is the importance of reflection independent variable(s) when explaining dependent variable effect, can according to the screening of VIP size and the quantity optimizing independent variable(s) in discrimination model.Discriminatory analysis is the Sample Establishing discrimination model utilizing known class, a kind of multivariate statistical method that the sample for unknown classification differentiates.There is not been reported to utilize 454 high throughput sequencing technologies and multiviate statistical analysis to differentiate the method for spirit quality in prior art.
As be 201310201060.5 in the patent No., patent name is that the Chinese invention patent of " a kind of discrimination model that builds differentiates the method for spirit quality " provides a kind of application solid-phase microextraction and spirit quality is differentiated in discriminatory analysis, the method is evaluated spirit quality by Daqu flavour substances, this method cost high and sentence accurate rate really allow for its cost people be difficult to accept.The patent No. be 200910228701.X, patent name is that the Chinese invention patent of " a kind of yeast of white spirit produce quality controlling means " provides a kind of DGGE Criterion finger printing applying Daqu microorganism, and mensuration gained collection of illustrative plates and standard diagram are compared and obtained the method for qualified product, in the method, DGGE technology can only detect tens kinds of dominant bacterias in sample; If learn concrete bacterial classification information, also need to carry out cloning, checking order, experimental implementation is loaded down with trivial details; And adopt the abundance situation that can not reflect microorganism in this way.In addition, the collection of illustrative plates comparison in the program is simple comparison, sentences accurate rate be difficult to effective raising for some comparatively special situations.
Summary of the invention
For solving the problems of the technologies described above, the invention provides a kind of method building discrimination model discriminating spirit quality, the method of this discriminating spirit quality compares to Daqu sample by setting up multivariate statistics discrimination model, make can low cost, the height mode of sentencing accurate rate to carry out the differentiation of spirit quality, and simple to operate.
The present invention is achieved by the following technical programs.
A kind of method building discrimination model discriminating spirit quality provided by the invention, comprises the following steps:
Step is information extraction 1.: the microorganism composition information adopting DNA sequencing technical limit spacing Daqu sample;
Step is Variable Selection and optimization 2.: the microorganism based on step 1. gained forms information and sample quality grade, carries out screening and optimizes microorganism variable index, obtains and contribute large variable index to sample quality classification;
3. step sets up discrimination model: the variable information 2. optimized based on step and sample quality grade, builds the discrimination model that spirit quality grade is differentiated, determines criterion;
Step is verification model 4.: carry out back sentencing to modeling sample, to verify differentiation effect;
5. step is differentiated: use discrimination model to differentiate test sample;
Aforesaid method is applied to the quality discrimination to Daqu in distiller's yeast.
Step 1. described in DNA sequencing technology be 454 high throughput sequencing technologies.
Step 2. described in carry out screening to microorganism variable index and adopt partial least square method (PLS) with optimizing.
Step 3. described in discrimination model structure adopt Bayes's classification.
The structure of described discrimination model specifically uses quadratic discriminatory analysis method.
Described step 1. in Daqu sample be high-temperature daqu, namely finished product song, the Huang Qu that delivers from godown, the Bai Qu that delivers from godown any one.
Step 2. described in carry out screening with the principle optimized to microorganism variable index be variable importance projection desired value >=1,
Step 2. described in Variable Selection by SIMCA-P software simulating.
Step 3. described in discrimination model built by R language.
Beneficial effect of the present invention is:
(1) utilize 454 high throughput sequencing technologies, solve the composition information that first-generation sequencing technologies accurately can not reflect Daqu microorganism comprehensively.
(2) carry out screening and optimize to microorganism variable by partial least square method (PLS), build spirit quality Identification Evaluation model in conjunction with quadratic discriminatory analysis simultaneously and be applied to spirit quality grade and differentiate, construct and be a set ofly applicable to finished product song, the Huang Quhe that delivers from godown delivers from godown the method for discrimination that white bent grade is differentiated, have operation use simple, differentiate high accuracy for examination.
Accompanying drawing explanation
Fig. 1 is the variable diagram of variable importance projection index (VIP) value >=1 in experimental example.
Embodiment
Further describe technical scheme of the present invention below, but described in claimed scope is not limited to.
A kind of method building discrimination model discriminating spirit quality provided by the invention, comprises the following steps:
Step is information extraction 1.: the microorganism composition information adopting DNA sequencing technical limit spacing Daqu sample;
Step is Variable Selection and optimization 2.: the microorganism based on step 1. gained forms information and sample quality grade, carries out screening and optimizes microorganism variable index, obtains and contribute large variable index to sample quality classification;
3. step sets up discrimination model: the variable information 2. optimized based on step and sample quality grade, builds the discrimination model that spirit quality grade is differentiated, determines criterion;
Step is verification model 4.: carry out back sentencing to modeling sample, to verify differentiation effect;
5. step is differentiated: use discrimination model to differentiate test sample;
Aforesaid method is applied to the quality discrimination to Daqu in distiller's yeast.
Step 1. described in DNA sequencing technology be 454 high throughput sequencing technologies.
Step 2. described in carry out screening to microorganism variable index and adopt partial least square method (PLS) with optimizing.
Step 3. described in discrimination model structure adopt Bayes's classification.
The structure of described discrimination model specifically uses quadratic discriminatory analysis method.
Described step 1. in Daqu sample be high-temperature daqu, namely finished product song, the Huang Qu that delivers from godown, the Bai Qu that delivers from godown any one.
Step 2. described in carry out screening with the principle optimized to microorganism variable index be variable importance projection index VIP value >=1,
Step 2. described in Variable Selection by SIMCA-P software simulating.
Step 3. described in discrimination model built by R language.
Experimental example 1
1. sample message
113 high-temperature daqus that sample source in the present embodiment provides in Kweichow Moutai Co., Ltd., wherein sample comprises:
Modeling sample: bent 37 of finished product, the Huang Qu 21 that delivers from godown, deliver from godown Bai Qu 20;
Test sample: bent 20 of finished product, the Huang Qu 8 that delivers from godown, deliver from godown Bai Qu 7.
2. information extraction
Utilize 454 high throughput sequencing technologies, sequencing analysis carried out to all samples, obtain altogether 580 quasi-microorganism kinds (microorganism is numbered x1, x2, x3 ..., x580) and relative content.
3. Variable Selection and optimization
Variable and sample message are inputted SIMCA-P software, utilize partial least square method (PLS), carry out screening to the microorganism variable obtained and optimize, according to the principle of variable importance projection index (VIP) value >=1, as shown in Figure 1,14 quasi-microorganism variablees are obtained altogether.
4. set up discrimination model
By R language, adopt quadratic discriminatory analysis method, with above-mentioned 14 quasi-microorganism data for independent variable(s), with the judgement of 3 kinds of high-temperature daqus for dependent variable, carry out quadratic discriminatory analysis, build the discrimination model of spirit quality grade.
5. verification model
First utilize cross validation to carry out back sentencing to modeling sample, to verify differentiation effect, the results are shown in Table 1.
Table 1 modeling sample cross validation results
Note: Q: finished product is bent; Y: deliver from godown Huang Qu; W: deliver from godown Bai Qu
As can be seen from Table 1, for totally 78, the sample of modeling: bent 37 of finished product, the Huang Qu 21 that delivers from godown, deliver from godown Bai Qu 20.The differentiation accuracy rate of this discrimination model to finished product song is 37/37=100.0%, be 20/21=95.2% to the differentiation accuracy rate of the Huang Qu that delivers from godown, be 19/20=95.0% to the differentiation accuracy rate of the Bai Qu that delivers from godown, comprehensive distinguishing accuracy rate is (37+19+20)/(37+20+21)=97.4%, shows that the differentiation that set up discrimination model is differentiated spirit quality is comparatively effective.
6. differentiate
Adopt discrimination model to differentiate 35 outside test samples (bent 20 of finished product, the Huang Qu 8 that delivers from godown, deliver from godown Bai Qu 7), the results are shown in Table 2.
Table 2 external testing sample the result
Note: Q: finished product is bent; Y: deliver from godown Huang Qu; W: deliver from godown Bai Qu
As can be seen from Table 2, this secondary discrimination is 19/20=95.0% to the differentiation accuracy rate of finished product song in outside test specimens product, be 8/10=80.0% to the differentiation accuracy rate of the Huang Qu that delivers from godown, be 6/6=100.0% to the differentiation accuracy rate of the Bai Qu that delivers from godown, comprehensive distinguishing accuracy rate is (19+8+6)/35=94.3%, and this result shows that the differentiation effect that set up discrimination model is differentiated spirit quality is better further.
Obviously, relative to the mode of solid-phase microextraction, the method provided by the invention time used is few, can complete within one day, and cost is extremely low, except step 1. in DNA sequencing may use except a little consumptive material, whole process is substantially without the need to other consumptive materials, and the extendability aspect of the method is also considerably beyond by the method for DGGE Criterion finger printing.Provide a lot for building routine package or the function of discrimination model in what is more important R language, therefore adopt R language to build discrimination model and can ensure that layman also can easy operation by less training, avoid operator's erroneous judgement of bringing of specialty not greatly, it also avoid the sky high cost that operator that enterprise is cultivate professional pay.
Claims (9)
1. build the method that discrimination model differentiates spirit quality, it is characterized in that: comprise the following steps:
Step is information extraction 1.: the microorganism composition information adopting DNA sequencing technical limit spacing Daqu sample;
Step is Variable Selection and optimization 2.: the microorganism based on step 1. gained forms information and sample quality grade, carries out screening and optimizes microorganism variable index, obtains and contribute large variable index to sample quality classification;
3. step sets up discrimination model: the variable information 2. optimized based on step and sample quality grade, builds the discrimination model that spirit quality grade is differentiated, determines criterion;
Step is verification model 4.: carry out back sentencing to modeling sample, to verify differentiation effect;
5. step is differentiated: use discrimination model to differentiate test sample;
Aforesaid method is applied to the quality discrimination to Daqu in distiller's yeast.
2. the as claimed in claim 1 method differentiating spirit quality, is characterized in that: step 1. described in DNA sequencing technology be 454 high throughput sequencing technologies.
3. the as claimed in claim 1 method differentiating spirit quality, is characterized in that: step 2. described in microorganism variable index carry out screen and optimized adopt partial least square method (PLS).
4. the as claimed in claim 1 method differentiating spirit quality, is characterized in that: step 3. described in the structure of discrimination model adopt Bayes's classification.
5. the method differentiating spirit quality as claimed in claim 4, is characterized in that: the structure of described discrimination model specifically uses quadratic discriminatory analysis method.
6. the as claimed in claim 1 method differentiating spirit quality, is characterized in that: described step 1. in Daqu sample be high-temperature daqu, namely finished product song, the Huang Qu that delivers from godown, the Bai Qu that delivers from godown any one.
7., as the method for the discriminating spirit quality in claim 1 or 3 as described in any one, it is characterized in that: step 2. described in carry out screening with the principle optimized to microorganism variable index be variable importance projection index (VIP) value >=1.
8. the as claimed in claim 7 method differentiating spirit quality, is characterized in that: step 2. described in Variable Selection by SIMCA-P software simulating.
9., as the method for the discriminating spirit quality in claim 1,4 or 5 as described in any one, it is characterized in that: step 3. described in discrimination model built by R language.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410419220.8A CN104372075B (en) | 2014-08-22 | A kind of method building discrimination model discriminating spirit quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410419220.8A CN104372075B (en) | 2014-08-22 | A kind of method building discrimination model discriminating spirit quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104372075A true CN104372075A (en) | 2015-02-25 |
| CN104372075B CN104372075B (en) | 2017-01-04 |
Family
ID=
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117607A (en) * | 2015-09-15 | 2015-12-02 | 安徽瑞思威尔科技有限公司 | Method for classifying yeasts of different qualities based on chemometrics method |
| CN105420027A (en) * | 2015-12-31 | 2016-03-23 | 贵州茅台酒股份有限公司 | High-temperature daqu cooperation application method |
| CN106990214A (en) * | 2017-05-08 | 2017-07-28 | 云南民族大学 | A kind of method for evaluating Chinese medicine quality |
| CN109142626A (en) * | 2018-07-19 | 2019-01-04 | 贵州茅台酒股份有限公司 | A kind of method that the sour taste discrimination model of fermented grain constructed and used the sour taste of the Model checking fermented grain |
| CN109949863A (en) * | 2019-02-18 | 2019-06-28 | 贵州茅台酒股份有限公司 | A method of spirit quality is identified based on Random Forest model |
| CN111537542A (en) * | 2020-06-01 | 2020-08-14 | 四川轻化工大学 | Method for rapidly identifying Daqu grade |
| CN114814011A (en) * | 2022-04-12 | 2022-07-29 | 贵州茅台酒股份有限公司 | Method for identifying storage time of Daqu |
| CN115436531A (en) * | 2022-10-20 | 2022-12-06 | 茅台学院 | Method for identifying quality of Daqu based on Daqu non-volatile substances |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104109719A (en) * | 2014-07-21 | 2014-10-22 | 贵州茅台酒股份有限公司 | Method for identifying quality of yeast for making hard liquor on basis of box plot |
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104109719A (en) * | 2014-07-21 | 2014-10-22 | 贵州茅台酒股份有限公司 | Method for identifying quality of yeast for making hard liquor on basis of box plot |
Non-Patent Citations (2)
| Title |
|---|
| 徐晓宇等: "454测序法在环境微生物生态研究中的作用", 《生物技术通报》 * |
| 杨代永等: "高温大曲中的微生物研究", 《酿酒科技》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105117607B (en) * | 2015-09-15 | 2017-10-03 | 安徽瑞思威尔科技有限公司 | A kind of method classified based on chemometrics method to the Daqu of different quality |
| CN105117607A (en) * | 2015-09-15 | 2015-12-02 | 安徽瑞思威尔科技有限公司 | Method for classifying yeasts of different qualities based on chemometrics method |
| CN105420027A (en) * | 2015-12-31 | 2016-03-23 | 贵州茅台酒股份有限公司 | High-temperature daqu cooperation application method |
| CN106990214B (en) * | 2017-05-08 | 2019-11-15 | 云南民族大学 | A method of evaluation Chinese medicine quality |
| CN106990214A (en) * | 2017-05-08 | 2017-07-28 | 云南民族大学 | A kind of method for evaluating Chinese medicine quality |
| CN109142626A (en) * | 2018-07-19 | 2019-01-04 | 贵州茅台酒股份有限公司 | A kind of method that the sour taste discrimination model of fermented grain constructed and used the sour taste of the Model checking fermented grain |
| CN109142626B (en) * | 2018-07-19 | 2021-03-30 | 贵州茅台酒股份有限公司 | Fermented grain rancidness distinguishing model construction and method for distinguishing fermented grain rancidness by adopting same |
| CN109949863A (en) * | 2019-02-18 | 2019-06-28 | 贵州茅台酒股份有限公司 | A method of spirit quality is identified based on Random Forest model |
| CN109949863B (en) * | 2019-02-18 | 2023-05-26 | 贵州茅台酒股份有限公司 | Method for identifying Daqu quality based on random forest model |
| CN111537542A (en) * | 2020-06-01 | 2020-08-14 | 四川轻化工大学 | Method for rapidly identifying Daqu grade |
| CN114814011A (en) * | 2022-04-12 | 2022-07-29 | 贵州茅台酒股份有限公司 | Method for identifying storage time of Daqu |
| CN114814011B (en) * | 2022-04-12 | 2023-04-21 | 贵州茅台酒股份有限公司 | Method for identifying storage time of Daqu |
| CN115436531A (en) * | 2022-10-20 | 2022-12-06 | 茅台学院 | Method for identifying quality of Daqu based on Daqu non-volatile substances |
| CN115436531B (en) * | 2022-10-20 | 2024-06-25 | 茅台学院 | Method for identifying quality of Daqu based on Daqu non-volatile matter |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| McCormack et al. | Building a better foundation: improving root‐trait measurements to understand and model plant and ecosystem processes | |
| Zaura | Next-generation sequencing approaches to understanding the oral microbiome | |
| CN104866863B (en) | A kind of biomarker screening technique | |
| Rojewski et al. | Use of t-test and ANOVA in career-technical education research | |
| Goberna et al. | Phylogenetic-scale disparities in the soil microbial diversity–ecosystem functioning relationship | |
| TWI783699B (en) | A method for identifying individual gene and its deep learning model | |
| Brandt et al. | Abundance tracking by long-read nanopore sequencing of complex microbial communities in samples from 20 different biogas/wastewater plants | |
| CN109949863A (en) | A method of spirit quality is identified based on Random Forest model | |
| Kuhn et al. | Convergence and continuity in the initial upper Paleolithic of Eurasia | |
| Falcucci et al. | Bringing shape into focus: Assessing differences between blades and bladelets and their technological significance in 3D form | |
| CN105095688A (en) | Method for detecting bacterial communities and abundances of human intestinal metagenome | |
| CN104109719B (en) | A kind of method differentiating spirit quality based on box traction substation | |
| Thompson et al. | Global observing for phytoplankton? A perspective | |
| CN104520715B (en) | Detection to mixture during mass spectrum microbial identification | |
| He | Microarrays | |
| CN104372075B (en) | A kind of method building discrimination model discriminating spirit quality | |
| EP3660853A3 (en) | Mass spectrometer, mass spectrometry method, and mass spectrometry program for discriminating a strain in a microorganism | |
| CN104372075A (en) | Method for construction of discrimination model for discriminating daqu quality | |
| CN107513572A (en) | A kind of method for differentiating pit mud cellar for storing things age | |
| Gross et al. | A selective approach to internal inference | |
| Ren et al. | Rapid identification of lactic acid bacteria at species/subspecies level via ensemble learning of Ramanomes | |
| CN118053500B (en) | Multi-layer neural network-based flora abundance prediction method and system | |
| Mo et al. | Tree-Based Methods: A Tool for Modeling Nonlinear Complex Relationships and Generating New Insights from Data | |
| CN107271533A (en) | The algorithm of bacterium biased sample is identified based on MALDI TOF mass spectrometric datas | |
| Konstantinidou et al. | Metaplat: a cloud based platform for analysis and visualisation of metagenomics data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |