CN110988153A - Optimization method of ultrasonic extraction process for effective components of Salvia miltiorrhiza based on LS-SVM model - Google Patents
Optimization method of ultrasonic extraction process for effective components of Salvia miltiorrhiza based on LS-SVM model Download PDFInfo
- Publication number
- CN110988153A CN110988153A CN201911107896.2A CN201911107896A CN110988153A CN 110988153 A CN110988153 A CN 110988153A CN 201911107896 A CN201911107896 A CN 201911107896A CN 110988153 A CN110988153 A CN 110988153A
- Authority
- CN
- China
- Prior art keywords
- extraction
- evaluation value
- model
- comprehensive evaluation
- salvia miltiorrhiza
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 241000304195 Salvia miltiorrhiza Species 0.000 title claims abstract description 36
- 235000011135 Salvia miltiorrhiza Nutrition 0.000 title claims abstract description 36
- 238000005457 optimization Methods 0.000 title claims abstract description 20
- 238000002137 ultrasound extraction Methods 0.000 title claims abstract description 20
- 230000008569 process Effects 0.000 title claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 68
- 238000011156 evaluation Methods 0.000 claims abstract description 51
- 230000006870 function Effects 0.000 claims abstract description 12
- 238000012706 support-vector machine Methods 0.000 claims abstract description 7
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 38
- 238000012360 testing method Methods 0.000 claims description 14
- 239000011344 liquid material Substances 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 239000004480 active ingredient Substances 0.000 claims description 11
- 238000013461 design Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims 1
- 239000003814 drug Substances 0.000 abstract description 8
- 238000011160 research Methods 0.000 abstract description 7
- 238000012843 least square support vector machine Methods 0.000 description 28
- OKKJLVBELUTLKV-UHFFFAOYSA-N Methanol Chemical compound OC OKKJLVBELUTLKV-UHFFFAOYSA-N 0.000 description 15
- 238000002474 experimental method Methods 0.000 description 12
- 238000005303 weighing Methods 0.000 description 11
- 239000000523 sample Substances 0.000 description 8
- WEVYAHXRMPXWCK-UHFFFAOYSA-N Acetonitrile Chemical compound CC#N WEVYAHXRMPXWCK-UHFFFAOYSA-N 0.000 description 6
- 239000013558 reference substance Substances 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 239000000243 solution Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 239000012488 sample solution Substances 0.000 description 4
- 239000012085 test solution Substances 0.000 description 4
- 239000003153 chemical reaction reagent Substances 0.000 description 3
- 239000000843 powder Substances 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 239000012088 reference solution Substances 0.000 description 3
- 239000002904 solvent Substances 0.000 description 3
- 239000011550 stock solution Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000017531 blood circulation Effects 0.000 description 2
- 238000013401 experimental design Methods 0.000 description 2
- 239000000706 filtrate Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000004128 high performance liquid chromatography Methods 0.000 description 2
- 239000004615 ingredient Substances 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- BDAGIHXWWSANSR-UHFFFAOYSA-N methanoic acid Natural products OC=O BDAGIHXWWSANSR-UHFFFAOYSA-N 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 229910021642 ultra pure water Inorganic materials 0.000 description 2
- 239000012498 ultrapure water Substances 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- OSWFIVFLDKOXQC-UHFFFAOYSA-N 4-(3-methoxyphenyl)aniline Chemical compound COC1=CC=CC(C=2C=CC(N)=CC=2)=C1 OSWFIVFLDKOXQC-UHFFFAOYSA-N 0.000 description 1
- 206010002660 Anoxia Diseases 0.000 description 1
- 241000976983 Anoxia Species 0.000 description 1
- 201000006474 Brain Ischemia Diseases 0.000 description 1
- 206010008120 Cerebral ischaemia Diseases 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 240000001462 Pleurotus ostreatus Species 0.000 description 1
- 208000001431 Psychomotor Agitation Diseases 0.000 description 1
- 206010063837 Reperfusion injury Diseases 0.000 description 1
- 206010038743 Restlessness Diseases 0.000 description 1
- AIGAZQPHXLWMOJ-UHFFFAOYSA-N Tanshinone I Chemical class C1=CC2=C(C)C=CC=C2C(C(=O)C2=O)=C1C1=C2C(C)=CO1 AIGAZQPHXLWMOJ-UHFFFAOYSA-N 0.000 description 1
- 238000002835 absorbance Methods 0.000 description 1
- 230000007953 anoxia Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 206010008118 cerebral infarction Diseases 0.000 description 1
- 229940126678 chinese medicines Drugs 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000010828 elution Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 235000019253 formic acid Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 229910001867 inorganic solvent Inorganic materials 0.000 description 1
- 239000003049 inorganic solvent Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000002175 menstrual effect Effects 0.000 description 1
- 239000012982 microporous membrane Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008689 nuclear function Effects 0.000 description 1
- 239000003960 organic solvent Substances 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000000144 pharmacologic effect Effects 0.000 description 1
- -1 phenolic acid compounds Chemical class 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- QEVHRUUCFGRFIF-MDEJGZGSSA-N reserpine Chemical compound O([C@H]1[C@@H]([C@H]([C@H]2C[C@@H]3C4=C(C5=CC=C(OC)C=C5N4)CCN3C[C@H]2C1)C(=O)OC)OC)C(=O)C1=CC(OC)=C(OC)C(OC)=C1 QEVHRUUCFGRFIF-MDEJGZGSSA-N 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000006228 supernatant Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000009210 therapy by ultrasound Methods 0.000 description 1
- 229940126680 traditional chinese medicines Drugs 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000004506 ultrasonic cleaning Methods 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/04—Preparation or injection of sample to be analysed
- G01N30/06—Preparation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/26—Conditioning of the fluid carrier; Flow patterns
- G01N30/28—Control of physical parameters of the fluid carrier
- G01N30/34—Control of physical parameters of the fluid carrier of fluid composition, e.g. gradient
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/62—Detectors specially adapted therefor
- G01N30/74—Optical detectors
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Medicines Containing Plant Substances (AREA)
Abstract
基于LS‑SVM模型的丹参有效成分超声提取工艺优化方法，属于中药提取技术领域。本发明在高维特征空间利用最小二乘支持向量机建立综合评价值关于提取因素的回归模型，将回归模型转化成与核函数相关的优化模型，最终通过数据集进行不断学习找出在最优参数下与真实综合评价值误差最小的预测综合评价值从而能够找出提取的最优工艺因素。依照本发明建立一个非线性模型，可揭示数据之间的定量关系，模型误差小，可靠性高，为丹参有效成分超声提取工艺优化研究提供了新的思路与参考。
An ultrasonic extraction process optimization method for effective components of Salvia miltiorrhiza based on LS-SVM model belongs to the technical field of traditional Chinese medicine extraction. The invention uses the least squares support vector machine to establish a regression model of the comprehensive evaluation value on the extraction factors in the high-dimensional feature space, transforms the regression model into an optimization model related to the kernel function, and finally finds out the optimal model through continuous learning through the data set. The predicted comprehensive evaluation value with the smallest error from the real comprehensive evaluation value under the parameters can find the optimal process factor for extraction. A nonlinear model is established according to the present invention, which can reveal the quantitative relationship between the data, the model error is small, and the reliability is high, which provides a new idea and reference for the optimization research of the ultrasonic extraction process of the effective components of Salvia miltiorrhiza.
Description
Technical Field
The invention belongs to the technical field of traditional Chinese medicine extraction, and particularly relates to an ultrasonic extraction process optimization method for active ingredients of salvia miltiorrhiza based on an LS-SVM model.
Background
The salvia miltiorrhiza is a traditional Chinese medicine and has the effects of removing blood stasis, stopping bleeding, promoting blood circulation, stimulating the menstrual flow, clearing away the heart-fire, relieving restlessness and the like. The Salvia miltiorrhiza has the pharmacological effects of protecting cardiovascular system, improving blood circulation, resisting oxidation, protecting cerebral ischemia, protecting reperfusion injury, enhancing anoxia resistance, improving renal function, etc. The active ingredients of the salvia miltiorrhiza mainly comprise two types, namely fat-soluble tanshinone compounds and water-soluble phenolic acid compounds, wherein the active ingredients playing a positive role can be dozens of types, and the optimization of the extraction process of the active ingredients is also the research focus.
A Support Vector Machine (SVM) is a Machine learning model for solving a regression problem, and solves a fussy nonlinear problem by introducing a kernel function, thereby avoiding a dimension disaster problem of high-latitude space calculation. A Least square Support Vector Machine (LS-SVM) is a further improvement of the LS-SVM, and the operation speed is increased and the calculation complexity is reduced by converting an objective function and optimizing equation conditions. At present, many researchers often analyze Chinese medicine extraction data by operating a neural network model in a Matlab environment, but researches on optimizing the process conditions for extracting effective substances of Chinese medicines by using a least square support vector machine are rarely reported.
Disclosure of Invention
Aiming at the defect that the prior art for optimizing the process of the effective ingredients of the traditional Chinese medicine is unstable in processing the nonlinear problem at high latitude, the invention establishes a regression model of a comprehensive evaluation value about extraction factors by using a least square support vector machine in a high-dimensional characteristic space, converts the regression model into an optimization model related to a kernel function, and finally continuously learns through a data set to find out a predictive comprehensive evaluation value with the minimum error with a real comprehensive evaluation value under an optimal parameter so as to find out the optimal extracted process factor, and the method specifically comprises the following steps:
(1) carrying out ultrasonic extraction on active ingredients Sal _ B and Tan _ IIA of the salvia miltiorrhiza bunge according to the Box-Benhnken Design principle, carrying out experimental determination on the extraction rate of the active ingredients and the real comprehensive evaluation value of each process to obtain m groups of analysis scheme experimental data sets D { (X)1,Y1),(X2,Y2),…,(Xm,Ym)}，X1,X2…XmIs a combination of m extraction factor processes, Y1,Y2…YmA real comprehensive evaluation value of m extraction rates corresponding to the extraction factor process combination;
(2) establishing a least square support vector machine model LS-SVM, establishing an extraction factor x based on a Matlab language environmentiAnd comprehensively evaluating the value y to obtain an extraction factor x1,x2…xiA quantitative relation with the predictive comprehensive evaluation value y of the extraction rate;
(3) optimizing a nuclear parameter g and a penalty factor C of a model parameter, wherein the nuclear function adopts a radial basis kernel function RBF, editing by Matlab software, performing cross validation on g and C simultaneously by a cross validation method, and checking each pair of parameter effects one by one in a parameter matrix consisting of g and C to obtain optimal parameters g and C;
(4) inputting the optimal parameters g and C in the step (3) into an LS-SVM model to obtain a comprehensive predictive evaluation value of the Box-Benhnken Design analysis scheme in the step (1);
(5) evaluating the simulated performance of the LS-SVM model using the mean square error MSE, wherein
m is the number of data sets, yiPredictive comprehensive evaluation value, Y, for LS-SVMiThe evaluation value is a real comprehensive evaluation value.
The real comprehensive evaluation value in the step (1) is the sum of numerical values obtained by multiplying the process extraction rate by the weight, and the weight is calculated by a standard deviation method.
And (5) when the MSE is more than or equal to 0 and less than or equal to 0.6, the model predicts that the comprehensive evaluation value is close to the real comprehensive evaluation value, and the model is reliable.
The optimal ultrasonic extraction conditions of the effective components Sal _ B and Tan _ IIA of the salvia miltiorrhiza are as follows: the extraction temperature is 85 deg.C, the ultrasonic treatment time is 52min, the liquid-material ratio is 12:1, and the ethanol concentration is 90%.
The invention has the following beneficial effects:
the LS-SVM model establishes a nonlinear model by using a batch of mutually corresponding input and output data of an ultrasonic extraction process optimization experiment of the effective components of the salvia miltiorrhiza, which is obtained by the Box-Benhnken Design principle, reveals the quantitative relation between the data, has small model error and high reliability, and provides a new thought and reference for the optimization research of the extraction process of the effective components of the traditional Chinese medicine.
Drawings
FIG. 1 is an HPLC chart of a mixed control solution (a) and a Salvia miltiorrhiza test solution (B), wherein 1 is Sal _ B and 2 is Tan _ IIA;
FIG. 2 is a graph of optimal parameter results;
FIG. 3 is a graph of the results of error analysis of experimental data and model predictive data;
FIG. 4 is a comparison graph of the real comprehensive evaluation value and the predictive comprehensive evaluation value of the experiment;
Detailed Description
The present invention is further illustrated by the following examples.
Example (b):
1. instruments and reagents
1.1 instruments XS250 electronic balance (Mettler International Inc.), ultrapure water (Mettler Toledo Inc.), Waters 2695 type high performance liquid chromatograph (on-line vacuum degasser, autosampler system, column oven, 2498 type ultraviolet detector, Empower software), 2-16PK centrifuge (Sigma, Germany), SK5210HP ultrasonic cleaning instrument (Shanghai Ke ultrasonic guide Co., Ltd.).
1.2 reagent salvia miltiorrhiza (Zhejiang, batch number: 190201) is purchased from Zhejiang Chinese medicine university herbal pieces Limited, is identified by professor Huang-rope Wu of the institute of medicine and pharmacy of Zhejiang Chinese medicine university, and accords with the related regulation under the term salvia miltiorrhiza in the 2015 edition pharmacopoeia of the people's republic of China (part one). Sal _ B Standard was purchased from Biotech limited of Nanjing Shimeji (batch No. 101996, content ≥ 98%); tan _ IIA standard is purchased from Shanghai Allantin Biotechnology, Inc. (batch No. D1720010, content is more than or equal to 98%); acetonitrile, methanol (chromatographically pure, Tedia corporation); the water is ultrapure water; other reagents were analytically pure.
2. Method and results
2.1 HPLC determination of SalB and Tan IIA
2.1.1 chromatographic conditions: the chromatographic column is Hypersil BDS C18(4.6 mm. times.300 mm, 5 μm); the mobile phase was acetonitrile (a), 0.1% formic acid (B), with gradient elution: 0-12min, 10% -22% A; 12-30min, 22% -30% A; 30-38min, 30% -45% A; 38-50min, 45% -90% A; 50-55min, 90% -90% A; 55-56min, 90-95% A; 56-60min, 95% -10% A; the flow rate is 1 mL/min; the column temperature is 25 ℃; the detection wavelength is 280 nm; the amount of the sample was 10. mu.L.
2.1.2 preparation of control solutions: accurately weighing appropriate amount of Sal _ B and Tan _ IIA reference substances, respectively placing in 10mL volumetric flasks, adding 75% methanol to scale mark, and thoroughly shaking to obtain single component reference substance stock solutions containing Sal _ B1.00 mg/mL and Tan _ IIA 1.00 mg/mL. Precisely sucking 4.00mL and 0.50mL of the 2 stock solutions respectively, placing in the same 10mL measuring flask, adding 75% methanol to dilute to scale, and shaking to obtain mixed reference solution (Sal _ B0.40 mg/mL, Tan _ II A0.05mg/mL).
2.1.3 preparation of test solution: precisely weighing 5g of Saviae Miltiorrhizae radix powder sample, placing in a conical flask, performing ultrasonic extraction at liquid-material ratio of 12:1, 75 deg.C, ethanol concentration of 80% and ultrasonic frequency of 40kHz for 50min, and vacuum filtering to obtain filtrate. Centrifuging the filtrate at 5000r/min for 10min, and filtering the supernatant with 0.22 μm microporous membrane to obtain test solution.
2.1.4 plotting of Standard Curve: accurately sucking appropriate amounts of 1.00mg/mLSal _ B and Tan _ IIA reference substance stock solutions respectively, placing in volumetric flasks of different specifications, adding 75% methanol to scale marks, shaking up, and preparing mixed reference substance solutions of No. 1-5 with different concentrations, wherein the Sal _ B concentrations in the solutions of No. 1-5 are respectively as follows: 0.30, 0.40, 0.70, 0.90, 1.00 mg/mL; the concentrations of Tan _ IIA are: 0.03, 0.04, 0.05, 0.06, 0.08 mg/mL. According to the sample injection detection under the chromatographic condition of '2.1.1', a standard curve is drawn by taking the solution concentration as an abscissa (X) and the absorbance as an ordinate (Y), and the obtained Sal _ B standard curve is as follows: y is 9.30 × 106X+1.60×105(R20.9990) and has good linear relation in the concentration range of 0.30-1.00 mg/mL; the Tan _ iia standard curve is: y2.10 × 107X-6.24×103(R20.9995) in the concentration range of 0.03-0.08 mg/mL, and has good linear relation. When the signal-to-noise ratio is 3:1, the lowest detection limits of Sal _ B and Tan _ IIA are 0.05 and 0.01mg/mL respectively.
2.1.5 specificity test: the mixed reference solution and the salvia miltiorrhiza sample solution with proper amount are precisely absorbed and respectively measured according to the chromatographic conditions under the item of 2.1.1, the Sal _ B and Tan _ IIA peaks are completely separated, the peak shape is better, the separation degree is more than 1.50, and the method is shown in figure 1, which shows that the specificity of the method is good.
2.1.6 precision test: accurately sucking appropriate amount of Sal _ B of 0.50mg/mL and Tan _ IIA reference solution of 0.05mg/mL, respectively, and repeatedly and parallelly determining for 6 times according to the chromatographic conditions under the term of '2.1.1', to obtain peak areas RSD values of 0.69% and 0.76%, which indicates that the instrument has good precision.
2.1.7 stability test: preparing a sample solution according to the method of the item 2.1.3, taking the sample solution to be tested according to the item 2.1.1 and the room temperature condition, respectively injecting samples for 0h, 2 h, 4 h, 6 h and 8h, measuring, recording the chromatographic peak areas of Sal _ B and Tan _ IIA, and calculating RSD values to be 1.24 percent and 1.68 percent respectively, which indicates that the sample solution is stable within 8 h. 2.1.8 repeatability test: precisely weighing 5g of salvia miltiorrhiza powder in the same batch, preparing 6 parts of solution for supply according to the method of the item 2.1.3, and measuring under the chromatographic condition of the item 2.1.1 to obtain the RSD value of the Sal _ B peak area of 0.35 percent and the RSD value of the Tan _ IIA peak area of 0.28 percent, which indicates that the method has good repeatability.
2.1.9 sample recovery test: precisely weighing 5g of salvia miltiorrhiza powder in the same batch, and 6 parts in total, adding 0.50mg of Sal _ B reference substance and 0.10mg of Tan _ IIA reference substance into each part to prepare a test solution, and measuring according to chromatographic conditions, wherein the average recovery rate of Sal _ B is 98.39%, and the RSD is 0.52%; the average recovery of Tan _ IIA was 97.8% and the RSD was 0.57%.
2.2 Single factor experiment
2.2.1 Effect of ethanol concentration on extraction yield: precisely weighing 5 parts of 5g of salvia miltiorrhiza, and performing ultrasonic extraction for 40min under the conditions of liquid-material ratio of 12:1, temperature of 55 ℃, ethanol concentration of 50%, 60%, 70%, 80% and 90% and ultrasonic frequency of 40kHz respectively, wherein experimental results show that the extraction rates of Sal _ B and Tan _ IIA are highest when the ethanol concentration is 80%, so 70%, 80% and 90% are selected as three levels of ethanol concentration in response surface design.
2.2.2 Effect of ultrasound time on extraction yield: precisely weighing 5 parts of 5g of salvia miltiorrhiza, and performing ultrasonic extraction for 20min, 30min, 40min, 50min and 60min respectively under the conditions of liquid-material ratio of 12:1, temperature of 55 ℃ and ethanol concentration of 80% and ultrasonic frequency of 40kHz, wherein experimental results show that the extraction rates of Sal _ B and Tan _ IIA are highest when the ultrasonic time is 50min, so that 40min, 50min and 60min are selected as three levels of ultrasonic time in response surface design.
2.2.3 Effect of ultrasound temperature on extraction yield: precisely weighing 5 parts of 5g of salvia miltiorrhiza, and performing ultrasonic extraction for 50min at 45, 55, 65, 75 and 85 ℃ respectively under the conditions of liquid-material ratio of 12:1, ethanol concentration of 80% and ultrasonic frequency of 40kHz, wherein experimental results show that the extraction rates of Sal _ B and Tan _ IIA are highest when the ultrasonic temperature is 75 ℃, so that 65, 75 and 85 ℃ are selected as three levels of ultrasonic temperature in response surface design.
2.2.4 influence of liquid-to-feed ratio on extraction yield: precisely weighing 5g of Saviae Miltiorrhizae radix, and performing ultrasonic extraction at ethanol concentration of 80%, temperature of 75 deg.C and ultrasonic frequency of 40kHz for 50min at liquid-to-material ratio of 8:1, 10:1, 12:1, 14:1 and 16: 1. The experimental result shows that when the liquid-material ratio is 12: at 1, the extraction rates of Sal _ B and Tan _ IIA are the highest, so 10:1, 12:1 and 14:1 are selected as three levels of liquid-to-material ratio in response surface design.
2.2.5 Effect of extraction times on extraction yield: respectively and precisely weighing 5 parts of 5g of salvia miltiorrhiza, and extracting for 1, 2, 3 and 4 times under the conditions of ethanol concentration of 80%, time of 50min, temperature of 75 ℃ and liquid-material ratio of 12:1, wherein experimental results show that when the extraction frequency is 3, the extraction rate of Sal _ B and Tan _ IIA is relatively high, and the extraction rate tends to be gentle after 3 times, which indicates that the extraction of Sal _ B and Tan _ IIA is finished at the moment.
2.3 optimization technique of response surface method
2.3.1 factor level design: on the basis of a single-factor test, because the extraction frequency has little influence on the extraction rate, the ultrasonic time (A), the liquid-material ratio (B), the ultrasonic temperature (C) and the ethanol concentration (D) are selected as four factors, and finally, the response surface test design of 4-factor 3 level is carried out, so that the optimal extraction process parameters are optimized, and the test factors and specific level values are shown in table 1.
TABLE 1 BBD test factors and codings
2.3.2 test methods: precisely weighing 30 parts of 5g of Salvia miltiorrhiza, selecting factor levels of each experimental group number according to the Box-Benhnken Design (BBD) principle, performing sample injection detection under the chromatographic condition of '2.1.1' term to obtain the peak area values of Sal _ B and Tan _ IIA, respectively calculating the concentrations of Sal _ B and Tan _ IIA according to a regression equation, and combining with an extraction rate formula
Wherein c is Sal _ B, Tan _ IIA concentration (mg/mL) calculated by a calibrated regression equation, v is total volume (mL) of the extract, m is Salvia miltiorrhiza Bunge mass (g) and the extraction rates of Sal _ B and Tan _ IIA are calculated, and the number of experimental groups and results are shown in Table 2.
2.3.3 calculation of comprehensive evaluation value: the weighting values were calculated by the standard dispersion method, and the weighting coefficients of Sal _ B and Tan _ iia were found to be 0.49 and 0.51, respectively, and the total evaluation value was Sal _ B extraction rate × 0.49+ Tan _ iia extraction rate × 0.51, and the calculation results of the total evaluation value are shown in table 2.
TABLE 2 BBD analysis protocol and Experimental results
2.4 least squares support vector machine modeling and analysis
2.4.1 construction of least squares support vector machine model
The least squares support vector machine model can explain several extraction factors (x)1,x2…xi) The relationship between the extraction rate and the comprehensive evaluation index y, the basic idea thereofThink that the ith group of data inputs X for the BBD analysis schemei＝(x1,x2…xn) Representing the corresponding n values of the extraction factor and the ith data output YiRepresenting the overall evaluation value for the extraction yield, given the known m sets of BBD analysis protocol experimental data sets D { (X)1,Y1),(X2,Y2),…,(Xm,Ym) And finding a quantitative relation between the extraction factors and the comprehensive evaluation value. Specifically, a regression model of the comprehensive evaluation value about the extraction factor is established in a high-dimensional feature space by using a least square support vector machine, a Lagrange multiplier is introduced according to a structure risk minimization principle, the regression model is converted into an optimization model related to a kernel function under the condition of the optimization theory Kuhn-Tucker conditions (KKT), and finally the prediction comprehensive evaluation value with the minimum error with the real comprehensive evaluation value under the optimal parameter is continuously learned through a data set so as to find out the extracted optimal process factor. The research is based on Matlab language environment, and sets four extraction process data as xiRespectively, the ultrasonic time (x)1) Liquid to feed ratio (x)2) Ultrasonic temperature (x)3) Ethanol concentration (x)4) And a comprehensive evaluation value Y, wherein Y is a comprehensive evaluation value calculated by linear weighting of extraction rates of Sal _ B and Tan _ IIA in the salvia miltiorrhiza through a standard deviation method.
2.4.2 model parameter optimization
For the LS-SVM model, values of a kernel parameter g and a penalty factor C are closely related to a data sample set, and meanwhile learning and generalization capabilities of the model are influenced. The larger the penalty factor C value is, the smaller the allowable error is, but the overlarge C value can cause overfitting, so that the generalization capability is reduced; the generalization capability of the LS-SVM model can be enhanced as the C value is smaller, and the allowable error becomes larger. If the input range of the experimental data sample is large, the value of the kernel parameter g needs to be increased, otherwise, the value of the kernel parameter g needs to be decreased.
For the small data volume of the experiment, the Radial Basis Function (RBF) has high performance and application range, so when the RBF kernel Function is selected, a proper kernel parameter g and a penalty factor C are required to be simultaneously selected to optimize the LS-SVM model. In the study, 30 groups of experimental result data of the BBD analysis scheme are preprocessed, and an experimental data matrix with 30 rows and 5 columns is divided into an input variable matrix with 30 rows and 4 columns and an output variable matrix with 30 rows and 1 column, which are led into a platform of Matlab 2015b software, wherein input variables are replaced by specific factor level values, and specific values are shown in Table 1. In order to avoid too large difference between input variable dimensions and output variable dimensions, the research simultaneously carries out normalization processing on experimental data, namely, after dividing each extracted index factor level value by the mean value of the extracted index factor level values, programming by using Matlab 2015b software, modeling by using LS-SVM, wherein a kernel function adopts an RBF (radial basis function), finally, carrying out cross verification on a kernel parameter g and a penalty factor C simultaneously by a cross verification method, detecting each pair of parameter effects one by one in a parameter matrix consisting of g and C, and traversing to obtain an optimal kernel parameter g which is 256 and an optimal penalty factor C which is 4.92, wherein the traversing process is shown as the following figure 2.
2.4.3 prediction results and analysis
The optimal parameter result chart of fig. 2 is analyzed and combined with the program result to obtain the optimal kernel parameter g-256 and the penalty factor C-4.92. The comprehensive evaluation prediction values of 30 BBD analysis schemes obtained by returning to the LS-SVM model after obtaining the appropriate nuclear parameter g and penalty factor C are shown in the following table 3.
Table 3 comprehensive evaluation prediction value of LS-SVM model
In the present study, the predicted comprehensive evaluation value is compared with the real comprehensive evaluation value of the experiment, the correlation coefficient R between the predicted value and the experimental value is 0.94, the maximum error is 20.58%, the minimum error is 0.07%, and the error result is shown in fig. 3.
And then using Mean-square Error (MSE) to evaluate the performance of the LS-SVM model, wherein a specific formula is as follows:
wherein m is 30 data sets; y isiFor LS-SVM prediction, YiActual values obtained by experiments.
Finally, in the study, 30 groups of original experimental values and predicted values are substituted into a formula to calculate MSE, and a comparison graph of the real comprehensive evaluation value and the predicted comprehensive evaluation value of the experiment shown in FIG. 4 is drawn.
Fig. 4 shows that the comprehensive evaluation values of 30 sets of actual data and predicted data are very close, which indicates that the trained data is fitted to the actual test data, and then the MSE is calculated to be 0.51, which indicates that the model training and prediction effects are good.
2.4.4 conditional optimization and outcome prediction for the model
Based on BBD experimental design, combining actual reachable conditions of experiments, 68 groups of data sets to be predicted are added in a gradient mode through Matlab 2015b software according to 4 factors (the gradient of three factors including ultrasonic time, ultrasonic temperature and ethanol concentration is 1, and the gradient of liquid-material ratio is 0.5), and then an LS-SVM model is used for predicting optimal combination. The optimal process conditions for the final extraction are as follows: the temperature is 85 ℃, the ultrasonic time is 52min, the liquid-material ratio is 12:1, the ethanol concentration is 90%, and the predictive comprehensive evaluation value under the optimal condition is 15.32.
2.5 validation test
And weighing 4 parts of salvia miltiorrhiza medicinal material according to the optimal extraction process conditions, wherein each part is 20g, and carrying out ultrasonic extraction. The extraction rates of Sal _ B and Tan _ IIA were measured and the overall evaluation value was calculated, and the results are shown in Table 4. As can be seen from table 4, the average comprehensive evaluation value of the ultrasonic experimental method is 15.34, the predicted value is 15.32, and the relative error between the actual experimental value and the predicted model value is 0.13%. The verification tests show that the error is within the allowable range of the tests, so that the LS-SVM model has certain value in optimizing the salvia miltiorrhiza extraction process, namely the best extraction process condition in the research is the result given by the LS-SVM model: the temperature is 85 ℃, the ultrasonic time is 52min, the liquid-material ratio is 12:1, and the ethanol concentration is 90%.
Table 4 validation test under optimum process
3. Analysis and discussion
According to the report of the existing documents and the 2015 edition of Chinese pharmacopoeia, the active ingredients in the salvia miltiorrhiza medicinal material comprise Sal _ B and Tan _ IIA, so the two ingredients are considered, reference is provided for quality control and quality evaluation of the active ingredients in the salvia miltiorrhiza, and reference is also provided for quantitative determination of traditional Chinese medicines.
In the extraction process of the traditional Chinese medicine, the extraction solvent has a great influence on the extraction rate. The commonly used extraction solvent includes inorganic solvent water and organic solvent ethanol, methanol, etc. As the Sal _ B and Tan _ IIA effective components in the salvia miltiorrhiza belong to water-soluble and fat-soluble components respectively, ethanol with different concentrations is selected as an extraction solvent in the experiment.
With the rapid development of computers in the 21 st century, researchers are continuously searching for new traditional Chinese medicine optimized extraction process models. The LS-SVM model is used for predicting the relation between multi-factors and interaction and evaluation indexes of the multi-factors, is successfully applied to the optimization process of multiple fields, and particularly aims at small sample data, a non-linear model is established through analyzing a batch of input data and output data which are provided by experiments and correspond to each other, so that the quantitative relation between the data is revealed. Meanwhile, the LS-SVM model does not need any assumption on experimental data, and the generated result can be judged by a cross-validation method, so that the LS-SVM model is a data mining method or an algorithm model.
The experiment utilizes BBD experimental design and LS-SVM model to optimize the extraction process of Sal _ B and Tan _ IIA in Salvia miltiorrhiza, and the optimal extraction conditions obtained after adjustment according to actual conditions are as follows: the temperature is 85 ℃, the ultrasonic time is 52min, the liquid-material ratio is 12:1, the ethanol concentration is 90%, the comprehensive predictive evaluation value is 15.32, the average verified true value under the condition is 15.34, the relative error is 0.13%, and the error is small, so that the model can reflect the extraction conditions of Sal _ B and Tan _ IIA to a certain extent.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911107896.2A CN110988153B (en) | 2019-11-13 | 2019-11-13 | Optimization method of ultrasonic extraction process of effective components of Salvia miltiorrhiza based on LS-SVM model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911107896.2A CN110988153B (en) | 2019-11-13 | 2019-11-13 | Optimization method of ultrasonic extraction process of effective components of Salvia miltiorrhiza based on LS-SVM model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110988153A true CN110988153A (en) | 2020-04-10 |
| CN110988153B CN110988153B (en) | 2022-09-16 |
Family
ID=70084164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911107896.2A Active CN110988153B (en) | 2019-11-13 | 2019-11-13 | Optimization method of ultrasonic extraction process of effective components of Salvia miltiorrhiza based on LS-SVM model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110988153B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022033019A1 (en) * | 2020-08-08 | 2022-02-17 | 无锡济煜山禾药业股份有限公司 | Extraction and determination method for volatile ether extract |
| CN115810426A (en) * | 2022-12-21 | 2023-03-17 | 河南科技大学第一附属医院 | Tool and system for prognosis of esophageal squamous cell carcinoma and application |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102313714A (en) * | 2011-09-21 | 2012-01-11 | 浙江大学 | Determination method of carthamus tinctorius extract |
| CN104915638A (en) * | 2015-05-08 | 2015-09-16 | 国家电网公司 | Least squares support vector machine electric shock current detection method based on parameter optimization |
-
2019
- 2019-11-13 CN CN201911107896.2A patent/CN110988153B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102313714A (en) * | 2011-09-21 | 2012-01-11 | 浙江大学 | Determination method of carthamus tinctorius extract |
| CN104915638A (en) * | 2015-05-08 | 2015-09-16 | 国家电网公司 | Least squares support vector machine electric shock current detection method based on parameter optimization |
Non-Patent Citations (8)
| Title |
|---|
| JIN, YE等: "Near infrared spectroscopy in combination with chemometrics as a process analytical technology (PAT) tool for on-line quantitative monitoring of alcohol precipitation", 《JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS》 * |
| 余小高等: "《基于大数据的高风险学生预测研究》", 31 May 2019, 厦门大学出版社 * |
| 杨洋: "超声波中药提取过程中提取率的检测", 《中国优秀博硕士学位论文全文数据库(硕士)医药卫生科技辑》 * |
| 王晖等: "多指标综合评价方法及权重系数的选择", 《广东药学院学报》 * |
| 苏婷等: "声光可调-近红外光谱法快速测定丹参药材中隐丹参酮的含量", 《中国药房》 * |
| 许麦成等: "基于最小二乘支持向量机的秦皮提取工艺的研究", 《中国药师》 * |
| 赵孟浩等: "响应面法优化丹酚酸B提取工艺", 《食品工业》 * |
| 赵辉等: "多指标综合评价优选丹参提取工艺", 《中国医药导报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022033019A1 (en) * | 2020-08-08 | 2022-02-17 | 无锡济煜山禾药业股份有限公司 | Extraction and determination method for volatile ether extract |
| CN115810426A (en) * | 2022-12-21 | 2023-03-17 | 河南科技大学第一附属医院 | Tool and system for prognosis of esophageal squamous cell carcinoma and application |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110988153B (en) | 2022-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103913433B (en) | Online detection method for double-effect concentration process of danhong injection | |
| CN110376312B (en) | Method for detecting quality grade of traditional Chinese medicine | |
| CN110988153A (en) | Optimization method of ultrasonic extraction process for effective components of Salvia miltiorrhiza based on LS-SVM model | |
| CN102621092A (en) | Method for detecting Danhong injection ethanol precipitation process on line | |
| CN108241033B (en) | Method for rapidly detecting content of 6 quality index substances in radix ophiopogonis alcohol extract and application | |
| CN106749495A (en) | R language combinations orthogonal experiment optimizes the process for extracting of tanshinone IIA | |
| CN107024446A (en) | A kind of Liuwei Dihuang Wan small honey pill crude drug powder multiple index quick detecting method | |
| CN108663337B (en) | Method for measuring tanshinone component and application thereof | |
| CN105842353A (en) | Establishing method of fingerprint spectrum of honeysuckle-fructus forsythiae heat-clearing tablets and fingerprint spectrum | |
| Zhang et al. | Assessment of quality consistency in traditional Chinese medicine using multi‐wavelength fusion profiling by integrated quantitative fingerprint method: Niuhuang Jiedu pill as an example | |
| CN102507829B (en) | Method for establishing tobacco HPLC (High Performance Liquid Chromatography) fingerprint database and application thereof | |
| CN111175429B (en) | Method for establishing fingerprint spectrum of bactericidal and antipruritic lotion | |
| CN107655841B (en) | Method for rapidly determining contents of various components in curcuma aromatica-gardenia water vapor distillation extraction process based on ultraviolet spectrum | |
| CN104390926A (en) | Online rapid detection method of herba andrographis concentrated decolorization process | |
| Yan et al. | Enhancing the selectivity of liquid chromatography–mass spectrometry by using trilinear decomposition on LC‐MS data: An application to three‐way calibration of coeluting analytes in human plasma | |
| CN117347532B (en) | HPLC characteristic spectrum detection method for Guizhi sugar-cellulitis granule preparation | |
| CN109223881A (en) | A method of optimization Taohe Chengqi decoction decoction preparation process | |
| CN108760928A (en) | A kind of construction method of temperature stomach relaxation grain finger-print | |
| CN112915579A (en) | Effective safflower component ultrasonic extraction process based on LS-SVM model | |
| CN107917894A (en) | A kind of method of tocolysis ball near infrared detection mass content | |
| Lei et al. | A novel device based on a fluorescent cross-responsive sensor array for detecting lung cancer related volatile organic compounds | |
| CN108714170A (en) | A kind of extracting method of the Danzhi Xiaoyao San optimized using response phase method combination genetic algorithm and Direct search algorithm | |
| CN109528829B (en) | A microwave processing technology of honey cinnamon stick optimized by response surface methodology | |
| CN115308317B (en) | High performance liquid chromatography detection method for index components in diabetes wound healing extract | |
| CN113933438B (en) | Content determination method and preparation method of astragalus membranaceus cough-relieving oral liquid |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Jin Weifeng Inventor after: Yu Li Inventor after: Zhang Yangyang Inventor after: Wan Haoyu Inventor before: Wan Haoyu Inventor before: Yu Li Inventor before: Zhang Yangyang Inventor before: Jin Weifeng |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |