Method for screening DES by using ANN and COSMO-RS and extracting camellia oleifera leaf polysaccharide based on DES combined with two-enzyme method

Abstract

The invention provides a method, equipment, a medium and a program product for screening DES by using ANN and COSMO-RS and extracting camellia oleifera leaf polysaccharide based on the DES in combination with a two-enzyme method, and relates to the technical field of biological extraction. According to the method, on the basis of the decomposition model of the P-CL and the chemical potential information of the DESs, the relative solubility of the P-CL in the DESs is predicted by using the COSMO-RS, the pH of the DESs is predicted by using the ANN, and the most promising DES combination is screened out. A composite extraction system of double enzymes and DES extraction is provided for the first time, and the composite system is optimized by using bioinformatics methods such as COSMO-RS and ANN. The invention provides a treatment method aiming at a complex extraction environment, and the method has a wide application prospect in extraction of natural products.

Description

Technical Field

[0001] The present invention relates to the field of biological extraction technology, and more specifically, to a method, device, medium and program product for screening DES by using ANN and COSMO-RS and extracting oil tea polysaccharide based on the DES in combination with a double enzyme method. Background Art

[0002] Camellia oleifera polysaccharides (P-CL) are important bioactive compounds with antioxidant, antitumor and hypolipidemic effects. P-CL can reduce ROS levels and further improve the survival rate of Caenorhabditis elegans under abiotic stress. Therefore, a technology for efficiently extracting active substances from by-products will be beneficial to the development of the camellia oleifera industry. In the past two decades, the latest progress has been that the traditional hot water extraction method is usually combined with multiple techniques, including enzyme extraction, ultrasonic extraction and microwave extraction, to separate natural polysaccharides. The yield of Armillaria mellea polysaccharides extracted by enzyme-assisted ultrasonic extraction is 1.64 times and 1.21 times that of enzyme-assisted extraction and ultrasonic extraction, respectively.

[0003] In recent years, deep eutectic solvents (DES) have become the preferred alternative to organic solvents in the extraction of natural products due to their economic and recyclable characteristics. DES is synthesized from hydrogen bond donors (HBD) and hydrogen bond acceptors (HBA) at a specific temperature. The physical properties of DES are affected by the type, molar ratio and content of the components HBA and HBD. The most important characteristic is that its melting point is lower than the melting point of each component, making DES mostly liquid at room temperature. Camellia oleifera polysaccharides are mainly present in the cell wall. Traditional hot water extraction is difficult to effectively destroy the cell wall, which limits the extraction efficiency of hot water extraction. Enzymes such as cellulase help to destroy the cell wall and increase the yield of polysaccharides. Lentinan was extracted using cellulase, papain and pectinase with a yield of 15.65%. However, DES and enzyme-assisted extraction methods are rarely used in combination to extract plant polysaccharides because DES contains salt components, which inactivates cellulase and protease during the extraction process. Currently, there is a lack of research methods that simultaneously deal with the relationship between DES and enzymes and the effect of DES on polysaccharide extraction rate. In this study, artificial neural networks (ANN) and conductor like screening model for realistic solvents (COSMO-RS) were used to screen the pH value and solubility of DES to create a suitable liquid environment for cellulase and protease. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a method, device, medium and program product for screening DES using ANN and COSMO-RS and extracting oil tea polysaccharides based on the DES combined with a dual enzyme method; the method of the present invention establishes a low eutectic solvent dual enzyme system (DES-dEAE) to achieve dual enzymatic hydrolysis reaction and DES extraction at the same time.

[0005] In a first aspect, the present application discloses a method for screening DES using ANN and COSMO-RS, the method comprising: 101, constructing a database consisting of sugar, HBA, HBD and DES molecules; 102, analyzing the DES molecule by COSMO-RS software to obtain molecular descriptors of the corresponding DES molecule and molecular descriptors of sugar (referred to as Sσ-profiles); 103, inputting the molecular descriptor of the DES molecule into the ANN model to obtain the pH prediction value of the corresponding DES molecule; determining the optimal pH range of the enzyme type used for extracting plant polysaccharides; comparing the pH prediction value with the optimal pH range of the dual enzyme crossover, and selecting the DES molecule whose pH prediction value is within the optimal pH range as the first candidate DES; 104, predicting the activity coefficient of the sugar in the DES using COSMO-RS software according to the molecular descriptor of the sugar, and screening the DES with a low activity coefficient as the second candidate DES; 105 , taking the intersection of the first candidate DES and the second candidate DES as the most suitable DES; if there is no intersection, taking the DES closest to the first candidate DES and the second candidate DES as the most suitable DES.

[0006] In some embodiments, the optimal DES is at least 1; Optionally, when the plant polysaccharide is tea leaf polysaccharide, the optimal DES is composed of choline chloride (ChCl) and sorbitol (Sor); Optionally, the DES molecule is created by a molecular pair of corresponding HBA and HBD molecules in a 1:1 molar ratio.

[0007] In some embodiments, the method for obtaining molecular descriptors in 102 includes: COSMO-RS software extracts the σ-profile and σ-surface of HBAs and HBDs within the range of ±0.025e / Å as "prf" data, and converts the σ-profile data into molecular descriptors by calculating the integral of the area under the σ-profile curve, which is recorded as Sσ-profiles.

[0008] In some embodiments, the method for constructing the ANN model in 103 includes: obtaining a training data set; the training data range is temperature, water content, molar ratio, and all measured pressures are 1.01 bar; the σ-profiles of HBA and HBD will be divided into 8 regions and the areas of the corresponding regions will be integrated; the training data set is input into the nonlinear model constructed by ANN, and the pH prediction value is output; Optionally, the nonlinear model includes 9 input layers (8 discrete Sσ-profiles and temperature), 3 hidden layers and an output layer.

[0009] In some embodiments, between 101 and 102, the method further includes: solving the DES molecules in the water environment at the first temperature (0°C) to obtain a solution result, and saving the solution result in a COSMO file format for subsequent calculations; and importing the COSMO file into COSMO-RS software for prediction.

[0010] The second aspect of the present application discloses a method for extracting tea leaf polysaccharides based on DES combined with a dual enzyme method, the method comprising: 201, drying and crushing the oil tea leaves to obtain oil tea leaf powder; 202, extracting the oil tea leaf powder using an enzyme-assisted extraction method comprising cellulase, protease and the optimal DES described in the first aspect of the present application to obtain an oil tea leaf polysaccharide extract; 203, collecting the precipitate after alcohol precipitation of the oil tea leaf polysaccharide extract, and freeze-drying to obtain oil tea leaf polysaccharide; Optionally, the optimal DES consists of choline chloride and sorbitol.

[0011] In some embodiments, the method further comprises: the DES is a DES containing a first percentage of water; optionally, the first percentage is 20%-40%, preferably 30%; Optionally, the liquid-to-solid ratio, enzyme-to-solid ratio, extraction time and water content of the enzyme-assisted DES extraction method are optimized using response surface methodology.

[0012] The third aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store a computer program; and the processor executes the computer program to implement the steps of the above method.

[0013] A fourth aspect of the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0014] A fifth aspect of the present application discloses a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0015] This application has the following beneficial effects: 1. This application innovatively discloses a method for screening DES using ANN and COSMO-RS. This method uses ANN and COSMO-RS to screen the most suitable DES by predicting the pH value and activity coefficient of DES according to the characteristics of the enzyme. When the plant polysaccharide is tea leaf polysaccharide, it is difficult to screen DES suitable for enzymes and polysaccharides in a complex extraction system. In this case, a computer-aided quantitative structure-property relationship (QSPR) model is used instead of experimental screening to link the molecular structure of the component with its macroscopic physicochemical properties. ANN predicts the pH value of DES based on the QSPR modeling results. COSMO-RS is used to predict the activity coefficients of tea leaf polysaccharides and DES. This study is the first to apply solvent property prediction to screen DES suitable for the dual enzyme system (dEAE); the most promising DES combination is screened out: sorbitol and choline chloride.

[0016] From the perspective of computational simulation, the characteristics of the two enzymes are combined, and the intersection of their optimal pH is used for prediction calculation, which provides a new idea for the prediction of complex extraction systems. That is, the enzyme characteristics are used to find the matching DES in a computational way, and the prediction of the solubility of DES and monosaccharides is combined to complete the screening of DES. The following problems that DES is difficult to coexist with enzymes due to its special physical and chemical properties are overcome: ① The polarity of the solvent is too strong or it interacts with the hydrogen bond network on the surface of the enzyme, which may destroy the natural conformation of the enzyme, denature the enzyme, and thus lose its activity; ② The enzyme is very sensitive to pH. Extreme pH conditions may make the structure of the enzyme unstable or even irreversibly denatured. In addition, high ionic strength will also shield the interaction between the charged groups on the surface of the enzyme, further destroying its conformation; ③ Low eutectic solvents usually have a high viscosity, which will limit the mass transfer rate between the substrate and the enzyme and reduce the efficiency of the enzyme-catalyzed reaction. The catalytic activity of the enzyme usually depends on the accessibility of the substrate molecules near its active site, and the increase in viscosity will reduce the possibility of the substrate molecules diffusing to the enzyme active site; ④ Enzymes usually have hydrophobic and hydrophilic regional distributions. The components in the low eutectic solvent may bind to the hydrophobic region of the enzyme, causing the natural conformation of the enzyme to be disturbed, and even the active center to be exposed or closed, thereby affecting the catalytic function of the enzyme and making it difficult for DES to coexist with the enzyme. Therefore, in the past, when using DES and enzymes, the materials were treated separately before and after. This work completed the extraction of camellia oleifera polysaccharides by the simultaneous action of DES and dual enzymes from an experimental perspective.

[0017] 2. This application innovatively extracts tea leaf polysaccharides based on the selected DES combined with a dual enzyme method or expands it to a natural polysaccharide method, completing the process of simultaneous extraction under the conditions of DES without destroying the enzyme, simplifying the current process of using DES and enzymes in the extraction process, which requires a two-step method to extract and has low extraction efficiency. The two-step extraction method requires first using an enzyme to destroy the cell wall and then using DES for extraction.

[0018] 3. Since complex polysaccharides are difficult to use for simulation modeling, this application decomposes polysaccharides into basic modules - monosaccharides for modeling simulation. This method greatly reduces the difficulty of modeling and the requirements for polysaccharide structure analysis.

[0019] 4. Both ANN and COSMO-RS in this application are based on QSPR calculations, and a new DES library is established (the library contains the structures, σ data and Si data of HBA, HBD, DES and sugars, all of which are newly synthesized and calculated).

[0020] In summary, this study used the DES-dEAE system to extract polysaccharides from Camellia oleifera, and optimized it by ANN and COSMO-RS. Based on the decomposition model of P-CL and the chemical potential information of DES, COSMO-RS was used to predict the relative solubility of P-CL in DES, and ANN was used to predict the pH of DES. The most promising DES combination was screened out: sorbitol and choline chloride. Then the ChCl-Sor and cellulase-protease extraction system was optimized to obtain a solid-liquid ratio of 33:1, an enzyme ratio of 3:1, an extraction time of 15 min, and a DES water content of 40%, and the optimized yield was 21.46 mg / g. In addition, the composition and activity of polysaccharides extracted by water, DES, and enzyme-assisted DES were compared horizontally, and it was found that the polysaccharides extracted by enzyme-assisted DES had different compositions and activities. This study proposed a composite extraction system of dual enzyme and DES extraction for the first time, and optimized the composite system using bioinformatics methods such as COSMO-RS and ANN. This study proposed a treatment method for complex extraction environments, which has broad application prospects in the extraction of natural products. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a schematic diagram of a method flow chart provided by the first aspect of an embodiment of the present invention; Figure 2is a schematic diagram of a method flow chart provided by the second aspect of an embodiment of the present invention; Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention; Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by an embodiment of the present invention; Figure 5 is a schematic diagram of a storage medium provided by an embodiment of the present invention; Figure 6 σ-profile and σ-potential diagrams of six sugars provided in the embodiments of the present invention, wherein: Figure 6 A is the σ-profile diagram, Figure 6 B is the σ-potential graph; Figure 7 is a σ-surface structure diagram of full sugar, HBA, HBD and DES provided in the embodiments of the present invention; Figure 8 is a prediction graph of the activity coefficient of DES and DES containing 30% water at 50°C provided in an embodiment of the present invention; wherein, Figure 8 A is the predicted activity coefficient of 36 DES, Figure 8 B is the predicted activity coefficient of DES containing 30% water; a, D-mannose; b, galacturonic acid; c, galactose; d, glucose; e, L-rhamnose; f, xylose; Fig. 9 is a discretized Sσ-contour descriptor represented by 8 segments provided in an embodiment of the present invention; wherein, Fig. 9 A is acid, Fig. 9 B is alcohol, Fig. 9 C stands for sugar, Fig. 9 D is acetamide, Fig. 9 E is water, ChCl and proline; Fig.10 Schematic diagram of experimental value and predicted value of pH value of ANN model provided by the embodiment of the present invention; Parity diagram during training; wherein, Fig.10 A is the training set, Fig.10 B is the external test set, Fig.10 C stands for totality; Fig.11 : is a schematic diagram of the pH value of predicted DESs provided by an embodiment of the present invention, wherein the red line represents the optimal pH; the black line represents the appropriate pH range; Fig.12 is an infrared spectrum of P-CL provided by an embodiment of the present invention; Fig.13is a SEM analysis of the apparent structure of P-CLs provided in an embodiment of the present invention, wherein: Fig.13 A and B are water-extracted tea oil polysaccharides (P-CL-W), Fig.13 C and D are polysaccharides extracted from tea oil by DES (P-CL-D). Fig.13 E and F are polysaccharides extracted from tea leaves using DES-dEAE (P-CL-E); Fig.14 is a monosaccharide composition diagram of P-CL provided in an embodiment of the present invention; Fig.15 is a graph showing the in vitro antioxidant activity results of different concentrations of P-CL provided in the embodiments of the present invention; wherein, Fig.15 A is the DPPH free radical scavenging ability, Fig.15 B is the ABTS free radical scavenging ability, Fig.15 C is the reducing power of iron ions. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0024] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] Figure 1 1 is a flow chart of a method for screening DES using ANN and COSMO-RS provided in the first aspect of an embodiment of the present invention. Specifically, the method comprises the following steps: 101: Construct a database consisting of sugar, HBA, HBD and DES molecules; In some embodiments, the DES molecule is created from corresponding HBA and HBD molecules in a 1:1 molar ratio.

[0027] In some embodiments, between 101 and 102, the method further includes: solving the DES molecules in the water environment at the first temperature (0°C) to obtain a solution result, and saving the solution result in a COSMO file format for subsequent calculations; and importing the COSMO file into the COSMO-RS software.

[0028] 102: Analyze the DES molecule by COSMO-RS software to obtain a molecular descriptor of the corresponding DES molecule and a molecular descriptor of the sugar (referred to as Sσ-profile); In some embodiments, the method further comprises: the structures of monosaccharides, HBA, and HBD are 3D structures; optimizing the 3D structures of monosaccharides, HBA, and HBD, and using COSMOThermX18 (Dassault Systèmes, Fance) to calculate the σ-profile and σ-surface of each DES molecule.

[0029] In some embodiments, the method for obtaining the molecular descriptor in 102 includes: COSMO-RS software extracts the σ-profile and σ-surface of HBAs and HBDs within the range of ±0.025e / Å as "prf" data, and converts the σ-profile data into molecular descriptors by calculating the integral of the area under the σ-profile curve, which is recorded as Sσprofiles.

[0030] 103: inputting the molecular descriptor of the DES molecule into the ANN model to obtain a pH prediction value of the corresponding DES molecule; determining the optimum pH range of the enzyme type used for extracting plant polysaccharides; comparing the pH prediction value with the optimum pH range, and selecting the DES molecule whose pH prediction value is within the optimum pH range as the first candidate DES; In some embodiments, when the plant polysaccharide is tea leaf polysaccharide, the types of enzymes are cellulase and protease, the optimal pH of protease is 2-5, the optimal pH of cellulase is 4.5-6, and the intersection of the optimal pH of protease and cellulase is the optimal pH; DES with a predicted pH value between 4.5-5 is taken as a candidate DES.

[0031] In some embodiments, the method for constructing the ANN model in 103 includes: obtaining a training data set; the training data range is temperature (358.15-293.15K), water content (0.18-26.7%), molar ratio (9:1-1:16), and the total measured pressure is 1.01 bar; the σ-profiles of HBA and HBD are processed using 8 segments and integrated in the entire area; the training data set is input into the nonlinear model constructed by ANN, and the pH prediction value is output. Optionally, the nonlinear model includes 9 input layers, 8 discrete Sσ-profiles and temperature, 3 hidden layers and an output layer. ANN is a neural network based on a feed-forward strategy. This is said because they continuously pass information through nodes until the information reaches the output node. This is also called the simplest type of neural network.

[0032] 104: predicting the activity coefficient of the sugar in the DESs using COSMO-RS software according to the molecular descriptor of the sugar, and screening the DES with a low activity coefficient as the second candidate DES; In some embodiments, COSMO-RS software is used to predict the activity coefficients of 6 common polyphenols in DESs in infinitely diluted DES at 50°C, and the test is performed under the condition of 30% (v / v) water content; for any compound, its relative solubility in the solvent is inversely proportional to its activity coefficient in the system, so the higher the activity coefficient of the polysaccharide in DES, the lower the solubility; the purpose is to find DES with higher solubility.

[0033] 105: Take the intersection of the first candidate DES and the second candidate DES as the optimal DES; if there is no intersection, take the DES closest to the first candidate DES and the second candidate DES as the optimal DES.

[0034] In some embodiments, the optimal DES is at least 1; Optionally, when the plant polysaccharide is tea leaf oleifera polysaccharide, the optimal DES is composed of choline chloride and sorbitol.

[0035] Figure 2 The present invention provides a method for extracting polysaccharides from tea leaves based on DES combined with a dual enzyme method. Specifically, the method comprises the following steps: 201, drying and crushing the oil tea leaves to obtain oil tea leaf powder; In some embodiments, between 201 and 202, the method further comprises: removing pigments, lipids, and saponins from the oil tea leaf powder by using petroleum ether and ethanol using a Soxhlet extraction method; and obtaining oil tea leaf polysaccharides (P-CL) by hot water extraction, DES extraction, and enzyme-assisted DES extraction; 202, extracting the oil tea leaf powder using an enzyme-assisted extraction method comprising cellulase, protease and the optimal DES described in the first aspect of the present application to obtain an oil tea leaf polysaccharide extract; 203, collecting the precipitate after alcohol precipitation of the oil tea leaf polysaccharide extract, and freeze-drying to obtain oil tea leaf polysaccharide; In some embodiments, the optimal DES consists of choline chloride and sorbitol.

[0036] In some embodiments, the method further comprises: the DES is a DES containing a first percentage of water; optionally, the first percentage is 20%-40%, preferably 30%, which can effectively improve the viscosity of the DES and reduce the amount of DES used; Optionally, the response surface methodology is used to optimize the liquid-to-solid ratio, enzyme-to-solid ratio, extraction time, and water content of the enzyme-assisted DES extraction method, with the liquid-to-solid ratio being 33:1; the enzyme-to-solid ratio being 3:1, the extraction time being 15 min, and the water content being 40%.

[0037] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention, such as Figure 3 As shown, the device may include: one or more processors, and one or more memories; wherein the memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, the method described above may be executed.

[0038] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, operations and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can be an X86 architecture or an ARM architecture.

[0039] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0040] For example, the method or device according to the embodiment of the present disclosure may also be implemented by Figure 4 The architecture of the computing device 3000 shown in FIG. Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as ROM 3030 or hard disk 3070, may store various data or files used for processing and / or communication of the method provided by the present disclosure and program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of a computing device are shown.

[0041] The embodiment of the present invention also provides a computer-readable storage medium, such as Figure 5 As shown, it is a schematic diagram of a storage medium provided by an embodiment of the present invention, and a computer readable instruction 4010 is stored on the computer storage medium 4020. When the computer readable instruction 4010 is executed by the processor, the method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0042] The embodiments of the present disclosure further provide a computer program product or system, including a computer program, which implements the steps of the above method when executed by a processor.

[0043] In some embodiments, this embodiment further discloses a system for screening DES using ANN and COSMO-RS, the system comprising: A database construction module, used for or configured to construct a database consisting of monosaccharides, HBAs, HBDs and DES molecules; A molecular descriptor acquisition module, used for or configured to analyze the DES molecule through COSMO-RS software to obtain molecular descriptors of the corresponding DES molecules and molecular descriptors of sugars (referred to as Sσ-profiles); A pH prediction value screening module is used or configured to input the molecular descriptor of the DES molecule into the ANN model to obtain the pH prediction value of the corresponding DES molecule; determine the optimal pH range of the enzyme type used to extract plant polysaccharides; compare the pH prediction value with the optimal pH range, and select the DES molecule whose pH prediction value is within the optimal pH range as the first candidate DES; An activity coefficient screening module, used for or configured to predict the activity coefficient of sugar in DESs using COSMO-RS software according to the molecular descriptor of the sugar, and screen DES with high activity coefficient as the second candidate DES; The optimal DES acquisition module is used or configured to take the intersection of the first candidate DES and the second candidate DES as the optimal DES; if there is no intersection, take the DES closest to the first candidate DES and the second candidate DES as the optimal DES.

[0044] In some embodiments, this embodiment further discloses a system for extracting tea leaf polysaccharides based on DES combined with a dual enzyme method, the system comprising: The oil tea leaf crushing processing module is used for or configured to dry and crush the oil tea leaves to obtain oil tea leaf powder; A tea leaf polysaccharide extract processing module, used for or configured to extract the tea leaf powder using an enzyme-assisted extraction method comprising cellulase, protease and the optimal DES described in the first aspect of the present application to obtain a tea leaf polysaccharide extract; The oil tea leaf polysaccharide processing module is used for or configured to collect the precipitate after alcohol precipitation of the oil tea leaf polysaccharide extract, and freeze-dry to obtain the oil tea leaf polysaccharide. Specific embodiments

[0046] 1. Materials and methods: 1.1. Materials and reagents: Tea leaves of oil tea were collected in Ya'an, Sichuan, China (102.75°, 30.06°) in August 2023. All samples were immediately freeze-dried and sealed at -20°C for future use. Cellulase, protease, 1-phenyl-3-methyl-5-pyrazolone (PMP), monosaccharide standard (T6-T2000), dextran series standard, TPTZ, DPPH, and ABTS were purchased from Sigma-Aldrich Co., Ltd. Choline chloride (ChCl, ≥98%), sorbitol (Sor, ≥98%), proline (Proline, ≥98%), formic acid (FA, ≥98%), propionic acid (PA, ≥98%), lactic acid (LA, ≥98%), acetic acid (AA, ≥98%), malonic acid (MA, ≥98%), 2-propylene glycol (PG, ≥98%), glycerol (Gly, ≥98%), xylitol (Xyl, ≥98%), ethylene glycol (EG, ≥98%), glucose (Glu, ≥98%), fructose (Fru, ≥98%), maltose (Mal, ≥98%), sucrose (Suc, ≥98%), urea (Ure, ≥98%), methylurea (Met, ≥98%), acetamide (Ace, ≥98%), and ethanolamine (Eth, ≥98%) were purchased from Aladdin Biochemical Technology Co., Ltd. (Shanghai, China).

[0047] 1.2. Synthesis of DES: Place HBA and HBD in a 65°C drying oven to fully remove moisture. Weigh the raw materials in a 1:1 molar ratio, mix them thoroughly in an 80°C water bath until a uniform and transparent solution is formed, and cool them naturally to room temperature for later use.

[0048] 1.3. Prediction method: 1.3.1. Preparation of molecules and molecular descriptors: A molecular database consisting of 6 sugars, 2 HBAs, 18 HBDs and 36 DESs was established. The 3D structures of sugars, HBAs and HBDs were downloaded from the PUBCHEM database in SDF format and constructed into 3D molecules in the software Materials studio2020. DES molecules were created by the corresponding HBA and HBD molecules in a 1:1 molar ratio molecular pair. The 3D structure was optimized at the density functional level using the DMol3 module, using GGA-BLYP as the generalized gradient approximation and DNP4.4 as the numerical basis set for determining the total energy of the system and solving the self-consistent field. The calculated SCF tolerance was set to 10 -6 The COSMO module is used to solve the molecules in a 0°C water environment and the results are used in the COSMO file format for subsequent calculations.

[0049] The generated COSMO files were imported into the COSMO-RS software COSMothermX18 (Dassault Systèmes, France). In the software, the σ-profile and σ-surface of HBA and HBD within ±0.025e / Å were automatically extracted as “prf” data. The σ-profile data were then converted into molecular descriptors, denoted as Sσ-profile, by calculating the integral of the area under the σ-profile curve. In a sense, the discretization of the σ-profile curve into 8 Sσ-profile descriptors has been determined. The Sσ-profile descriptors were calculated for each HBA and HBD, and the Sσ-profile of DES was calculated as follows:

[0050] Where S i is the descriptor in region i (e / Å2), x HBA 、x HBD and xH2O are the mole fractions of HBA, HBD and water, respectively. In this study, the σ-profile of the DES molecular pair is not directly generated as a molecular descriptor. The advantage of this is that it increases the flexibility of DES design, so that the molar ratio of HBA, HBD and water molecules can be changed at will. At the same time, this processing method greatly reduces the workload, making it possible to create a large number of molecular descriptors of the corresponding DES.

[0051] 1.3.2.COSMO-RS simulation: The geometry-optimized structures were imported into COSMOThermX18 (DassaultSystèmes, Fance) to calculate the σ-profile and σ-surface of each molecule. For any compound, its solubility in a solvent is inversely proportional to its activity coefficient in the system. Therefore, COSMO-RS was used to predict the activity coefficients of six common polyphenols in DES at infinite dilution at 50 °C and tested at a water content of 30% (v / v).

[0052] 1.3.3.ANN: A feed-forward ANN has been used to exploit robust nonlinear correlations between descriptors and pH of DES. The network consists of multiple processing elements represented as “neuron nodes”. Neurons are interconnected by direct communication activation functions, which contain the information required to generate the output. The hyperbolic tangent sigmoid activation function of each hidden neuron (Hk) can be calculated as follows:

[0053] The tanh activation function converts the Yk values ​​to between -1 and 1. Yk is a linear combination of the inputs associated with hidden neuron k and can be calculated as follows:

[0054] Where Wk,input represents the weight coefficient of the link between each input and hidden neuron k, and bk represents the intercept bias of hidden neuron k. The neural network was developed using the Neural Network Toolbox of JMP statistical software. Discretized Sσ-profile descriptors and temperature were selected as inputs to the network, while pH values ​​of DES were selected as outputs. The learning rate of the network was fixed to 0.1, the square penalty method was used, and the internal cross-validation retention ratio was 25%.

[0055] 1.4. Extraction of Camellia oleifera polysaccharides: The collected Camellia oleifera leaves were dried in an oven at 65°C and then crushed into powder. Soxhlet extraction was performed using petroleum ether and ethanol to remove pigments, lipids, saponins and other substances from Camellia oleifera powder. Camellia oleifera polysaccharides (P-CL) were then obtained by hot water extraction, DES extraction and enzyme-assisted DES extraction (cellulase and protease). The polysaccharide aqueous solution was mixed with Sevag reagent (n-butanol: chloroform = 1:4, v / v) in a ratio of 1:3 to remove denatured proteins in P-CL. These solutions were dialyzed (3500Da) for 3 d and further evaporated, concentrated and freeze-dried. The freeze-dried samples of water extraction, DES extraction and enzyme-assisted DES extraction were P-CL-W, P-CL-D and P-CL-E, respectively.

[0056] 1.5. Chemical composition determination: The total carbohydrates were determined by the phenol-sulfuric acid method. The protein content was determined by the Coomassie brilliant blue method. The uronic acid content was determined by the m-hydroxybiphenyl colorimetric method.

[0057] 1.6. Response surface optimization: 1.6.1. Single factor test: Liquid-to-solid ratio (A, 5:1-40:1 mL / g), DES moisture content (B, 25%-65% v / v), ultrasound time (C, 5-40 min) and PKFs yield were used as evaluation indicators to evaluate the cellulose-to-proteinase ratio (D, 4:1-1:3 mg / mg) by single factor test.

[0058] 1.6.2. Response surface optimization: According to Box-Behnken design (BBD), Design-Expert13 software was used to design and analyze the four-factor (AD) and three-level response surface method (RSM). The design results are shown in Table 1. According to the single factor test results with P-CL yield as the response, the appropriate AD value was selected.

[0059] Table 1 Response surface analysis factors and their levels

[0060] 1.7. Structural characterization: 1.7.1. Fourier transform infrared (FT-IR) analysis: Camellia oleifera polysaccharide was placed in an oven at 60 °C for 12 hours to fully remove moisture. 2 mg of polysaccharide was mixed with KBr, crushed, and pressed into 1.0 mm thick tablets. Fourier transform infrared spectrometer was used to analyze the polysaccharide at 400-4000 cm -1 Scan the sample within the range.

[0061] 1.7.2. Analysis of monosaccharide components: 5 mg of polysaccharide was dissolved in 3 mL of 3 mol / L trifluoroacetic acid (TFA). The ampoule containing the sample was sealed and placed in a 100°C water bath for 10 h. The hydrolyzate was dried using a vacuum rotary evaporator and washed with methanol three times to remove residual TFA. The cleaved polysaccharide fragments were then dissolved in 3 mL of ddH2O, followed by the addition of 0.5 mol / L PMP reagent and 0.3 mol / L NaOH at 70°C. After 40 min, the excess NaOH was neutralized with 0.3 mol / L HCl, and the aqueous layer was collected with the resulting solution of CH3Cl and filtered using a 0.22 μm filter. 10 mg of monosaccharide sample was dissolved in deionized water and diluted to a 1.0 mg / mL monosaccharide standard solution.

[0062] Chromatographic analysis was performed using a ThermoICS5000+ ion chromatography system (ICS5000+, Thermo Fisher Scientific, USA) with a ZorbaxSB-C18 (150 × 4.6 mm) liquid chromatography column and an injection volume of 20 µL. Mobile phases A (PBS) and B (acetonitrile, 85:15, v / v) were used at a column temperature of 30°C.

[0063] 1.7.3. Molecular weight determination: Weigh 50 mg of glucan standard and camellia oleifera polysaccharide respectively, dissolve in deionized water, dilute to scale with a 10 mL volumetric flask, and filter with a 0.22 μm filter membrane. The work was performed using a ThermoICS5000+ ion chromatography system (ICS5000+, Thermo Fisher Scientific, USA), a PLaquagel-OH column (7.5 × 300 μm) chromatographic column, a liquid chromatography column, and an injection volume of 20 μL. The mobile phase (NaCl) was used, and the column temperature was 30°C.

[0064] 1.7.4. Surface morphology test: The samples were observed using a scanning electron microscope (SEM; Gemini, Germany) under high vacuum conditions with an accelerating voltage of 5 kV. The magnifications of the 145 images were 180 times, 500 times, and 3000 times, respectively.

[0065] 1.8. In vitro antioxidant activity of Camellia oleifera polysaccharides: 1.8.1. DPPH free radical scavenging ability: P-CL was dissolved into solutions of different concentrations (0.1-2 mg / mL). Vitamin C (VC) was used as a positive control, and deionized water was used instead of polysaccharide solution as a blank control. The sugar solution was mixed evenly with 0.2 mmol / L DPPH ethanol solution at a ratio of 1:8, reacted at room temperature in the dark for 15 min, and the absorbance of the solution at 517 nm was measured. The calculation formula is as follows: DPPH free radical scavenging rate (%) = (A2-A1) / A2×100%; where A1 is the absorbance of the sample group and A2 is the absorbance of the blank control group.

[0066] 1.8.2.ABTS free radical scavenging ability: P-CL was dissolved into solutions of different concentrations (0.1-2 mg / mL). VC was used as the positive control, and deionized water was used instead of the polysaccharide solution as the blank control. The sugar solution was mixed with the pre-prepared ABTS working solution at a ratio of 1:40. After being uniform, the working solution was reacted at room temperature in the dark for 10 min, and the absorbance was measured at 734 nm. The calculation formula is as follows: ABTS free radical scavenging rate (%) = (A2-A1) / A2×100%; where A1 is the absorbance of the sample group and A2 is the absorbance of the blank control group.

[0067] 1.8.3. Total antioxidant capacity (FRAP): P-CL was dissolved into solutions of different concentrations (0.1-2 mg / mL). VC was used as a positive control, and deionized water was used instead of polysaccharide solution as a blank control. The sugar solution was mixed with the pre-prepared FRAP working solution at a ratio of 1:10. The working solution reacted evenly at room temperature in the dark. After 30 min, the absorbance at 593 nm was measured. Ferrous sulfate-anhydrous ethanol solution was used as the standard solution to prepare a standard curve, and the absorbance corresponding to 1 mmol / LFeSO4 was defined as the FRAP value.

[0068] 1.9. Statistical analysis: All experiments were performed in triplicate at least. SPSS (SPSS29, IBM, USA) was used to analyze the data with variance. One-way ANOVA and Tukey test were used to test the significance of differences (P < 0.05). Origin2024 was used for drawing. Data are shown as mean ± standard deviation based on three replicates.

[0069] 2 Results: 2.1. Extraction system prediction: 2.1.1 Model establishment: The construction of models and molecular descriptors of DES and Camellia oleifera polysaccharides is a prerequisite for prediction. The construction of the DES molecular model follows the minimum energy principle. HBA and HBD molecules are docked at a fixed molar ratio. In the DES system, different HBA and HBD ratios, such as 1:1, 1:2 and 1:3, can be used depending on the molecular size and the number of hydrogen bond donor and acceptor sites. However, in this study, all DES configurations were selected in a 1:1 ratio because this facilitates comparative analysis of the roles played by HBA and HBD in DES during COSMO-RS and ANN analysis. This strategy effectively produces all the required DES molecules and is more conducive to subsequent prediction calculations. COSMO-RS describes the distribution of molecular surface polarity and is presented in the form of σ-surface, σ-profile and σ-potential, respectively. The σ-surface is regarded as a mapping of the σ-profile in space, which is constructed by assigning each electric field intensity value in the σ-profile to the corresponding position in space. In addition, the σ-potential is the integral of the σ-profile, which shows the overall electric field intensity response. Sugar σ-profile and σ potential Figure 6 As shown. The σ-profile and σ-potential distribution are divided into three regions, namely the hydrogen bond body region (σ<-0.0082eÅ-2), the non-polar region (-0.0082eÅ-2<σ<0.0082eÅ-2) and the hydrogen bond acceptor region (σ>0.0082eÅ-2), which correspond to the blue, green and red blocks of the σ-surface, respectively, as shown Figure 7 As shown. Figure 6 As shown in A, all 6 sugars are polar, which means they have good solubility in water, so polar DES were selected.

[0070] 2.1.2 COSMO-RS relative solubility prediction results: The activity coefficients of 6 sugar models in 36 DES at 50°C were calculated. Figure 8 As shown in Figure 2. Since the activity coefficient is inversely proportional to the relative solubility, the higher the activity coefficient of the polysaccharide in DESs, the lower the solubility. Figure 8 As shown in Figure A, the relative solubility of the six monosaccharides in DES is similar, which corresponds to their similar σ curves. It is clearly found that the solubility of monosaccharides in ChCl-based DES is better than that in proline-based DES. In addition, amine- and amide-based DES perform better than other HBD-based DES, while sugar-based DES perform second only to them. Figure 8 In B, due to the presence of 30% water in the DESs system, the upper and lower limits of solubility are reduced accordingly, but the effect is minimal. Adding water to DES can effectively improve the viscosity of DES and reduce the amount of DES used. From a production perspective, this is very important and economical.

[0071] In general, since the prediction object is monosaccharide rather than the whole polysaccharide, there is still a deviation between the prediction result and the actual extraction effect. But it clearly confirms that ChCl-based DES is a better choice than proline-based DES. Similarly, amino- and amide-based DES and sugar-based DES are given priority in subsequent screening.

[0072] 2.1.3ANN: A dataset of 648 training data was collected from the literature. The training data ranged from temperature (358.15-293.15K), water content (0.18-26.7%), and molar ratio (9:1-1:16), and all measured at a pressure of 1.01 bar. In addition, the σ-profiles of HBA and HBD were processed using 8 segments and integrated over the entire region. The results are shown in Figure 2. Fig. 9 And as shown in Table 2.

[0073] Table 2 ANN test library;

[0074] A nonlinear model was constructed using ANN with 9 input layers, 8 discrete Sσ-profiles and temperature, and 3 hidden layers (containing 10 neurons) and pH as output. Fig.10 ) is the regression coefficient (R 2 ) is greater than 0.99, which has good prediction performance. The prepared data is introduced into the model to obtain the pH prediction value of DES in the experiment ( Fig.11 ). The optimum pH values ​​of the proteases and cellulases used in this experiment are 2-5 and 4.5-6, respectively. Therefore, the pH value of the DES used in this experiment should be between 4.5 and 5. The predicted value of ChCl-Sor is 4.58, which is similar to the existing actual measurement results. In addition, the pH values ​​of ChCl-Glg, ChCl-Xyl, ChCl-EG and ChCl-Ace are close to the optimum pH values, which is also similar to the description in the literature.

[0075] Overall, combined with the prediction results of COSMO-RS, DES32 is the most suitable DES for use in the dual-enzyme system.

[0076] 2.2. Comparison of chemical composition: The results showed that the extraction method had a certain effect on the chemical composition of crude polysaccharides from oil tea leaves, as shown in Table 3: The enzyme-assisted DES extraction method had a high extraction efficiency, and the carbohydrates extracted by this method reached 78.27%. In addition, this method significantly reduced the protein content in polysaccharides. The protein content was as low as 4.02%, and the ratio of protein to total sugar was only 1:19.47, which was much lower than the ratios of 1:3.35 and 1:3.21 observed by the first two methods. These results show that the enzyme-assisted DES extraction method is superior to the other two extraction methods in terms of polysaccharide extraction efficiency and quality.

[0077] Table 3 Chemical composition of P-CL, different letters in the table indicate significance, P < 0.05;

[0078] 2.3. Structural characterization and analysis of P-CL 2.3.1. Structural characterization of P-CL obtained by different extraction methods: Fig.12 As shown in the figure, tea leaf polysaccharide has typical polysaccharide infrared spectral characteristics. -1 There is an OH stretching vibration peak nearby; 2931 cm -1 The CH stretching vibration peak near 1620 cm -1 Asymmetric C=O stretching vibration peak near 1421 cm -1 There is a carboxyl OH vibration absorption peak nearby; the COH and COC glycosidic bond absorption peaks of the pyranose ring are at 1088 cm -1 and 1041 cm -1 The weak absorption peaks of β-glycosidic bond and pyranose ring are located at 600-800 cm -1 Area. 1620 cm -1 The absorption peaks near 1620.27 cm -1 The absorption peak at showed a smaller vibration amplitude, which indicated a lower protein content.

[0079] SEM results showed that the apparent structures of P-CLs were significantly different. Fig.13 As shown, P-CL-W is an irregular sheet with a hollow center. The holes of P-CL-D are denser, which may be due to the fact that DES destroys the spatial structure of polysaccharides and reduces aggregation behavior. The structure of P-CL-E is a smooth and complete sheet, which is similar to existing studies. The complex enzyme effectively destroys the cell wall of tea oil tea cells, releases plant polysaccharides in the cell wall, and makes its structure more solid.

[0080] 2.3.2. Molecular weight detection: According to the different retention times of dextran with different molecular weights on the chromatographic column, a linear relationship between the retention time and the logarithm of the molecular weight of dextran was established. The molecular weight distribution and composition ratio of the three P-CLs were further calculated using the fitted linear equation (Table 4). The results showed that the molecular weight distribution range of the three P-CLs was 6~106 kDa, and the distribution was uneven. Compared with P-CL-W, P-CL-D and P-CL-E both contained additional components with a molecular weight of 20~30 kDa, with contents of 11.2% and 20.46%, respectively, indicating that P-CL-W has higher purity. In addition, the maximum molecular weight of the components extracted by enzyme-assisted DES was smaller than that of the components extracted by the other two methods.

[0081] Table 4 Molecular weight and composition ratio of P-CL.

[0082]

[0083] 2.3.3. Monosaccharide composition analysis: as shown in Table 5 and Fig.14 As shown in the figure, the P-CL obtained by the three extraction methods are composed of mannose, galactose, glucuronic acid, glucose, xylose and rhamnose, but the relative content of each monosaccharide is different. P-CL-W has higher levels of xylose, galactose and glucose. P-CL-D has higher levels of xylose, galactose and rhamnose. In contrast, P-CL-E has higher contents of xylose, galactose and glucose. The relative content of xylose in P-CL-W and P-CL-D is high, both exceeding 40%. In contrast, P-CL-E has lower xylose content but higher glucose content, which are 24.17% and 15.60%, respectively. The difference in the relative content of monosaccharides in the three camellia oil polysaccharides may explain the observed differences in their biological activities.

[0084] Table 5 Monosaccharide composition and relative content of P-CL (%).

[0085]

[0086] 2.4. Optimization of extraction conditions: To further improve the extraction rate of polysaccharides, we analyzed the effects of liquid-to-solid ratio (A, 1:5-1:50, mL / g), enzyme ratio (B, 4:1–1:3, g), extraction time (C, 5-45, min), and water content (D, 25–65, %) on the extraction rate of polysaccharides. Based on the analysis results, a solid-to-liquid ratio of 1:20-1:40, an enzyme ratio of 2:1-4:1, an extraction time of 10-20 min, and a water content of 25-45% were selected for RSM optimization. Twenty-nine four-factor three-level experimental BBDs were performed to illustrate the interaction of the four independent variables and determine the optimal extraction conditions. Second-order polynomial regression and statistical analysis of variance were performed using Design Expert 8.06 software. The causal relationship between the response variable and the four independent variables is described as follows: Y=21.20+1.25A+0.25B+2.333C+2.10D-1.55AB-1.76AC+0.24AD+0.81BC-1.36BD+0.42CD-2.53A 2 -2.63B 2 -1.25C 2 -2.47D 2 ; The variance, goodness of fit, and adequacy analysis of the model were summarized. The F value was 32.03, confirming the high significance of the model. The adjusted value of the correlation coefficient (R2) (R 2 adj) and coefficient of variation (CV%) show the goodness of fit. 2 is 0.9697, indicating that the model can explain 96.97% of the total variation, R 2 adj is 0.9395, indicating that the model can predict most of the variation in extraction rate. Three-dimensional (3D) response surface plots and two-dimensional (2D) response contour plots are useful tools to visually represent the interaction between two independent variables. Specifically, the 3D response surface plot can effectively illustrate the relationship between the independent and response variables, while the 2D response contour plot can further provide insight into the mutual relationship between the independent variables and assess the significance of their interaction. It is worth noting that the circular response contour plot indicates that the corresponding variables have an insignificant interaction, while the elliptical response contour plot indicates that the corresponding variables have a significant interaction. 2.5. In vitro antioxidant activity: Natural polysaccharides derived from plants are considered promising candidates for antioxidant applications. Although their free radical scavenging ability is generally lower than that of small molecule antioxidants such as polyphenols, carotenoids, and vitamins, these biomacromolecules effectively stabilize free radicals by donating hydrogen atoms or transferring electrons, thus exhibiting significant in vitro antioxidant activity. + , FRAP was used to evaluate the in vitro antioxidant effect of P-CL. 2.5.1.DPPH scavenging ability of P-CL: Fig.15 As shown in A, the polysaccharides extracted from tea leaves by the three methods all have DPPH radical scavenging activity. When the polysaccharide concentration reaches 0.1 mg / mL, its scavenging activity gradually stabilizes. At present, the scavenging rates of P-CL-E are 37.5%, respectively, indicating that there is no significant difference in their DPPH radical scavenging ability. The existing study found that the DPPH radical scavenging ability of P-CL-W at 2 mg / mL was 35%, which is similar to the results.

[0087] 2.5.2. ABTS of P-CL + The clearing ability: Fig.15 As shown in Figure B, P-CL has good ABTS·+ scavenging activity and is positively correlated with the polysaccharide concentration. At a concentration of 2.0 mg / mL, the scavenging rates of tea polysaccharides on ABTS·+ free radicals reached 82.5% (water extraction), 51.3% (DES extraction) and 73.2% (enzyme-assisted DES extraction), respectively. Their IC50 values ​​were 0.829, 2.045 and 1.038 mg / mL, respectively. The results showed that. In terms of ABTS·+ scavenging ability, P-CL-W had the best effect, followed by P-CL-D and finally P-CL-E. This result may be due to the lowest purity of P-CL-W. Small molecular active substances with strong antioxidant activity were mixed into the sample, which increased the scavenging ability of ABTS·+. 2.5.3. Total antioxidant capacity: Compare the iron ion reducing capacity of P-CL, and then convert the total antioxidant capacity of P-CL into FRAP value for comparison. Fig.15 As shown in Figure C, P-CL extracted by the three methods all have a certain total antioxidant capacity, which increases with the increase of polysaccharide concentration. The total antioxidant capacity of P-CL-W and P-CL-D is relatively close. And at the same concentration, its effect is better than that of P-CL-E. This trend is closely related to enzyme-assisted extraction. Fig.15 C shows that the iron chelating activity of P-CL-E is unstable and increases proportionally with the concentration, which indicates that the enzymatically hydrolyzed Camellia oleifera cell wall is unstable. There is great potential to identify a more stable enzymatic hydrolysis system. In general, P-CL has the potential to be a natural antioxidant. It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units. The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. It should be understood by those skilled in the art that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A method for screening DES using ANN and COSMO-RS, characterized in that: The method comprises: 101, constructing a database consisting of sugar, HBA, HBD and DES molecules; 102, analyzing the DES molecules by COSMO-RS software to obtain molecular descriptors of corresponding DES molecules and sugars; 103, inputting the molecular descriptor of the DES molecule into the ANN model to obtain the pH prediction value of the corresponding DES molecule; determining the optimal pH range of the enzyme type used for extracting plant polysaccharides; comparing the pH prediction value with the optimal pH range, and selecting the DES molecule whose pH prediction value is within the optimal pH range as the first candidate DES; 104, predicting the activity coefficient of the sugar in the DESs using COSMO-RS software according to the molecular descriptor of the sugar, and selecting a DES with a high activity coefficient as a second candidate DES; 105 , taking the intersection of the first candidate DES and the second candidate DES as the most suitable DES; if there is no intersection, taking the DES closest to the first candidate DES and the second candidate DES as the most suitable DES.

2. The method for screening DES using ANN and COSMO-RS according to claim 1, characterized in that: The optimal DES is at least one; Optionally, when the plant polysaccharide is tea leaf oleifera polysaccharide, the optimal DES is composed of choline chloride and sorbitol; Optionally, the DES molecule is created by a molecular pair of corresponding HBA and HBD molecules in a 1:1 molar ratio.

3. The method for screening DES using ANN and COSMO-RS according to claim 1, characterized in that: The method for obtaining the molecular descriptor in 102 includes: extracting the σ-profile and σ-surface of HBAs and HBDs within the range of ±0.025e / Å as "prf" data using COSMO-RS software, and converting the σ-profile data into a molecular descriptor by calculating the integral of the area under the σ-profile curve, which is recorded as Sσ-profile.

4. The method for screening DES using ANN and COSMO-RS according to claim 1, characterized in that: The method for constructing the ANN model in 103 includes: obtaining a training data set; the training data range is temperature, water content, molar ratio, and all measured pressures are 1.01 bar; the σ-profiles of HBA and HBD are divided into 8 regions and the areas of the corresponding regions are integrated; the training data set is input into the nonlinear model constructed by the ANN, and the pH prediction value is output; Optionally, the nonlinear model includes 9 input layers, 3 hidden layers and an output layer.

5. The method for screening DES using ANN and COSMO-RS according to claim 1, characterized in that: Between 101 and 102, the method further includes: solving the DES molecules in the water environment at a first temperature to obtain a solution result, saving the solution result in a COSMO file format, and importing the COSMO file into the COSMO-RS software for prediction; optionally, the first temperature is 0°C.

6. A method for extracting tea leaf polysaccharides based on DES combined with a dual enzyme method, characterized in that: The method comprises: 201, drying and crushing the oil tea leaves to obtain oil tea leaf powder; 202, extracting the oil tea leaf powder using an enzyme-assisted extraction method comprising cellulase, protease and the optimal DES according to any one of claims 1 to 5 to obtain an oil tea leaf polysaccharide extract; 203, collecting the precipitate after alcohol precipitation of the oil tea leaf polysaccharide extract, and freeze-drying to obtain oil tea leaf polysaccharide; Optionally, the optimal DES consists of choline chloride and sorbitol.

7. The method for extracting tea leaf polysaccharides based on DES combined with double enzyme method according to claim 6, characterized in that: The method further includes: the DES being a DES comprising a first percentage of water; Optionally, the first percentage is 20%-40%, preferably 30%; Optionally, the liquid-to-solid ratio, enzyme-to-solid ratio, extraction time and water content of the enzyme-assisted DES extraction method are optimized using response surface methodology.

8. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images