Calculation Method for Molecular Weight of Biomacromolecule Materials Based on AI Algorithm

Abstract

The present invention relates to a method for calculating the molecular weight of biomacromolecule materials based on AI algorithms. After some biopolymer materials are dissolved into aqueous solutions, it is difficult to form single molecular chains. The present invention selects an ionic liquid as the dissolution system. After the macromolecule materials are dissolved, they can well form single molecular chains, and then rheological methods are used to test the rheological data of the biomacromolecules dissolved in the ionic liquid. The present invention selects the Rouse model as the polymer solution model. By measuring a large amount of data, the model is trained with AI algorithms and non-linear fitting is carried out to obtain the key parameter values, so as to calculate the molecular weight value of the measured materials. This calculation method has the characteristics of accuracy and rapidity, and can be well promoted to the computer research field of polymer materials.

Description

Technical Field

[0001] The present invention relates to a method for measuring the molecular weight of biomacromolecular materials, and particularly to calculating the molecular weight of materials that are difficult to measure based on a rheological model and solving the molecular weight of biomaterials by AI non-linear fitting. Background Art

[0002] With the continuous development of biomolecular science, biomacromolecular materials have received more extensive attention. For example, silk fibroin, hyaluronic acid, collagen, recombinant collagen, sericin, etc. have been used as important medical and cosmetic raw materials. The biological properties of many biomacromolecular materials are closely related to their relative molecular weight. Biomacromolecular materials with different relative molecular weights have different physiological activities, and some even have completely opposite effects. For example, hyaluronic acid with a molecular weight greater than 2000 kDa has good moisturizing, viscoelasticity, lubrication, anti-inflammatory and other functions, and can be used in ophthalmic surgery and joint injection preparations; hyaluronic acid with a molecular weight of 10 kDa - 80 kDa can be taken orally directly and absorbed by the intestine to play the role of beauty and skin care. Another example is that the swelling property and light transmittance of silk fibroin hydrogel decrease with the increase of the molecular weight of silk fibroin. Therefore, if the molecular weight of the polymer material can be accurately obtained, the performance of the material can be utilized more fully.

[0003] Traditional methods for measuring the molecular weight of proteins include: gel electrophoresis (SDS-PAGE), light scattering (SLS), small-angle neutron diffraction (SANS), gel permeation chromatography (GPC), etc. However, traditional measurement methods often have some limitations in use, that is, they cannot accurately measure some polymer materials with aggregation behavior in solution. For example, the unique structure of silk fibroin molecules (a multi-block copolymer structure with alternating hydrophilic and hydrophobic segments) will cause regenerated silk fibroin to easily aggregate into aggregates such as micelles in solution, rather than existing in the form of "free" single molecular chains. Therefore, it is necessary to first find a good solvent in which silk fibroin can exist in the form of "free" single chains. Then find a suitable test method that can quantitatively describe the chain state and viscoelastic behavior of polymer chains in solution.

[0004] In addition, a suitable polymer solution model needs to be found. In order to study the structure and kinetic characteristics of polymer solutions, several coarse-grained geometric models have been established by researchers, such as the bead-stick model, bead-spring model, pearl-necklace model, and reptation model, etc. Which model is more suitable for calculating the molecular weight of silk fibroin needs further exploration.

[0005] The molecular weight calculations based on the above models are all relatively complex, requiring a large amount of data testing and introducing a large amount of calculations. Then, if it is manual calculation, the efficiency is relatively low and the accuracy is not high. If the AI algorithm is introduced into the traditional calculation method of polymer molecular weight, it can solve the timeliness and accuracy of the calculation, greatly improve the work efficiency of R & D personnel, and further explore the innovation in the field of biological polymer calculation. Summary of the Invention

[0006] The problem to be solved by the present invention is to invent a calculation method for the molecular weight of biological macromolecular materials based on the AI algorithm in view of the problems existing in the measurement of the molecular weight of existing biological polymer materials.

[0007] The present invention proposes a method for measuring the molecular weight of biological macromolecular materials based on rheology. The present invention selects ionic liquid as the dissolution system and the Rouse model as the polymer solution model. By measuring a large amount of data and training the model with the AI algorithm, the key parameter values are obtained, thereby calculating the molecular weight value of the measured material.

[0008] First, the present invention screens out ionic liquid, a good solvent, through testing different solvent systems for dissolving biological macromolecules.

[0009] Ionic liquid refers to an ionic compound in the liquid state, or an ionic compound with a melting point lower than a certain temperature. In recent years, ionic liquid, as a new type of green solvent, has attracted great attention from countries around the world. It has many excellent properties such as good thermal stability, structural designability, low vapor pressure, non-toxicity and recyclability, which is beneficial to environmental protection and the health of operators. Ionic liquid is not only widely used as a solvent and reaction medium for organic synthesis reactions, but also regarded as a green solvent for some natural macromolecules. In terms of dissolving biological polymer materials, ionic liquid also shows excellent properties. For example, silk fibroin molecules with a unique structure can also exist in the form of single chains in it.

[0010] Secondly, the present invention screens out the Rouse model from numerous polymer solution models through simulation calculations. This model is more suitable for the calculation of the molecular weight of biological macromolecules. The relationship between the viscoelastic data of polymers and the molecular weight function in the Rouse model is as follows:

[0011]

[0012] Then, rheological methods are used to test the rheological data of biological macromolecules dissolved in ionic liquid. Rheological methods can well reflect the chain state and viscoelastic behavior of polymer chains in solution. Rheological data such as the viscoelasticity of polymers in ionic liquid can be measured by rheology.

[0013] Finally, the present invention introduces an AI algorithm to solve the problem of calculating a large amount of rheological data, improving timeliness and accuracy, enhancing the work efficiency of R & D personnel, and further exploring innovation in the field of biopolymer computing.

[0014] The present invention is implemented through the following technical solutions:

[0015] A method for calculating the molecular weight of biopolymer materials based on an AI algorithm, comprising the following steps:

[0016] S1. Prepare a sample: Take a sample of the biopolymer material to be measured, dissolve it in an ionic liquid to obtain a sample solution to be measured;

[0017] S2. Sample testing: Place the sample prepared in step S1 on a rheometer for sample testing to obtain the data required for calculation;

[0018] S3. Establish an AI algorithm to evaluate the Rouse model;

[0019] S4. Establish a Rouse model to fit the biopolymer system;

[0020] S5. Use the Rouse model optimized by the AI algorithm to calculate molecular weight-related data;

[0021] Preferably, in step S1, the specific method for preparing the sample is as follows:

[0022] a) Dissolution: Add the dried biopolymer material to the ionic liquid and mix, and dissolve at room temperature;

[0023] b) Drying to remove water;

[0024] c) Dissolution under reduced pressure.

[0025] Preferably, in step S1, the ionic liquid is 1-allyl-3-methylimidazolium chloride ([AMIm]Cl) and 1-hexyl-3-methylimidazolium hydrogen sulfate ([Hmim]HSO4).

[0026] Preferably, in step S1, the biopolymer materials include: silk fibroin, hyaluronic acid, collagen, recombinant collagen, sericin. Preferably, the silk fibroin is selected from mulberry silk fibroin, spider silk fibroin, tussah silk fibroin. The mulberry silk fibroin is the remaining part after removing sericin from the cocoon, also known as silk fibroin (SILK FIBROIN). Preferably, in step S1, when preparing the ionic liquid solution of the biopolymer material silk fibroin, the concentration is 0.1%-50%, preferably 1%-25%, and more preferably 5%-20%.

[0027] Preferably, in the step S1, freeze drying is selected for drying and water removal: the sample is placed in liquid nitrogen for freezing to fully solidify the ionic liquid, and then placed in a freeze dryer for sufficient dehumidification and then taken out, and thawed in a sealed manner at room temperature.

[0028] Preferably, in the step S1, the specific method of decompression dissolution is: the silk fibroin ionic liquid mixture prepared in step b is heated in an oil bath under stirring, and vacuum distillation is carried out with an oil pump to remove the possible residual trace moisture in the mixture and eliminate air bubbles, and heating is continued until the biopolymer is completely dissolved.

[0029] Preferably, the silk fibroin ionic liquid mixture prepared in step S1(b) is heated in an oil bath under stirring at a temperature of 0-180 °C, and vacuum distillation is carried out with an oil pump, and the vacuum degree ranges from -0.01 MPa to -0.5 MPa to remove the possible residual trace moisture in the mixture and eliminate air bubbles, and heating is continued until the biopolymer is completely dissolved; stop heating and stirring, and a uniform and transparent solution is obtained after cooling.

[0030] More preferably, the obtained biopolymer ionic liquid solution is stored at room temperature in a sealed and dry environment for standby.

[0031] Preferably, in the step S2, the specific method of testing the sample with a rheometer is:

[0032] a) Storage modulus and loss modulus test

[0033] Select parallel clamping plates, and protect the test by purging nitrogen through the temperature control cover during the test.

[0034] Adopt linear dynamic elasticity test, that is, the strain amplitude in the oscillation mode is controlled below 50% to ensure that the storage modulus and loss modulus are linear within the frequency sweep range (1×10 2 rad / s~30×10 -2 rad / s).

[0035] Perform frequency sweep at the following temperatures (0 °C, 10 °C, 20 °C and 30 °C) to obtain the storage modulus and loss modulus curves of the sample at different temperatures.

[0036] b) Viscosity test

[0037] Select parallel clamping plates, and protect the test by purging nitrogen through the temperature control cover during the test.

[0038] Carry out a steady-state test experiment: the shear rate is scanned from low to high, and the shear rate range is: 10 -5 ~10 5 s -1 . Record the viscosity value of the plateau curve.

[0039] Preferably, in step S3, the specific method for establishing an AI algorithm to evaluate the Rouse model is as follows: Based on common AI model optimization algorithms, an algorithm for evaluating the quality of the prediction results of the Rouse model is established. This algorithm describes the degree of agreement between the Rouse model prediction and the experimental results. The fitting process requires the theoretical prediction results of the Rouse model to approach the experiment. Therefore, the following algorithm parameters need to be set in advance:

[0040] a) Set a reasonable error threshold ε th , when the prediction error ε of the Rouse model is less than ε th , it is considered that the accuracy of the Rouse model is high enough to truly describe the situation of the experimental polymer system;

[0041] b) Set a reasonable initial learning rate α0 to control the iteration speed of the algorithm;

[0042] C) Use the gradient descent method to continuously correct the model parameters until the prediction error is less than 0.01.

[0043] Preferably, in step S3, the AI model optimization algorithms include Gradient Descent, Conjugate Descent, Adam, AdamGrad, and RMSProp.

[0044] Preferably, in step S3, the selection range of the error threshold ε th is 0.001 - 0.25.

[0045] Preferably, in step S3, the selection range of the learning rate α0 is 0.0001 - 0.1.

[0046] Preferably, in step S4, the specific method for establishing the Rouse model to fit the biological polymer system is as follows: a) Assume that the structure of the biological polymer system satisfies the Rouse model, and the molecular weight distribution of the system satisfies the normal distribution. Model the experimental system and initialize the average value and the standard deviation ΔM0 of the molecular weight distribution.

[0047] b) Use and ΔM0 to construct the normal distribution of the molecular weight [Formula (4)], and sample according to this distribution to establish an initial simulated physical system.

[0048]

[0049] c) According to the molecular weight distribution of the simulated physical system, calculate the relaxation time τ in mode p according to formula (3) ip .

[0050] d) Consider the contributions of all vibration modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to formulas (1) and (2). The density ρ of the polymer in the solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent used in the calculation s Consistent with the experimental data.

[0051] e) According to the simulation data obtained from the Rouse theory model, the relationships of logG′~logω and logG″~logω of the simulated physical system can be calculated. The difference ε between the predicted values logG′ and logG″ of the Rouse model and the experimental values measured in step S2 can be solved by the root-mean-square formula.

[0052] f) The difference ε between the calculated logG′ and logG″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the prediction results of the Rouse model approach the experimental measurement results. Therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, and the optimization objective is

[0053]

[0054] The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, the objective function of formula (5) is optimized. Compare the actual ε with the error threshold ε of the AI algorithm th , if ε≥ε th , then optimize and update the normal distribution parameters and ΔM through the AI algorithm, and after the update, return to process b) to recalculate the Rouse model; if ε<ε th , it means that the Rouse model at this time can already accurately describe the experimental results, complete this step and enter the next step.

[0055] Preferably, in step S5, when calculating the molecular weight using the Rouse model optimized by the AI algorithm, the molecular weight-related data are the weight-average molecular weight, the number-average molecular weight, and the molecular weight distribution.

[0056] Further, in step S5, using the optimized Rouse model obtained in step S4, use the molecular weight distribution of the simulated physical system to complete the calculation of the weight-average molecular weight M w , the number-average molecular weight M n and the molecular weight distribution, that is, M w / M n . Description of the Drawings

[0057] Figure 1It is a process for fitting and calculating the molecular weight of a biopolymer system based on the Rouse model.

[0058] Figure 2 It corresponds to the relationship between the storage modulus and the loss modulus of the silk fibroin ionic liquid solution and the shear frequency of silk fibroin with different molecular weights in the oscillation mode according to Example 1 of the present invention.

[0059] Figure 3 It corresponds to the relationship between the storage modulus and the loss modulus of the silk fibroin ionic liquid solution and the shear frequency of silk fibroin with different molecular weights in the oscillation mode according to Example 2 of the present invention.

[0060] Figure 4 It corresponds to the relationship between the storage modulus and the loss modulus of the silk fibroin ionic liquid solution and the shear frequency of silk fibroin with different molecular weights in the oscillation mode according to Example 3 of the present invention.

[0061] Figure 5 It corresponds to the relationship between the storage modulus and the loss modulus of the silk fibroin ionic liquid solution and the shear frequency of silk fibroin with different molecular weights in the oscillation mode according to Example 4 of the present invention.

[0062] Figure 6 It is the calculation result of different silk fibroin molecular weights in Examples 1-4 of the present invention. Detailed implementation manners

[0063] The present invention is implemented as follows. However, those skilled in the art know that the following specific implementation manners do not limit the protection scope of the present invention.

[0064] Example 1:

[0065] S1: Sample preparation

[0066] a) Dissolution: Select the mulberry silk fibroin fiber degummed with sodium carbonate for 15 minutes, mix the mulberry silk fibroin with the ionic liquid 1-allyl-3-methylimidazolium chloride, and control the concentration of the silk fibroin to 20%.

[0067] b) Freeze-drying for water removal: Place the sample in liquid nitrogen for freezing to fully solidify the ionic liquid, place it in a freeze dryer for sufficient moisture extraction and then take it out, and thaw it at room temperature under sealed conditions.

[0068] c) Vacuum dissolution: Under stirring, heat the silk fibroin ionic liquid mixture obtained in step b in an oil bath at a temperature of 150 °C, and carry out vacuum distillation with an oil pump (vacuum range: -0.01 MPa to -0.5 MPa) to remove the possible residual trace moisture in the mixture and eliminate air bubbles, and heat until the silk fibroin is completely dissolved. Stop heating and stirring, and cool down to obtain a uniform and transparent solution. The obtained silk fibroin ionic liquid solution is stored at room temperature in a sealed and dry environment for standby.

[0069] S2: Rheological method test:

[0070] 1) Storage modulus and loss modulus test

[0071] Select parallel clamping plates, and protect the test by purging nitrogen through the temperature control cover during the test.

[0072] Adopt linear dynamic elasticity test, that is, the strain amplitude in the oscillation mode is controlled below 50% to ensure that the storage modulus and loss modulus are linear within the frequency sweep range (1×10 2 rad / s~30×10 -2 rad / s).

[0073] Perform frequency sweep at the following temperatures (0°C, 10°C, 20°C and 30°C) to obtain the storage modulus and loss modulus curves of the sample at different temperatures.

[0074] 2) Viscosity test

[0075] Select parallel clamping plates, and protect the test by purging nitrogen through the temperature control cover during the test.

[0076] Conduct steady-state test experiments: scan the shear rate from low to high, and the shear rate range is: 10 -5 ~10 5 s -1 . Record the viscosity value of the plateau curve.

[0077] S3: Model with the Rouse model: Based on the commonly used AI model optimization algorithm, establish an algorithm to evaluate the quality of the prediction results of the Rouse model:

[0078] a) Set the error threshold ε th = 0.01. When the prediction error ε of the Rouse model is less than ε th , it is considered that the accuracy of the Rouse model is high enough to truly describe the experimental polymer system.

[0079] b) Set the initial learning rate α0 = 0.05 to control the iteration speed of the algorithm.

[0080] C) Continuously correct the model parameters using the gradient descent method until the prediction error is less than 0.01.

[0081] S4: The specific method for establishing the Rouse model to fit the biopolymer system is: a) Assume that the structure of the biopolymer system satisfies the Rouse model, and the molecular weight distribution of the system satisfies the normal distribution. Model the experimental system and initialize the average value and standard deviation ΔM0 of the molecular weight distribution.

[0082] b) Use Construct a normal distribution of molecular weights with ΔM0 [Equation (4)], sample according to this distribution, and establish an initial simulated physical system.

[0083]

[0084] c) According to the molecular weight distribution of the simulated physical system, calculate the relaxation time τ in mode p according to Equation (3) ip .

[0085] d) Consider the contributions of all vibration modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to Equations (1) and (2). The density ρ of the polymer in solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent used in the calculation s are consistent with the experimental data.

[0086] e) According to the simulation data obtained from the Rouse theoretical model, the relationships of log G′~logω and logG″~logω of the simulated physical system can be calculated. The difference ε between the predicted values logG′ and log G″ of the Rouse model and the experimental values measured in step S2 can be solved by the root mean square formula.

[0087] f) The difference ε between the calculated log G′ and log G″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the prediction results of the Rouse model approach the experimental measurement results. Therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, and the optimization objective is

[0088]

[0089] The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, optimize the objective function of Equation (5). Compare the actual ε with the error threshold ε of the AI algorithm th , if ε≥ε th , then optimize and update the normal distribution parameters and ΔM through the AI algorithm. After the update, return to process b) and recalculate the Rouse model; if ε<ε th , it means that the Rouse model at this time can already accurately describe the experimental results, complete this step and enter the next step.

[0090] S5: Calculate molecular weight-related data using the Rouse model optimized by the AI algorithm: Use the optimized Rouse model obtained in step S4 and the molecular weight distribution of the simulated physical system to complete the weight-average molecular weight M wThe number average molecular weight is 266 kDa. n It is 253 kDa and has a molecular weight distribution of 1.05.

[0091] Example 2

[0092] S1: Sample preparation:

[0093] a) Dissolution: Select mulberry silk protein fibers prepared by degumming with sodium carbonate for 30 minutes, mix the mulberry silk protein with ionic liquid 1-allyl-3-methylimidazolium chloride, and control the concentration of the silk protein to be 20%.

[0094] b) Freeze drying to remove water: freeze the sample in liquid nitrogen to fully solidify the ionic liquid, place it in a freeze dryer to fully dehumidify it, then take it out and seal it to thaw at room temperature.

[0095] c) Dissolving under reduced pressure: The silk protein ionic liquid mixture prepared in step b is heated in an oil bath at 150° C. under stirring, and distilled under reduced pressure using an oil pump (vacuum range: -0.01 MPa to -0.5 MPa) to remove any trace amount of water that may remain in the mixture and eliminate bubbles, and the mixture is heated until the silk protein is completely dissolved. Stop heating and stirring, and cool down to obtain a uniform and transparent solution. The obtained silk protein ionic liquid solution is stored at room temperature in a sealed and dry environment for later use.

[0096] S2: Rheological method test: same as step S2 in Example 1.

[0097] S3: Modeling using the Rouse model: the same as step S3 in Example 1.

[0098] S4: Establishing Rouse model to fit biopolymer system: Same as step S4 in Example 1.

[0099] S5: Calculate molecular weight related data using the Rouse model optimized by AI algorithm: The optimized Rouse model obtained in step S4 is used to simulate the molecular weight distribution of the physical system Complete weight average molecular weight M w The number average molecular weight is 181 kDa. n The molecular weight distribution is 97 kDa and 1.87.

[0100] Example 3

[0101] S1: Sample preparation:

[0102] a) Dissolution: Soluble high molecular weight spray-dried mulberry silk protein powder prepared by sodium carbonate degumming for 45 minutes is selected, and the mulberry silk protein powder is mixed with ionic liquid 1-allyl-3-methylimidazolium chloride, and the concentration of the silk protein is controlled to be 20%.

[0103] b) Water removal by freeze-drying: Place the sample in liquid nitrogen for freezing to fully solidify the ionic liquid, then place it in a freeze-dryer for sufficient moisture extraction and take it out, and thaw it in a sealed manner at room temperature.

[0104] c) Dissolution under reduced pressure: Under stirring, heat the silk fibroin ionic liquid mixture prepared in step b in an oil bath at a temperature of 120 °C, and carry out vacuum distillation with an oil pump (vacuum range: -0.01 MPa to -0.5 MPa) to remove possible residual trace moisture in the mixture and eliminate bubbles, and heat until the silk fibroin is completely dissolved. Stop heating and stirring, and obtain a uniform and transparent solution after cooling. The obtained silk fibroin ionic liquid solution is stored at room temperature for standby in a sealed and dry environment.

[0105] S2: Rheological method testing: The same as step S2 in Example 1.

[0106] S3: Modeling with the rouse model: The same as step S3 in Example 1.

[0107] S4: Establishing a Rouse model to fit the biopolymer system: The same as step S4 in Example 1.

[0108] S5: Calculating molecular weight-related data using the Rouse model optimized by the AI algorithm: For the optimized Rouse model obtained in step S4, use the molecular weight distribution of the simulated physical system to complete the weight-average molecular weight M w of 145 kDa, the number-average molecular weight M n of 71 kDa and the molecular weight distribution of 2.05..

[0109] Example 4

[0110] S1: Sample preparation:

[0111] a) Dissolution: Select the soluble large-molecular-weight freeze-dried mulberry silk fibroin powder obtained by degumming with sodium carbonate for 60 minutes, mix the mulberry silk fibroin powder with the ionic liquid 1-allyl-3-methylimidazolium chloride, and control the concentration of the silk fibroin to 20%.

[0112] b) Water removal by freeze-drying: Place the sample in liquid nitrogen for freezing to fully solidify the ionic liquid, then place it in a freeze-dryer for sufficient moisture extraction and take it out, and thaw it in a sealed manner at room temperature.

[0113] c) Dissolving under reduced pressure: The silk protein ionic liquid mixture prepared in step b is heated in an oil bath at 120° C. under stirring, and distilled under reduced pressure using an oil pump (vacuum range: -0.01 MPa to -0.5 MPa) to remove any trace amount of water that may remain in the mixture and eliminate bubbles, and the mixture is heated until the silk protein is completely dissolved. Stop heating and stirring, and cool down to obtain a uniform and transparent solution. The obtained silk protein ionic liquid solution is stored at room temperature in a sealed and dry environment for later use.

[0114] S2: Rheological method test: same as step S2 in Example 1.

[0115] S3: Modeling using the Rouse model: the same as step S3 in Example 1.

[0116] S4: Establishing Rouse model to fit biopolymer system: Same as step S4 in Example 1.

[0117] S5: Calculate molecular weight related data using the Rouse model optimized by AI algorithm: The optimized Rouse model obtained in step S4 is used to simulate the molecular weight distribution of the physical system Complete weight average molecular weight M w The average molecular weight is 115 kDa. n The molecular weight distribution is 58 kDa and 1.97.

Claims

1. A method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm, characterized in that, It includes the following steps: S1: Prepare the sample: Take the biological macromolecular material sample to be tested, dissolve it in an ionic liquid to obtain the sample solution to be tested, which is the ionic liquid solution of the biological macromolecular material; S2: Sample testing: Place the sample prepared in step S1 on a rheometer for sample testing and calculate the required data; S3: Establish an AI algorithm to evaluate the Rouse model: Based on the commonly used AI model optimization algorithm, establish an algorithm to evaluate the quality of the prediction results of the Rouse model; S4: Establish a Rouse model to fit the biological macromolecular system; S5: Calculate the molecular weight using the Rouse model optimized by the AI algorithm.

2. The calculation method of the molecular weight of biomacromolecular materials based on the AI algorithm according to claim 1, wherein, The specific method for preparing the sample in step S1 is as follows: a) Dissolution: Add the dry biological macromolecular material sample to the ionic liquid and mix, and dissolve it at room temperature; b) Dry to remove water; c) Dissolve under reduced pressure, In step S1, the biological macromolecular materials include: silk fibroin, hyaluronic acid, collagen, recombinant collagen, sericin; The silk fibroin is selected from mulberry silk fibroin, spider silk fibroin, tussah silk fibroin; The ionic liquid in step S1 is selected from [AMIm]Cl and [HMIm]HSO4.

3. The method for calculating the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 1 or 2, characterized in that, In the ionic liquid solution of the biological macromolecular material silk fibroin prepared in step S1, the concentration of silk fibroin is 0.1%-50%, or it can also be 1%-20%, or it can also be 5%-15%.

4. The calculation method of the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 2, characterized in that, In step S1, the freeze-drying method is selected to dry and remove water. Specifically, place the sample in liquid nitrogen for freezing to fully solidify the ionic liquid, place it in a freeze dryer to fully dehumidify and then take it out, and seal and thaw it at room temperature.

5. The method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 2 or 4, characterized in that, The specific method for dissolving under reduced pressure in the sample preparation in step S1 is: Under stirring, heat the silk fibroin ionic liquid mixture prepared in step S1(b) in an oil bath and distill it under reduced pressure with an oil pump to remove the possible residual trace moisture in the mixture and eliminate bubbles, and heat until the biological macromolecule is completely dissolved; Under stirring, heat the silk fibroin ionic liquid mixture prepared in step S1(b) in an oil bath at a temperature of 0-180°C, and distill it under reduced pressure with an oil pump, and the vacuum degree ranges from -0.01 MPa to -0.5 MPa to remove the possible residual trace moisture in the mixture and eliminate bubbles, and heat until the biological macromolecule is completely dissolved; Stop heating and stirring, and after cooling, obtain a uniform and transparent solution; Store the obtained biological macromolecular ionic liquid solution at room temperature in a sealed and dry environment for standby.

6. The method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 1 or 2 or 4, characterized in that, The specific method for sample testing in step S2 is as follows: a) Storage modulus and loss modulus testing: Select parallel clamps, and protect the testing by purging nitrogen through the temperature control cover during the testing process; Linear dynamic elasticity testing is adopted, that is, the strain amplitude in the oscillation mode is controlled below 50% to ensure that the storage modulus and loss modulus are linear within the frequency sweep range of 1×10 2 rad / s - 30×10 -2 rad / s. Among the following different temperatures: 0°C, 10°C, 20°C and 30°C, select for frequency scanning to obtain the storage modulus and loss modulus curves of the sample at different temperatures; b) Viscosity testing: Select parallel clamps, and protect the testing by purging nitrogen through the temperature control cover during the testing process; Steady-state test experiments were conducted: the shear rate was scanned from low to high, and the shear rate range was: 10 -5 -10 5 s -1 , and the viscosity values of the plateau curve were recorded.

7. The method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 3, wherein The specific method for sample testing in step S2 is as follows: a) Storage modulus and loss modulus testing: Select parallel clamps, and protect the testing by purging nitrogen through the temperature control cover during the testing process; Linear dynamic elasticity testing is adopted, that is, the strain amplitude in the oscillation mode is controlled below 50% to ensure that the storage modulus and loss modulus are linear within the frequency sweep range of 1×10 2 rad / s - 30×10 -2 rad / s. Among the following different temperatures: 0 °C, 10 °C, 20 °C, and 30 °C, frequency scans are selected to obtain the storage modulus and loss modulus curves of the sample at different temperatures; b) Viscosity test: Select parallel clamping plates, and protect the test by purging nitrogen through the temperature control cover during the test; Steady-state test experiments were carried out: the shear rate was scanned from low to high, and the shear rate range was: 10 -5 -10 5 s -1 , and the viscosity values of the plateau curve were recorded.

8. The calculation method of the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 5, wherein The specific method for testing the sample in step S2 is as follows: a) Storage modulus and loss modulus test: Select parallel clamping plates, and protect the test by purging nitrogen through the temperature control cover during the test; Linear dynamic elastic testing is adopted, that is, the strain amplitude in the oscillation mode is controlled below 50% to ensure that the storage modulus and loss modulus are linear within the frequency sweep range of 1×10 2 rad / s - 30×10 -2 rad / s. Among the following different temperatures: 0 °C, 10 °C, 20 °C, and 30 °C, frequency scans are selected to obtain the storage modulus and loss modulus curves of the sample at different temperatures; b) Viscosity test: Select parallel clamping plates, and protect the test by purging nitrogen through the temperature control cover during the test; Steady-state test experiments were conducted: the shear rate was scanned from low to high, and the shear rate range was: 10 -5 -10 5 s -1 , and the viscosity values of the plateau curve were recorded.

9. The method for calculating the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 1 or 2 or 4 or 7 or 8, characterized in that, The specific method for establishing the AI algorithm to evaluate the Rouse model in step S3 is as follows: a) Set a reasonable error threshold ε th , when the prediction error ε of the Rouse model is less than ε th , it is considered that the accuracy of the Rouse model is high enough to truly describe the experimental polymer system; b) Set a reasonable initial learning rate α0 to control the iteration speed of the algorithm; c) Continuously correct the model parameters using the gradient descent method until the prediction error is less than 0.01, The AI model optimization algorithms in step S3 include the gradient descent method, conjugate gradient method, Adam, AdamGrad, and RMSProp.

10. The calculation method of the molecular weight of biomacromolecular materials based on the AI algorithm according to claim 3, characterized in that, The specific method for establishing the AI algorithm to evaluate the Rouse model in step S3 is as follows: a) Set a reasonable error threshold ε th , when the prediction error ε of the Rouse model is less than ε th , it is considered that the accuracy of the Rouse model is high enough to truly describe the experimental polymer system; b) Set a reasonable initial learning rate α0 to control the iteration speed of the algorithm; c) Continuously correct the model parameters using the gradient descent method until the prediction error is less than 0.01, The AI model optimization algorithms in step S3 include the gradient descent method, conjugate gradient method, Adam, AdamGrad, and RMSProp.

11. The method for calculating the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 5, wherein, The specific method for establishing the AI algorithm to evaluate the Rouse model in step S3 is as follows: a) Set a reasonable error threshold ε th , when the prediction error ε of the Rouse model is less than ε th , it is considered that the accuracy of the Rouse model is high enough to truly describe the experimental polymer system; b) Set a reasonable initial learning rate α0 to control the iteration speed of the algorithm; c) Continuously correct the model parameters using the gradient descent method until the prediction error is less than 0.01, The AI model optimization algorithms in step S3 include the gradient descent method, conjugate gradient method, Adam, AdamGrad, and RMSProp.

12. The calculation method of the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 6, characterized in that, The specific method for establishing the AI algorithm to evaluate the Rouse model in step S3 is as follows: a) Set a reasonable error threshold ε th , when the prediction error ε of the Rouse model is less than ε th , it is considered that the accuracy of the Rouse model is high enough to truly describe the experimental polymer system; b) Set a reasonable initial learning rate α0 to control the iteration speed of the algorithm; c) Continuously correct the model parameters using the gradient descent method until the prediction error is less than 0.01, The AI model optimization algorithms in step S3 include the gradient descent method, conjugate gradient method, Adam, AdamGrad, and RMSProp.

13. The method for calculating the molecular weight of a biomacromolecular material based on an AI algorithm according to any one of claims 1, 2, 4, 7, 8, 10, 11, or 12, characterized in that The error threshold ε in step S3 th is selected in the range of 0.001 - 0.25, and the learning rate α0 is selected in the range of 0.0001 - 0.

1.

14. The method for calculating the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 3, wherein The error threshold ε in step S3 th is selected in the range of 0.001 - 0.25, and the learning rate α0 is selected in the range of 0.0001 - 0.

1.

15. The calculation method of the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 5, characterized in that, The error threshold ε in the step S3 th is selected in the range of 0.001 - 0.25, and the learning rate α0 is selected in the range of 0.0001 - 0.

1.

16. The method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 6, wherein The error threshold ε in step S3 th is selected in the range of 0.001 - 0.25, and the learning rate α0 is selected in the range of 0.0001 - 0.

1.

17. The method for calculating the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 9, wherein The error threshold ε in step S3 th is selected in the range of 0.001 - 0.25, and the learning rate α0 is selected in the range of 0.0001 - 0.

1.

18. The method for calculating the molecular weight of a biomacromolecular material based on an AI algorithm according to any one of claims 1, 2, 4, 7-8, 10-12, and 14-17, characterized in that The steps for establishing the Rouse model to fit the biopolymer system in step S4 are as follows: a) Assume that the structure of the biopolymer system satisfies the Rouse model, and the molecular weight distribution of the system satisfies the normal distribution; model the experimental system and initialize the mean value and the standard deviation ΔM0 of the molecular weight distribution; b) Usage Use and ΔM0 to construct a normal distribution of the molecular weight of ΔM0 Sample according to this distribution to establish an initial simulated physical system; where M i and f(M i ) are the molecular weight and its probability density function of the i-th silk fibroin component, ΔM is the standard deviation of the molecular weight distribution, is the overall molecular weight mean, and σ is the overall standard deviation; c) Calculate the relaxation time τ in mode p according to the molecular weight distribution of the simulated physical system using Equation (3). ip ; Among them, formula (3) is: Among them, τ ip is the relaxation time, p is the p-th relaxation mode, ρ is the solution density, η0 is the zero-shear viscosity of the polymer solution, M i is the molecular weight of the i-th silk fibroin component, M w is the weight-average molecular weight; d) Consider the contributions of all vibration modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to formulas (1) and (2). In the calculation, the density ρ of the polymer in the solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent are used. s Consistent with the experimental data; Among them, formula (1) is: Among them, G′ is the storage modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; Among them, formula (2) is: Among them, G″ is the loss modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; e) According to the simulation data obtained from the Rouse theoretical model, the relationships of log G′~logω and log G″~logω of the simulated physical system can be calculated. The difference ε between the predicted values log G′ and log G″ of the Rouse model and the measured experimental values in step S2 can be obtained by solving using the root mean square formula; f) The difference ε between the calculated log G′ and log G″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the prediction results of the Rouse model approach the experimental measurement results. Therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, with the optimization objective being The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, the objective function of formula (5) is optimized; the actual ε is compared with the error threshold ε of the AI algorithm th , if ε ≥ ε th , then the normal distribution parameters and ΔM are optimized and updated through the AI algorithm, and after the update, return to process b) to recalculate the Rouse model; if ε < ε th , it indicates that the Rouse model at this time can already accurately describe the experimental results.

19. The method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 3, wherein The steps for establishing the Rouse model to fit the biopolymer system in step S4 are as follows: a) Assume that the structure of the biopolymer system satisfies the Rouse model and the molecular weight distribution of the system satisfies the normal distribution; model the experimental system and initialize the mean value of the molecular weight distribution and the standard deviation ΔM0; b) Usage Use and ΔM0 to construct a normal distribution of the molecular weight of ΔM0 Sample according to this distribution to establish an initial simulated physical system; where M i and f(M i ) are the molecular weight and its probability density function of the i-th silk fibroin component, ΔM is the standard deviation of the molecular weight distribution, is the overall molecular weight mean, and σ is the overall standard deviation; c) Calculate the relaxation time τ in mode p according to the molecular weight distribution of the simulated physical system using Equation (3). ip ; Among them, formula (3) is: where τ ip is the relaxation time, p is the p-th relaxation mode, ρ is the solution density, η0 is the zero-shear viscosity of the polymer solution, M i is the molecular weight of the i-th silk fibroin component, M w is the weight-average molecular weight; d) Consider the contributions of all vibrational modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to formulas (1) and (2). The density ρ of the polymer in solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent used in the calculation s in agreement with the experimental data; Among them, formula (1) is: Among them, G′ is the storage modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; Among them, formula (2) is: where G″ is the loss modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; e) Based on the simulation data obtained according to the Rouse theoretical model, the relationships of log G′~logω and log G″~logω of the simulated physical system can be calculated. The difference ε between the predicted values log G′ and log G″ of the Rouse model and the experimental values measured in step S2 can be obtained by solving through the root mean square formula; f) The difference ε between the calculated log G′ and log G″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the prediction results of the Rouse model approach the experimental measurement results. Therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, with the optimization objective being The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, the objective function of formula (5) is optimized; the actual ε is compared with the error threshold ε of the AI algorithm th , if ε ≥ ε th , then the normal distribution parameters and ΔM are optimized and updated through the AI algorithm, and after the update, return to process b), and recalculate the Rouse model; if ε < ε th , it indicates that the Rouse model at this time can already accurately describe the experimental results.

20. The calculation method of the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 5, characterized in that The steps for establishing the Rouse model to fit the biopolymer system in step S4 are as follows: a) Assume that the structure of the biopolymer system satisfies the Rouse model, and the molecular weight distribution of the system satisfies the normal distribution; model the experimental system and initialize the mean value and the standard deviation ΔM0 of the molecular weight distribution; b) Usage and ΔM0 to construct a normal distribution of the molecular weight of ΔM0 Sample according to this distribution to establish an initial simulated physical system; where, M i and f(M i ) are the molecular weight and its probability density function of the i-th silk fibroin component, ΔM is the standard deviation of the molecular weight distribution, is the overall molecular weight mean, and σ is the overall standard deviation; c) Calculate the relaxation time τ in mode p according to the molecular weight distribution of the simulated physical system using Equation (3). ip ; Among them, formula (3) is: where τ ip is the relaxation time, p is the p-th relaxation mode, ρ is the solution density, η0 is the zero-shear viscosity of the polymer solution, M i is the molecular weight of the i-th silk fibroin component, M w is the weight-average molecular weight; d) Consider the contributions of all vibrational modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to formulas (1) and (2). The density ρ of the polymer in solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent used in the calculation s Consistent with the experimental data; Among them, formula (1) is: Among them, G′ is the storage modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; Among them, formula (2) is: Among them, G is the loss modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; e) Based on the simulation data obtained according to the Rouse theoretical model, the relationships of log G′~logω and log G″~logω of the simulated physical system can be calculated. The difference ε between the predicted values log G′ and log G″ of the Rouse model and the experimental values measured in step S2 can be obtained by solving through the root mean square formula; f) The difference ε between the calculated log G′ and log G″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the prediction results of the Rouse model approach the experimental measurement results. Therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, with the optimization objective being The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, the objective function of formula (5) is optimized; the actual ε is compared with the error threshold ε of the AI algorithm th , if ε ≥ ε th , then the normal distribution parameters and ΔM are optimized and updated through the AI algorithm. After the update, return to process b) and recalculate the Rouse model; if ε < ε th , it indicates that the Rouse model at this time can already accurately describe the experimental results.

21. The calculation method of the molecular weight of biomacromolecular materials based on the AI algorithm according to claim 6, characterized in that, The steps for establishing the Rouse model to fit the biopolymer system in step S4 are as follows: a) Assume that the structure of the biopolymer system satisfies the Rouse model, and the molecular weight distribution of the system satisfies the normal distribution; model the experimental system and initialize the mean value and the standard deviation ΔM0 of the molecular weight distribution; b) Use and ΔM0 to construct a normal distribution of the molecular weight of ΔM0 Sample according to this distribution to establish an initial simulated physical system; where M i and f(M i ) are the molecular weight and its probability density function of the i-th silk fibroin component, ΔM is the standard deviation of the molecular weight distribution, is the overall molecular weight mean, and σ is the overall standard deviation; c) Calculate the relaxation time τ in mode p according to the molecular weight distribution of the simulated physical system using Equation (3). ip ; Among them, formula (3) is: where τ ip is the relaxation time, p is the p-th relaxation mode, ρ is the solution density, η0 is the zero-shear viscosity of the polymer solution, M i is the molecular weight of the i-th silk fibroin component, M w is the weight-average molecular weight; d) Consider the contributions of all vibration modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to formulas (1) and (2). The density ρ of the polymer in solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent used in the calculation s in agreement with the experimental data; Among them, formula (1) is: Among them, G′ is the storage modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; Among them, formula (2) is: Among them, G″ is the loss modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; e) Based on the simulation data obtained according to the Rouse theoretical model, the relationships of log G′~logω and log G″~logω of the simulated physical system can be calculated. The difference ε between the predicted values log G′ and log G″ of the Rouse model and the experimental values measured in step S2 can be obtained by solving through the root mean square formula; f) The difference ε between the calculated log G′ and log G″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the prediction results of the Rouse model approach the experimental measurement results. Therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, with the optimization objective being The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, the objective function of formula (5) is optimized; the actual ε is compared with the error threshold ε of the AI algorithm th , if ε ≥ ε th , then the normal distribution parameters and ΔM are optimized and updated through the AI algorithm, and after the update, return to process b) to recalculate the Rouse model; if ε < ε th , it indicates that the Rouse model at this time can already accurately describe the experimental results.

22. The calculation method of the molecular weight of a biomacromolecular material based on an AI algorithm according to claim 9, characterized in that, The steps for establishing the Rouse model to fit the biopolymer system in step S4 are as follows: a) Assume that the structure of the biopolymer system satisfies the Rouse model, and the molecular weight distribution of the system satisfies the normal distribution; model the experimental system and initialize the mean value and the standard deviation ΔM0 of the molecular weight distribution; b) Usage Use and ΔM0 to construct a normal distribution of the molecular weight of ΔM0 Sample according to this distribution to establish an initial simulated physical system; where M i and f(M i ) are the molecular weight and its probability density function of the i-th silk fibroin component, ΔM is the standard deviation of the molecular weight distribution, is the overall molecular weight mean, and σ is the overall standard deviation; c) Calculate the relaxation time τ in mode p according to the molecular weight distribution of the simulated physical system using Equation (3). ip ; Among them, formula (3) is: where τ ip is the relaxation time, p is the p-th relaxation mode, ρ is the solution density, η0 is the zero-shear viscosity of the polymer solution, M i is the molecular weight of the i-th silk fibroin component, M w is the weight-average molecular weight; d) Consider the contributions of all vibration modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to formulas (1) and (2). The density ρ of the polymer in solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent used in the calculation s in agreement with the experimental data; Among them, formula (1) is: Among them, G′ is the storage modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; Among them, formula (2) is: Among them, G″ is the loss modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; e) From the simulation data obtained according to the Rouse theoretical model, the relationships of log G′~logω and log G″~logω of the simulated physical system can be calculated. The differences ε between the predicted values log G′ and log G″ of the Rouse model and the experimental values measured in step S2 can be obtained by solving through the root mean square formula; f) The difference ε between the calculated log G′ and log G″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the predicted results of the Rouse model approach the experimental measurement results; therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, and the optimization objective is The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, the objective function of formula (5) is optimized; the actual ε is compared with the error threshold ε of the AI algorithm th , if ε ≥ ε th , then the normal distribution parameters and ΔM are optimized and updated through the AI algorithm, and after the update, return to process b) to recalculate the Rouse model; if ε < ε th , it indicates that the Rouse model at this time can already accurately describe the experimental results.

23. The method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 13, wherein The steps for establishing the Rouse model to fit the biopolymer system in step S4 are: a) Assume that the structure of the biopolymer system satisfies the Rouse model and the molecular weight distribution of the system satisfies the normal distribution; model the experimental system and initialize the mean value of the molecular weight distribution and the standard deviation ΔM0; b) Usage Use and ΔM0 to construct a normal distribution of the molecular weight of ΔM0 Sample according to this distribution to establish an initial simulated physical system; where, M i and f(M i ) are the molecular weight and its probability density function of the i-th silk fibroin component, ΔM is the standard deviation of the molecular weight distribution, is the overall molecular weight mean, and σ is the overall standard deviation; c) Calculate the relaxation time τ in mode p according to the molecular weight distribution of the simulated physical system using Equation (3). ip ; Among them, formula (3) is: where τ ip is the relaxation time, p is the p-th relaxation mode, ρ is the solution density, η0 is the zero-shear viscosity of the polymer solution, M i is the molecular weight of the i-th silk fibroin component, M w is the weight-average molecular weight; d) Consider the contributions of all vibrational modes p to the storage modulus G′ and the loss modulus G″, and calculate G′ and G″ of the simulated physical system according to formulas (1) and (2). In the calculation, the density ρ of the polymer in solution, the zero-shear viscosity η0 of the solution, and the viscosity η of the solvent are used. s Consistent with the experimental data; Among them, formula (1) is: Among them, G is the storage modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; Among them, formula (2) is: Among them, G″ is the loss modulus, p is the p-th relaxation mode, N is the total number of relaxation modes, ρ is the solution density, M i is the molecular weight of the i-th silk fibroin component, f(i) is the molecular weight distribution of the i-th silk fibroin component, τ ip is the relaxation time; e) From the simulation data obtained according to the Rouse theoretical model, the relationships of log G′~logω and log G″~logω of the simulated physical system can be calculated. The differences ε between the predicted values log G′ and log G″ of the Rouse model and the experimental values measured in step S2 can be obtained by solving through the root mean square formula; f) The difference ε between the calculated log G′ and log G″ data describes the degree of agreement between the Rouse model and the experimental results. The fitting process requires that the predicted results of the Rouse model approach the experimental measurement results; therefore, the difference ε must be as small as possible, and the fitting of the Rouse model evolves into an optimization problem, and the optimization objective is The difference ε varies with the distribution of the polymer. Using the AI algorithm described in step S3, the objective function of formula (5) is optimized; the actual ε is compared with the error threshold ε of the AI algorithm th , if ε ≥ ε th , then the normal distribution parameters and ΔM are optimized and updated by the AI algorithm. After the update, return to process b) and recalculate the Rouse model; if ε < ε th , it indicates that the Rouse model at this time can already accurately describe the experimental results.

24. The method for calculating the molecular weight of a biomacromolecule material based on an AI algorithm according to claim 1, wherein In step S5, the molecular weight data are the weight-average molecular weight, number-average molecular weight, and molecular weight distribution. The method for calculating the molecular weight using the Rouse model optimized by the AI algorithm in step S5 is as follows: Using the optimized Rouse model obtained in steps S1 - S4, the molecular weight distribution of the simulated physical system is used to complete the calculation of the weight-average molecular weight M w , the number-average molecular weight M n and the molecular weight distribution, i.e., M w / M n .

Images