Culture and application method of gentian callus cells

Abstract

The invention discloses a radix gentianae callus cell culture and application method, and relates to the technical field of plant biology.The method comprises the following steps that in the laser irradiation process, a real-time spectrum analyzer is used for monitoring radix gentianae tissue, and absorption characteristic information of the plant tissue to light with different wavelengths is obtained. By combining the real-time spectral analysis and the machine learning model, the scheme can accurately monitor the interaction between the laser wavelength and the photosensitive component in the plant tissue, and by intelligently evaluating and dynamically adjusting the laser wavelength, the excessive absorption of laser energy is avoided, and the photochemical reaction and cell damage are reduced. The method not only reduces the potential damage of laser irradiation to plant cells, but also optimizes the synthesis process of medicinal components, and ensures the high efficiency, repeatability and reliability of callus culture. According to the scheme, powerful support is provided for improving the accuracy of experimental results and commercialized application of the gentiana scabra bunge.

Description

Technical Field

[0001] The invention relates to the field of plant biotechnology, and in particular to a culture and application method of gentiana callus cells. Background Art

[0002] Gentiana callus cell culture involves inducing the formation of callus (an undifferentiated cell mass) from Gentiana plant tissues (such as stems, leaves, or roots) under specific culture conditions, followed by cell division and proliferation in a suitable culture medium. Callus tissue, formed by a process of asexual plant cell division and expansion, possesses strong regenerative potential. Appropriate hormone regulation can induce callus cells to further differentiate into multiple plants or produce specific active ingredients. This technology is of great significance for the rapid propagation of Gentiana, the screening of superior varieties, and the extraction of medicinal ingredients.

[0003] Gentiana callus cell culture can be cultured using laser-induced culture. The laser-induced culture method uses a laser beam to irradiate callus cells to stimulate specific biological responses of the cells. The energy of the laser can activate intracellular signal transduction pathways by directly irradiating cells or local tissues, promoting gene expression, cell proliferation or differentiation. In callus cell culture, lasers can be used to stimulate cell proliferation, induce gene mutations, or enhance the synthesis of certain specific metabolites. In addition, the laser-induced method can also achieve precise regulation of the cell growth process by precisely controlling the irradiation area and intensity, avoiding unnecessary effects on the culture system. Therefore, this technology can effectively improve the efficiency of callus cell culture and provide technical support for the efficient synthesis of specific medicinal ingredients.

[0004] Existing technologies have the following drawbacks: During the laser-induced culture of gentiana, plant tissues (such as stems, leaves, or roots) may contain natural photosensitizing components, such as flavonoids. These components have specific absorption properties. When the laser wavelength resonates with the absorption peaks of these components, excessive absorption of the laser energy can occur, triggering photochemical reactions and producing reactive oxygen molecules or free radicals. These reactions can cause cell membrane damage, DNA damage, and even cell death, thereby affecting the growth and proliferation of callus cells. Such cytotoxic reactions are often unintended and may be unpredictable during laser irradiation. Failure to effectively avoid this resonance effect can lead to failure of gentiana callus culture, hindered cell proliferation, and even impaired synthesis of medicinal ingredients, ultimately compromising the reliability and reproducibility of experimental results.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a method for culturing and applying gentian callus cells. By combining real-time spectral analysis and machine learning models, this solution can accurately monitor the interaction between laser wavelength and photosensitive components in plant tissues, and through intelligent evaluation and dynamic adjustment of laser wavelength, avoid excessive absorption of laser energy, reduce photochemical reactions and cell damage. This method not only reduces the potential damage of laser irradiation to plant cells, but also optimizes the synthesis process of medicinal ingredients, ensuring the efficiency, repeatability and reliability of callus cell culture. This solution provides strong support for improving the accuracy of experimental results and the commercial application of gentian, thereby solving the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for culturing and applying gentian callus cells, comprising the following steps: During the laser irradiation process, a real-time spectrum analyzer was used to monitor the gentian tissue to obtain information on the absorption characteristics of the plant tissue to light of different wavelengths. Preprocessing the acquired raw absorption characteristic information and organizing the preprocessed data into a data set; Extract key features from the dataset that reflect the risk of resonance between the laser wavelength and the photosensitizing components in plant tissues, analyze the extracted key features, and quantify the resonance risk; The analyzed key features are input into a pre-trained machine learning model, which then intelligently evaluates whether the laser wavelength resonates with the photosensitizing component, thereby determining whether there is a risk of resonance between the laser wavelength and the plant's photosensitizing component. According to the evaluation results of the machine learning model, when there is a risk of resonance between the laser wavelength and the photosensitizing components in plant tissue, the wavelength output of the laser is automatically adjusted to move the laser wavelength out of the absorption peak area of ​​the photosensitizing components in the plant tissue, thereby reducing the resonance risk.

[0008] Preferably, during the laser irradiation process, the specific steps of using a real-time spectrum analyzer to monitor the gentian tissue are as follows: First, aim the spectrum analyzer at the plant tissue to ensure that the instrument can capture the plant's reflection or transmission spectrum data of different wavelengths of light in real time; Then, a laser source emits light of different wavelengths and irradiates the gentian tissue. The analytical instrument receives the reflected or transmitted light signals and records the light absorption of the plant tissue at each wavelength. Next, the spectrum analyzer processes the received signal and converts it into absorption spectrum data, which reflects the absorption characteristics of plant tissue at different wavelengths.

[0009] Preferably, key features reflecting the risk of resonance between the laser wavelength and the photosensitivity components in the plant tissue are extracted from the data set. The extracted features include the response sensitivity of the plant tissue to lasers of different wavelengths and the rate of change of the spectrum at different wavelengths. The response sensitivity of the plant tissue to lasers of different wavelengths and the rate of change of the spectrum at different wavelengths are analyzed under the detection window to generate wavelength sensitivity reference values ​​and spectral response change reference values, respectively. The resonance risk is quantified by the wavelength sensitivity reference values ​​and spectral response change reference values.

[0010] Preferably, the specific steps of analyzing the response sensitivity of plant tissue to lasers of different wavelengths in the detection window to generate wavelength sensitivity reference values ​​are as follows: By irradiating plant tissue with laser and monitoring the changes in its absorbance in real time, the response data of plant tissue to lasers of different wavelengths are obtained. Based on the obtained data, the absorbance change rate of plant tissue at each wavelength is calculated to measure its response sensitivity to laser. The absorbance change rate calculation expression is as follows: , where The wavelength of plant tissue after laser irradiation The absorbance under It is the wavelength of plant tissue before laser irradiation The absorbance under is a small change in wavelength, is the rate of change of absorbance; After obtaining the absorbance change rate, the absorbance changes at each wavelength are combined to generate a wavelength sensitivity reference value to quantify the resonance risk between the laser wavelength and the plant's photosensitizing components. The generation formula is as follows: , where is the wavelength sensitivity reference value, is the wavelength detection range, It is the absorption peak wavelength of the plant's photosensitizing components. is the peak weight attenuation coefficient.

[0011] Preferably, the specific steps of analyzing the change rate of the absorption spectrum at different wavelengths in the detection window to generate a reference value of the spectrum response change are as follows: The absorption spectrum data of plant tissues at different wavelengths are obtained by a spectrum analyzer, and the change rate of absorbance at each wavelength is calculated. The calculation expression of the absorption change rate is as follows: , where It is wavelength , It is wavelength , is the wavelength The absorbance under is the wavelength The absorbance of the plant tissue below, is the rate of change of absorption; Based on the calculated absorption change rate, the absorption change rate at different wavelengths is further weighted and summed to generate a reference value of spectral response change. The calculation expression is as follows: , where is the reference value of spectral response change, is the wavelength The weight factor of .

[0012] Preferably, the analyzed wavelength sensitivity reference value and spectral response change reference value are input into a pre-trained machine learning model, a resonance risk coefficient is generated by the machine learning model, and an intelligent evaluation is performed on whether the laser wavelength resonates with the photosensitive component by the resonance risk coefficient.

[0013] Preferably, the resonance risk coefficient generated by the intelligent evaluation of whether the laser wavelength resonates with the photosensitizing component by the pre-trained machine learning model is compared with the pre-set resonance risk coefficient reference threshold to determine whether there is a resonance risk between the laser wavelength and the plant photosensitizing component. The judgment logic is as follows: If the resonance risk coefficient is greater than a preset resonance risk coefficient reference threshold, it is judged that there is a resonance risk between the laser wavelength and the plant photosensitizing component; if the resonance risk coefficient is less than or equal to the preset resonance risk coefficient reference threshold, it is judged that there is no resonance risk between the laser wavelength and the plant photosensitizing component.

[0014] Preferably, according to the evaluation results of the machine learning model, when there is a risk of resonance between the laser wavelength and the photosensitizing components in the plant tissue, the wavelength output of the laser is automatically adjusted to move the laser wavelength out of the absorption peak region of the photosensitizing components in the plant tissue. The specific steps are as follows: After confirming that there is a risk of resonance between the laser wavelength and the photosensitizing components of the plant, the laser wavelength output is automatically adjusted. Based on the initial flow scanning frequency, the adjusted flow scanning frequency is calculated. The calculation expression is as follows: , where is the adjusted flow scan frequency, is the initial flow scan frequency, is the resonance risk coefficient, is the reference threshold of the resonance risk coefficient, is the change in absorbance of plant tissue before and after laser irradiation. is the maximum absorbance value of plant tissue at different wavelengths. and are weight coefficients, Control the sensitivity of scanning frequency changes during wavelength adjustment, Control the influence of absorbance changes on scanning frequency adjustment; After adjusting the flow scanning frequency, the laser wavelength is further precisely adjusted to keep it away from the absorption peak area of ​​the photosensitive component, thereby reducing the risk of resonance. The adjustment formula is as follows: , where is the adjusted laser wavelength, is the initial laser wavelength, is the weight coefficient, is the maximum wavelength offset, which indicates the maximum offset allowed during the laser wavelength adjustment process. Indicates the adjusted flow scanning frequency Over time The rate of change.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: This method, combining real-time spectral analysis with machine learning models, can precisely monitor the interaction between laser wavelength and photosensitive components in plant tissues. Through intelligent assessment and dynamic adjustment of the laser wavelength, it effectively avoids excessive absorption of laser energy, minimizing photochemical reactions and cell damage. This approach not only reduces the potential damage to plant cells from laser irradiation but also optimizes the synthesis of medicinal ingredients, ensuring the efficiency, repeatability, and reliability of the cultivation process. This approach paves the way for improved experimental accuracy and the commercial application of gentian. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0017] Figure 1 The present invention provides a flow chart of a method for culturing and applying gentian callus cells. DETAILED DESCRIPTION

[0018] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0019] The present invention provides Figure 1 The method for culturing and applying gentian callus cells includes the following steps: During the laser irradiation process, a real-time spectrum analyzer was used to monitor the gentian tissue to obtain information on the absorption characteristics of the plant tissue to light of different wavelengths. Real-time spectrum analyzers can precisely measure light absorption in plant tissue at different wavelengths, capturing the absorption characteristics of photosensitive components in plant tissue (such as flavonoids and chlorogenic acid). Real-time monitoring provides detailed spectral data on plant light absorption, providing essential information for subsequent risk assessment. This step accurately captures the immediate absorption characteristics of plant tissue under laser irradiation, providing a reliable foundation for subsequent data preprocessing and feature extraction.

[0020] The specific steps for using a real-time spectrum analyzer to monitor gentian tissue during laser irradiation are as follows: First, aim the spectrum analyzer at the plant tissue to ensure that the instrument can capture the plant's reflection or transmission spectrum data for light of different wavelengths in real time; then, light of different wavelengths is emitted by a laser source and irradiated onto the gentian tissue. The analyzer will receive the reflected or transmitted light signal and record the light absorption of the plant tissue at each wavelength; next, the spectrum analyzer will process the received signal and convert it into absorption spectrum data, reflecting the absorption characteristics of the plant tissue at different wavelengths. Through continuous monitoring, the analyzer can provide real-time absorbance data of the plant tissue during laser irradiation, helping to obtain information on its absorption characteristics for light of different wavelengths. This information provides the necessary basic data for subsequent spectral analysis, resonance risk assessment, and laser wavelength adjustment.

[0021] Preprocessing the acquired raw absorption characteristic information and organizing the preprocessed data into a data set; Acquired spectral data often contains noise or irregular fluctuations, necessitating data preprocessing to improve data quality. Common preprocessing operations include denoising, smoothing, and normalization. For example, denoising can remove interfering signals from the environment through filtering algorithms, smoothing can remove random fluctuations in the spectrum, and normalization can help eliminate data differences between different experimental conditions. These preprocessing steps ensure data accuracy and consistency, providing a clear and usable dataset for subsequent data analysis and feature extraction. Preprocessed data effectively removes extraneous factors, ensuring the reliability and accuracy of analysis.

[0022] All valid spectral data should be integrated into a standardized structure for subsequent analysis and machine learning model training. The dataset should include variables such as laser wavelength, absorption intensity, relevant characteristics of plant photosensitizers, and environmental factors. This stage is crucial in providing structured input data for the machine learning model. The quality and completeness of the dataset directly impact the accuracy and effectiveness of subsequent assessments. Establishing this dataset lays the foundation for further feature extraction, risk quantification, and intelligent assessment.

[0023] Extract key features from the dataset that reflect the risk of resonance between the laser wavelength and the photosensitizing components in plant tissues, analyze the extracted key features, and quantify the resonance risk; Key features reflecting the resonance risk between the laser wavelength and the photosensitizing components in plant tissue are extracted from the dataset. The extracted features include the response sensitivity of plant tissue to lasers of different wavelengths and the rate of change of the spectrum at different wavelengths. The response sensitivity of plant tissue to lasers of different wavelengths and the rate of change of the spectrum at different wavelengths are analyzed within the detection window to generate wavelength sensitivity reference values ​​and spectral response change reference values, respectively. The resonance risk is quantified using the wavelength sensitivity reference values ​​and spectral response change reference values.

[0024] A sudden increase in plant tissue sensitivity to lasers of varying wavelengths typically indicates a risk of resonance between the laser wavelength and photosensitizing components in the tissue. When the laser wavelength approaches or overlaps with the absorption peak of photosensitizing components in plant tissue, the components' light absorption capacity is significantly enhanced. Photosensitizing components, such as flavonoids, have strong light absorption within a specific wavelength range. A close laser wavelength can trigger excessive absorption by these components. This excessive absorption not only causes the components to absorb more light energy but can also trigger a series of photochemical reactions, such as the generation of free radicals and the accumulation of reactive oxygen species, which can damage cells or even lead to cell death. Therefore, a sharp increase in plant tissue sensitivity indicates excessive absorption of laser energy by photosensitizing components, increasing the risk of resonance effects and potentially causing irreversible damage to plant tissue cells. This sudden increase in sensitivity can serve as an indicative indicator of potential resonance risk, providing a warning of potential photochemical damage from laser irradiation and providing a basis for adjusting the laser wavelength to avoid resonance effects.

[0025] The specific steps for analyzing the response sensitivity of plant tissue to lasers of different wavelengths in the detection window to generate wavelength sensitivity reference values ​​are as follows: By irradiating plant tissue with laser and monitoring the changes in its absorbance in real time, the response data of plant tissue to lasers of different wavelengths are obtained. Based on the obtained data, the absorbance change rate of plant tissue at each wavelength is calculated to measure its response sensitivity to laser. The absorbance change rate calculation expression is as follows: , where The wavelength of plant tissue after laser irradiation The absorbance under It is the wavelength of plant tissue before laser irradiation The absorbance under It is a small change in wavelength and is a parameter used to standardize response changes. It can ensure that the absorbance change at each wavelength is consistent with the change in the wavelength itself, so that the response sensitivity at different wavelengths can be compared. is the rate of change of absorbance; By comparing changes in absorbance at different wavelengths before and after laser irradiation, the sensitivity of plant tissue to lasers of various wavelengths can be quantitatively assessed. By calculating the rate of absorbance change, it is possible to identify wavelengths that are likely to strongly interact with photosensitive components in plant tissue, providing basic data support for subsequent resonance risk analysis and identification of sensitive wavelengths.

[0026] After obtaining the absorbance change rate, the absorbance changes at each wavelength are combined to generate a wavelength sensitivity reference value to quantify the resonance risk between the laser wavelength and the plant's photosensitizing components. The generation formula is as follows: , where is the wavelength sensitivity reference value, is the wavelength detection range, which represents the set of wavelengths analyzed within the monitoring window. It is the absorption peak wavelength of plant photosensitivity components, and refers to the wavelength at which the photosensitivity components in plant tissues (such as flavonoids, chlorogenic acid, etc.) show the highest absorption intensity in the spectrum. is the peak weight attenuation coefficient, which controls the influence of wavelength shift in the exponential function and reflects the breadth of the "influence area" of the absorption peak.

[0027] By introducing the absorbance change rate and absorption peak weighting mechanism, the response sensitivity of plant tissue to different wavelength lasers is constructed into a quantifiable wavelength sensitivity reference value, accurately measuring the resonance risk relationship between laser wavelength and the absorption behavior of photosensitizing components. This step not only achieves dynamic normalization and integration of multi-wavelength response intensities, but also strengthens the ability to identify "high-risk bands near absorption peaks," providing a scientific basis for subsequent intelligent control of laser parameters.

[0028] The larger the wavelength sensitivity reference value generated after analyzing the response sensitivity of plant tissue to lasers of different wavelengths within the detection window, the larger the wavelength sensitivity reference value, which generally means that the response of the plant tissue at that wavelength is significantly enhanced, indicating that the laser wavelength is close to or overlaps with the absorption peak of the photosensitive components in the plant tissue, thereby triggering a resonance effect. This resonance effect can lead to excessive absorption of photosensitizing components, increase the risk of photochemical reactions, and further may cause damage or death to plant cells. Therefore, a larger wavelength sensitivity reference value indicates a higher risk of resonance between the laser wavelength and the photosensitizing components. Conversely, when the wavelength sensitivity reference value is small or close to zero, it means that the absorption capacity of the plant tissue has not changed significantly, and the laser wavelength is far away from the absorption peak of the photosensitizing components, indicating that there is no risk of resonance between the laser wavelength and the photosensitizing components in the plant tissue.

[0029] When the rate of change in the absorption spectrum at different wavelengths accelerates, it may indeed indicate a risk of resonance between the laser wavelength and photosensitizing components in plant tissue. This is because photosensitizing components in plant tissue, such as flavonoids, have specific absorption peaks and exhibit strong absorption of light at specific wavelengths. When the laser wavelength approaches the absorption peaks of these photosensitizing components, the plant tissue's absorption of the laser light increases dramatically, manifesting as an accelerated rate of change in the absorption spectrum. This occurs because the laser wavelength resonates with the absorption peaks of the photosensitizing components, leading to excessive absorption of the laser energy within that wavelength range. This triggers photochemical reactions, producing free radicals and reactive oxygen species, potentially causing cell damage or death. Specifically, an accelerated rate of change in the absorption spectrum indicates a rapid increase in absorbance in plant tissue near the resonant wavelength, indicating concentrated absorption of the laser energy. This phenomenon often indicates the occurrence of a resonance effect between the laser irradiation and the photosensitizing components. Therefore, by monitoring the rate of change in the absorption spectrum, it is possible to effectively identify whether the laser wavelength is close to the absorption peaks of plant photosensitizing components, thereby quantifying the risk of resonance and implementing appropriate preventive measures.

[0030] The specific steps for analyzing the change rate of the absorption spectrum at different wavelengths in the detection window to generate the reference value of the spectrum response change are as follows: The absorption spectrum data of plant tissues at different wavelengths are obtained by a spectrum analyzer, and the change rate of absorbance at each wavelength is calculated. The calculation expression of the absorption change rate is as follows: , where It is wavelength , It is wavelength , which is the next wavelength, is the wavelength The absorbance under the wavelength indicates that the plant tissue The absorbance value at is the wavelength The absorbance of the plant tissue at the next wavelength, that is, the absorbance value of the plant tissue at the next wavelength, It is the absorption change rate, which indicates the rate at which the absorption intensity of laser by plant tissue changes between adjacent wavelengths; This formula calculates the absolute change in absorbance at adjacent wavelengths, expressed as a per-unit wavelength shift, to reflect the rate of change in plant tissue absorption characteristics at different wavelengths. This process can identify areas where the rate of change in the absorption spectrum accelerates during laser irradiation. This is particularly true near the absorption peak of photosensitizing components in plant tissue, where the rate of change typically increases significantly, indicating potential resonance risk.

[0031] Based on the calculated absorption change rate, the absorption change rate at different wavelengths is further weighted and summed to generate a reference value of spectral response change. The calculation expression is as follows: , where is the reference value of spectral response change, is the wavelength The weight factor of .

[0032] The calculated results from this step It can reflect whether the laser wavelength resonates with the photosensitive components in plant tissues. When it is higher, it indicates that the spectral response changes are aggravated, which means that there is a risk of resonance between the laser wavelength and the photosensitive components in the plant tissue, which may lead to excessive absorption and photochemical reaction. This indicates that there is no significant resonance effect between the laser wavelength and the photosensitizing component. Therefore, based on this spectral response change reference value, the resonance risk can be effectively quantified and provide a decision-making basis for the dynamic adjustment of the laser wavelength.

[0033] A larger spectral response change reference value, generated by analyzing the rate of change of the absorption spectrum at different wavelengths within the detection window, indicates a faster rate of change in the plant tissue's absorption of the laser wavelength. This typically indicates that the laser wavelength is close to the absorption peak of the photosensitizing components in the plant tissue. Because photosensitizing components have a strong absorption capacity for specific wavelengths of light, the absorption spectrum changes rapidly when the wavelength approaches the absorption peak, exhibiting a significant rate of change. This phenomenon typically indicates that the laser wavelength resonates with the photosensitizing components in the plant tissue, leading to excessive absorption of laser energy, potentially triggering photochemical reactions, free radical generation, and other cellular damage. Conversely, a smaller spectral response change reference value indicates a more gradual change in the absorption spectrum, with the laser wavelength being far from the absorption peak of the photosensitizing components, and typically no resonance effect occurs.

[0034] The analyzed key features are input into a pre-trained machine learning model, which then intelligently evaluates whether the laser wavelength resonates with the photosensitizing component, thereby determining whether there is a risk of resonance between the laser wavelength and the plant's photosensitizing component. The analyzed wavelength sensitivity reference value and spectral response change reference value are input into a pre-trained machine learning model, and a resonance risk coefficient is generated by the machine learning model. The resonance risk coefficient is used to intelligently evaluate whether the laser wavelength resonates with the photosensitive component.

[0035] A pre-trained machine learning model is one that has been trained using historical and experimental data before actual application. This allows the model to automatically learn and identify the relationship between input features (such as wavelength sensitivity reference values ​​and spectral response variation reference values) and resonance risk. The training process typically includes steps such as data preprocessing, feature selection, algorithm selection, model training, and validation. During training, the machine learning model uses a large amount of known input and output data to learn how to extract useful information from the input features and predict the target variable (such as the resonance risk coefficient) based on these features. The pre-trained model not only learns the relationship between specific wavelengths and photosensitizing components of plants but also predicts resonance risk based on the wavelength sensitivity and absorption characteristics of different laser wavelengths used in experiments, providing real-time, accurate decision support for actual operations.

[0036] In machine learning applications, models are typically trained using supervised learning algorithms, which require labeled datasets (i.e., known inputs and outputs). For example, by collecting a large amount of experimental data and annotating whether resonance risk or resonance intensity occurs. Common machine learning algorithms, such as support vector machines (SVMs), random forests, gradient boosting tree (GBDT), or neural networks, can be used in this process. Each algorithm has its own unique advantages, and choosing the most appropriate algorithm depends on the characteristics of the data and the complexity of the problem. The trained model can automatically generate a resonance risk coefficient when receiving new wavelength sensitivity reference values ​​and spectral response change reference values. Through this process, the machine learning model can not only improve the intelligence level of resonance risk assessment, but also adjust the laser wavelength through real-time feedback to avoid unnecessary risks and ensure the effectiveness of laser irradiation and the safety of plant cells during the experiment.

[0037] The machine learning model is not limited here and can achieve the wavelength sensitivity reference value and spectral response variation reference values Conduct comprehensive analysis to generate resonance risk coefficients The machine learning model can be used. In order to implement the technical solution of the present invention, the present invention provides a specific implementation method: Resonance risk factor The generation formula is as follows: , where and Wavelength sensitivity reference values and spectral response variation reference values The preset scaling factor of and Both are greater than 0.

[0038] Preset scale factor ( and ) are two key parameters in the machine learning model, which are used to adjust the wavelength sensitivity reference value and spectral response variation reference values In calculating the resonance risk factor Specifically, these two proportional coefficients determine the contribution of the wavelength sensitivity reference value and the spectral response change reference value to the resonance risk coefficient.

[0039] and It is determined through experiments or training process and is used to balance the wavelength sensitivity reference value and spectral response variation reference values right Since these two parameters may have different effects on the risk factor under different conditions, and The value of is usually adjusted according to specific experimental data.

[0040] and The setting helps ensure that the model can flexibly adjust the wavelength sensitivity reference value under different experimental conditions. and spectral response variation reference values Through these coefficients, the contribution of wavelength sensitivity and absorption amplification to the resonance risk can be balanced, thereby improving the accuracy of model prediction.

[0041] In summary, the preset proportional coefficient is obtained by adjusting different characteristics (wavelength sensitivity reference value and spectral response variation reference values ) for the resonance risk factor , providing support for the flexibility and accuracy of the model.

[0042] It can be seen from the resonance risk coefficient that the larger the wavelength sensitivity reference value generated after analyzing the response sensitivity of plant tissue to lasers of different wavelengths in the detection window, and the larger the spectral response change reference value generated after analyzing the rate of change of the spectrum at different wavelengths in the detection window, the larger the resonance risk coefficient generated when the pre-trained machine learning model is used to intelligently evaluate whether the laser wavelength resonates with the photosensitizing component, the greater the probability that there is a resonance risk between the laser wavelength and the photosensitizing component of the plant, and vice versa.

[0043] The resonance risk coefficient generated by the pre-trained machine learning model when intelligently evaluating whether the laser wavelength resonates with the photosensitizing component is compared with the pre-set resonance risk coefficient reference threshold to determine whether there is a resonance risk between the laser wavelength and the plant photosensitizing component. The judgment logic is as follows: If the resonance risk coefficient is greater than a preset resonance risk coefficient reference threshold, it is judged that there is a resonance risk between the laser wavelength and the plant photosensitizing component; if the resonance risk coefficient is less than or equal to the preset resonance risk coefficient reference threshold, it is judged that there is no resonance risk between the laser wavelength and the plant photosensitizing component.

[0044] Based on the evaluation results of the machine learning model, when there is a risk of resonance between the laser wavelength and the photosensitizing components in the plant tissue, the laser wavelength output is automatically adjusted to move the laser wavelength out of the absorption peak region of the photosensitizing components in the plant tissue, thereby reducing the resonance risk. Intelligently adjusting the laser wavelength ensures safety and efficiency during laser irradiation, minimizing damage to plant tissue. During laser irradiation, photosensitive components in plant tissue (such as flavonoids and chlorogenic acid) exhibit specific light absorption characteristics. When the laser wavelength approaches the absorption peak of these photosensitive components, excessive absorption of laser energy can occur, triggering photochemical reactions such as free radical generation or oxidation, which can damage plant cells. Therefore, when the laser wavelength resonates with photosensitive components in plant tissue, these adverse reactions can be exacerbated, impacting callus cell growth and the reliability of experimental results.

[0045] By using a machine learning model to evaluate absorption characteristics in real time, it is possible to intelligently determine whether there is a risk of resonance. Based on real-time spectral data, absorption characteristics, and environmental parameters, the model can identify the resonance between the laser wavelength and the plant's photosensitizing components and provide a corresponding risk assessment. Once the assessment indicates the presence of a resonance risk, the system automatically adjusts the laser's wavelength output to avoid overlap between the laser wavelength and the absorption peak of the photosensitizing component. This dynamic adjustment effectively shifts the laser wavelength out of the absorption peak region of the photosensitizing component in plant tissue, reducing the risk of overabsorption. This prevents excessive concentration of laser energy, minimizes damage to plant cells, and ensures normal callus growth and the smooth progress of the experiment.

[0046] This automated adjustment mechanism not only improves the accuracy of laser irradiation but also responds to changes in experimental conditions in real time, reducing the need for human intervention. Ultimately, this step ensures the controllability and safety of the experiment, ensuring the stability and effectiveness of the plant cell culture process.

[0047] Based on the machine learning model's evaluation results, when there's a risk of resonance between the laser wavelength and photosensitizing components in plant tissue, the laser's wavelength output is automatically adjusted to move the laser wavelength out of the absorption peak region of the photosensitizing components in plant tissue. The specific steps are as follows: After confirming that there is a risk of resonance between the laser wavelength and the photosensitizing components of the plant, the laser wavelength output is automatically adjusted. Based on the initial flow scanning frequency, the adjusted flow scanning frequency is calculated. The calculation expression is as follows: , where is the adjusted flow scanning frequency, which is used to control the adjustment rate of the laser wavelength. is the initial flow scan frequency, is the resonance risk coefficient, is the reference threshold of the resonance risk coefficient, It is the change in plant tissue absorbance before and after laser irradiation, which measures the effect of laser irradiation on the light absorption characteristics of plant tissue. is the maximum absorbance value of plant tissue at different wavelengths. and are weight coefficients, Control the sensitivity of scanning frequency changes during wavelength adjustment, Control the influence of absorbance changes on scanning frequency adjustment; Through this formula, the scanning frequency is dynamically adjusted based on the change of the resonance risk coefficient to ensure the smooth progress of the wavelength adjustment process, avoid over-adjustment, and optimize the adjustment strategy according to the light absorption characteristics of plants.

[0048] After adjusting the flow scanning frequency, the laser wavelength is further precisely adjusted to keep it away from the absorption peak area of ​​the photosensitive component, thereby reducing the risk of resonance. The adjustment formula is as follows: , where is the adjusted laser wavelength, is the initial laser wavelength, is the weight coefficient, which controls the sensitivity of wavelength adjustment and determines the response degree of the laser wavelength adjustment amplitude. It is the maximum wavelength offset, which indicates the maximum offset allowed during the laser wavelength adjustment process. It is the maximum range in which the laser wavelength can be offset during the laser irradiation process. Indicates the adjusted flow scanning frequency Over time The rate of change.

[0049] This step ensures that the laser irradiation wavelength moves out of the absorption peak area of ​​the plant's photosensitive components by dynamically adjusting the wavelength. The square root term in the formula takes into account the interaction between the speed of frequency adjustment and the wavelength offset, making the wavelength adjustment process both accurate and smooth. The sensitivity of wavelength adjustment is further controlled to ensure that the system can adjust the wavelength quickly and effectively without the risk of resonance.

[0050] This method, combining real-time spectral analysis with machine learning models, can precisely monitor the interaction between laser wavelength and photosensitive components in plant tissues. Through intelligent assessment and dynamic adjustment of the laser wavelength, it effectively avoids excessive absorption of laser energy, minimizing photochemical reactions and cell damage. This approach not only reduces the potential damage to plant cells from laser irradiation but also optimizes the synthesis of medicinal ingredients, ensuring the efficiency, repeatability, and reliability of the cultivation process. This approach paves the way for improved experimental accuracy and the commercial application of gentian.

[0051] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0052] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

[0053] It should be noted that, in this document, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0054] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0056] Those skilled in the art will 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.

[0057] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0058] In addition, each functional unit in each embodiment of the present application 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.

[0059] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0060] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A method for culturing and applying gentian callus cells, characterized in that: The following steps are involved: During the laser irradiation process, a real-time spectrum analyzer was used to monitor the gentian tissue to obtain information on the absorption characteristics of the plant tissue to light of different wavelengths. Preprocessing the acquired raw absorption characteristic information and organizing the preprocessed data into a data set; Extract key features from the dataset that reflect the risk of resonance between the laser wavelength and the photosensitizing components in plant tissues, analyze the extracted key features, and quantify the resonance risk; The analyzed key features are input into a pre-trained machine learning model, which then intelligently evaluates whether the laser wavelength resonates with the photosensitizing component, thereby determining whether there is a risk of resonance between the laser wavelength and the plant's photosensitizing component. According to the evaluation results of the machine learning model, when there is a risk of resonance between the laser wavelength and the photosensitizing components in plant tissue, the wavelength output of the laser is automatically adjusted to move the laser wavelength out of the absorption peak area of ​​the photosensitizing components in the plant tissue, thereby reducing the resonance risk.

2. The method for culturing and applying gentiana callus cells according to claim 1, wherein: The specific steps for monitoring gentiana tissue using a real-time spectrum analyzer during laser irradiation are as follows: First, aim the spectrum analyzer at the plant tissue to ensure that the instrument can capture the plant's reflection or transmission spectrum data of different wavelengths of light in real time; Then, a laser source emits light of different wavelengths and irradiates the gentian tissue. The analytical instrument receives the reflected or transmitted light signals and records the light absorption of the plant tissue at each wavelength. Next, the spectrum analyzer processes the received signal and converts it into absorption spectrum data, which reflects the absorption characteristics of plant tissue at different wavelengths.

3. The method for culturing and applying gentiana callus cells according to claim 1, wherein: Key features reflecting the resonance risk between the laser wavelength and the photosensitizing components in plant tissue are extracted from the dataset. The extracted features include the response sensitivity of plant tissue to lasers of different wavelengths and the rate of change of the spectrum at different wavelengths. The response sensitivity of plant tissue to lasers of different wavelengths and the rate of change of the spectrum at different wavelengths are analyzed within the detection window to generate wavelength sensitivity reference values ​​and spectral response change reference values, respectively. The resonance risk is quantified using the wavelength sensitivity reference values ​​and spectral response change reference values.

4. The method for culturing and applying gentiana callus cells according to claim 3, wherein: The specific steps for analyzing the response sensitivity of plant tissue to lasers of different wavelengths in the detection window to generate wavelength sensitivity reference values ​​are as follows: By irradiating plant tissue with laser and monitoring the changes in its absorbance in real time, the response data of plant tissue to lasers of different wavelengths are obtained. Based on the obtained data, the absorbance change rate of plant tissue at each wavelength is calculated to measure its response sensitivity to laser. The absorbance change rate calculation expression is as follows: , where The wavelength of plant tissue after laser irradiation The absorbance under It is the wavelength of plant tissue before laser irradiation The absorbance under is a small change in wavelength, is the rate of change of absorbance; After obtaining the absorbance change rate, the absorbance changes at each wavelength are combined to generate a wavelength sensitivity reference value to quantify the resonance risk between the laser wavelength and the plant's photosensitizing components. The generation formula is as follows: , where is the wavelength sensitivity reference value, is the wavelength detection range, It is the absorption peak wavelength of the plant's photosensitizing components. is the peak weight attenuation coefficient.

5. The method for culturing and applying gentiana callus cells according to claim 3, characterized in that: The specific steps for analyzing the change rate of the absorption spectrum at different wavelengths in the detection window to generate the reference value of the spectrum response change are as follows: The absorption spectrum data of plant tissues at different wavelengths are obtained by a spectrum analyzer, and the change rate of absorbance at each wavelength is calculated. The calculation expression of the absorption change rate is as follows: , where It is wavelength , It is wavelength , is the wavelength The absorbance under is the wavelength The absorbance of the plant tissue below, is the rate of change of absorption; Based on the calculated absorption change rate, the absorption change rate at different wavelengths is further weighted and summed to generate a reference value of spectral response change. The calculation expression is as follows: , where is the reference value of spectral response change, is the wavelength The weight factor of .

6. The method for culturing and applying gentiana callus cells according to claim 3, characterized in that: The analyzed wavelength sensitivity reference value and spectral response change reference value are input into a pre-trained machine learning model, and a resonance risk coefficient is generated by the machine learning model. The resonance risk coefficient is used to intelligently evaluate whether the laser wavelength resonates with the photosensitive component.

7. The method for culturing and applying gentiana callus cells according to claim 6, characterized in that: The resonance risk coefficient generated by the pre-trained machine learning model when intelligently evaluating whether the laser wavelength resonates with the photosensitizing component is compared with the pre-set resonance risk coefficient reference threshold to determine whether there is a resonance risk between the laser wavelength and the plant photosensitizing component. The judgment logic is as follows: If the resonance risk coefficient is greater than a preset resonance risk coefficient reference threshold, it is judged that there is a resonance risk between the laser wavelength and the plant photosensitizing component; if the resonance risk coefficient is less than or equal to the preset resonance risk coefficient reference threshold, it is judged that there is no resonance risk between the laser wavelength and the plant photosensitizing component.

8. The method for culturing and applying gentiana callus cells according to claim 7, characterized in that: Based on the machine learning model's evaluation results, when there's a risk of resonance between the laser wavelength and photosensitizing components in plant tissue, the laser's wavelength output is automatically adjusted to move the laser wavelength out of the absorption peak region of the photosensitizing components in plant tissue. The specific steps are as follows: After confirming that there is a risk of resonance between the laser wavelength and the photosensitizing components of the plant, the laser wavelength output is automatically adjusted. Based on the initial flow scanning frequency, the adjusted flow scanning frequency is calculated. The calculation expression is as follows: , where is the adjusted flow scan frequency, is the initial flow scan frequency, is the resonance risk coefficient, is the reference threshold of the resonance risk coefficient, is the change in absorbance of plant tissue before and after laser irradiation. is the maximum absorbance value of plant tissue at different wavelengths. and are weight coefficients, Control the sensitivity of scanning frequency changes during wavelength adjustment, Control the influence of absorbance changes on scanning frequency adjustment; After adjusting the flow scanning frequency, the laser wavelength is further precisely adjusted to keep it away from the absorption peak area of ​​the photosensitive component, thereby reducing the risk of resonance. The adjustment formula is as follows: , where is the adjusted laser wavelength, is the initial laser wavelength, is the weight coefficient, is the maximum wavelength offset, which indicates the maximum offset allowed during the laser wavelength adjustment process. Indicates the adjusted flow scanning frequency Over time The rate of change.

Images