RAA constant-temperature fluorescence data analysis method for IHNV virus detection

Abstract

The invention discloses an RAA constant-temperature fluorescence data analysis method for IHNV virus detection. According to the method, fluorescence signal change data under different environmental conditions are obtained and compared with standard data, and the influence of environmental characteristics on signal drift is analyzed. And evaluating the signal accuracy according to the drift influence data, and correcting the signal accuracy. Then, constructing a fluorescence signal correction model, acquiring environmental characteristics and fluorescence signal data of a to-be-detected sample in real time, and obtaining accurate fluorescence signal change data through model correction; and finally, performing feature extraction on the correction data to determine whether the sample is infected with the IHNV. The method can effectively improve the accuracy and reliability of virus detection, eliminates interference of environmental factors, is widely applicable to the fields of aquaculture and virus monitoring, and provides effective support for rapid detection of IHNV viruses.

Description

Technical Field

[0001] The present invention relates to the technical field of virus detection, and in particular to a RAA constant temperature fluorescence data analysis method for IHNV virus detection. Background Art

[0002] IHNV (Infectious Hemorrhagic Necrosis Virus) is a pathogenic virus that seriously affects cold-water fish, especially salmon and trout in aquaculture, causing significant economic losses. In order to quickly and accurately detect IHNV, traditional nucleic acid detection methods (such as RT-PCR) are highly sensitive, but the operation is complex and time-consuming, and cannot meet the needs of rapid on-site detection.

[0003] In recent years, RAA (recombinase-assisted amplification) technology, as an emerging isothermal amplification method, has gained wide attention in nucleic acid detection because it does not rely on thermal cycling, is easy to operate and has a fast detection speed. Combined with isothermal fluorescence detection, RAA technology can monitor the amplification process through real-time fluorescence signals, with high sensitivity and specificity.

[0004] However, the influence of environmental factors (such as temperature, humidity, light intensity, etc.) on the fluorescence signal may cause signal drift, thereby affecting the accuracy of the detection results. Existing technologies generally fail to fully solve this problem and it is difficult to ensure stable detection performance under different environmental conditions.

[0005] To this end, this application proposes a RAA constant temperature fluorescence data analysis method, which can effectively reduce environmental interference, improve the accuracy and sensitivity of IHNV virus detection, and meet the needs of fast and reliable on-site detection by real-time correction of fluorescence signal changes and combining environmental characteristic data. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes a RAA constant temperature fluorescence data analysis method for IHNV virus detection.

[0007] The first aspect of the present invention provides a RAA constant temperature fluorescence data analysis method for IHNV virus detection, comprising:

[0008] Obtaining fluorescence signal change data and standard fluorescence signal change data of RAA constant temperature fluorescence detection of IHNV virus samples under various environmental characteristics, determining the signal drift influence of each environmental characteristic on the fluorescence signal change data according to the fluorescence signal change data and the standard fluorescence signal change data under various environmental characteristics, and obtaining signal drift influence data;

[0009] Determine the accuracy of IHNV virus detection using the fluorescence signal change data under each environmental feature according to the signal drift influence data, perform correction operations on the fluorescence signal change data according to the accuracy, and determine correction parameters for the fluorescence signal change data obtained under each environmental feature;

[0010] Constructing a fluorescence signal correction model according to the correction parameters, obtaining real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection in real time, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model for data correction, and obtaining corrected fluorescence signal change data;

[0011] Feature extraction is performed on the corrected fluorescence signal change data to obtain fluorescence signal change features, and the infection status of the IHNV virus is determined according to the fluorescence signal change features.

[0012] In this scheme, the fluorescence signal change data and standard fluorescence signal change data of the IHNV virus sample subjected to RAA constant temperature fluorescence detection under various environmental characteristics are obtained, and the signal drift influence of each environmental characteristic on the fluorescence signal change data is determined according to the fluorescence signal change data under various environmental characteristics and the standard fluorescence signal change data, and the signal drift influence data is obtained, specifically:

[0013] Obtaining fluorescence signal change data of IHNV virus samples with different virus contents subjected to RAA constant temperature fluorescence detection under various environmental characteristics, wherein the environmental characteristics include temperature, humidity, and light intensity;

[0014] Obtain standard fluorescence signal change data for IHNV virus detection at different virus contents;

[0015] Dividing the fluorescence signal change data and the standard fluorescence signal change data under each environmental feature into a plurality of fluorescence signal change data segments according to a preset time step, to obtain fluorescence signal change data segments and standard fluorescence signal change data segments;

[0016] Aligning the fluorescence signal change data segment and the standard fluorescence signal change data segment according to the timestamps, and calculating the Euclidean distance between the fluorescence signal change data segment and the standard fluorescence signal change data segment with the same timestamp;

[0017] Evaluate the difference between each fluorescence signal change data segment and the standard fluorescence signal change data segment according to the Euclidean distance, and determine the degree of signal data segment drift between the fluorescence signal change data segment and the standard fluorescence signal change data segment according to the difference;

[0018] The comprehensive signal drift degree of the fluorescence signal change data under each environmental feature is calculated according to the drift degree of the signal data segment, and the correlation analysis is performed between the comprehensive signal drift degree and each environmental feature to determine the signal drift influence of each environmental feature on the fluorescence signal change data, and obtain the signal drift influence data.

[0019] In this scheme, the accuracy of IHNV virus detection is determined by determining the fluorescence signal change data under each environmental feature according to the signal drift influence data, and the correction operation is performed on the fluorescence signal change data according to the accuracy to determine the correction parameters of the fluorescence signal change data obtained under each environmental feature, specifically:

[0020] Determine the accuracy of IHNV virus detection by the fluorescence signal change data with different drift degrees under each environmental feature according to the signal drift influence data, mark the environmental features and fluorescence signal change data whose accuracy is less than a preset value, and form a one-to-one correspondence between the marked environmental features and the corresponding fluorescence signal change data to obtain the environmental feature-fluorescence signal change data to be corrected;

[0021] Calculating the change in slope of the curve of the to-be-corrected environmental feature-fluorescence signal change data and the standard fluorescence signal change data to obtain a to-be-corrected slope change feature and a standard slope change feature;

[0022] Calculate the difference change of the intercept between the environmental feature to be corrected-fluorescence signal change data and the standard fluorescence signal change data to obtain the intercept difference change feature;

[0023] According to the slope change characteristics to be corrected, the standard slope change characteristics, and the intercept difference change characteristics, a curve fitting operation is performed on the environmental characteristic-fluorescence signal change data to be corrected and the standard fluorescence signal change data to determine the slope correction coefficient and intercept correction coefficient of the curve of the environmental characteristic-fluorescence signal change data to be corrected, and the correction parameters of the fluorescence signal change data obtained under each environmental characteristic are obtained.

[0024] In this scheme, the fluorescence signal correction model is constructed according to the correction parameters, the real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection are obtained in real time, and the real-time environmental characteristics and real-time fluorescence signal change data are imported into the fluorescence signal correction model for data correction to obtain the corrected fluorescence signal change data, specifically:

[0025] Constructing a fluorescence signal correction model based on a multivariate linear regression algorithm, importing the correction parameters into the fluorescence signal correction model for training, and determining the model parameters for correcting the fluorescence signal data under each environmental feature, wherein the model parameters include regression coefficients;

[0026] Real-time acquisition of real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model, and determining the real-time correction parameters of the real-time fluorescence signal change data under the real-time environmental characteristics;

[0027] The real-time fluorescence signal change data is corrected according to the real-time correction parameters to obtain corrected fluorescence signal change data.

[0028] In this solution, the feature extraction of the corrected fluorescence signal change data is performed to obtain the fluorescence signal change feature, and the infection state of the IHNV virus is determined according to the fluorescence signal change feature, specifically:

[0029] Based on the wavelet basis function, the standard fluorescence signal change data is decomposed at multiple scales to obtain low-frequency approximate signals and high-frequency detail signals.

[0030] For the low-frequency approximate signal, calculating the slope change and local extreme value points of the low-frequency approximate signal at different time points, and determining the change characteristics of the low-frequency approximate signal according to the slope change and local extreme value points;

[0031] Analyzing the high-frequency detail signal, determining the frequency band variation characteristics of the high-frequency detail signal, and obtaining the high-frequency detail signal variation characteristics;

[0032] Obtaining the effect data of IHNV virus nucleic acid amplification on the change of the fluorescence signal, and determining the IHNV virus nucleic acid amplification state of the standard fluorescence signal change data at each time point according to the change effect data;

[0033] The low-frequency approximate signal change characteristics, the high-frequency detail signal change characteristics and the IHNV virus nucleic acid amplification state at each time point are correlated and analyzed to determine the influence of the IHNV virus on the low-frequency approximate signal change characteristics and the high-frequency detail signal change characteristics in different nucleic acid amplification states, and obtain nucleic acid amplification state-fluorescence signal change characteristic data;

[0034] Extracting features of the corrected fluorescence signal change data to obtain fluorescence signal change features, wherein the fluorescence signal change features include low-frequency approximate signal change features and high-frequency detail signal change features;

[0035] The fluorescence signal change characteristics are analyzed according to the nucleic acid amplification status-fluorescence signal change characteristic data to determine the infection status of the IHNV virus in the IHNV virus sample to be detected.

[0036] In this solution, the fluorescence signal change characteristics are analyzed according to the nucleic acid amplification state-fluorescence signal change characteristic data to determine the infection state of the IHNV virus in the IHNV virus sample to be detected, specifically:

[0037] Constructing an IHNV virus infection state recognition model based on a hidden Markov algorithm, converting the nucleic acid amplification state-fluorescence signal change characteristic data into a feature vector and importing it into the IHNV virus infection state recognition model for training, and determining the IHNV virus infection state recognition model parameters, wherein the recognition model parameters include a transition probability matrix, an emission probability matrix, and an initial state probability vector;

[0038] Importing the fluorescence signal change characteristics into the IHNV virus infection state recognition model, calculating the hidden state sequence of the fluorescence signal change characteristics, and determining the viral nucleic acid amplification state of the IHNV virus sample to be detected according to the hidden state sequence;

[0039] The infection status of the IHNV virus in the IHNV virus sample to be detected is determined according to the viral nucleic acid amplification status.

[0040] The second aspect of the present invention also provides a RAA constant temperature fluorescence data analysis system for IHNV virus detection, the system comprising: a memory, a processor, the memory comprising a RAA constant temperature fluorescence data analysis method program for IHNV virus detection, and when the RAA constant temperature fluorescence data analysis method program for IHNV virus detection is executed by the processor, the following steps are implemented:

[0041] Obtaining fluorescence signal change data and standard fluorescence signal change data of RAA constant temperature fluorescence detection of IHNV virus samples under various environmental characteristics, determining the signal drift influence of each environmental characteristic on the fluorescence signal change data according to the fluorescence signal change data and the standard fluorescence signal change data under various environmental characteristics, and obtaining signal drift influence data;

[0042] Determine the accuracy of IHNV virus detection using the fluorescence signal change data under each environmental feature according to the signal drift influence data, perform correction operations on the fluorescence signal change data according to the accuracy, and determine correction parameters for the fluorescence signal change data obtained under each environmental feature;

[0043] Constructing a fluorescence signal correction model according to the correction parameters, obtaining real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection in real time, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model for data correction, and obtaining corrected fluorescence signal change data;

[0044] Feature extraction is performed on the corrected fluorescence signal change data to obtain fluorescence signal change features, and the infection status of the IHNV virus is determined according to the fluorescence signal change features.

[0045] The present invention discloses a RAA constant temperature fluorescence data analysis method for IHNV virus detection. The method obtains the fluorescence signal change data under different environmental conditions and compares it with the standard data to analyze the influence of environmental characteristics on signal drift. The signal accuracy is evaluated according to the drift impact data and corrected. Then, a fluorescence signal correction model is constructed to obtain the environmental characteristics and fluorescence signal data of the sample to be detected in real time, and accurate fluorescence signal change data is obtained through model correction. Finally, by extracting features from the correction data, it is determined whether the sample is infected with the IHNV virus. This method can effectively improve the accuracy and reliability of virus detection, eliminate interference from environmental factors, and is widely applicable to the fields of aquaculture and virus monitoring, providing effective support for the rapid detection of IHNV virus. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flow chart of a RAA constant temperature fluorescence data analysis method for IHNV virus detection according to the present invention is shown;

[0047] Figure 2 The flow chart of obtaining the corrected fluorescence signal change data of the present invention is shown;

[0048] Figure 3 A flow chart of determining the infection status of an IHNV virus in a sample to be tested for the IHNV virus according to the present invention is shown;

[0049] Figure 4 A block diagram of a RAA constant temperature fluorescence data analysis system for IHNV virus detection according to the present invention is shown. DETAILED DESCRIPTION

[0050] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0052] Figure 1 A flow chart of a RAA constant temperature fluorescence data analysis method for IHNV virus detection according to the present invention is shown.

[0053] like Figure 1 As shown, the first aspect of the present invention provides a RAA constant temperature fluorescence data analysis method for IHNV virus detection, comprising:

[0054] S102, obtaining fluorescence signal change data and standard fluorescence signal change data of RAA constant temperature fluorescence detection of IHNV virus samples under various environmental characteristics, and determining the signal drift influence of each environmental characteristic on the fluorescence signal change data according to the fluorescence signal change data and the standard fluorescence signal change data under various environmental characteristics, to obtain signal drift influence data;

[0055] S104, determining the accuracy of IHNV virus detection using the fluorescence signal change data under each environmental feature according to the signal drift influence data, performing a correction operation on the fluorescence signal change data according to the accuracy, and determining correction parameters for the fluorescence signal change data obtained under each environmental feature;

[0056] S106, constructing a fluorescence signal correction model according to the correction parameters, obtaining real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection in real time, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model for data correction, and obtaining corrected fluorescence signal change data;

[0057] S108, performing feature extraction on the corrected fluorescence signal change data to obtain fluorescence signal change features, and determining the infection status of the IHNV virus according to the fluorescence signal change features.

[0058] It should be noted that by accurately obtaining the fluorescence signal change data of IHNV virus samples under different environmental characteristics and comparing them with the standard signal, the impact of environmental factors on the fluorescence signal can be identified and quantified in real time, significantly improving the signal stability during the detection process. By analyzing the signal drift data, this method can accurately evaluate the impact of environmental factors on detection accuracy, automatically correct the fluorescence signal, and ensure that reliable detection results can be obtained even under environmental changes. At the same time, combined with the feature extraction of the corrected fluorescence signal data, the infection status of the IHNV virus can be accurately identified, greatly improving the sensitivity and accuracy of the detection, which is particularly suitable for rapid and accurate detection of IHNV virus infection on site, reducing false negative or false positive results caused by environmental interference.

[0059] According to an embodiment of the present invention, the fluorescence signal change data and standard fluorescence signal change data of the IHNV virus sample subjected to RAA constant temperature fluorescence detection under various environmental characteristics are obtained, and the signal drift influence of each environmental characteristic on the fluorescence signal change data is determined according to the fluorescence signal change data under various environmental characteristics and the standard fluorescence signal change data, and the signal drift influence data is obtained, specifically:

[0060] Obtaining fluorescence signal change data of IHNV virus samples with different virus contents subjected to RAA constant temperature fluorescence detection under various environmental characteristics, wherein the environmental characteristics include temperature, humidity, and light intensity;

[0061] Obtain standard fluorescence signal change data for IHNV virus detection at different virus contents;

[0062] Dividing the fluorescence signal change data and the standard fluorescence signal change data under each environmental feature into a plurality of fluorescence signal change data segments according to a preset time step, to obtain fluorescence signal change data segments and standard fluorescence signal change data segments;

[0063] Aligning the fluorescence signal change data segment and the standard fluorescence signal change data segment according to the timestamps, and calculating the Euclidean distance between the fluorescence signal change data segment and the standard fluorescence signal change data segment with the same timestamp;

[0064] Evaluate the difference between each fluorescence signal change data segment and the standard fluorescence signal change data segment according to the Euclidean distance, and determine the degree of signal data segment drift between the fluorescence signal change data segment and the standard fluorescence signal change data segment according to the difference;

[0065] The comprehensive signal drift degree of the fluorescence signal change data under each environmental feature is calculated according to the drift degree of the signal data segment, and the correlation analysis is performed between the comprehensive signal drift degree and each environmental feature to determine the signal drift influence of each environmental feature on the fluorescence signal change data, and obtain the signal drift influence data.

[0066] It should be noted that by obtaining the fluorescence signal change data and standard fluorescence signal change data of IHNV virus samples with different virus contents under environmental characteristics such as temperature, humidity, and light intensity, and dividing the data segments according to the preset time step, and calculating the Euclidean distance based on timestamp alignment, it is possible to accurately quantify the specific impact of environmental factors on the fluorescence signal change data at different times and virus contents, and avoid the inaccuracy of general evaluation. Secondly, by evaluating the difference of data segments based on the Euclidean distance to determine the degree of drift of the signal data segment, the specific conditions such as the direction and amplitude of the signal drift in each time period under different environmental characteristics can be clearly known, such as the drift direction and size of the signal in a certain period of time in a high humidity environment, providing a detailed basis for subsequent analysis. Furthermore, the correlation analysis of the comprehensive signal drift degree and each environmental feature is carried out to determine its signal drift influence on the fluorescence signal change data, which can clarify the degree and key factors of the drift influence of each environmental factor on the fluorescence signal, such as knowing the specific relationship between temperature change and fluorescence signal drift and the relative stability influence of humidity in a certain interval. The temperature is a different constant temperature interval.

[0067] According to an embodiment of the present invention, the accuracy of IHNV virus detection is determined by determining the fluorescence signal change data under each environmental feature according to the signal drift influence data, and the correction operation is performed on the fluorescence signal change data according to the accuracy to determine the correction parameters of the fluorescence signal change data obtained under each environmental feature, specifically:

[0068] Determine the accuracy of IHNV virus detection by the fluorescence signal change data with different drift degrees under each environmental feature according to the signal drift influence data, mark the environmental features and fluorescence signal change data whose accuracy is less than a preset value, and form a one-to-one correspondence between the marked environmental features and the corresponding fluorescence signal change data to obtain the environmental feature-fluorescence signal change data to be corrected;

[0069] Calculating the change in slope of the curve of the to-be-corrected environmental feature-fluorescence signal change data and the standard fluorescence signal change data to obtain a to-be-corrected slope change feature and a standard slope change feature;

[0070] Calculate the difference change of the intercept between the environmental feature to be corrected-fluorescence signal change data and the standard fluorescence signal change data to obtain the intercept difference change feature;

[0071] According to the slope change characteristics to be corrected, the standard slope change characteristics, and the intercept difference change characteristics, a curve fitting operation is performed on the environmental characteristic-fluorescence signal change data to be corrected and the standard fluorescence signal change data to determine the slope correction coefficient and intercept correction coefficient of the curve of the environmental characteristic-fluorescence signal change data to be corrected, and the correction parameters of the fluorescence signal change data obtained under each environmental characteristic are obtained.

[0072] It should be noted that by determining the accuracy of the fluorescence signal change data with different drift degrees under each environmental feature in IHNV virus detection based on the signal drift influence data, and marking the environmental features and fluorescence signal change data whose accuracy is less than the preset value, the environmental feature-fluorescence signal change data to be corrected is formed, which can accurately screen out the fluorescence signal data that may cause inaccurate detection due to interference from environmental factors, thereby improving the pertinence and efficiency of the correction; the slope change of the curve of the environmental feature-fluorescence signal change data to be corrected and the standard fluorescence signal change data and the difference change of the intercept are calculated to obtain the slope change characteristics to be corrected, the standard slope change characteristics and the intercept difference change characteristics, which can determine the difference in curve morphology between the fluorescence signal data affected by environmental interference and the standard data. For example, the slope change characteristic can reflect the difference in the rate of change of the fluorescence signal over time or the detection process, and the intercept difference change characteristic reflects the degree of deviation of the signal starting point or the overall level; based on the above-mentioned slope change characteristic to be corrected, the standard slope change characteristic and the intercept difference change characteristic, the environmental characteristic-fluorescence signal change data to be corrected and the standard fluorescence signal change data are subjected to curve fitting operation, and the curve slope correction coefficient and the intercept correction coefficient are determined as correction parameters. Through these correction parameters, the fluorescence signal curve can be stretched, translated or deformed in a targeted manner, so that the corrected fluorescence signal change data can restore the signal change trend that should be in an ideal state without environmental interference to the greatest extent, thereby significantly improving the accuracy and reliability of IHNV virus detection results under different environmental conditions, effectively reducing detection errors caused by environmental factors, and ensuring that the detection data can truly reflect the actual situation of the virus.

[0073] Figure 2 A flow chart of obtaining corrected fluorescence signal change data according to the present invention is shown.

[0074] According to an embodiment of the present invention, the fluorescence signal correction model is constructed according to the correction parameters, the real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection are obtained in real time, and the real-time environmental characteristics and real-time fluorescence signal change data are imported into the fluorescence signal correction model for data correction to obtain the corrected fluorescence signal change data, specifically:

[0075] S202, constructing a fluorescence signal correction model based on a multivariate linear regression algorithm, importing the correction parameters into the fluorescence signal correction model for training, and determining model parameters for correcting fluorescence signal data under each environmental feature, wherein the model parameters include regression coefficients;

[0076] S204, real-time acquisition of real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model, and determining real-time correction parameters of the real-time fluorescence signal change data under the real-time environmental characteristics;

[0077] S206, performing data correction on the real-time fluorescence signal change data according to the real-time correction parameters to obtain corrected fluorescence signal change data.

[0078] It should be noted that the fluorescence signal correction model is constructed based on the multivariate linear regression algorithm, and the correction parameters are imported into the training to determine the model parameters such as regression coefficients under each environmental feature, which enables the model to be accurately constructed according to the inherent correlation between different environmental features and fluorescence signal changes. Through the learning and parameter determination of a large amount of data, the model has a high degree of adaptability and professionalism for fluorescence signal correction in different environmental scenes, and can effectively handle the influence of complex and changeable environmental factors on the fluorescence signal. Secondly, after obtaining the real-time environmental characteristics and real-time fluorescence signal change data of the RAA constant temperature fluorescence detection of the IHNV virus to be detected in real time, it is imported into the trained model to determine the real-time correction parameters, realizing the instant dynamic correction capability during the detection process. Regardless of how the environmental conditions such as temperature, humidity, and light intensity change during the detection, the model can quickly give appropriate correction parameters based on the real-time data to ensure that the fluorescence signal data of each sample detection can be accurately corrected in its specific real-time environment. Finally, the real-time fluorescence signal change data is corrected according to these real-time correction parameters to obtain the corrected fluorescence signal change data, which effectively eliminates environmental interference factors and greatly improves the accuracy and stability of the fluorescence signal data.

[0079] According to an embodiment of the present invention, the feature extraction of the corrected fluorescence signal change data to obtain the fluorescence signal change feature, and the infection state of the IHNV virus is determined according to the fluorescence signal change feature, specifically:

[0080] Based on the wavelet basis function, the standard fluorescence signal change data is decomposed at multiple scales to obtain low-frequency approximate signals and high-frequency detail signals.

[0081] For the low-frequency approximate signal, calculating the slope change and local extreme value points of the low-frequency approximate signal at different time points, and determining the change characteristics of the low-frequency approximate signal according to the slope change and local extreme value points;

[0082] Analyzing the high-frequency detail signal, determining the frequency band variation characteristics of the high-frequency detail signal, and obtaining the high-frequency detail signal variation characteristics;

[0083] Obtaining the effect data of IHNV virus nucleic acid amplification on the change of the fluorescence signal, and determining the IHNV virus nucleic acid amplification state of the standard fluorescence signal change data at each time point according to the change effect data;

[0084] The low-frequency approximate signal change characteristics, the high-frequency detail signal change characteristics and the IHNV virus nucleic acid amplification state at each time point are correlated and analyzed to determine the influence of the IHNV virus on the low-frequency approximate signal change characteristics and the high-frequency detail signal change characteristics in different nucleic acid amplification states, and obtain nucleic acid amplification state-fluorescence signal change characteristic data;

[0085] Extracting features of the corrected fluorescence signal change data to obtain fluorescence signal change features, wherein the fluorescence signal change features include low-frequency approximate signal change features and high-frequency detail signal change features;

[0086] The fluorescence signal change characteristics are analyzed according to the nucleic acid amplification status-fluorescence signal change characteristic data to determine the infection status of the IHNV virus in the IHNV virus sample to be detected.

[0087] It should be noted that the standard fluorescence signal change data is decomposed at multiple scales based on the wavelet basis function to obtain low-frequency approximate signals and high-frequency detail signals. This decomposition method effectively separates the different frequency components in the signal, so that the signals with different frequency characteristics can be analyzed in depth in the future. For the low-frequency approximate signal, the slope change and local extreme point at different time points are calculated to determine the change characteristics of the low-frequency approximate signal, which can accurately capture the overall trend and key change points of the signal, reflecting the relatively stable and macroscopic change law of the signal. The high-frequency detail signal is analyzed to determine the frequency band change characteristics, which can keenly detect the subtle fluctuations and rapid changes in the signal and dig out the potential features hidden in the high-frequency part. Obtaining the data on the impact of IHNV virus nucleic acid amplification on the change of the fluorescence signal and determining the nucleic acid amplification state of the standard fluorescence signal change data at each time point provides a key biological basis for the association analysis. The low-frequency approximate signal change characteristics, the high-frequency detail signal change characteristics and the nucleic acid amplification state are correlated to obtain the nucleic acid amplification state-fluorescence signal change characteristic data, thereby clearly defining the intrinsic connection between the viral nucleic acid amplification process and the fluorescence signal characteristics, which helps to deeply understand the manifestation of the virus infection process in the fluorescence signal. After extracting the fluorescence signal change characteristics including low-frequency approximate signal change characteristics and high-frequency detail signal change characteristics from the corrected fluorescence signal change data, the infection status of the IHNV virus sample to be tested can be accurately and comprehensively determined based on the nucleic acid amplification state-fluorescence signal change characteristic data; in wavelet transform, the low-frequency approximate signal is an approximate representation of the original signal, which contains the low-frequency component of the signal, that is, the relatively slow-changing part of the signal; the high-frequency detail signal contains the high-frequency component of the original signal, that is, the relatively fast and drastic part of the signal. The viral nucleic acid amplification state includes the start, continue and end states.

[0088] Figure 3 The flowchart of the present invention for determining the infection status of the IHNV virus in a sample to be tested for the IHNV virus is shown.

[0089] According to an embodiment of the present invention, the fluorescence signal change characteristics are analyzed according to the nucleic acid amplification state-fluorescence signal change characteristic data to determine the infection state of the IHNV virus in the IHNV virus to be detected sample, specifically:

[0090] S302, constructing an IHNV virus infection state recognition model based on a hidden Markov algorithm, converting the nucleic acid amplification state-fluorescence signal change characteristic data into a feature vector and importing it into the IHNV virus infection state recognition model for training, and determining the IHNV virus infection state recognition model parameters, wherein the recognition model parameters include a transition probability matrix, an emission probability matrix, and an initial state probability vector;

[0091] S304, importing the fluorescence signal change characteristics into the IHNV virus infection state recognition model, calculating the hidden state sequence of the fluorescence signal change characteristics, and determining the viral nucleic acid amplification state of the IHNV virus sample to be detected according to the hidden state sequence;

[0092] S306, judging the infection status of the IHNV virus of the IHNV virus sample to be detected according to the viral nucleic acid amplification status.

[0093] It should be noted that the viral infection process is a complex dynamic process with many uncertain factors. The hidden Markov algorithm is suitable for dealing with such problems with hidden states and observation sequences. In the IHNV virus infection process, the nucleic acid amplification state is a hidden state, and the fluorescence signal change characteristics are observable sequences. For example, viral nucleic acid amplification may be interfered by various factors and show irregular changes. The hidden Markov algorithm can handle this uncertainty through a probability model, so as to better fit the actual situation of viral infection; the transition probability matrix in the hidden Markov algorithm can describe the transition probability between viral nucleic acid amplification states. In the IHNV virus infection process, viral nucleic acid amplification may gradually increase from a low level, or it may stagnate or fluctuate at a certain stage. The transition probability matrix obtained by training the nucleic acid amplification state-fluorescence signal change feature data can accurately characterize the transition law between such states; the emission probability matrix plays a role in associating the fluorescence signal change characteristics (observation sequence) and the viral nucleic acid amplification state (hidden state) in the model. Different viral nucleic acid amplification states will lead to different fluorescence signal change characteristics. By training a large amount of nucleic acid amplification state-fluorescence signal change feature data, the model can learn the probability of generating specific fluorescence signal change features under various nucleic acid amplification states; the initial state probability vector takes into account various possibilities of IHNV virus infection in the initial stage. Since the viral nucleic acid amplification state may be in different states such as uninfected and early infected at the beginning of the test, the initial state probability vector can give the probability of each initial state according to the actual situation (determined by training data); the transition probability matrix is ​​the probability of an element transferring from one hidden state to another. The emission probability matrix is ​​the probability of an element observing a certain characteristic symbol under a specific hidden state. The initial state probability vector is the probability of the element being in each hidden state at the initial moment; after extracting the feature vector sequence for the fluorescence signal data to be detected, the trained HMM model is used for analysis. The Viterbi algorithm is used to calculate the most likely hidden state sequence. The algorithm uses the idea of ​​dynamic programming to calculate the optimal path from the initial state to the current state (i.e., the hidden state sequence with the maximum probability) at each time point t. According to the obtained hidden state sequence, the starting, continuous and termination states of viral nucleic acid amplification are judged. If the hidden state sequence transitions from start to continue, it means that the viral nucleic acid amplification has begun; if it is in the continuous state for a long time, it means that the amplification is continuing; if it transitions from continue to stop, it means that the amplification has been completed. According to these state judgment results, it is determined whether the sample is infected with IHNV virus. For example, if there is an obvious state transition process from amplification not started to ongoing and then to completed, the sample is determined to be infected with IHNV virus; if it is always in the state of amplification not started or the state transition does not conform to the law of virus amplification, the sample is determined to be uninfected.

[0094] Figure 4 A block diagram of a RAA constant temperature fluorescence data analysis system for IHNV virus detection according to the present invention is shown.

[0095] The second aspect of the present invention further provides a RAA constant temperature fluorescence data analysis system 4 for IHNV virus detection, the system comprising: a memory 41, a processor 42, the memory comprising a RAA constant temperature fluorescence data analysis method program for IHNV virus detection, the RAA constant temperature fluorescence data analysis method program for IHNV virus detection when executed by the processor, implements the following steps:

[0096] Obtaining fluorescence signal change data and standard fluorescence signal change data of RAA constant temperature fluorescence detection of IHNV virus samples under various environmental characteristics, determining the signal drift influence of each environmental characteristic on the fluorescence signal change data according to the fluorescence signal change data and the standard fluorescence signal change data under various environmental characteristics, and obtaining signal drift influence data;

[0097] Determine the accuracy of IHNV virus detection using the fluorescence signal change data under each environmental feature according to the signal drift influence data, perform correction operations on the fluorescence signal change data according to the accuracy, and determine correction parameters for the fluorescence signal change data obtained under each environmental feature;

[0098] Constructing a fluorescence signal correction model according to the correction parameters, obtaining real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection in real time, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model for data correction, and obtaining corrected fluorescence signal change data;

[0099] Feature extraction is performed on the corrected fluorescence signal change data to obtain fluorescence signal change features, and the infection status of the IHNV virus is determined according to the fluorescence signal change features.

[0100] The present invention discloses a RAA constant temperature fluorescence data analysis method for IHNV virus detection. The method obtains the fluorescence signal change data under different environmental conditions and compares it with the standard data to analyze the influence of environmental characteristics on signal drift. The signal accuracy is evaluated according to the drift impact data and corrected. Then, a fluorescence signal correction model is constructed to obtain the environmental characteristics and fluorescence signal data of the sample to be detected in real time, and accurate fluorescence signal change data is obtained through model correction. Finally, by extracting features from the correction data, it is determined whether the sample is infected with the IHNV virus. This method can effectively improve the accuracy and reliability of virus detection, eliminate interference from environmental factors, and is widely applicable to the fields of aquaculture and virus monitoring, providing effective support for the rapid detection of IHNV virus.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0102] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0103] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0104] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0105] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0106] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A RAA constant temperature fluorescence data analysis method for IHNV virus detection, characterized in that: The following steps are involved: Obtaining fluorescence signal change data and standard fluorescence signal change data of RAA constant temperature fluorescence detection of IHNV virus samples under various environmental characteristics, determining the signal drift influence of each environmental characteristic on the fluorescence signal change data according to the fluorescence signal change data and the standard fluorescence signal change data under various environmental characteristics, and obtaining signal drift influence data; Determine the accuracy of IHNV virus detection using the fluorescence signal change data under each environmental feature according to the signal drift influence data, perform correction operations on the fluorescence signal change data according to the accuracy, and determine correction parameters for the fluorescence signal change data obtained under each environmental feature; Constructing a fluorescence signal correction model according to the correction parameters, obtaining real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection in real time, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model for data correction, and obtaining corrected fluorescence signal change data; Feature extraction is performed on the corrected fluorescence signal change data to obtain fluorescence signal change features, and the infection status of the IHNV virus is determined according to the fluorescence signal change features.

2. A RAA constant temperature fluorescence data analysis method for IHNV virus detection according to claim 1, characterized in that: The fluorescence signal change data and standard fluorescence signal change data of the IHNV virus sample subjected to RAA constant temperature fluorescence detection under various environmental characteristics are obtained, and the signal drift influence of each environmental characteristic on the fluorescence signal change data is determined according to the fluorescence signal change data and the standard fluorescence signal change data under various environmental characteristics to obtain the signal drift influence data, specifically: Obtaining fluorescence signal change data of IHNV virus samples with different virus contents subjected to RAA constant temperature fluorescence detection under various environmental characteristics, wherein the environmental characteristics include temperature, humidity, and light intensity; Obtain standard fluorescence signal change data for IHNV virus detection at different virus contents; Dividing the fluorescence signal change data and the standard fluorescence signal change data under each environmental feature into a plurality of fluorescence signal change data segments according to a preset time step, to obtain fluorescence signal change data segments and standard fluorescence signal change data segments; Aligning the fluorescence signal change data segment and the standard fluorescence signal change data segment according to the timestamps, and calculating the Euclidean distance between the fluorescence signal change data segment and the standard fluorescence signal change data segment with the same timestamp; Evaluate the difference between each fluorescence signal change data segment and the standard fluorescence signal change data segment according to the Euclidean distance, and determine the degree of signal data segment drift between the fluorescence signal change data segment and the standard fluorescence signal change data segment according to the difference; The comprehensive signal drift degree of the fluorescence signal change data under each environmental feature is calculated according to the drift degree of the signal data segment, and the correlation analysis is performed between the comprehensive signal drift degree and each environmental feature to determine the signal drift influence of each environmental feature on the fluorescence signal change data, and obtain the signal drift influence data.

3. A RAA constant temperature fluorescence data analysis method for IHNV virus detection according to claim 1, characterized in that: The accuracy of IHNV virus detection is determined according to the signal drift influence data by the fluorescence signal change data under each environmental feature, and the correction operation is performed on the fluorescence signal change data according to the accuracy to determine the correction parameters of the fluorescence signal change data obtained under each environmental feature, specifically: Determine the accuracy of IHNV virus detection by the fluorescence signal change data with different drift degrees under each environmental feature according to the signal drift influence data, mark the environmental features and fluorescence signal change data whose accuracy is less than a preset value, and form a one-to-one correspondence between the marked environmental features and the corresponding fluorescence signal change data to obtain the environmental feature-fluorescence signal change data to be corrected; Calculating the change in slope of the curve of the to-be-corrected environmental feature-fluorescence signal change data and the standard fluorescence signal change data to obtain a to-be-corrected slope change feature and a standard slope change feature; Calculate the difference change of the intercept between the environmental feature to be corrected-fluorescence signal change data and the standard fluorescence signal change data to obtain the intercept difference change feature; According to the slope change characteristics to be corrected, the standard slope change characteristics, and the intercept difference change characteristics, a curve fitting operation is performed on the environmental characteristic-fluorescence signal change data to be corrected and the standard fluorescence signal change data to determine the slope correction coefficient and intercept correction coefficient of the curve of the environmental characteristic-fluorescence signal change data to be corrected, and the correction parameters of the fluorescence signal change data obtained under each environmental characteristic are obtained.

4. The RAA constant temperature fluorescence data analysis method for IHNV virus detection according to claim 1, characterized in that: The fluorescent signal correction model is constructed according to the correction parameters, and the real-time environmental characteristics and real-time fluorescent signal change data of the sample to be detected of the I HNV virus are obtained in real time for RAA constant temperature fluorescent detection, and the real-time environmental characteristics and real-time fluorescent signal change data are imported into the fluorescent signal correction model for data correction to obtain the corrected fluorescent signal change data, specifically: Constructing a fluorescence signal correction model based on a multivariate linear regression algorithm, importing the correction parameters into the fluorescence signal correction model for training, and determining the model parameters for correcting the fluorescence signal data under each environmental feature, wherein the model parameters include regression coefficients; Real-time acquisition of real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model, and determining the real-time correction parameters of the real-time fluorescence signal change data under the real-time environmental characteristics; The real-time fluorescence signal change data is corrected according to the real-time correction parameters to obtain corrected fluorescence signal change data.

5. The RAA constant temperature fluorescence data analysis method for IHNV virus detection according to claim 1, characterized in that: The feature extraction of the corrected fluorescence signal change data is performed to obtain the fluorescence signal change feature, and the infection state of the IHNV virus is determined according to the fluorescence signal change feature, specifically: Based on the wavelet basis function, the standard fluorescence signal change data is decomposed at multiple scales to obtain low-frequency approximate signals and high-frequency detail signals. For the low-frequency approximate signal, calculating the slope change and local extreme value points of the low-frequency approximate signal at different time points, and determining the change characteristics of the low-frequency approximate signal according to the slope change and local extreme value points; Analyzing the high-frequency detail signal, determining the frequency band variation characteristics of the high-frequency detail signal, and obtaining the high-frequency detail signal variation characteristics; Obtaining the effect data of IHNV virus nucleic acid amplification on the change of the fluorescence signal, and determining the IHNV virus nucleic acid amplification state of the standard fluorescence signal change data at each time point according to the change effect data; The low-frequency approximate signal change characteristics, the high-frequency detail signal change characteristics and the IHNV virus nucleic acid amplification state at each time point are correlated and analyzed to determine the influence of the IHNV virus on the low-frequency approximate signal change characteristics and the high-frequency detail signal change characteristics in different nucleic acid amplification states, and obtain nucleic acid amplification state-fluorescence signal change characteristic data; Extracting features of the corrected fluorescence signal change data to obtain fluorescence signal change features, wherein the fluorescence signal change features include low-frequency approximate signal change features and high-frequency detail signal change features; The fluorescence signal change characteristics are analyzed according to the nucleic acid amplification status-fluorescence signal change characteristic data to determine the infection status of the IHNV virus in the IHNV virus sample to be detected.

6. A RAA constant temperature fluorescence data analysis method for IHNV virus detection according to claim 5, characterized in that: The analysis of the fluorescence signal change characteristics according to the nucleic acid amplification state-fluorescence signal change characteristic data to determine the infection state of the IHNV virus in the IHNV virus to be detected sample is specifically: Constructing an IHNV virus infection state recognition model based on a hidden Markov algorithm, converting the nucleic acid amplification state-fluorescence signal change characteristic data into a feature vector and importing it into the IHNV virus infection state recognition model for training, and determining the IHNV virus infection state recognition model parameters, wherein the recognition model parameters include a transition probability matrix, an emission probability matrix, and an initial state probability vector; Importing the fluorescence signal change characteristics into the IHNV virus infection state recognition model, calculating the hidden state sequence of the fluorescence signal change characteristics, and determining the viral nucleic acid amplification state of the IHNV virus sample to be detected according to the hidden state sequence; The infection status of the IHNV virus in the IHNV virus sample to be detected is determined according to the viral nucleic acid amplification status.

7. A RAA constant temperature fluorescence data analysis system for IHNV virus detection, characterized in that: The RAA constant temperature fluorescence data analysis system for IHNV virus detection includes a storage device and a processor, wherein the storage device includes a RAA constant temperature fluorescence data analysis method program for IHNV virus detection, and when the RAA constant temperature fluorescence data analysis method program for IHNV virus detection is executed by the processor, the following steps are implemented: Obtaining fluorescence signal change data and standard fluorescence signal change data of RAA constant temperature fluorescence detection of IHNV virus samples under various environmental characteristics, determining the signal drift influence of each environmental characteristic on the fluorescence signal change data according to the fluorescence signal change data and the standard fluorescence signal change data under various environmental characteristics, and obtaining signal drift influence data; Determine the accuracy of IHNV virus detection using the fluorescence signal change data under each environmental feature according to the signal drift influence data, perform correction operations on the fluorescence signal change data according to the accuracy, and determine correction parameters for the fluorescence signal change data obtained under each environmental feature; Constructing a fluorescence signal correction model according to the correction parameters, obtaining real-time environmental characteristics and real-time fluorescence signal change data of the IHNV virus to be detected sample for RAA constant temperature fluorescence detection in real time, importing the real-time environmental characteristics and real-time fluorescence signal change data into the fluorescence signal correction model for data correction, and obtaining corrected fluorescence signal change data; Feature extraction is performed on the corrected fluorescence signal change data to obtain fluorescence signal change features, and the infection status of the IHNV virus is determined according to the fluorescence signal change features.

Images