Newborn disease dynamic monitoring system based on phenotype and gene correlation analysis

Abstract

The invention relates to the field of disease detection, in particular to a newborn disease dynamic monitoring system based on phenotype and gene correlation analysis, which comprises a phenotype data acquisition module, a gene data acquisition module, a cell metabolism data acquisition module, a correlation analysis module, an early warning module and a man-machine interaction module, the phenotype data acquisition module is used for acquiring various phenotype data of the newborn; the gene data acquisition module is used for acquiring gene data of the newborn; the cell metabolism data acquisition module is used for acquiring various cell metabolism data of the newborn; the correlation analysis module is used for outputting disease risk indexes; the early warning module is used for monitoring disease risk indexes in real time; and the man-machine interaction module is used for displaying various acquired data and disease risk indexes of various diseases. According to the method, the stability of cell metabolism is considered in the calculation of the disease risk index, so that the disease risk can be reflected more accurately and comprehensively through the disease risk index.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of disease monitoring, and in particular to a neonatal disease dynamic monitoring system based on phenotype and gene correlation analysis. BACKGROUND

[0002] The neonatal period is a critical stage of human growth and development. Early detection and intervention of many congenital diseases, genetic metabolic diseases or other major health problems during this period can significantly reduce the rate of disability and mortality. Currently, the monitoring of neonatal diseases mainly includes traditional clinical sign monitoring and genetic testing technology.

[0003] The prior art such as CN118412134A discloses a neonatal neurological development monitoring method and system. The method comprises the following steps: based on a prediction model, the probability of fetal placental methylmercury causing neurological damage to the newborn is predicted; wherein the independent variables of the prediction model include: based on the methylmercury in the placenta, the mother's age, the mother's nationality, the mother's dietary intake frequency of fresh aquatic products, the mother's condition of installing false teeth during pregnancy, the father's genetic history, the family genetic disease history, the father's smoking condition, occupational mercury exposure, the newborn's 1-minute Apgar score, the newborn's congenital malformation, the birth season, the placental weight, and the probability of the newborn having a neurological development disorder is predicted.

[0004] The disease detection technology of the prior art generally pays more attention to phenotype data or gene data, and less attention to the influence of cell metabolism on the above two. In order to solve the problems existing in the field, the present application is made. SUMMARY

[0005] The present application aims to overcome the deficiencies of the prior art and provides a neonatal disease dynamic monitoring system based on phenotype and gene correlation analysis.

[0006] In order to overcome the deficiencies of the prior art, the present application adopts the following technical solutions: The application discloses a neonatal disease dynamic monitoring system based on phenotype and gene correlation analysis, which comprises a phenotype data acquisition module, a gene data acquisition module, a cell metabolism data acquisition module, a correlation analysis module, a warning module and a man-machine interaction module, wherein the phenotype data acquisition module is used for acquiring various phenotype data of a neonate and providing real-time phenotype data support; the gene data acquisition module is used for acquiring gene data of the neonate; the cell metabolism data acquisition module is used for acquiring various cell metabolism data of the neonate; the correlation analysis module is used for classifying and extracting features of the data acquired by the phenotype data acquisition module, the gene data acquisition module and the cell metabolism data acquisition module, and performing disease risk analysis by combining the phenotype data, the gene data and the cell metabolism data after feature extraction; the warning module is used for monitoring the disease risk in real time, generating an alarm signal when the disease risk is high and sending the alarm signal to the man-machine interaction module; and the man-machine interaction module is used for displaying various acquisition data and disease risks of various diseases to medical staff and management personnel and displaying the alarm signal when needed.

[0007] Further, the phenotype data acquisition module comprises a physical sign acquisition unit and a neonate room data interface unit, the physical sign acquisition unit is used for acquiring physical sign information of the neonate, and the neonate room data interface unit is used for receiving various data output by a neonate room.

[0008] Further, the gene data acquisition module comprises a gene sequencing unit and a data preprocessing unit, the gene sequencing unit is used for sequencing a whole genome, an exon group or a target gene region of the neonate, and the data preprocessing unit is used for quality control, alignment, annotation and standardization processing of original gene data.

[0009] Further, the correlation analysis module comprises a data fusion unit, a feature extraction unit and a risk calculation unit, the data fusion unit is used for time sequence alignment and classification of the phenotype data, the gene data and the cell metabolism data, the feature extraction unit is used for extracting required phenotype features, gene data and cell metabolism data from the classified data, and the risk calculation unit is used for calculating disease risk indexes of various diseases of the neonate according to the extracted features.

[0010] Further, the warning module comprises a storage unit and an alarm signal generation unit, the storage unit is used for storing various disease risk indexes generated by the correlation analysis module, and the alarm signal generation unit is used for comparing the disease risk indexes with a disease risk index threshold value, generating an alarm signal when the disease risk indexes are greater than the disease risk index threshold value and sending the alarm signal to the man-machine interaction module.

[0011] Further, the working process of the system comprises the following steps: S1, the phenotype data acquisition module collects various phenotype data of the newborn, the cell metabolism data acquisition module collects cell metabolism data of the newborn, and the gene data acquisition module acquires gene data of the newborn; S2, the correlation analysis module performs data classification, feature extraction and risk analysis on the phenotype data, the gene data and the cell metabolism data, and outputs disease risk indexes of various diseases of the newborn; S3, the early warning module monitors the disease risk indexes of various diseases in real time, and generates an alarm signal and sends it to the human-computer interaction module when the disease risk index is greater than the corresponding disease risk index threshold; S4, the human-computer interaction module displays various collected data and disease risk indexes of various diseases, and displays the alarm signal when needed.

[0012] The beneficial effects obtained by the present application are: 1. On the basis of combining phenotype data and gene data to judge disease risk, by considering the stability of cell metabolism in the calculation of disease risk indexes, it is beneficial to more accurately and comprehensively reflect disease risk through disease risk indexes.

[0013] 2. By using logarithmic form to reflect the stability of cell metabolism in the process of calculating the indexes, the contribution of ZB to the logarithm is avoided when the content in the logarithm is too large. BRIEF DESCRIPTION OF DRAWINGS

[0014] The present application can be further understood from the following description in conjunction with the accompanying drawings. The components in the drawings are not necessarily drawn to scale, but the emphasis is placed on showing the principles of the embodiments. In different views, the same reference numerals designate the same parts.

[0015] Figure 1 It is a structural schematic diagram of the present application.

[0016] Figure 2 It is a structural diagram of the correlation analysis module of the present application.

[0017] Figure 3 It is a workflow diagram of the present application.

[0018] Figure 4 It is a relationship diagram of the synchronization rate of phenotype data a and gene data b and the number of groups in which the phenotype data a and the gene data b in the past data simultaneously exceed their corresponding normal ranges. DETAILED DESCRIPTION

[0019] The following embodiments are illustrative of the present application and do not limit the scope of the application described in this disclosure. Any conclusions drawn in these embodiments are inappropriately limited and should not be construed as a limitation on the scope of the application. The present application can be carried out in other different embodiments and its specifics are convered in detail in the following embodiments without departing from the spirit of the present application. In addition, the drawings of the present application are only simple schematic illustrations and are not actual size depictions, as previously stated. The following embodiments will further illustrate the relevant technical content of the present application, but the disclosed content is not intended to limit the scope of protection of the present application.

[0020] Embodiment one: according to Figure 1 , Figure 2 , Figure 3 and Figure 4 , the present embodiment provides a newborn disease dynamic monitoring system based on phenotype and gene association analysis, comprising a phenotype data acquisition module, a gene data acquisition module, a cell metabolism data acquisition module, an association analysis module, a warning module and a man-machine interaction module, the phenotype data acquisition module is used to acquire various phenotype data of the newborn, and real-time phenotype data support is provided; the gene data acquisition module is used to acquire the gene data of the newborn; the cell metabolism data acquisition module is used to acquire various cell metabolism data of the newborn; the association analysis module is used to classify and extract features of the data acquired by the phenotype data acquisition module, the gene data acquisition module and the cell metabolism data acquisition module, and combine the phenotype data, the gene data and the cell metabolism data after feature extraction to analyze the disease risk; the warning module is used to monitor the disease risk in real time and generate an alarm signal when the disease risk is high and send it to the man-machine interaction module, the man-machine interaction module is used to display various acquisition data and disease risks of various diseases to medical staff and management personnel, and display the alarm signal when needed.

[0021] Further, the phenotype data acquisition module comprises a physical sign acquisition unit and a newborn room data interface unit, the physical sign acquisition unit acquires physical sign information of the newborn, and the newborn room data interface unit is used to receive various data output by the newborn room.

[0022] Specifically, the physical sign information includes but is not limited to weight, jaundice degree, respiratory rate, heart rate, skin color, etc.; the data received by the newborn room data interface unit includes but is not limited to metabolite concentration, blood gas analysis data, etc.

[0023] Further, the gene data acquisition module comprises a gene sequencing unit and a data preprocessing unit, the gene sequencing unit is used for sequencing the whole genome, exome or target gene region of the newborn; the data preprocessing unit is used for quality control, alignment, annotation and standardization processing of the original gene data.

[0024] Further, the correlation analysis module comprises a data fusion unit, a feature extraction unit and a risk calculation unit, the data fusion unit is used for time sequence alignment and classification of phenotype data, gene data and cell metabolism data; the feature extraction unit is used for extracting required phenotype features, gene data and cell metabolism data from the classified data, and the risk calculation unit is used for calculating disease risk indexes of various diseases of the newborn according to the extracted features.

[0025] Further, the early warning module comprises a storage unit and an alarm signal generation unit, the storage unit is used for storing various disease risk indexes generated by the correlation analysis module, and the alarm signal generation unit is used for comparing the disease risk indexes with a disease risk index threshold value and generating an alarm signal and sending it to the man-machine interaction module when the disease risk indexes are greater than the disease risk index threshold value.

[0026] Further, the workflow of the system comprises the following steps: S1, the phenotype data acquisition module acquires various phenotype data of the newborn, the cell metabolism data acquisition module acquires cell metabolism data of the newborn, and the gene data acquisition module acquires gene data of the newborn; S2, the correlation analysis module classifies, extracts features and analyzes risks of the phenotype data, the gene data and the cell metabolism data, and outputs disease risk indexes of various diseases of the newborn; Specifically, the disease risk index of a certain disease can be calculated according to the following formula:

[0027] ;

[0028] Wherein, ZB is the disease risk index of a certain disease, A is the number of phenotype data related to the disease, is the exceeding degree parameter of the a th phenotype data, used to represent the degree of the phenotype data exceeding its corresponding normal range, is the a th phenotype data value, is the lower limit value of the normal range of the a th phenotype data, is the upper limit value of the normal range of the a th phenotype data, which is set through classification so as to accurately reflect the exceeding degree of the data, is the number of gene data related to the disease, is the exceeding degree parameter of the b th gene data, and its setting method is the same as that of is the lower limit value of the normal range of the b th gene data, is the upper limit value of the normal range of the b th gene data, is the value of the bth gene data, commonly represent the distance of each phenotype data and gene data from its normal range; is the average value of the ATP / ADP ratio of each cell, is the standard deviation of the ATP / ADP ratio of each cell, ATP is adenosine triphosphate, ADP is adenosine diphosphate, ATP and ADP are constantly converted, the larger the ratio, the more conversion, the more active the cell, the cell is preferably peripheral blood mononuclear cells, which are easy to collect and can reflect the overall immune and metabolic activity of the body, and the ATP / ADP can be detected by cell lysis and high performance liquid chromatography, is the coefficient of variation of the oxidative phosphorylation pathway activity (OCR) , which can be obtained by Seahorse XFe and other devices, and is used to characterize the stability of mitochondrial respiration, the larger the coefficient, the worse the stability, is used to jointly characterize the stability of neonatal cell metabolism, and the logarithmic form is used to avoid the contribution of the logarithm to the ZB being too large when the content in the logarithm is too large, and the 1 in the logarithm ensures that the value of the logarithm is greater than 0; in the prior art, only phenotype data and gene data are considered in the prediction of diseases in newborns, and the influence of cell metabolism on disease manifestation is not considered, when the cell energy metabolism is unstable, even if there is a pathogenic mutation, it may not present a phenotype due to the failure of expression process, so that the actual phenotype data cannot correctly reflect the disease risk, at the same time, when the cell energy metabolism is unstable, it may also amplify the influence of certain genes, so that the disease risk is increased, by considering the stability of cell metabolism in the calculation of the disease risk index, the disease risk index can more accurately and comprehensively reflect the disease risk.

[0029] S3, the early warning module monitors the disease risk index of each type of disease in real time and generates an alarm signal when it is greater than the corresponding disease risk index threshold value and sends it to the human-computer interaction module; Specifically, the disease risk index threshold value of the certain type of disease is set by a person skilled in the art according to the minimum value of the disease risk index when the past newborns have diseases.

[0030] S4, the human-computer interaction module displays each item of collected data and the disease risk index of each type of disease, and displays the alarm signal when needed.

[0031] The beneficial effects of the embodiment are: 1. On the basis of judging the disease risk by combining phenotype data and gene data, by considering the stability of cell metabolism in the calculation of the disease risk index, the disease risk index can more accurately and comprehensively reflect the disease risk.

[0032] 2. By using logarithmic form to embody the stability of cell metabolism in the process of calculating the index, the contribution of ZB is avoided when the content in logarithm is too large.

[0033] Embodiment two: this embodiment should be understood as including all the features of any one of the preceding embodiments and further improving on the basis thereof, and further comprising a method for The preferred method for obtaining the coefficient of variation of oxidative phosphorylation pathway activity is as follows: first, the vibrational spectroscopy signal intensity of reduced coenzyme I (NADH), the vibrational spectroscopy signal intensity of flavin adenine dinucleotide (FAD), and the total vibrational spectroscopy signal intensity of neonatal cells (preferably peripheral blood mononuclear cells) are obtained by vibrational spectroscopy metabolic imaging technology; then, the amount of corresponding ions is obtained according to the signal intensity; then, the value of the oxidative phosphorylation pathway activity is calculated according to the ion concentration The value of the oxidative phosphorylation pathway activity is calculated according to the ion concentration The coefficient of variation of the oxidative phosphorylation pathway activity is calculated according to the values of the oxidative phosphorylation pathway activity of different cells The method for calculating the coefficient of variation is known in the art and will not be described in detail here.

[0034] Further, in order to ensure the accuracy and reliability of the data, a series of pretreatment steps will be performed before obtaining the vibrational spectroscopy signal intensity. These steps include but are not limited to: standardizing the samples to ensure that all samples are in consistent conditions before detection; calibrating the detection equipment to reduce the impact of equipment errors on the results; and using the method of taking the average of multiple measurements to reduce random errors.

[0035] Specifically, the amount of corresponding ions is obtained according to the signal intensity. The functional relationship between signal intensity and ion amount can be obtained through experiments and data fitting in advance, and then the corresponding ion amount is obtained according to the signal intensity obtained this time.

[0036] The functional relationship between signal intensity and ion amount can be obtained through experiments and data fitting, which can include the following steps: I. Select a series of standard samples with known ion amounts, use vibrational spectroscopy metabolic imaging technology to detect these standard samples, and record the vibrational spectroscopy signal intensity of each sample; II. Organize the experimental data, including the ion amount of each standard sample and the corresponding vibrational spectroscopy signal intensity; III. Select a suitable function model (such as linear function, polynomial function, exponential function, etc.), take the ion concentration as the independent variable, and the vibrational spectroscopy signal intensity as the dependent variable, and use mathematical statistical software (such as SPSS, MATLAB, etc.) to fit the experimental data; IV. According to the fitting result, select the function model with the highest determination coefficient as the final functional relationship.

[0037] The beneficial effects of the embodiment: the scheme adopts vibrational spectral metabolic imaging technology to obtain OXPHOS, instead of using the traditional way to obtain OXPHOS, compared with the traditional way, without destroying the cells or tissues, which is conducive to realize the continuous observation in vivo, at the same time, the traditional way to obtain OXPHOS is slow, while the vibrational spectral metabolic imaging is faster, which can more efficiently obtain OXPHOS.

[0038] Embodiment three: the embodiment should be understood as containing all the features of any one of the preceding embodiments, and further improving on the basis thereof, further comprising an analysis method of the correlation of phenotype data and gene data, the method judges the correlation of the two by calculating the correlation index of the phenotype data a and the gene data b The correlation index can be calculated according to the following formula:

[0039]

[0040]

[0041] Wherein, is the correlation index of the phenotype data a and the gene data b, is used to jointly represent the stability of the metabolism of the neonatal cells, the logarithmic form is adopted to avoid the excessive contribution of the logarithmic content to ZB when it is too large, and 1 in the logarithm ensures that the value of the logarithm is greater than 0, is the synchronization rate of the phenotype data a and the gene data b, is the fitting parameter of the phenotype data a and the gene data b, is the number of groups of past data used to obtain the correlation index of the phenotype data a and the gene data b, preferably, the detected phenotype data and gene data are taken as a group of data each time, is the number of groups of past data in which the phenotype data a and the gene data b simultaneously exceed the corresponding normal range, is the function of the change of the phenotype data a with the gene data b, which is fitted by the past data with the gene data b as the independent variable and the phenotype data a as the dependent variable, and the final fitting function is the fitting function with the largest determination coefficient in the fitting results obtained by using each fitting model, is the determination coefficient corresponding to the fitting function, and the calculation method of the determination coefficient belongs to the prior art, which will not be described here, is the value of the phenotype data a in the zth group of past data, is the function value obtained by inputting the value of the gene data b in the zth group of past data into , is the minimum value. By setting , the average is realized, and by setting Thus, the smaller the difference between the fitting result and the actual value, the higher the fitting degree of the phenotype data a and the gene data b. By considering the correlation between the phenotype data a and the gene data b, the influence of the gene data on the phenotype data can be determined, and the greater the correlation index, the greater the influence, which is beneficial for medical staff to analyze the cause and the gene expression ability of the newborn according to the correlation index. Meanwhile, by considering the stability of the cell metabolism of the newborn in the calculation, the phenomenon that the gene cannot be normally expressed when the stability is poor can be considered, so as to reduce the corresponding correlation degree.

[0042] As shown in Figure 4 , Figure 4 is a relationship diagram of the synchronization rate of the phenotype data a and the gene data b when Z is 20 and the number of groups in which the phenotype data a and the gene data b simultaneously exceed the corresponding normal range in the past data.

[0043] The beneficial effects of the embodiment are that by considering the correlation between the phenotype data and the gene data, the influence of the gene data on the phenotype data can be determined, and the correlation index is beneficial for medical staff to analyze the cause and the gene expression ability of the newborn.

[0044] The above disclosed content is only a preferred feasible embodiment of the present application, and does not limit the protection scope of the present application, so any equivalent technical changes made according to the content of the specification and drawings of the present application are included in the protection scope of the present application, and furthermore, the elements can be updated as the technology develops. The above units are only examples, and those skilled in the art can design different units according to actual needs when implementing the scheme.

Claims

1. A dynamic monitoring system for neonatal diseases based on phenotypic and gene association analysis, characterized in that, The system includes a phenotypic data acquisition module, a gene data acquisition module, a cell metabolism data acquisition module, a correlation analysis module, an early warning module, and a human-computer interaction module. The phenotypic data acquisition module collects various phenotypic data from newborns, providing real-time phenotypic data support. The gene data acquisition module acquires the gene data of newborns. The cell metabolism data acquisition module acquires various cell metabolism data from newborns. The correlation analysis module classifies and extracts features from the data acquired by the phenotypic data acquisition module, gene data acquisition module, and cell metabolism data acquisition module, and performs disease risk analysis by combining the extracted phenotypic data, gene data, and cell metabolism data. The early warning module monitors disease risk in real time and generates an alarm signal when the disease risk is high, sending it to the human-computer interaction module. The human-computer interaction module displays the collected data and disease risks of various diseases to relevant personnel and displays alarm signals when necessary.

2. The neonatal disease dynamic monitoring system based on phenotypic and gene association analysis according to claim 1, characterized in that, The phenotypic data acquisition module includes a vital sign acquisition unit and a neonatal room data interface unit. The vital sign acquisition unit is used to collect the vital sign information of newborns, and the neonatal room data interface unit is used to receive various data output from the neonatal room.

3. The neonatal disease dynamic monitoring system based on phenotypic and gene association analysis according to claim 1, characterized in that, The gene data acquisition module includes a gene sequencing unit and a data preprocessing unit. The gene sequencing unit is used to sequence the whole genome, exome, or target gene region of a newborn. The data preprocessing unit is used to perform quality control, alignment, annotation, and standardization on the raw gene data.

4. The neonatal disease dynamic monitoring system based on phenotypic and gene association analysis according to claim 1, characterized in that, The correlation analysis module includes a data fusion unit, a feature extraction unit, and a risk calculation unit. The data fusion unit is used to perform time-series alignment and classification of phenotypic data, gene data, and cell metabolism data. The feature extraction unit is used to extract the required phenotypic features, gene data, and cell metabolism data from the classified data. The risk calculation unit is used to calculate disease risk indicators for various neonatal diseases based on the extracted features.

5. A dynamic monitoring system for neonatal diseases based on phenotypic and gene association analysis according to claim 1, characterized in that, The early warning module includes a storage unit and an alarm signal generation unit. The storage unit is used to store various disease risk indicators generated by the correlation analysis module. The alarm signal generation unit is used to compare the disease risk indicators with disease risk indicator thresholds and generate an alarm signal when the disease risk indicator is greater than or equal to the disease risk indicator threshold, and send it to the human-computer interaction module.

6. A dynamic monitoring system for neonatal diseases based on phenotypic and gene association analysis according to claim 1, characterized in that, The system's workflow includes the following steps: S1, the phenotypic data acquisition module collects various phenotypic data of newborns, the cell metabolism data acquisition module collects cell metabolism data of newborns, and the gene data acquisition module acquires gene data of newborns. S2, the association analysis module performs data classification, feature extraction and risk analysis on phenotypic data, gene data and cell metabolism data, and outputs disease risk indicators for various neonatal diseases; S3, the early warning module monitors the disease risk indicators of various diseases in real time and generates an alarm signal when the indicators exceed the corresponding disease risk indicator threshold and sends it to the human-computer interaction module. The S4 human-computer interaction module displays various collected data and disease risk indicators for various diseases, and displays alarm signals when necessary.

Images