Method and system for rapidly detecting gene sequence of input type infectious disease

Abstract

The invention belongs to the technical field of gene engineering, and discloses a method and a system for rapidly detecting gene sequences of input type infectious diseases. A detection data set and a sample data set are collected and preprocessed, the detection data set comprises virus gene sequence data, fungus gene sequence data and parasite gene sequence data, and the sample data set comprises local virus gene sequence data, local fungus gene sequence data and local parasite gene sequence data; analyzing the detection data set and the sample data set to obtain an input type infectious disease data set, and detecting to obtain a virus hazard degree classification result; analyzing the virus hazard degree classification result to obtain a decision suggestion result; in general, the method has the remarkable advantages that the rapid sample detection capability is high, the response measure auxiliary efficiency is high, and the disease toxicity degree feedback effect is great.

Description

Technical Field

[0001] The present invention relates to the field of genetic engineering technology, and more specifically, to a method and system for rapid detection of imported infectious disease gene sequences. Background Art

[0002] Imported infectious diseases refer to infectious diseases that did not originally exist in the country or region, have not yet been discovered or have been eliminated but are introduced from the outside. With the rapid development of our country in recent years, integrating with the world has become an inevitable choice for the current national development. Although the country's opening up is beneficial to all aspects of people's lives, it is also accompanied by the risk of imported infectious diseases. Thanks to the rapid development of the country, medical means are also improving year by year. How to better utilize current medical means to prevent imported infectious diseases has become a major problem that the relevant departments need to face.

[0003] The patent application with the publication number CN101751517B discloses a rapid processing method and system for genome short sequence mapping. The method sorts the sequencing sequences according to the base values ​​of the short strings of preset length, cuts the contigs into short strings of preset length one by one, searches for the corresponding sequencing sequences in the sorted sequencing sequences according to the base values ​​of the short strings cut from the contigs, and establishes a mapping relationship. The technical solution starts from the comparison between the contigs and the sequences involved in the splicing, and utilizes the characteristic of the contigs assembled based on the de Bruijn graph that there is no repetition in the short strings of fixed length, thereby realizing the short sequence mapping used in the short sequence assembly, and the required processing time is significantly shortened and the efficiency is greatly improved.

[0004] However, although the above-mentioned rapid processing method and system for genome short sequence mapping has achieved the purpose of shortening nursing time and improving efficiency to a certain extent by establishing a mapping relationship, in the rapid detection of imported infectious disease gene sequences, how to better utilize the information of imported infectious disease gene sequences to provide more convenience and information feedback to staff is a major problem that the relevant departments urgently need to solve.

[0005] In view of this, the present invention proposes a method and system for rapid detection of imported infectious disease gene sequences to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: comprising: A data collection module is used to collect detection data sets and sample data sets and perform preprocessing. The detection data sets include viral gene sequence data, fungal gene sequence data and parasite gene sequence data. The sample data sets include native viral gene sequence data, native fungal gene sequence data and native parasite gene sequence data. Furthermore, the method of collecting the detection data set and the sample data set includes: By performing high-throughput sequencing on the genetic material in the test sample, the genetic material sequences of the virus, fungus and parasite in the test sample are collected respectively to obtain viral gene sequence data, fungal gene sequence data and parasite gene sequence data; By reading the local disease gene database, the genome sequences of viruses, fungi and parasites in the database are collected respectively to obtain local virus gene sequence data, local fungal gene sequence data and local parasite gene sequence data; The preprocessing methods include data cleaning, data denoising and normalization; The data processing module is used to analyze the test data set and the sample data set to obtain the input infectious disease data set, and perform detection to obtain the classification result of the virus harm degree; Furthermore, the steps of analyzing the test data set and the sample data set include: Q1: Based on the detection data set, read the viral gene sequence data, fungal gene sequence data and parasite gene sequence data in the detection data set, starting from the first base of the gene sequence in the detection data set, take a short sequence of length K each time, record it as K-mer, and traverse all gene sequences in the detection data set based on the sliding window method to obtain a series of K-mers; Q2: Collect M groups of historical feature vectors as sample sets, and divide the sample sets into 70%M training sets, 15%M test sets, and 15%M validation sets; Q3: Establish a gene sequence classification model based on the sample set, obtain the historical feature vector in the training set, preset the included data cluster L1 and the excluded data cluster L2, and select two data points in the training set as the first cluster center by artificial setting, representing the included data cluster L1 and the excluded data cluster L2 respectively; Q4: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the data cluster L1 and the data cluster L2, and assign the data items to the data cluster with the closest distance, and get two new data clusters as the second cluster center, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; Q5: Calculate the means of the two new data clusters in the second cluster center respectively, and calculate them again as the new first cluster center; Q6: Repeat Q4 and Q5 until the preset number of iterations is reached to obtain a disease classification model; Q7: Input the feature vector into the disease classification model and output the input infectious disease data set; Further, the detection method includes: Obtain an imported infectious disease data set, and detect the toxicity coefficient of virulence factors in viruses, fungi or parasites in the imported infectious disease data set based on metagenomic next-generation sequencing technology; The toxicity threshold interval (R1, R2) is preset. When the toxicity coefficient is less than R1, a micro-toxicity signal is generated. When the toxicity coefficient is greater than R1 and less than R2, a medium-toxicity signal is generated. When the toxicity coefficient is greater than R2, a high-toxicity signal is generated. The micro-toxicity signal contains a set of fields representing that the disease gene sequence contains a trace amount of toxicity, the medium-toxicity signal contains a set of fields representing that the disease gene sequence contains a medium amount of toxicity, and the high-toxicity signal contains a set of fields representing that the disease gene sequence contains a high amount of toxicity; Pack micro-toxicity signals, medium-toxicity signals and high-toxicity signals to obtain the classification results of the virus harm degree; The decision-making push module is used to analyze the classification results of the virus harm degree and obtain decision-making recommendations; Furthermore, the methods for analyzing the classification results of the virus harm degree include: When the virus hazard level classification result is a micro toxicity signal, a micro toxicity SMS is sent to the display analysis module through the communication unit; when the virus hazard level classification result is a medium toxicity signal, a medium toxicity SMS is sent to the display analysis module through the communication unit; when the virus hazard level classification result is a high toxicity signal, a high toxicity SMS is sent to the display analysis module through the communication unit; The trace toxicity message includes information about the presence of trace toxicity of imported infectious diseases in the test samples, reminding staff to continuously monitor patients and samples to observe changes in toxicity, provide patients or the public with prevention information on imported infectious diseases, and regularly check medical protective supplies; The medium-level toxicity message includes a statement that the imported infectious disease in the test sample has a medium level of toxicity, requiring staff to isolate the patient in a designated location, trace and test people who have had contact with the patient, and provide medical treatment to the patient; The high-toxicity message includes a statement that the imported infectious disease in the test sample has a high level of toxicity, requiring staff to immediately isolate people who have had contact with the patient, seal off and disinfect the potentially contaminated environment, and concentrate superior medical resources to treat the patient; Packing micro-toxicity SMS, medium-toxicity SMS and high-toxicity SMS to obtain decision-making recommendation results; The display analysis module is used to display the decision-making recommendation results and analyze the toxicity coefficient to obtain the similarity results; Furthermore, the method of analyzing the toxicity coefficient includes reading the local disease gene database, bringing the toxicity coefficient into the local disease gene database for comparison based on the Pandas library tool, and outputting the similarity result; Further, S1: collecting a detection data set and a sample data set, and performing preprocessing, the detection data set includes viral gene sequence data, fungal gene sequence data, and parasite gene sequence data, and the sample data set includes native viral gene sequence data, native fungal gene sequence data, and native parasite gene sequence data; S2: Analyze the test data set and the sample data set to obtain the input infection disease data set, and perform testing to obtain the classification results of the virus harm degree; S3: Analyze the classification results of the virus harm degree and obtain decision-making recommendations; S4: Display the decision recommendation results, analyze the toxicity coefficient, and obtain the similarity results.

[0007] The technical effects and advantages of the method and system for rapid detection of imported infectious disease gene sequences of the present invention are as follows: The present invention analyzes the detection data set and the sample data set to obtain the imported infectious disease data set, which can quickly complete the identification of imported infectious diseases. Compared with traditional monitoring, it not only improves the detection speed and accuracy, but also reduces the detection cost. The decision-making recommendation results obtained by analyzing the virus hazard degree classification results can assist the staff to quickly implement more targeted response measures based on the toxicity coefficient of the detected sample, greatly reducing the spread of the disease caused by the long decision-making time. The similarity results obtained by analyzing the toxicity coefficient can effectively reflect the toxicity intensity relationship between the toxicity of imported infectious diseases and the local infectious diseases, which is conducive to the staff to further implement response and improvement measures for infectious diseases based on past experience in responding to infectious diseases. Generally speaking, the present invention has the significant advantages of strong sample rapid detection capability, high auxiliary efficiency of response measures and large feedback effect on the toxicity of diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of a rapid detection system for gene sequences of imported infectious diseases according to the present invention; Figure 2 This is a schematic diagram of a method for rapid detection of imported infectious disease gene sequences according to the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0010] Example 1 See also Figure 1 As shown, the imported infectious disease gene sequence rapid detection system described in this embodiment includes: A data collection module is used to collect detection data sets and sample data sets and perform preprocessing. The detection data sets include viral gene sequence data, fungal gene sequence data and parasite gene sequence data. The sample data sets include native viral gene sequence data, native fungal gene sequence data and native parasite gene sequence data. Furthermore, the method of collecting the detection data set and the sample data set includes: By performing high-throughput sequencing on the genetic material in the test sample, the genetic material sequences of the virus, fungus and parasite in the test sample are collected respectively to obtain viral gene sequence data, fungal gene sequence data and parasite gene sequence data; It needs to be explained that genetic material is nucleic acid; By reading the local disease gene database, the genome sequences of viruses, fungi and parasites in the database are collected respectively to obtain local virus gene sequence data, local fungal gene sequence data and local parasite gene sequence data; It should be explained that the local disease gene database is a database obtained by gathering the gene data of historical diseases existing in the country or region where the test is conducted; The preprocessing methods include data cleaning, data denoising and normalization; The data processing module is used to analyze the test data set and the sample data set to obtain the input infectious disease data set, and perform detection to obtain the classification result of the virus harm degree; Furthermore, the steps of analyzing the test data set and the sample data set include: Q1: Based on the detection data set, read the viral gene sequence data, fungal gene sequence data and parasite gene sequence data in the detection data set, starting from the first base of the gene sequence in the detection data set, take a short sequence of length K each time, record it as K-mer, and traverse all gene sequences in the detection data set based on the sliding window method to obtain a series of K-mers; It needs to be explained that the gene sequence is composed of four bases: A, C, G, and T, which are similar to the characters in a text; Q2: Collect M groups of historical feature vectors as sample sets, and divide the sample sets into 70%M training sets, 15%M test sets, and 15%M validation sets; It needs to be explained that the feature vector is a K-mer; Q3: Establish a gene sequence classification model based on the sample set, obtain the historical feature vector in the training set, preset the included data cluster L1 and the excluded data cluster L2, and select two data points in the training set as the first cluster center by artificial setting, representing the included data cluster L1 and the excluded data cluster L2 respectively; Q4: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the data cluster L1 and the data cluster L2, and assign the data items to the data cluster with the closest distance, and get two new data clusters as the second cluster center, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; Q5: Calculate the means of the two new data clusters in the second cluster center respectively, and calculate them again as the new first cluster center; Q6: Repeat Q4 and Q5 until the preset number of iterations is reached to obtain a disease classification model; Q7: Input the feature vector into the disease classification model and output the input infectious disease data set; It should be explained that the input infectious disease data set is a collection of feature vectors located in a region without data clusters; Further, the detection method includes: Obtain an imported infectious disease data set, and detect the toxicity coefficient of virulence factors in viruses, fungi or parasites in the imported infectious disease data set based on metagenomic next-generation sequencing technology; It should be explained that the virulence coefficient is the weighted sum of the lethality and infectivity of the virulence factor; The toxicity threshold interval (R1, R2) is preset. When the toxicity coefficient is less than R1, a micro-toxicity signal is generated. When the toxicity coefficient is greater than R1 and less than R2, a medium-toxicity signal is generated. When the toxicity coefficient is greater than R2, a high-toxicity signal is generated. The micro-toxicity signal contains a set of fields representing that the disease gene sequence contains a trace amount of toxicity, the medium-toxicity signal contains a set of fields representing that the disease gene sequence contains a medium amount of toxicity, and the high-toxicity signal contains a set of fields representing that the disease gene sequence contains a high amount of toxicity; Pack micro-toxicity signals, medium-toxicity signals and high-toxicity signals to obtain the classification results of the virus harm degree; The decision-making push module is used to analyze the classification results of the virus harm degree and obtain decision-making recommendations; Further, the methods for analyzing the classification results of the virus harm degree include: When the virus hazard level classification result is a micro toxicity signal, a micro toxicity SMS is sent to the display analysis module through the communication unit; when the virus hazard level classification result is a medium toxicity signal, a medium toxicity SMS is sent to the display analysis module through the communication unit; when the virus hazard level classification result is a high toxicity signal, a high toxicity SMS is sent to the display analysis module through the communication unit; The trace toxicity message includes information about the presence of trace toxicity of imported infectious diseases in the test samples, reminding staff to continuously monitor patients and samples to observe changes in toxicity, provide patients or the public with prevention information on imported infectious diseases, and regularly check medical protective supplies; The medium-level toxicity message includes a statement that the imported infectious disease in the test sample has a medium level of toxicity, requiring staff to isolate the patient in a designated location, trace and test people who have had contact with the patient, and provide medical treatment to the patient; The high-toxicity message includes a statement that the imported infectious disease in the test sample has a high level of toxicity, requiring staff to immediately isolate people who have had contact with the patient, seal off and disinfect the potentially contaminated environment, and concentrate superior medical resources to treat the patient; Packing micro-toxicity SMS, medium-toxicity SMS and high-toxicity SMS to obtain decision-making recommendation results; The display analysis module is used to display the decision-making recommendation results and analyze the toxicity coefficient to obtain the similarity results; Furthermore, the method of analyzing the toxicity coefficient includes reading the local disease gene database, and based on the Pandas library tool, bringing the toxicity coefficient into the local disease gene database for comparison, and outputting the similarity result; This embodiment has the beneficial effect that the imported infectious disease data set obtained by analyzing the detection data set and the sample data set can quickly complete the identification of imported infectious diseases. Compared with traditional monitoring, it not only improves the detection speed and accuracy, but also reduces the detection cost. The decision-making recommendation results obtained by analyzing the virus hazard level classification results can assist the staff to quickly implement more targeted response measures based on the toxicity coefficient of the test sample, greatly reducing the spread of the disease caused by the long decision-making time. The similarity results obtained by analyzing the toxicity coefficient can effectively reflect the relationship between the toxicity level of imported infectious diseases and the toxicity intensity of locally existing infectious diseases, which is beneficial for the staff to further implement response and improvement measures for infectious diseases based on past experience in responding to infectious diseases. Generally speaking, the present invention has the significant advantages of strong sample rapid detection capability, high auxiliary efficiency of response measures and large feedback effect on the toxicity level of diseases.

[0011] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, which provides a method for rapid detection of gene sequences of imported infectious diseases, including: S1: collecting a detection data set and a sample data set, and preprocessing them, the detection data set includes viral gene sequence data, fungal gene sequence data and parasite gene sequence data, and the sample data set includes local viral gene sequence data, local fungal gene sequence data and local parasite gene sequence data; S2: Analyze the test data set and the sample data set to obtain the input infection disease data set, and perform testing to obtain the classification results of the virus harm degree; S3: Analyze the classification results of the virus harm degree and obtain decision-making recommendations; S4: Display the decision recommendation results, analyze the toxicity coefficients, and obtain similarity results.

[0012] Example 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the method for rapid detection of gene sequences of imported infectious diseases provided above is implemented.

[0013] Since the electronic device introduced in this embodiment is an electronic device used to implement a method for rapid detection of an imported infectious disease gene sequence in the embodiment of this application, based on the method for rapid detection of an imported infectious disease gene sequence introduced in the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as a person skilled in the art implements an electronic device used in a method for rapid detection of an imported infectious disease gene sequence in the embodiment of this application, it belongs to the scope of protection of this application.

[0014] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0015] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A rapid detection system for imported infectious disease gene sequences, characterized in that: include: A data collection module is used to collect detection data sets and sample data sets and perform preprocessing. The detection data sets include viral gene sequence data, fungal gene sequence data and parasite gene sequence data. The sample data sets include native viral gene sequence data, native fungal gene sequence data and native parasite gene sequence data. The data processing module is used to analyze the test data set and the sample data set to obtain the input infectious disease data set, and perform detection to obtain the classification result of the virus harm degree; The decision-making push module is used to analyze the classification results of the virus harm degree and obtain decision-making recommendations; The display analysis module is used to display the decision recommendation results and analyze the toxicity coefficient to obtain the similarity results.

2. According to claim 1, a rapid detection system for imported infectious disease gene sequences, characterized in that: Methods for collecting test data sets and sample data sets include: By performing high-throughput sequencing on the genetic material in the test sample, the genetic material sequences of the virus, fungus and parasite in the test sample are collected respectively to obtain viral gene sequence data, fungal gene sequence data and parasite gene sequence data; By reading the local disease gene database, the genome sequences of viruses, fungi and parasites in the database are collected respectively to obtain local virus gene sequence data, local fungal gene sequence data and local parasite gene sequence data; The preprocessing methods include data cleaning, data denoising and normalization.

3. A rapid detection system for imported infectious disease gene sequences according to claim 2, characterized in that: The steps for analyzing the test dataset and sample dataset include: Q1: Based on the detection data set, read the viral gene sequence data, fungal gene sequence data and parasite gene sequence data in the detection data set, starting from the first base of the gene sequence in the detection data set, take a short sequence of length K each time, record it as K-mer, and traverse all gene sequences in the detection data set based on the sliding window method to obtain a series of K-mers; Q2: Collect M groups of historical feature vectors as sample sets, and divide the sample sets into 70%M training sets, 15%M test sets, and 15%M validation sets; Q3: Establish a gene sequence classification model based on the sample set, obtain the historical feature vector in the training set, preset the included data cluster L1 and the excluded data cluster L2, and select two data points in the training set as the first cluster center by artificial setting, representing the included data cluster L1 and the excluded data cluster L2 respectively; Q4: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the data cluster L1 and the data cluster L2, and assign the data items to the data cluster with the closest distance, and get two new data clusters as the second cluster center, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; Q5: Calculate the means of the two new data clusters in the second cluster center respectively, and calculate them again as the new first cluster center; Q6: Repeat Q4 and Q5 until the preset number of iterations is reached to obtain a disease classification model; Q7: Input the feature vector into the disease classification model and output the input infectious disease data set.

4. A rapid detection system for imported infectious disease gene sequences according to claim 3, characterized in that: The methods of testing include: Obtain an imported infectious disease data set, and detect the toxicity coefficient of virulence factors in viruses, fungi or parasites in the imported infectious disease data set based on metagenomic next-generation sequencing technology; The toxicity threshold interval (R1, R2) is preset. When the toxicity coefficient is less than R1, a micro-toxicity signal is generated. When the toxicity coefficient is greater than R1 and less than R2, a medium-toxicity signal is generated. When the toxicity coefficient is greater than R2, a high-toxicity signal is generated. The micro-toxicity signal contains a set of fields representing that the disease gene sequence contains a trace amount of toxicity, the medium-toxicity signal contains a set of fields representing that the disease gene sequence contains a medium amount of toxicity, and the high-toxicity signal contains a set of fields representing that the disease gene sequence contains a high amount of toxicity; Micro-toxicity signals, medium-toxicity signals and high-toxicity signals are packaged to obtain the classification results of the virus hazard level.

5. A rapid detection system for imported infectious disease gene sequences according to claim 4, characterized in that: Methods for analyzing the results of virus hazard classification include: When the virus hazard level classification result is a micro toxicity signal, a micro toxicity SMS is sent to the display analysis module through the communication unit; when the virus hazard level classification result is a medium toxicity signal, a medium toxicity SMS is sent to the display analysis module through the communication unit; when the virus hazard level classification result is a high toxicity signal, a high toxicity SMS is sent to the display analysis module through the communication unit; The trace toxicity message includes information about the presence of trace toxicity of imported infectious diseases in the test samples, reminding staff to continuously monitor patients and samples to observe changes in toxicity, providing patients or the public with prevention information on imported infectious diseases, and regularly checking medical protective supplies; The medium-level toxicity message includes a statement that the imported infectious disease in the test sample has a medium level of toxicity, requiring staff to isolate the patient in a designated location, trace and test people who have had contact with the patient, and provide medical treatment to the patient; The high-toxicity message includes a statement that the imported infectious disease in the test sample has a high level of toxicity, requiring staff to immediately isolate people who have had contact with the patient, seal off and disinfect the potentially contaminated environment, and concentrate superior medical resources to treat the patient; The trace toxicity SMS, medium toxicity SMS and high toxicity SMS are packaged to obtain decision-making recommendation results.

6. A rapid detection system for imported infectious disease gene sequences according to claim 5, characterized in that: The method of analyzing the toxicity coefficient includes reading the local disease gene database, and based on the Pandas library tool, bringing the toxicity coefficient into the local disease gene database for comparison, and outputting the similarity result.

7. A method for rapid detection of imported infectious disease gene sequences, implemented according to any one of the systems for rapid detection of imported infectious disease gene sequences according to claims 1-6, characterized in that: S1: Collect test data sets and sample data sets and perform preprocessing. The test data sets include viral gene sequence data, fungal gene sequence data and parasite gene sequence data. The sample data sets include local viral gene sequence data, local fungal gene sequence data and local parasite gene sequence data. S2: Analyze the test data set and the sample data set to obtain the input infection disease data set, and perform testing to obtain the classification results of the virus harm degree; S3: Analyze the classification results of the virus harm degree and obtain decision-making recommendations; S4: Display the decision recommendation results, analyze the toxicity coefficient, and obtain the similarity results.

Images