Infective disease gene sequence diagnosis and management method and system

Abstract

The invention discloses an infectious disease gene sequence diagnosis and management method and system, and relates to the technical field of gene sequence diagnos.The system comprises a sequence collection module, a patient management module, a mutation analysis module, a diagnosis analysis module and an authority management module; the sequence acquisition module acquires a disease genome sequence of a patient, preprocesses the disease genome sequence and converts the disease genome sequence into an FASTQ format; the pathogen type, the mutation sequence and the drug resistance mutation are effectively identified by analyzing the gene sequence of a patient, a targeted treatment scheme is provided for the patient in combination with clinical symptoms, gene data are analyzed by using a deep learning model convolutional neural network training model, and the drug resistance of the patient is identified by combining various technologies. Comprising genome sequencing, comparison algorithm and mutation analysis, and pathogen types can be analyzed more accurately, so that the diagnosis accuracy is remarkably improved, personal errors in a traditional diagnosis method are avoided, more accurate treatment suggestions are provided, treatment can be started as early as possible, and misdiagnosis conditions are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of gene sequence diagnosis, and in particular to a method and system for diagnosing and managing gene sequences of infectious diseases. Background Art

[0002] Gene sequence diagnosis technology is a means of diagnosing and identifying diseases based on comprehensive analysis of the genome DNA or RNA of organisms combined with high-throughput sequencing technology. With the rapid development of genomics and molecular biology, traditional disease diagnosis methods are gradually facing certain limitations. In the field of infectious diseases, gene sequence diagnosis has obvious advantages. Through efficient sequencing of the genome of pathogens, the types, mutation characteristics and drug resistance of pathogens such as bacteria, viruses and fungi can be identified. The presence of drug-resistant genes can be identified through genome analysis to help doctors choose appropriate antibiotics. Traditional methods rely on culture, specific test kits, and manual intervention, which results in diagnostic delays. They cannot fully cover all possible pathogens for infectious diseases with a large number of pathogens, can only detect specific types of pathogens, and cannot extract and identify diverse genomic data for identification; In view of the above technical defects, a solution is now proposed. Summary of the invention

[0003] In view of the deficiencies of the prior art, the present invention provides a method and system for diagnosing and managing infectious disease gene sequences.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method and system for diagnosing and managing infectious disease gene sequences, including: a sequence acquisition module, a patient management module, a mutation analysis module, a diagnosis analysis module, and a rights management module; The sequence acquisition module collects the patient's disease genome sequence for preprocessing and converts it into FASTQ format, transmits the processed data to the patient management module and associates it with the patient information; The patient management module stores basic patient information, disease history, family history and other data information, tracks the treatment process and generates regular reports to doctors; The mutation analysis module uses BWA to compare disease genes with GRCh38, marks mutation positions and sequences, compares them with the drug resistance gene database ARDB to determine and mark drug resistance mutations, and transmits the marking information to the diagnosis management module; The diagnostic analysis module uses CNN to extract gene sequence features and train the model. The model inputs processed gene sequences and clinical data. The model outputs the pathogen type and recommends treatment plans and targeted drugs based on symptoms. The permission management module controls permission allocation, authorizes doctors and laboratory personnel to access patient sensitive data, supports fine-grained permission allocation, and controls the storage and transmission of genetic data and personal information using AES-256 encryption.

[0005] The sequence acquisition module performs genome sequencing technology WES analysis on the pathogen target source to collect the patient's disease genome data, the collected data includes DNA and RNA sequences, the pathogen target source comes from patients infected with the disease, and the original disease gene data is preprocessed, including removing low-quality sequences, sequencing error sequences and contaminated sequences, removing low-confidence bases in multiple sequencings, and then uniformly converting the collected data into the standard format FASTQ, and transmitting the processed disease genome data to the patient management module for association labeling with patient information.

[0006] The patient management module is responsible for storing and managing the patient's basic information, including name, age, gender, contact information, and detailed disease history and family history information. The disease gene data is stored in the database and marked and associated with the patient's basic information. The patient management module records the treatment history of each patient, including the drug treatment taken, treatment response and efficacy evaluation information, and continuously records the patient's treatment effect and generates detailed reports regularly.

[0007] The mutation analysis module uses the alignment algorithm BWA to align the disease gene data with the human genome GRCh38, marks the mutation position and mutation sequence in the disease genome, and uses the Samtools algorithm to detect the mutation type for the mutation position. The mutation types include single nucleotide polymorphism, insertion and deletion, and copy number variation. The mutation analysis module compares the mutation position with the drug resistance gene database ARDB to determine whether there is a known drug resistance mutation and mark it, and transmits the mutation sequence and mutation type as well as the marked drug resistance mutation to the diagnosis management module.

[0008] The diagnostic analysis module uses a convolutional neural network (CNN) to extract local features from a large number of gene sequences in the database. The markers of drug-resistant mutations are also converted into numerical features and input into the neural network. The neural network is trained using the extracted data set, and the gradient descent method is used to minimize the loss function. The loss function selects the mean square error. During the training process, the network parameters are updated through the back propagation algorithm to optimize the prediction ability of the model. The input of the model is the processed gene sequence and clinical data, and the output is the type of infected pathogen, the type of disease and the recommended drug information. The trained model is used to analyze the mutation sequence and mutation type to identify the type of pathogen infected by the patient. The comprehensive clinical symptoms are analyzed to recommend personalized treatment plans for patients, and targeted drugs are recommended based on the marked drug-resistant mutations.

[0009] The permission management module implements a permission control mechanism by classifying user roles. Only authorized doctors and laboratory staff can access patients' sensitive data. The system supports fine-grained permission allocation, including viewing, modifying and deleting operation permissions, and uses the encryption algorithm AES-256 to store and transmit patients' genetic data and personal information.

[0010] The specific method for infectious disease gene sequence diagnosis and management is as follows: S1. Pathogen target sources are collected from patients infected with the disease. The sequence collection module uses the genome sequencing technology WES to collect disease gene sequences, pre-process the original disease gene data, remove low-quality sequences, sequencing error sequences and contaminated sequences, remove low-confidence bases in multiple sequencing, and convert the processed data into FASTQ format; S2, the patient management module stores and manages the patient's basic information, such as name, age, gender, contact information, etc., as well as detailed disease history and family history, and records the treatment process of each patient; S3. Use the comparison algorithm BWA to compare the collected disease gene data with the human genome GRCh38, mark the mutation position and mutation sequence in the genome, compare the mutation position with the drug resistance gene database ARDB, determine whether there is a drug resistance mutation, and transmit the detected mutation sequence, mutation type and drug resistance mutation marker information to the diagnosis management module; S4. Use the trained neural network model to analyze mutation sequences and mutation types, identify the type of pathogen that the patient is infected with, analyze the clinical symptoms comprehensively, recommend personalized treatment plans for patients, and recommend targeted drugs.

[0011] The present invention provides a method and system for diagnosing and managing infectious disease gene sequences. Compared with the prior art, it has the following beneficial effects: The present invention effectively identifies pathogen types, mutation sequences, and drug-resistant mutations by analyzing the patient's gene sequence, and provides targeted treatment plans for patients in combination with clinical symptoms. It uses a deep learning model convolutional neural network training model to analyze gene data, and combines multiple technologies, including genome sequencing, alignment algorithms, and mutation analysis, to more accurately analyze pathogen types, thereby significantly improving the accuracy of diagnosis, avoiding human errors in traditional diagnostic methods, and providing more accurate treatment recommendations, which helps to start treatment as early as possible and reduce misdiagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a schematic diagram of the principle framework of the present invention. DETAILED DESCRIPTION

[0013] 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.

[0014] See also Figure 1 , the present application provides a method and system for diagnosing and managing infectious disease gene sequences, including a sequence acquisition module, a patient management module, a mutation analysis module, a diagnosis analysis module, and a rights management module; The sequence acquisition module collects the patient's disease genome sequence for preprocessing and converts it into FASTQ format, transmits the processed data to the patient management module and associates it with the patient information; The patient management module stores basic patient information, disease history, family history and other data information, tracks the treatment process and generates regular reports to doctors; The mutation analysis module uses BWA to compare disease genes with GRCh38, marks mutation positions and sequences, compares them with the drug resistance gene database ARDB to determine and mark drug resistance mutations, and transmits the marking information to the diagnosis management module; The diagnostic analysis module uses CNN to extract gene sequence features and train the model. The model inputs processed gene sequences and clinical data. The model outputs the pathogen type and recommends treatment plans and targeted drugs based on symptoms. The permission management module controls permission allocation, authorizes doctors and laboratory personnel to access patient sensitive data, supports fine-grained permission allocation, and controls the storage and transmission of genetic data and personal information using AES-256 encryption.

[0015] The sequence acquisition module uses genome sequencing technology WES to analyze the pathogen target source to collect the patient's disease genome data. The collected data includes DNA and RNA sequences. The pathogen target source comes from patients infected with the disease. The original disease gene data is preprocessed, including removing low-quality sequences, sequencing error sequences and contaminated sequences, and removing low-confidence bases in multiple sequencing runs. The collected data is then uniformly converted into the standard format FASTQ, and the processed disease genome data is transmitted to the patient management module for association and labeling with patient information.

[0016] After data collection, the sequence acquisition module will pre-process the original disease gene data to ensure the reliability of the data. It will remove low-quality sequence data, which may not meet the quality standards due to errors in the sequencing instrument or problems in sample processing. It will also eliminate sequences with sequencing errors and possible contamination sequences to avoid interference with the sequencing results by external factors.

[0017] The patient management module is responsible for storing and managing the patient's basic information, including name, age, gender, contact information, and detailed medical history and family history information. Disease gene data is stored in the database and tagged with the patient's basic information. The patient management module records each patient's treatment history, including the medications taken, treatment responses and efficacy evaluation information, and continuously records the patient's treatment effects and generates detailed reports on a regular basis.

[0018] The mutation analysis module uses the alignment algorithm BWA to align the disease gene data with the human genome GRCh38, marks the mutation position and mutation sequence in the disease genome, and uses the Samtools algorithm to detect the mutation type for the mutation position. The mutation types include single nucleotide polymorphism, insertion and deletion, and copy number variation. The mutation analysis module compares the mutation position with the drug resistance gene database ARDB to determine whether there are known drug resistance mutations and mark them, and transmits the mutation sequence, mutation type, and marked drug resistance mutations to the diagnosis management module.

[0019] After obtaining the mutation site, Samtools can be used to further analyze the mutation position and identify different types of mutations. The mutation types mainly include single nucleotide polymorphisms (SNPs), insertions and deletions (Indels), and copy number variations (CNVs). These mutation types are of reference significance in the patient's disease progression and may be related to the occurrence, development, and response to treatment of the disease.

[0020] The diagnostic analysis module uses a convolutional neural network (CNN) to extract local features from a large number of gene sequences in the database. The markers of drug-resistant mutations are also converted into numerical features and input into the neural network. The extracted data set is used to train the neural network, and the gradient descent method is used to minimize the loss function. The loss function selects the mean square error. During the training process, the network parameters are updated through the back propagation algorithm to optimize the model's predictive ability. The input of the model is the processed gene sequence and clinical data, and the output is the type of infected pathogen, the type of disease, and the recommended drug information. The trained model is used to analyze the mutation sequence and mutation type to identify the type of pathogen infected by the patient. The comprehensive clinical symptoms are analyzed to recommend personalized treatment plans for patients, and targeted drugs are recommended based on the marked drug-resistant mutations.

[0021] The permission management module implements a permission control mechanism by classifying user roles. Only authorized doctors and laboratory staff can access patients' sensitive data. The system supports fine-grained permission allocation, including viewing, modifying and deleting operation permissions, and uses the encryption algorithm AES-256 to store and transmit patients' genetic data and personal information.

[0022] The system supports fine-grained permission settings and provides detailed logging functions. Every data viewing, modification or deletion operation will be recorded, and an operation log will be generated and timestamped to trace the doctor's behavior. This mechanism ensures the traceability of data use and enhances the security of patient data.

[0023] A specific method for diagnosis and management of infectious disease gene sequences is as follows: S1. Pathogen target sources are collected from patients infected with the disease. The sequence collection module uses the genome sequencing technology WES to collect disease gene sequences, pre-process the original disease gene data, remove low-quality sequences, sequencing error sequences and contaminated sequences, remove low-confidence bases in multiple sequencing, and convert the processed data into FASTQ format; S2, the patient management module stores and manages the patient's basic information, such as name, age, gender, contact information, etc., as well as detailed disease history and family history, and records the treatment process of each patient; S3. Use the comparison algorithm BWA to compare the collected disease gene data with the human genome GRCh38, mark the mutation position and mutation sequence in the genome, compare the mutation position with the drug resistance gene database ARDB, determine whether there is a drug resistance mutation, and transmit the detected mutation sequence, mutation type and drug resistance mutation marker information to the diagnosis management module; S4. Use the trained neural network model to analyze mutation sequences and mutation types, identify the type of pathogen that the patient is infected with, analyze the clinical symptoms comprehensively, recommend personalized treatment plans for patients, and recommend targeted drugs.

[0024] Specific workflow: The target source of pathogens is extracted from the patient's body. The sequence acquisition module uses the genome sequencing technology WES to obtain the patient's DNA and RNA sequence data, pre-processes the gene sequence data, and then converts it into the standard FASTQ format. The patient management module obtains the patient's information from the hospital database, including name, age, gender, detailed disease history and family history of the patient, tracks the patient's treatment process and regularly generates regular reports for doctors. The mutation analysis module uses the alignment algorithm BWA to align the disease gene sequence with the human reference genome GRCh38, marks the mutation position and mutation sequence, identifies the mutation type through the Samtools algorithm, compares the mutation information with the drug resistance gene database ARDB to determine whether there is a drug resistance mutation, and transmits the marked information to the diagnosis and analysis module. The diagnosis and analysis module uses the convolutional neural network CNN to train the data in the hospital data. The generated model can analyze and output the type of pathogen and disease infected by the patient, and recommend treatment plans and targeted drugs for the patient based on clinical symptoms.

[0025] Furthermore, the present invention effectively identifies pathogen types, mutation sequences, and drug-resistant mutations through analysis of patient gene sequences, and provides targeted treatment plans for patients based on clinical symptoms. It uses a deep learning model convolutional neural network training model to analyze genetic data. It combines multiple technologies, including genome sequencing, alignment algorithms, and mutation analysis, to more accurately analyze pathogen types, thereby significantly improving diagnostic accuracy, avoiding human errors in traditional diagnostic methods, and providing more accurate treatment recommendations, which helps to start treatment as early as possible and reduce misdiagnosis.

[0026] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0027] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A system for diagnosing and managing infectious disease gene sequences, characterized in that: include: Sequence acquisition module, patient management module, mutation analysis module, diagnostic analysis module, and authority management module; The sequence acquisition module collects the patient's disease genome sequence for preprocessing and converts it into FASTQ format, transmits the processed data to the patient management module and associates it with the patient information; The patient management module stores basic patient information, disease history, family history and other data information, tracks the treatment process and generates regular reports to doctors; The mutation analysis module uses BWA to compare disease genes with GRCh38, marks mutation positions and sequences, compares them with the drug resistance gene database ARDB to determine and mark drug resistance mutations, and transmits the marking information to the diagnosis management module; The diagnostic analysis module uses CNN to extract gene sequence features and train the model. The model inputs processed gene sequences and clinical data. The model outputs the pathogen type and recommends treatment plans and targeted drugs based on symptoms. The permission management module controls permission allocation, authorizes doctors and laboratory personnel to access patient sensitive data, supports fine-grained permission allocation, and controls the storage and transmission of genetic data and personal information using AES-256 encryption.

2. The infectious disease gene sequence diagnosis and management system according to claim 1, characterized in that: The sequence acquisition module performs genome sequencing technology WES analysis on the pathogen target source to collect the patient's disease genome data, the collected data includes DNA and RNA sequences, the pathogen target source comes from patients infected with the disease, and the original disease gene data is preprocessed, including removing low-quality sequences, sequencing error sequences and contaminated sequences, removing low-confidence bases in multiple sequencings, and then uniformly converting the collected data into the standard format FASTQ, and transmitting the processed disease genome data to the patient management module for association labeling with patient information.

3. The infectious disease gene sequence diagnosis and management system according to claim 1, characterized in that: The patient management module is responsible for storing and managing the patient's basic information, including name, age, gender, contact information, and detailed disease history and family history information. The disease gene data is stored in the database and marked and associated with the patient's basic information. The patient management module records the treatment history of each patient, including the drug treatment taken, treatment response and efficacy evaluation information, and continuously records the patient's treatment effect and generates detailed reports regularly.

4. The infectious disease gene sequence diagnosis and management system according to claim 1, characterized in that: The mutation analysis module uses the alignment algorithm BWA to align the disease gene data with the human genome GRCh38, marks the mutation position and mutation sequence in the disease genome, and uses the Samtools algorithm to detect the mutation type for the mutation position. The mutation types include single nucleotide polymorphism, insertion and deletion, and copy number variation. The mutation analysis module compares the mutation position with the drug resistance gene database ARDB to determine whether there is a known drug resistance mutation and mark it, and transmits the mutation sequence and mutation type as well as the marked drug resistance mutation to the diagnosis management module.

5. The infectious disease gene sequence diagnosis and management system according to claim 1, characterized in that: The diagnostic analysis module uses a convolutional neural network (CNN) to extract local features from a large number of gene sequences in the database. The markers of drug-resistant mutations are also converted into numerical features and input into the neural network. The neural network is trained using the extracted data set, and the gradient descent method is used to minimize the loss function. The loss function selects the mean square error. During the training process, the network parameters are updated through the back propagation algorithm to optimize the prediction ability of the model. The input of the model is the processed gene sequence and clinical data, and the output is the type of infected pathogen, the type of disease and the recommended drug information. The trained model is used to analyze the mutation sequence and mutation type to identify the type of pathogen infected by the patient. The comprehensive clinical symptoms are analyzed to recommend personalized treatment plans for patients, and targeted drugs are recommended based on the marked drug-resistant mutations.

6. The infectious disease gene sequence diagnosis and management system according to claim 1, characterized in that: The permission management module implements a permission control mechanism by classifying user roles. Only authorized doctors and laboratory staff can access patients' sensitive data. The system supports fine-grained permission allocation, including viewing, modifying and deleting operation permissions, and uses the encryption algorithm AES-256 to store and transmit patients' genetic data and personal information.

7. A method and system for diagnosing and managing infectious disease gene sequences, characterized in that: The specific method for infectious disease gene sequence diagnosis and management is as follows: S1. Pathogen target sources are collected from patients infected with the disease. The sequence collection module uses the genome sequencing technology WES to collect disease gene sequences, pre-process the original disease gene data, remove low-quality sequences, sequencing error sequences and contaminated sequences, remove low-confidence bases in multiple sequencing, and convert the processed data into FASTQ format; S2, the patient management module stores and manages the patient's basic information, such as name, age, gender, contact information, etc., as well as detailed disease history and family history, and records the treatment process of each patient; S3. Use the comparison algorithm BWA to compare the collected disease gene data with the human genome GRCh38, mark the mutation position and mutation sequence in the genome, compare the mutation position with the drug resistance gene database ARDB, determine whether there is a drug resistance mutation, and transmit the detected mutation sequence, mutation type and drug resistance mutation marker information to the diagnosis management module; S4. Use the trained neural network model to analyze mutation sequences and mutation types, identify the type of pathogen that the patient is infected with, analyze the clinical symptoms comprehensively, recommend personalized treatment plans for patients, and recommend targeted drugs.

Images