CN111966708A

CN111966708A - Tumor accurate medication reading system, reading method and device

Info

Publication number: CN111966708A
Application number: CN202010911319.5A
Authority: CN
Inventors: 李明明; 蔡文君; 李明壮; 胡菲菲
Original assignee: Ronglian Technology Group Co Ltd
Current assignee: Ronglian Technology Group Co Ltd
Priority date: 2020-09-02
Filing date: 2020-09-02
Publication date: 2020-11-20

Abstract

One or more embodiments of the present specification provide a tumor accurate medication interpretation system, a tumor accurate medication interpretation method, and a tumor accurate medication interpretation device, where the system includes a task management platform, a knowledge base platform, and a report interpretation platform, and the report interpretation platform is connected to the task management platform and the knowledge base platform, respectively; the interpretation method comprises the steps of docking sequencing off-line data of a gene sample, starting a data analysis process, and obtaining genetic variation annotation information of the gene sample; and performing correlation reading on the sample information of the gene sample, the gene variation annotation information of the gene sample and a database in a knowledge base platform to obtain correlation data corresponding to the gene sample. The full-process automatic intelligent interpretation of accurate tumor sequencing data medication is realized, the fields of variation types and tumor treatment medication are comprehensively covered, the specialty and the guidance of medication are improved, an auxiliary decision is provided for clinical personalized medication and treatment, the analysis efficiency is improved, and the treatment cost is saved.

Description

Tumor accurate medication reading system, reading method and device

Technical Field

One or more embodiments of the present disclosure relate to the field of biological information technology, and in particular, to a system, a method, and a device for reading tumor accurate medication.

Background

Tumor refers to a new organism formed by abnormal proliferation of local histiocyte under the action of various tumorigenic factors. WHO data show that the incidence and the death rate of tumors are in a rapid growth trend all over the world, and the social and economic burden is continuously increased. In 2019, statistical data published by the cancer center in China shows that about 392.9 million people develop national malignant tumors, the growth rate is 3.2%, and the mean that 7.5 people per minute are diagnosed as cancer.

With the popularization and development of accurate medical treatment and the reduction of sequencing cost, numerous organizations at home and abroad begin to provide detection and interpretation services of individualized accurate treatment for tumor patients. However, in the prior art, a certain space for improving the accuracy and efficiency of reading the accurate tumor medication cannot be well met with clinical requirements, and high-efficiency and high-quality services are provided.

Disclosure of Invention

In view of this, one or more embodiments of the present disclosure are directed to a system, a method and a device for reading tumor precise medication, so as to solve the problems of poor accuracy and low efficiency in reading tumor precise medication in the prior art.

In view of the above, a first aspect of one or more embodiments of the present specification provides a tumor precise medication interpretation system, which includes a task management platform, a knowledge base platform, and a report interpretation platform, where the report interpretation platform is connected to the task management platform and the knowledge base platform, respectively; wherein the content of the first and second substances,

the task management platform is used for automatically docking sequencing off-line data of the gene sample, starting a data analysis process and acquiring and viewing variation result information after annotation;

the knowledge base platform is used for constructing, collecting, storing and maintaining and reading knowledge data;

and the report interpretation platform is used for performing associated reading on the sample information of the gene sample, the annotated variation result information and the interpretation knowledge data in the knowledge base platform, and calling a report template to generate an interpretation report.

Optionally, the report interpretation platform is further configured to modify, review and download the interpretation report.

Optionally, the task management platform includes a data transmission plate, a task delivery plate, a biological information automatic analysis plate, a variation annotation information plate and a variation visualization plate, which are connected in sequence; the data transmission block is used for automatically extracting sequencing off-line data of a gene sample to obtain input data and process information; the task delivery plate block is used for confirming the input data and the process information through visual interactive operation and starting the biological information automatic analysis plate block; the biological information automatic analysis plate block is used for generating a variation detection information file which corresponds to the gene sample and is used for describing genome variation through an analysis process corresponding to the sequencing off-line data of the gene sample; the variant annotation information section is used for annotating the variant detection information file through an annotation process corresponding to the sequencing offline data of the gene sample to generate a variant annotation information file; the variant visualization layout block is used for visually presenting the variant annotation information file.

Optionally, the knowledge base platform includes a database updating and maintaining block, a database security management block, and a data management system building block, a data query collecting block, a data extraction, reference, cleaning block, an evidence grading block, a data integration and entry block, and a data auditing block, which are connected in sequence; the data management system building block is used for determining a data set to be acquired and the structural information of the data set, completing building of a database framework, and building a database according to the data set and the structural information of the data set; the data query collection block is used for downloading collected data from a public data source according to the data set to be collected determined by the data management system construction block; the data extraction and cleaning version block is used for extracting information from the data downloaded by the data query and collection version block according to an identifiable mode, cleaning and sorting the extracted information according to defined attributes and field rules, and classifying the extracted information into different data units; the evidence grading edition block is used for grading and storing the data after the data extraction and cleaning edition block processing according to the evidence-based medical evidence grade judgment standard and the AMP guideline standard; the data integration entry version is used for integrating the data after the data extraction and cleaning version processing, and entering the data into the data management system to construct a version; the data auditing section is used for auditing the data of the database according to the record ID of the input information; the database updating and maintaining block is used for regularly updating and checking the content of the database, regularly collecting the latest data related to the data set to be acquired, which is determined by the data management system building block, in a public data source, and regularly updating the data; the database security management block is used for providing security guarantee and management for the system and data of the database.

Optionally, the report reading platform includes a sample information entry section, a call section, a decision tree implementation section, a result output section, a report automatic generation section, a report audit section, and a report download section, which are connected in sequence; the sample information input block is used for inputting sample information and analysis requirements; the calling block is used for calling the sample information, the sample variation annotation information and relational data corresponding to the sample variation annotation information in a database established by the knowledge base platform; the decision tree implementation block is used for automatically judging the sample information, the sample variation annotation information and the associated data and performing decision output; the result output plate block is used for naming the output result of the decision tree implementation plate block according to the biological information automatic analysis plate block corresponding to the output result and outputting a statistical file; the report automatic generation block is used for matching a report template based on the sample information and the statistical file and calling the information of the statistical file to generate a report; the report auditing section is used for auditing the report to obtain a target interpretation report; the report downloading section is used for managing the report generated by the report interpretation platform.

In a second aspect of one or more embodiments of the present disclosure, there is provided a method for accurate interpretation of a tumor, the method including:

docking sequencing off-line data of a gene sample, starting a data analysis process, and obtaining genetic variation annotation information of the gene sample;

obtaining sample information of the gene sample;

and performing correlation reading on the sample information of the gene sample, the gene variation annotation information of the gene sample and a database in a knowledge base platform to obtain correlation data corresponding to the gene sample.

Optionally, the docking of the sequencing data of the gene sample, starting a data analysis process, and obtaining the genetic variation annotation information of the gene sample includes:

docking sequencing off-line data of a gene sample, and extracting input data and process information from the sequencing off-line data of the gene sample;

responding to an operation instruction sent by a user, confirming the input data and the process information, starting a data analysis process corresponding to the sequencing off-line data of the gene sample, and generating genetic variation detection information of the gene sample;

or the like, or, alternatively,

responding to an operation instruction sent by a user after confirming the input data and the process information, starting a data analysis process corresponding to the sequencing off-line data of the gene sample, and generating genetic variation detection information of the gene sample;

and starting an annotation process corresponding to the sequencing off-line data of the gene sample, and annotating the gene variation detection information of the gene sample to obtain the gene variation annotation information of the gene sample.

Optionally, the associating and reading the sample information of the gene sample, the genetic variation annotation information of the gene sample, and a database in a knowledge base platform to obtain associated data corresponding to the gene sample includes: and comparing the sample information of the gene sample, the gene variation annotation information of the gene sample with the data units in the database to obtain the associated data corresponding to the gene sample.

Optionally, the method further includes: judging the sample information of the gene sample, the gene variation annotation information of the gene sample and the associated data corresponding to the gene sample, and performing decision output to obtain an output statistical file; and calling a report template matched with the sample information of the gene sample and the statistical file, calling the information of the statistical file, and generating an interpretation report.

In accordance with the same object, a third aspect of one or more embodiments of the present disclosure provides a tumor precise medication interpretation device, comprising:

the genetic variation annotation information acquisition module is used for docking sequencing off-line data of a genetic sample, starting a data analysis process and acquiring genetic variation annotation information of the genetic sample;

the sample information acquisition module is used for acquiring sample information of the gene sample;

and the associated data acquisition module is used for reading the sample information of the gene sample, the gene variation annotation information of the gene sample and a database in a knowledge base platform in an associated manner to acquire associated data corresponding to the gene sample.

Optionally, the genetic variation annotation information acquisition module is specifically configured to:

or the like, or, alternatively,

Optionally, the associated data acquiring module is specifically configured to: and comparing the sample information of the gene sample, the gene variation annotation information of the gene sample with the data units in the database to obtain the associated data corresponding to the gene sample.

Optionally, the apparatus further comprises: a statistical file obtaining module, configured to judge sample information of the gene sample, genetic variation annotation information of the gene sample, and associated data corresponding to the gene sample, perform decision output, and obtain an output statistical file; and the interpretation report generating module is used for calling a report template matched with the sample information of the gene sample and the statistical file, calling the information of the statistical file and generating an interpretation report.

A fourth aspect of one or more embodiments of the present specification provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method according to any one of the first aspect of the specification when executing the program.

A fifth aspect of one or more embodiments of the present specification provides, for the same purpose, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of the first aspects of the present specification.

As can be seen from the above description, the tumor precise medication interpretation system, the tumor precise medication interpretation method and the tumor precise medication interpretation device provided in one or more embodiments of the present specification include a task management platform, a knowledge base platform, and a report interpretation platform connected to the task management platform and the knowledge base platform, respectively; when tumor accurate medication is read, a data analysis process is started through a sequencing off-line data automatic docking analysis task of a gene sample, variation result information after annotation is automatically obtained and checked, comprehensive and rich reading knowledge data is collected, stored and updated, the requirement of information reading in the reading process is met, sample information, variation result information after annotation and data in a knowledge base platform are integrated for relevant reading, and a report template is called to automatically generate a reading report; the tumor accurate medication reading system can realize full-automatic intelligent reading of tumor sequencing data accurate medication, comprehensively cover variation types and the field of tumor treatment medication, improve the specialty and guidance of medication, provide auxiliary decision for clinical personalized medication and treatment, improve the analysis efficiency and save the treatment cost.

Drawings

In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.

Fig. 1 is a schematic structural diagram of a tumor precise medication interpretation system according to one or more embodiments of the present disclosure;

fig. 2 is a schematic flowchart of a tumor precise medication interpretation method according to one or more embodiments of the present disclosure;

fig. 3 is an explanation of step S21 in fig. 2;

fig. 4 is a schematic structural diagram of a tumor precise medication interpretation device according to one or more embodiments of the present disclosure;

fig. 5 is a more specific hardware structure diagram of an electronic device according to one or more embodiments of the present disclosure.

Detailed Description

For the purpose of promoting a better understanding of the objects, aspects and advantages of the present disclosure, reference is made to the following detailed description taken in conjunction with the accompanying drawings.

It is to be noted that unless otherwise defined, technical or scientific terms used in one or more embodiments of the present specification should have the ordinary meaning as understood by those of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in one or more embodiments of the specification is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections.

With the popularization and development of accurate medical treatment and the reduction of sequencing cost, numerous organizations at home and abroad begin to provide detection and interpretation services of individualized accurate treatment for tumor patients. As the industry belongs to emerging industries, interpretation standards are not perfect enough, and result interpretation is a core link for restricting the application of accurate treatment and transformation of tumors. At present, the existing accurate tumor medication service has certain limitations, which are mainly embodied in the following aspects:

1) the method adopts a pure manual mode to collect and arrange data and issue a medication guidance report, and the interpretation mode has low efficiency and can be influenced to a certain extent;

2) the interpretation and variation of the data recording are single or limited, and the data integration and utilization are to be improved;

3) the interpretation and medication scheme mainly focuses on targeting and chemotherapy drugs, the interpretation content is incomplete, and the immunological drugs are concerned and accepted day by day and should be actively included;

4) the medication interpretation process is centered on gene variation, and has insufficient association on the action mechanism of the medicament, sample information and the like, so that the guidance value of the clinician is to be improved.

Therefore, in the prior art, a certain promotion space exists for reading accurate tumor medication in accuracy, efficiency, comprehensiveness, data utilization and guidance value, clinical requirements cannot be well met, and high-efficiency and high-quality services are provided.

In order to solve the above problems, the present specification provides a tumor accurate medication interpretation system, a method and a device for interpretation, where the tumor accurate medication interpretation system includes a task management platform, a knowledge base platform, and a report interpretation platform connected to the task management platform and the knowledge base platform, respectively; when tumor accurate medication is read, a data analysis process is started through a sequencing off-line data automatic docking analysis task of a gene sample, variation result information after annotation is automatically acquired and checked, comprehensive and rich reading knowledge data is maintained through collection, storage and updating, the requirement of information reading in the reading process is met, sample information, variation result information after annotation and data in a knowledge base platform are integrated for relevant reading, and a report template is called to automatically generate a reading report. The method and the device can be applied to electronic equipment such as a tablet personal computer, a smart phone and a computer, and are not limited specifically.

For the convenience of understanding, the tumor precise medication reading system is described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic structural diagram of a tumor precise medication interpretation system provided in the present specification; as shown in fig. 1, the tumor precise medication interpretation system comprises a task management platform 1, a knowledge base platform 2 and a report interpretation platform 3, wherein the report interpretation platform 3 is respectively connected with the task management platform 1 and the knowledge base platform 2; the task management platform 1 is used for automatically docking sequencing off-line data of a gene sample, starting a data analysis process, and acquiring and viewing variation result information after annotation; the knowledge base platform 2 is used for constructing, collecting, storing and maintaining and reading knowledge data; the report interpretation platform 3 is used for performing associated reading on the sample information of the gene sample, the annotated variation result information and interpretation knowledge data in the knowledge base platform, and calling a report template to generate an interpretation report.

The tumor accurate medication interpretation system can realize full-process automatic intelligent interpretation of tumor sequencing data accurate medication, comprehensively cover the fields of variation types and tumor treatment medication, improve the specialty and guidance of medication, provide auxiliary decision for clinical personalized medication and treatment, improve the analysis efficiency and save the treatment cost.

In some possible implementations, the report interpretation platform 3 is also used to modify, audit, and download interpretation reports. In practical application, a user can modify, audit and download the interpretation report through the report interpretation platform 3, so that the user can conveniently obtain a more exact interpretation report.

In some possible embodiments, the task management platform 1 includes a data transmission section 11, a task delivery section 12, a biological information automation analysis section 13, a variant annotation information section 14, and a variant visualization section 15, which are connected in sequence.

The data transmission block 11 is used for automatically extracting sequencing off-line data of the gene sample to obtain input data and flow information so as to facilitate automatic analysis of data in a subsequent process.

The task delivery plate 12 is used for confirming input data and flow information through visual interactive operation and starting a biological information automatic analysis plate 13. In practical application, in one case, the task delivery plate 12 receives an operation instruction of a user through visual interactive operation, confirms input data and flow information in response to the operation instruction of the user, and starts the biological information automatic analysis plate 13; in one case, the user confirms the input data and the flow information through visual interactive operation and issues an operation instruction, and the task delivery block 12 starts the biological information automation analysis block 13 in response to the operation instruction of the user.

The biological information automatic analysis plate 13 is used for generating a variation detection information file which corresponds to the gene sample and is used for describing genome variation through an analysis process corresponding to the sequencing off-line data of the gene sample; the biological information automatic analysis plate 13 generates a variation detection information file corresponding to the gene sample and used for describing genome variation by butting an analysis flow corresponding to the sequencing off-line data of the gene sample; the task management platform 1 can detect various variation forms such as single nucleotide variation, insertion/deletion mutation, copy number variation, structural variation and the like of genes, can also provide detection and analysis processes of a whole exon, a whole genome and various customized gene packages, and meets the off-line data analysis requirements of different sequencers.

The variant annotation information section 14 is used for annotating the variant detection information file through an annotation process corresponding to the sequencing offline data of the gene sample to generate a variant annotation information file; the variation annotation information section 14 annotates the variation detection information file generated by the biological information automation analysis section 13 through an annotation process to obtain a corresponding variation annotation information file.

The variant visualization section 15 is used for visually presenting the variant annotation information file; the variant visualization section 15 visually presents the variant annotation information file generated by the variant annotation information section 14, so that a user can conveniently view a BAM (band-effective Mapping) diagram, a sequencing depth, a base quality value, a Mapping value, a transcript, a public database and the like of a gene variant locus, and can conveniently view variant authenticity.

In some possible embodiments, the knowledge base platform 2 includes a database updating maintenance block 27, a database security management block 28, and a data management system building block 21, a data query collection block 22, a data extraction and cleaning block 23, an evidence grading block 24, a data integration entry block 25, and a data auditing block 26, which are connected in sequence.

The data management system building block 21 is used for determining a data set to be acquired and the structural information of the data set, completing building of a database framework, and building a database according to the data set and the structural information of the data set; the data related to tumor medication guidance and the structural framework of a related tumor medication reading database which need to be extracted are determined through preliminary investigation, and the database built by the data management system building block 21 comprises a tumor information unit, a drug information unit, a genetic variation clinical meaning unit, a gene analysis unit, a targeted therapy and evidence grade block unit, a chemical drug therapy and evidence grade unit, an immunotherapy and evidence grade unit, a tumor prognosis and evidence grade unit, a biomarker unit, a clinical test unit and a reference document unit.

The tumor information unit is used for storing basic introduction of tumors, relationship between the tumors and pathogenic genes and introduction of tumor treatment progress; the drug information unit stores information of targeted drugs, chemotherapeutic drugs and immune drugs related to accurate medication; the gene variation information unit stores the tumor hotspot gene variation information; the gene variation clinical meaning unit stores clinical meaning information of gene variation; the gene analysis unit stores gene biological functions and information of the relationship between genes and tumorigenesis and development; the targeted therapy and evidence grade unit stores information for guiding tumor targeted therapy and tumor targeted therapy evidence grade; the chemical drug treatment and evidence grade unit stores information for guiding the tumor chemical drug treatment and the evidence grade of the tumor chemical drug treatment; the immunotherapy and evidence grade unit stores information for guiding tumor immunotherapy and tumor immunotherapy evidence grade; the tumor prognosis and evidence grade unit stores information for guiding tumor prognosis and tumor prognosis evidence grade; the biomarker unit stores immunotherapy-related genes and biomarker information; the clinical test unit stores Chinese clinical test and international clinical test database information; the reference unit stores a reference source of instructional information.

The biomarker information may include TMB, MSI, PD-L1, without limitation; the TMB judging standards are that the TMB value judges the state TMB-H (> <20Muts/Mb), TMB-M (5< TMB <20Muts/Mb) and TMB-L (< ═ 5Muts/Mb) of the TMB. MSI status of MSI value determination: MSI-H represents that the detection value of the instability level of the microsatellite is high, and MSI-L represents that the detection value of the instability level of the microsatellite is low; MSI-H represents that the number of the changed STRs is more than or equal to 20 percent; MSI-L indicates that the number of STRs that changed is < 20%. PD-L1 expression and interpretation criteria: tumor cells tc (tumor cell) represent the proportion of cells presenting any intensity of cell staining (PD-L1 expression) in the white slide examined; TC 3: the expression cell ratio is more than or equal to 50 percent, and the PD-L1 has high expression; TC 2: the expression cell ratio is more than or equal to 5 percent and less than 50 percent, and the expression of PD-L1 is moderate; TC 1: the expression cell ratio is more than or equal to 1 percent and less than 5 percent, the expression of PD-L1 is low, and the like; TC 0: the expression cell ratio is less than 1%, and the expression of PD-L1 is negative.

The tumor information unit and the gene analysis unit are associated by combining a disease ID and a gene ID; the gene analysis unit and the gene variation information unit are associated by combining a gene ID and a variation ID; the genetic variation information unit and the genetic variation clinical meaning unit are associated by combination of variation ID and disease ID; the gene variation clinical meaning unit is respectively associated with the targeted therapy and evidence grade unit, the chemical drug therapy and evidence grade unit, the immunotherapy and evidence grade unit and the tumor prognosis and evidence grade unit through the combination of a disease ID and a variation ID; the tumor information unit and the drug information unit are associated by a disease ID and drug ID combination; the medicine information unit is respectively associated with the targeted therapy and evidence grade unit, the chemical therapy and evidence grade unit, the immunotherapy and evidence grade unit and the tumor prognosis and evidence grade unit through the combination of a disease ID and a medicine ID; the clinical test unit is respectively associated with the targeted therapy and evidence grade unit, the chemical drug therapy and evidence grade unit, the immunotherapy and evidence grade unit and the tumor prognosis and evidence grade unit through the combination of a disease ID and a drug ID; the biomarker unit and the tumor immunotherapy and evidence grade unit are associated by a disease ID and biomarker name combination, or by a disease ID and biomarker ID combination; the reference unit is respectively associated with the gene variation information unit, the gene variation clinical meaning unit, the gene analysis unit, the drug information unit, the tumor information unit, the targeted therapy and evidence grade unit, the chemical drug therapy and evidence grade unit, the immunotherapy and evidence grade unit, the tumor prognosis and evidence grade unit, the biomarker unit and the clinical test unit through reference IDs.

When the database is used for accurate tumor medication reading, a search keyword is input into a search box of the data unit, and the search keyword is compared with information in the data unit to obtain a search result matched with the search keyword; and because each data unit in the database is associated through the same key field or the same key field combination, the information of the corresponding retrieval key field can be obtained in the data unit associated with the retrieval key field input in any data unit in the database, and therefore, the comprehensive information of accurate tumor medication can be conveniently obtained by reading personnel.

The database framework also comprises a key field input unit, and the key field input unit inputs the information corresponding to the key field into the corresponding field position and the association rule of the database framework according to the unified standardized input rule, so that the construction of the database framework is completed, and the database for guiding the clinical tumor personalized medication is obtained.

The data query collection block 22 is used for downloading collected data from a public data source according to a data set to be collected determined by the data management system building block; the acquired data may include biomarker information, genetic information, variation information, disease information, drug information, clinical evidence information, and the like related to tumor chemotherapy, targeting therapy, and immunotherapy, and is not limited specifically.

In practical applications, the collected data may be downloaded from the following common data sources, which mainly include the following aspects:

1) extracting treatment information related to tumor gene variation from treatment guidelines of websites such as NCCN, ESMO, ASCO and CSCO;

2) extracting tumor gene variation related treatment information from drug labels such as FDA (food and drug administration) and EMA (electron emission technology);

3) downloading the variation information of tumor patients from databases such as COSMIC, Clinvar, CIViC, OncoKB, Cancer Hotspots and the like, and screening out high-frequency mutant genes;

4) inquiring related genes of the tumor pathway from a KEGG biological pathway database and literature;

5) downloading information related to gene drug therapy, metabolism, toxicity and other indications from databases such as CIViC, OncoKB, my cancer gene, PharmGKB and the like;

6) downloading Gene and medicine data from a genome-related database such as NCBI Gene, Genbank, EMBL, Gene Ontology, Drugbank, PubChem and the like, and extracting Gene and medicine-related information;

7) downloading Disease data from databases such as Disease Ontology, ICD10, MalaCards and the like;

8) downloading clinical trial data from databases such as clinical Trials and drug clinical trial registration and information disclosure platforms (Chinadrug Trials);

9) screening NCBI Pubmed and google academic literatures, selecting gene variation and medicine related literatures, and extracting information related to gene variation and intervention treatment. When the document is screened, text mining is carried out through various types of key words such as genes, diseases, drug intervention, drug effects and the like, and corresponding field evidences are provided for realizing abstract or full text downloading, analysis and classification of the documents.

The data extraction and cleaning block 23 is used for extracting information from the data downloaded by the data query and collection block 22 according to an identifiable mode, cleaning and sorting the extracted information according to defined attributes and field rules, and classifying the information into different data units. The data extraction and cleaning block 23 extracts information from the downloaded data according to an identifiable mode, cleans the information, checks the consistency of the data, processes invalid values, missing values and repeated values, and removes the data which do not accord with the input conditions; the information extracted from the downloaded data is cleaned and sorted according to defined attributes and field rules, and then classified into various data units.

The evidence grading block 24 is used for grading and storing the data after the data extraction and cleaning block processing according to the evidence-based medical evidence grade judgment standard and the AMP guideline standard; the evidence grading block 24 performs importance grading and storage on the data processed by the data extraction and cleaning block 23 according to an AMP guideline standard, and judges and marks clinical significance according to the relationship among the biomarker, the tumor type and the medicine and the evidence grade of evidence-based medicine.

In practical application, the supporting evidence grade is divided into six types including Level1A, Level 1B, Level 2C, Level 2D, Level 3 and Level4 according to the standard design of the reference AMP guideline; wherein, when the biomarker is associated with clinical evidence information between the targeting and immune drugs, the evidence grade is defined as:

level 1A-information approved by professionally approved medical guidelines or major health systems, standard treatment biomarker prediction recommended by guidelines such as NCCN/CSCO, FDA/NMPA approved drugs suitable for the tumor.

Level 1B-multiple or one high quality random control study (RCT) study, more than three clinical stages, with significant statistical test results; the random controlled trial (randomized controlled trial) randomly groups research objects, performs different interventions on different groups, has various advantages of being capable of avoiding various biases possibly occurring in the design and implementation of clinical trials to the maximum extent, balancing confounding factors, improving the effectiveness of statistical tests and the like according to the difference of contrast effects, and is generally known as a gold standard for evaluating intervention measures.

Level 2C — standard treatment biomarkers consensus mentioned in the NCCN guideline for this tumor or other guidelines predict FDA/NMPA approval for other tumor (non-present tumor) drugs, significant in at least one clinical study over stage ii and under stage iii or a plurality of studies over stage ii but not significant, and also includes prospective studies, systematic assessment or Meta analysis of retrospective analysis, case controls, etc.; systematic review (Systematic review) is a scientific basis for the diagnosis and treatment of diseases by systematically and clearly collecting, selecting and evaluating relevant clinical original researches according to a specific clinical problem, screening qualified subjects and extracting and analyzing data from the qualified subjects; meta analysis refers to the quantitative analysis of multiple independent, synthesizable clinical studies for the same clinical problem, using statistical methods.

Level 2D-preclinical tests such as animal tests, cell tests, case reports with inconsistent results, expert opinions/personal opinions; case reporting: exhaustive clinical reports of single or less than 10 cases. Expert opinion/personal opinion: expert opinions without explicitly stated critical evaluations, or inferences based on physiology, laboratory studies, or obtained on a "first line of thumb" basis, are empirical and have not been rigorously demonstrated.

Level 3, which is a current unreliable research report related to treatment or does not exist tumor genes in a known database, such as oncogenes/cancer suppressor genes, driver genes, high-frequency mutant genes, tumor pathway related genes and the like.

Level 4-No tumor-related research reports exist in the common normal population database at present.

Wherein, the evaluation of tumor targeting, immunity and prognosis curative effect is recommended for Level1 and Level 2; when the clinical evidence association between the biomarker and the drug is sensitive, the evidence ranks from high to low are ranked as follows: level1A, Level 1B, Level 2C and Level 2D. Similarly, when the clinical evidence correlation between the biomarker and the drug is drug resistance, the evidence grade is recorded according to the Level 1A-Level 2D division standard.

The corresponding relationship between the biomarker and the chemotherapeutic drug is inconsistent with the evidence classification of the corresponding relationship between the targeting drug and the immunological drug, and the classification of the grades is as follows: according to PharmGKB website http:// www.pharmgkb.org/page/clinAnn, wherein Level 1A: the annotation is based on guidelines approved by the medical community or approved by some major health system; level 1B: annotation is based on multiple statistically significant studies; level 2A: the annotation is based on multiple repeated studies, so the pharmacodynamic relationship is likely to be meaningful; level 2B: annotations were based on multiple repeat studies, but some studies may be statistically insignificant or the number of samples is small; level 3: annotations differ significantly based on only 1 term; level 4: annotations were based on only a few cases, non-authoritative studies or in vitro studies of molecular function. The evidence ranks from high to low are as follows: level1A, Level 1B, Level2A, Level 2B, Level 3 and Level 4.

The clinical significance of evidence grade judgment and annotation of evidence-based medicine is divided into four grades of I-IV. Wherein Level I characterizes treatment evidence data for a particular cancer approved by a drug administration or included in clinical guidelines, or diagnosis or prognostic evidence (Level 1A) for a particular cancer species included in clinical guidelines; level II characterizes clinical trials or other population-based studies and obtains expert consensus therapeutic, diagnostic or prognostic evidence data (Level 1B) for a particular cancer; grade III characterizes evidence of other cancers treated with drugs approved by the drug administration, or biomarker evidence that is being used as an admission criterion for clinical trials, or clinically significant diagnostic or prognostic evidence based on multiple small trials (Level 2C); grade IV characterizes preclinical studies showing biomarker evidence of therapeutic significance, or small trials or cases of reports showing biomarker evidence (Level 2D) that can aid in disease diagnosis or prognosis. Wherein, the grade I and the grade II have stronger clinical significance, and the grade III and the grade IV have potential clinical significance.

The data integration and entry block 25 is used for integrating the data after the data extraction and cleaning block 23 is processed, and entering the data management system to construct the block 21; the data integration entry block 25 integrates the data extracted by the data extraction and cleaning block 23 after cleaning according to the structural information of the data set to be acquired, which is determined by the data management system construction block 21, to obtain a target data set, and automatically enters a database framework built by the data management system construction block 21 through a script program, wherein the entry script can be realized by a Python language, and can realize local operation.

The data auditing block 26 is used for auditing data of the database according to the record ID of the input information; the data auditing block 26 realizes the auditing of the data in the database constructed by the data management system construction block 21 according to the record ID of the input information and double manual auditing, records the name and date of a modification submitter, the type description of the modification content and the like, and provides an SQL log for subsequent users to trace the source of the information.

The database updating and maintaining block 27 is used for regularly updating and checking the content of the database, regularly collecting the latest data related to the data set to be acquired, which is determined by the data management system building block, in the public data source, and regularly updating the data; the database updating and maintaining block 27 regularly updates and verifies the content and structure of the database constructed by the data management system construction block 21, regularly collects the latest data related to the data set to be collected in the public data source, regularly updates the data by adopting an automatic process and manual inspection combined mode, and performs professional evaluation to ensure the comprehensiveness and the specialty of the database.

The database security management block 28 is used for providing security guarantee and management for the system and data of the database; the method comprises a configuration management sub-version block, an account management sub-version block, a safety management sub-version block of an operating system, a data backup management sub-version block and a log management sub-version block; the configuration management sub-version block is responsible for system maintenance management such as service start and stop of a database, version of an operating system, file system capacity, system performance and the like; the account management sub-version block changes the account and the password of the database and also manages the establishment, deletion and modification of the account authority of the database; the security management sub-version of the operating system is to access the data in the database only through the DBMS, and the enabled identity is checked to be legal through the security measures provided by the DBMS: each user with the use authority has an identification identity and a password in the system, the use authority is provided after the identification, the use users of the third-party database are controlled, and the operation authority of the third-party database for accessing the database is set, namely, each user can only access the data with the authority setting and carry out comprehensive audit on the operation of the user; the data backup management sub-version block regularly performs backup and recovery tests on the data in the database; the log in the log management sub-version block is composed of an operating system, a database management system and the like, the content can comprise system events, error information and the like, the log storage period is determined according to the risk level of the system, the log cannot be randomly modified and deleted, and the log is stored in an encrypted form.

In some possible embodiments, the report reading platform 3 includes a sample information entry section 31, a call section 32, a decision tree implementation section 33, a result output section 34, a report automatic generation section 35, a report review section 36, and a report download section 37, which are connected in sequence.

The sample information input block 31 is used for inputting sample information and analysis requirements; the sample information entry section 31 is responsive to user input of sample information and analysis requirements for use by the call section 32. The sample information refers to phenotype information related to the gene sample, and may include sample type, disease name (clinical diagnosis), sampling time, censorship unit, sample collection date, sample part, sample number, sample detection mechanism, and name, sex, age, family history, treatment history, etc. of the subject to which the sample belongs, and is not particularly limited; the sample information entry block 31 can identify sample information input by a user according to a sample number, and can select analysis requirements according to clinical practical conditions.

The calling block 32 is used for calling the sample information, the sample variation annotation information and the associated data corresponding to the sample variation annotation information in the database established by the knowledge base platform 2.

The decision tree implementation block 33 is used for automatically judging the sample information, the sample variation annotation information and the associated data and performing decision output; the decision tree implementation block 33 performs automatic determination and decision output on the sample information, the sample variation annotation information, and the associated information corresponding to the sample variation annotation information acquired from the database of the knowledge base platform, and the process of performing automatic determination and then performing decision output by the decision tree implementation block 33 is as follows:

1) performing variation screening on variation annotation information of the examiner by accessing a database constructed by the knowledge base platform 2; 2) screening variation information corresponding to treatment, and extracting treatment methods and curative effect information corresponding to the variation information; 3) and (4) judging the information related to the treatment method according to the target drugs, the chemotherapeutic drugs, the immunological drugs and the tumor prognosis sequence.

The result output plate block 34 is used for naming the output result of the decision tree implementation plate block 33 according to the biological information automatic analysis plate block corresponding to the output result and outputting a statistical file; the result output section 34 names the output result of the decision tree implementation section 33 according to the biological information automatic analysis section corresponding to the output result, and then outputs a statistical file.

The report automatic generation section 35 is used for generating a report based on the sample information and the information of the statistical file, which is called by the report template matching method. The report automatic generation block 35 matches a report template according to the sample information and the statistical file, and invokes information of the statistical file output by the result output block 34 to generate a report. The report content may include sample information of the subject, gene mutation information, mutation and drug analysis information, detection analysis instructions, reference documents, and the like, and is not limited specifically. Through generating the report, the user can conveniently and directly obtain the tumor accurate medication reading result. The report auditing section 36 is used for auditing the report to obtain a target interpretation report; in practical application, a user can audit the report generated by the report automatic generation section 35 through the report audit section 36, and check the integrity and accuracy of the report to obtain a target interpretation report.

The report download block 37 is used for managing reports generated by the report interpretation platform 3; in practical application, a user can manage the report generated by the report interpretation platform 3 through the report downloading block 37, so as to realize downloading, viewing and saving of the report.

Fig. 2 is a schematic flow chart of a tumor precise medication interpretation method provided in the present specification; as shown in fig. 2, the method for accurately reading a tumor with a drug comprises:

s21, testing and downloading data of the gene sample, starting a data analysis process, and obtaining gene variation annotation information of the gene sample;

s22, obtaining sample information of the gene sample;

and S23, performing correlation reading on the sample information of the gene sample and the gene variation annotation information of the gene sample and a database in the knowledge base platform to obtain correlation data corresponding to the gene sample.

The associated data corresponding to the gene sample comprises the clinical significance of the gene variation, the clinical test information of the tumor, the tumor immunotherapy and evidence grade corresponding to the gene sample, and the targeted therapy and evidence grade information, the immunotherapy and evidence grade information, the chemical therapy and evidence grade information, the prognosis evaluation and evidence grade information and the respective corresponding reference guidance basis of the gene variation corresponding to the gene sample.

In practical application, the gene sample refers to gene sample data to be analyzed of a tumor patient; the sample information of the genetic sample refers to phenotype information related to the sample, and may include sample type, disease name (clinical diagnosis), sampling time, censorship unit, sample collection date, sample part, sample number, sample detection mechanism, and name, sex, age, family history, treatment history, etc. of the subject to which the sample belongs, and is not particularly limited; the relevant data corresponding to the gene sample refers to data which is stored in the database and is closely related to the gene sample.

An electronic device (hereinafter referred to as the electronic device) executing the method acquires sample information of the gene sample by a user input method, namely, the user inputs the sample information of the gene sample into the electronic device, and the electronic device acquires the sample information of the gene sample input by the user; the user may input the sample information of the gene sample after the electronic device obtains the genetic variation annotation information of the gene sample, or may input the sample information of the gene sample before the electronic device obtains the genetic variation annotation information of the gene sample, which is not limited specifically.

It can be understood that the tumor accurate medication interpretation method can realize full-process automatic intelligent interpretation of tumor sequencing data accurate medication, comprehensively cover variation types and the field of tumor treatment medication, improve the specialty and guidance of medication, provide auxiliary decision for clinical personalized medication and treatment, improve analysis efficiency and save treatment cost.

Fig. 3 is an explanation of step S21; as shown in fig. 3, in practical applications, in order to perform accurate tumor drug interpretation on a gene sample, it is first necessary to obtain annotation information of gene variation of the gene sample; in some possible embodiments, the docking of the sequencing data of the gene sample, starting the data analysis process, and obtaining the annotation information of the genetic variation of the gene sample comprises:

s31, docking sequencing off-line data of the gene sample, and extracting the sequencing off-line data of the gene sample to obtain input data and process information;

s32, responding to an operation instruction sent by a user, confirming input data and process information, starting a data analysis process corresponding to the sequencing off-line data of the gene sample, and generating genetic variation detection information of the gene sample; or the like, or, alternatively,

responding to an operation instruction sent by a user after confirming input data and process information, starting a data analysis process corresponding to the sequencing off-line data of the gene sample, and generating genetic variation detection information of the gene sample;

and S33, starting an annotation process corresponding to the sequencing off-line data of the gene sample, and annotating the gene variation detection information of the gene sample to obtain the gene variation annotation information of the gene sample.

In this embodiment, the input data refers to the result data of double-ended sequencing, and may be in a compressed form, i.e., gz end, or in a non-compressed format, i.e., fastq format; if the input data may include a BED region file, detecting a BED region mutation; if the BED region file is not included in the input data, genome-wide mutations are detected. Depending on the purpose of the analysis, it may be necessary to provide a double-sided primer file when the gene package data is involved. For example, the input data for whole genome detection is mainly the paired end sequencing result of tumor sample and the paired end sequencing result of normal sample.

The process information refers to a tumor whole-external/whole-genome/gene packet analysis process, the analysis items relate to SNV/InDel/CNV/SV, and the specific steps in the analysis process are as follows: filtering original data by using fastp software, comparing and sequencing filtered data with a reference genome version (Grch37) by using BWA software, removing a PCR repeated sequence by using Picard software, performing realign and recall correction on the duplicate bam, obtaining corrected bam by using corresponding variation detection software, obtaining SNV, InDel, CNV and SV analysis results, and storing the analysis results in a variation identification file VCF. For example, the process information of whole genome detection can be extracted from the analysis process of "physical pipeline analysis (wgs)", and the subsequent operations can be performed.

In practical application, in order to obtain the genetic variation annotation information, sequencing off-line data of a gene sample can be docked first, and the testing off-line data is extracted to obtain input data and flow information required for starting accurate tumor medication interpretation.

Then, input data and process information are confirmed, and a data analysis process corresponding to the sequencing off-line data is started. Under one condition, a user confirms whether input data and process information are correct through visual interactive operation, if so, an operation instruction is sent out, and the electronic equipment responds to the operation instruction of the user, starts a data analysis process corresponding to sequencing off-line data, and obtains genetic variation detection information of a gene sample; at this time, the operation instruction of the user is to start the data analysis process. In one case, a user sends an operation instruction through visual interactive operation, the electronic equipment responds to the operation instruction of the user to confirm input data and flow information, starts a data analysis flow corresponding to sequencing off-line data, and obtains genetic variation detection information of a gene sample; at this time, the user's operation instruction is to determine whether the input data and the process information are correct and to start the data analysis process.

And after the genetic variation detection information is obtained, starting an annotation process corresponding to the sequencing off-line data, and annotating the genetic variation detection information to obtain the genetic variation annotation information corresponding to the genetic sample.

It can be understood that the genetic variation annotation information corresponding to the gene sample is obtained by performing data analysis on the sequencing off-line data, so that the database can perform correlation reading based on the genetic variation annotation information, and the correlation data of the gene sample can be obtained accurately.

In practical application, in order to perform accurate tumor medication interpretation on a gene sample and obtain gene variation annotation information, data in a database needs to be further read; then, in some possible embodiments, the associating and reading the sample information of the gene sample and the genetic variation annotation information of the gene sample with a database in a knowledge base platform to obtain associated data corresponding to the gene sample includes:

and comparing the sample information of the gene sample, the gene variation annotation information of the gene sample with the key fields or key field combinations of the data units in the database to obtain the associated data corresponding to the gene sample.

In this embodiment, when performing the association reading, the sample information and the genetic variation annotation information of the gene sample are both compared with the data units in the database for the key field comparison or the key field combination, the same key field or key field combination is obtained through the comparison, then the data corresponding to the same key field or key field combination is obtained by screening from the data stored in the data units, and further, the progressive key field comparison or key field combination comparison can be performed between different data units, so as to obtain the association data corresponding to the gene sample from the database.

In practical application, the sample information of the gene sample comprises disease information of the gene sample; the genetic variation annotation information of the gene sample comprises detected biomarkers and marker level state results of the gene sample; then, the sample information of the gene sample, the gene variation annotation information of the gene sample, and the database in the knowledge base platform are read in a correlated manner to obtain the correlated data corresponding to the gene sample, and the following method can be adopted:

comparing the genetic variation annotation information of the gene sample with genetic variation information in a genetic variation information unit in a database of a knowledge base platform 2, screening out the genetic variation information consistent with the genetic variation annotation information of the gene sample from the genetic variation information unit, and further acquiring a genetic variation ID and a disease ID corresponding to the genetic variation information in the genetic variation information unit; and comparing the screened genetic variation ID and the screened disease ID with key fields of the genetic variation clinical significance unit, and screening out the genetic variation clinical significance corresponding to the genetic sample. Comparing the screened clinical significance of the gene variation with gene variation IDs and disease IDs of a targeted therapy and evidence grade unit, a chemical therapy and evidence grade unit, an immunotherapy and evidence grade unit and a prognosis evaluation and evidence grade unit respectively, and screening to obtain targeted therapy and evidence grade information, immunotherapy and evidence grade information, chemical therapy and evidence grade information, prognosis evaluation and evidence grade information of the gene variation corresponding to the gene sample; the target treatment and evidence grade information, the chemical treatment and evidence grade information, the immunotherapy and evidence grade information, the prognosis evaluation and the evidence grade information respectively comprise the names of the treatment medicines. And (3) comparing the targeted therapy and evidence grade information, the chemical drug therapy and evidence grade information, the immunotherapy and evidence grade information and the prognosis evaluation and evidence grade information of the gene variation corresponding to the screened gene sample with the reference document ID of the reference document unit respectively, and screening to obtain reference guidance bases corresponding to the targeted therapy and evidence grade information, the chemical drug therapy and evidence grade information, the immunotherapy and evidence grade information and the prognosis evaluation and evidence grade information respectively. And comparing the name or the disease of the treatment drug with the disease ID and the drug ID of the clinical test unit, and screening to obtain the tumor clinical test information corresponding to the gene sample.

And comparing the detected biomarker and marker level state results of the gene sample with the biomarker unit to obtain the key fields of the user-defined biomarker, namely disease ID and biomarker ID, and acquiring tumor immunotherapy and evidence grade information corresponding to the gene sample by the immunotherapy and evidence grade unit based on the disease ID and the biomarker ID.

It can be understood that by associating and reading the sample information and the genetic variation annotation information of the gene sample with the database, more comprehensive and accurate associated data can be obtained, and the analysis efficiency is improved.

In practical application, after the associated data of the gene sample is obtained, further processing needs to be carried out on the sample information, the gene variation annotation information and the associated data; then, in some possible embodiments, the method further comprises:

judging the sample information of the gene sample, the gene variation annotation information of the gene sample and the associated data corresponding to the gene sample, and performing decision output to obtain an output statistical file;

and calling a report template matched with the sample information of the gene sample and the statistical file, calling the information of the statistical file, and generating an interpretation report.

In this embodiment, after obtaining the associated data corresponding to the gene sample, it is necessary to perform comprehensive judgment on the sample information, the genetic variation annotation information, and the associated data of the gene sample, and determine and output a treatment decision corresponding to the gene sample based on a judgment result; and when the judgment is carried out, acquiring the corresponding disease ID according to the sample information, matching and extracting the associated data such as information of clinical significance, treatment suggestion, support basis and the like by combining the gene ID in the gene variation annotation information or the biomarker ID in the biomarker information.

Then naming the output treatment decision according to the corresponding biological information automatic analysis plate block, and outputting a statistical file containing sample information, genetic variation annotation information, associated data and the treatment decision of the gene sample; and matching the interpretation report template according to the sample information and the statistical file, calling the information in the statistical file, filling in an interpretation report module, and generating an interpretation report.

The report template comprises basic information, detection results, medication and prognosis analysis, statement, reference documents, annexes and other main items. When the interpretation report template is filled in, the interpretation report template is respectively extracted from the sample information and the statistical file; for example, basic information is extracted from sample information of a gene sample, and detection results, drug administration and prognosis analyses, references, and the like are extracted from a statistical file. Specifically, the detection result items are retrieved from the variation annotation information and the related information of the variation clinical meaning unit, the medication and prognosis analysis, the related information of the variation annotation information and the variation medication/prognosis and related evidence grade unit, and the like.

In practical application, a user can modify, audit and download the interpretation report, so that the user can conveniently obtain a more exact interpretation report.

It can be understood that the sample information, the genetic variation annotation information and the associated data are further judged, the treatment decision is output based on the judgment result, and finally the interpretation report is generated, and the user can modify, check and download the interpretation report, so that a more accurate treatment decision suggestion about the gene sample can be provided for the user.

In conclusion, the tumor accurate medication interpretation system comprises a task management platform, a knowledge base platform and a report interpretation platform which is respectively connected with the task management platform and the knowledge base platform; when tumor accurate medication is read, a data analysis process is started through a sequencing off-line data automatic docking analysis task of a gene sample, variation result information after annotation is automatically obtained and checked, comprehensive and rich reading knowledge data is collected, stored and updated, the requirement of information reading in the reading process is met, sample information, variation result information after annotation and data in a knowledge base platform are integrated for relevant reading, and a report template is called to automatically generate a reading report; the tumor accurate medication reading system can realize full-automatic intelligent reading of tumor sequencing data accurate medication, comprehensively cover variation types and the field of tumor treatment medication, improve the specialty and guidance of medication, provide auxiliary decision for clinical personalized medication and treatment, improve the analysis efficiency and save the treatment cost.

It should be noted that the method of one or more embodiments of the present disclosure may be performed by a single device, such as a computer or server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the devices may perform only one or more steps of the method of one or more embodiments of the present disclosure, and the devices may interact with each other to complete the method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Fig. 4 is a schematic structural diagram of a tumor precise medication interpretation device provided in the present specification; as shown in fig. 3, the apparatus includes:

a gene variation annotation information acquisition module 41, configured to interface sequencing off-line data of the gene sample, start a data analysis process, and acquire gene variation annotation information of the gene sample;

a sample information acquiring module 42, configured to acquire sample information of a gene sample;

and the associated data acquiring module 43 is configured to perform associated reading on the sample information of the gene sample, the gene variation annotation information of the gene sample, and the database in the knowledge base platform, so as to acquire associated data corresponding to the gene sample.

In a possible embodiment, the genetic variation annotation information obtaining module 41 is specifically configured to:

docking sequencing off-line data of the gene sample, and extracting the sequencing off-line data of the gene sample to obtain input data and process information;

responding to an operation instruction of a user, confirming input data and process information, starting a data analysis process corresponding to the sequencing off-line data of the gene sample, and generating genetic variation detection information of the gene sample;

or the like, or, alternatively,

In a possible implementation, the association data obtaining module 42 is specifically configured to:

and comparing the sample information of the gene sample, the gene variation annotation information of the gene sample with each data unit in the database to obtain the associated data corresponding to the gene sample.

In a possible implementation manner, the apparatus further includes a statistical file obtaining module (not shown in the figure) and an interpretation report generating module (not shown in the figure); wherein the content of the first and second substances,

the statistical file obtaining module is used for judging the sample information of the gene sample, the gene variation annotation information of the gene sample and the associated data corresponding to the gene sample, making a decision and outputting to obtain an output statistical file;

and the interpretation report generating module is used for calling a report template matched with the sample information of the gene sample and the statistical file, calling the information of the statistical file and generating an interpretation report.

For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the modules may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.

The apparatus of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.

The present specification also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the method for tumor precise medication interpretation.

Fig. 5 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.

The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.

The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.

The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.

The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).

Bus 1050 includes a path that transfers information between various components of the device, such as processor 1010, memory 1020, input/output interface 1030, and communication interface 1040.

It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.

The present specification also provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method for tumor precise medication interpretation as set forth in any one of the above.

Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the spirit of the present disclosure, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.

In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures, for simplicity of illustration and discussion, and so as not to obscure one or more embodiments of the disclosure. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the understanding of one or more embodiments of the present description, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the one or more embodiments of the present description are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the disclosure, it should be apparent to one skilled in the art that one or more embodiments of the disclosure can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.

While the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.

It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. The tumor precise medication interpretation system is characterized by comprising a task management platform, a knowledge base platform and a report interpretation platform, wherein the report interpretation platform is respectively connected with the task management platform and the knowledge base platform; wherein the content of the first and second substances,

2. The system according to claim 1, wherein the report interpretation platform is further configured to modify, review and download the interpretation report.

3. The accurate tumor medication interpretation system according to claim 1, wherein the task management platform comprises a data transmission section, a task delivery section, a biological information automatic analysis section, a variation annotation information section and a variation visualization section which are connected in sequence; wherein the content of the first and second substances,

the data transmission block is used for automatically extracting sequencing off-line data of the gene sample to obtain input data and flow information;

the task delivery plate block is used for confirming the input data and the process information through visual interactive operation and starting the biological information automatic analysis plate block;

the biological information automatic analysis plate block is used for generating a variation detection information file which corresponds to the gene sample and is used for describing genome variation through an analysis process corresponding to the sequencing off-line data of the gene sample;

the variant annotation information section is used for annotating the variant detection information file through an annotation process corresponding to the sequencing offline data of the gene sample to generate a variant annotation information file;

the variant visualization layout block is used for visually presenting the variant annotation information file.

4. The accurate tumor medication interpretation system according to claim 1, wherein the knowledge base platform comprises a database updating maintenance section, a database security management section, and a data management system construction section, a data query collection section, a data extraction and cleaning section, an evidence grading section, a data integration entry section and a data auditing section which are connected in sequence; wherein the content of the first and second substances,

the data management system building block is used for determining a data set to be acquired and the structural information of the data set, completing building of a database framework, and then building a database according to the data set and the structural information of the data set;

the data query collection block is used for downloading collected data from a public data source according to the data set to be collected determined by the data management system construction block;

the data extraction and cleaning version block is used for extracting information from the data downloaded by the data query and collection version block according to an identifiable mode, cleaning and sorting the extracted information according to defined attributes and field rules, and classifying the extracted information into different data units;

the evidence grading edition block is used for grading and storing the data after the data extraction and cleaning edition block processing according to the evidence-based medical evidence grade judgment standard and the AMP guideline standard;

the data integration entry version is used for integrating the data after the data extraction and cleaning version processing, and entering the data into the data management system to construct a version;

the data auditing section is used for auditing the data of the database according to the record ID of the input information;

the database updating and maintaining block is used for regularly updating and checking the content of the database, regularly collecting the latest data related to the data set to be acquired, which is determined by the data management system building block, in a public data source, and regularly updating the data;

the database security management block is used for providing security guarantee and management for the system and data of the database.

5. The accurate tumor medication interpretation system according to claim 1, wherein the report interpretation platform comprises a sample information input section, a calling section, a decision tree implementation section, a result output section, a report automatic generation section, a report audit section and a report download section which are connected in sequence; wherein the content of the first and second substances,

the sample information input block is used for inputting sample information and analysis requirements;

the calling block is used for calling the sample information, the sample variation annotation information and associated data corresponding to the sample variation annotation information in a database established by the knowledge base platform;

the decision tree implementation block is used for automatically judging the sample information, the sample variation annotation information and the associated data and performing decision output;

the result output plate block is used for naming the output result of the decision tree implementation plate block according to the biological information automatic analysis plate block corresponding to the output result and outputting a statistical file;

the report automatic generation block is used for matching a report template based on the sample information and the statistical file and calling the information of the statistical file to generate a report;

the report auditing section is used for auditing the report to obtain a target interpretation report;

the report downloading section is used for managing the report generated by the report interpretation platform.

6. A method for accurate dosing and interpretation of a tumor, the method comprising:

obtaining sample information of the gene sample;

7. The method for accurately interpreting drugs for tumors according to claim 6, wherein the sequencing of the docked gene sample is performed on the data, a data analysis process is started, and the annotation information of genetic variations of the gene sample is obtained, which comprises:

or the like, or, alternatively,

8. The method for accurately interpreting drugs for tumors according to claim 6, wherein the reading of the sample information of the gene sample and the annotation information of the gene variation of the gene sample in association with the database in the knowledge base platform to obtain the associated data corresponding to the gene sample comprises:

and comparing the sample information of the gene sample, the gene variation annotation information of the gene sample with the data units in the database to obtain the associated data corresponding to the gene sample.

9. The method for precise dosing and interpretation of tumors as recited in claim 6, further comprising:

10. An accurate tumor medication reading device, the device comprising: