WO2024254825A1 - 一种用于基因检测的加速方法、装置及电子设备 - Google Patents

一种用于基因检测的加速方法、装置及电子设备 Download PDF

Info

Publication number
WO2024254825A1
WO2024254825A1 PCT/CN2023/100431 CN2023100431W WO2024254825A1 WO 2024254825 A1 WO2024254825 A1 WO 2024254825A1 CN 2023100431 W CN2023100431 W CN 2023100431W WO 2024254825 A1 WO2024254825 A1 WO 2024254825A1
Authority
WO
WIPO (PCT)
Prior art keywords
variation
data set
gene
variation data
quality control
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/100431
Other languages
English (en)
French (fr)
Inventor
唐静波
钟子寅
谢寅龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
MGI Tech Co Ltd
Original Assignee
MGI Tech Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by MGI Tech Co Ltd filed Critical MGI Tech Co Ltd
Priority to CN202380098537.3A priority Critical patent/CN121175755A/zh
Priority to PCT/CN2023/100431 priority patent/WO2024254825A1/zh
Publication of WO2024254825A1 publication Critical patent/WO2024254825A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
    • G16B20/20—Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection

Definitions

  • the present disclosure relates to the field of bioinformatics, and in particular to an acceleration method, device and electronic equipment for gene detection.
  • whole genome sequencing is a commonly used genetic analysis method that can quickly and inexpensively determine the complete genome sequence of an organism and detect a set of variants in its genome.
  • scale of whole genome data rises to 10,000 or 100,000 people, large-scale population genome analysis will face serious problems of memory overload and excessive time consumption. Therefore, how to efficiently use computing and storage resources to quickly and accurately analyze large-scale genome samples is a problem that needs to be solved.
  • the present disclosure provides an acceleration method, device and electronic device for gene detection to solve the problems in related technologies and improve the speed of population gene detection.
  • a first aspect embodiment of the present disclosure proposes an acceleration method for gene detection, the method comprising: obtaining a first variation data set and a second variation data set based on a first gene sample set, wherein the first gene sample set includes multiple gene sample variation data, and the first gene sample set is obtained by preprocessing the original data; obtaining a variation quality control model based on the second variation data set, and processing the first variation data set according to the variation quality control model to obtain a first variation detection result corresponding to the first variation data set.
  • obtaining the first variant data set includes: obtaining a gene variation density table; and merging the first gene sample set according to the gene variation density table to obtain the first variant data set.
  • merging the first gene sample set according to the gene variation density table to obtain the first variation data set includes: determining multiple intervals of the first gene sample set according to the gene variation density table; processing the gene sample variation data in the same interval to obtain multiple first variation data, and the multiple first variation data form the first variation data set.
  • obtaining the second variant data set includes: acquiring gene chromosome information; and merging the first variant data set according to the gene chromosome information to obtain the second variant data set.
  • merging the first variant data set according to gene chromosome information to obtain the second variant data set includes: determining multiple intervals of multiple first variant data according to the gene chromosome information; processing the first variant data in the same interval to obtain multiple second variant data, and the multiple second variant data form the second variant data set.
  • a variation quality control model is obtained based on a second variation data set, and a first variation data set is processed based on the variation quality control model to obtain a first variation detection result corresponding to the first variation data set, including: training a preset model using the second variation data set to obtain the variation quality control model; and screening the first variation data set based on the variation quality control model to obtain the first variation detection result.
  • obtaining a variation quality control model includes: obtaining a standard data set for gene variation detection; and training and constructing a variation quality control model based on a second variation data set and a standard data set for gene variation detection.
  • the method further includes: obtaining gene chromosome information; and merging the first variation detection results according to the gene chromosome information.
  • the method after processing the first variant data set according to the variant quality control model to obtain the first variant detection result, or after obtaining the first variant data set, the method also includes: acquiring a second gene sample set; obtaining a third variant data set according to the second gene sample set; processing the third variant data set according to the variant quality control model to obtain a second variant detection result corresponding to the third variant data set.
  • a second aspect embodiment of the present disclosure proposes an acceleration device for gene detection, the device comprising: an acquisition unit, used to obtain a first variation data set and a second variation data set based on a first gene sample set, wherein the first gene sample set includes multiple gene sample variation data, and the first gene sample set is obtained by preprocessing the original data; a processing unit, used to obtain a variation quality control model based on the second variation data set, and process the first variation data set according to the variation quality control model to obtain a first variation detection result corresponding to the first variation data set.
  • the third aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect embodiment of the present disclosure.
  • the electronic device is a single server or a computer cluster.
  • a fourth aspect of the present disclosure provides a non-transient computer programmable Read the storage medium, wherein the computer instructions are used to cause the computer to execute the method described in the embodiment of the first aspect of the present disclosure.
  • a fifth aspect embodiment of the present disclosure provides a computer program product, including a computer program, which executes the method described in the first aspect embodiment of the present disclosure when a processor is used to execute the computer program.
  • the acceleration method, device, electronic device and storage medium for gene detection include: obtaining a first variation data set and a second variation data set according to a first gene sample set, wherein the first gene sample set includes a plurality of gene sample variation data, and the first gene sample set is obtained by preprocessing the original data; obtaining a variation quality control model according to the second variation data set, and processing the first variation data set according to the variation quality control model to obtain a first variation detection result corresponding to the first variation data set.
  • the present disclosure utilizes temporary interval information to divide the variation detection data into the first and second variation data sets, so that in the subsequent application quality control, the interval processing is directly oriented to achieve the effect of speeding up parallel computing. Compared with the previous method of re-splitting data and assigning tasks when applying quality control, this method reduces the time consumption of detection and effectively improves the efficiency of population genome analysis and calculation.
  • FIG1 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure
  • FIG2 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure
  • FIG3 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure.
  • FIG4 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure.
  • FIG5 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure.
  • FIG6 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure.
  • FIG7 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure.
  • FIG8 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure.
  • FIG9 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure.
  • FIG10 is a schematic diagram of a process for performing gene testing provided by an embodiment of the present disclosure.
  • FIG11 is a schematic diagram of a process for performing gene testing provided by an embodiment of the present disclosure.
  • FIG12 is a block diagram of a composition of an acceleration device for gene detection provided by an embodiment of the present disclosure.
  • FIG. 13 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.
  • whole genome sequencing is a commonly used genetic analysis method that can quickly and inexpensively determine the complete genome sequence of an organism and detect a set of variants in its genome.
  • scale of whole genome data rises to 10,000 or 100,000 people, large-scale population genome analysis will face serious problems of memory overload and excessive time consumption. Therefore, how to efficiently use computing and storage resources to quickly and accurately analyze large-scale genome samples is a problem that needs to be solved.
  • the present invention uses temporary interval information to divide the variation detection data into the first and second variation data sets, so that the subsequent application quality control can directly face the interval processing to achieve the effect of speeding up parallel computing. Compared with the previous method of re-splitting data and assigning tasks when applying quality control, this method reduces the time consumption of detection and effectively improves the efficiency of population genome analysis and calculation.
  • sample generally refers to an aliquot of material obtained or derived from a source of interest, as well as a collection of data, charts, etc. formed by the labels, identifications, or analysis results of these samples.
  • the source of interest is a biological or environmental source.
  • the source of interest can be or include cells or organisms, such as microorganisms, plants, or animals (e.g., humans).
  • the source of interest is or includes biological tissue or fluid.
  • the biological tissue or fluid can be or include amniotic fluid, aqueous humor, ascites, bile, bone marrow, blood, breast milk, cerebrospinal fluid, cerumen, chyle, chime, ejaculate, endolymph, exudate, feces, gastric acid, gastric juice, lymph, mucus, pericardial fluid, perilymph, peritoneal fluid, pleural fluid, pus, etc.
  • biological fluids may be or include intracellular fluid, extracellular fluid, intravascular fluid (plasma), interstitial fluid, lymph and/or transcellular fluid.
  • biological fluids may be or include plant exudates.
  • biological tissues or samples may be obtained, for example, by suction, biopsy (e.g., fine needle or tissue biopsy), swab (e.g., oral, nasal, skin or vaginal swab), scraping, surgery, washing or lavage (e.g., bronchoalveolar, duct, nose, eye, oral cavity, uterus, vagina or other washing or lavage).
  • biological samples may be or include cells obtained from individuals.
  • samples are "primary samples" obtained directly from a source of interest by any suitable means.
  • sample refers to a preparation obtained by processing a primary sample (e.g., by removing one or more components thereof and/or by adding one or more agents thereto). For example, filtering using a semipermeable membrane.
  • processed samples may include, for example, nucleic acids (including DNA, RNA), proteins, or chromatin, etc., extracted from a sample or obtained by subjecting the primary sample to one or more techniques (such as amplification or reverse transcription of nucleic acids, separation and/or purification of certain components, etc.).
  • sequencer generally refers to a sequencer used to determine the sequence of genetic material of a sample. Sequencers can function in a variety of ways and based on a variety of technologies, including sequencing by primer extension using labeled or unlabeled nucleotides, such as sequencing-by-ligation or pyrophosphate sequencing, for example, using any of the Sanger dideoxy method, nanopore or "NexGen” sequencing methods in the art (e.g., using the sequencing platform of MGI, the ROCHE 454 sequencing platform, the ILLUMINATM SOLEXATM sequencing platform, the SOLIDTM sequencing platform of LIFE TECHNOLOGIES/APPLIED BIOSYSTEMS, the SMRTTM sequencing platform of PACIFIC BIOSCIENCES, the POLLONATOR Polony sequencing platform, the COMPLETE GENOMICS sequencing platform, the INTELLIGENT BIOSYSTEMS sequencing platform, the HELICOS sequencing platform, or any other sequencer and system in the art).
  • Fig. 1 is a flow chart of an acceleration method for gene detection provided by an embodiment of the present disclosure. As shown in Fig. 1, steps 101-102 are included.
  • Step 101 Obtain a first variation data set and a second variation data set according to a first gene sample set.
  • the first gene sample set includes multiple gene sample variation data, which is obtained by preprocessing the original data.
  • the sample to be tested may be a single sample or multiple samples.
  • the specific biological species and the specific number of samples are not limited by the present disclosure.
  • the preprocessing is to process the data of the collected samples in sequence to obtain the variation data of each gene sample.
  • the processing flow may include whole genome sequencing WGS completed by a sequencer.
  • the main steps include data quality control, sequence alignment, sorting, tag deduplication, base quality calibration, variation detection and other related processing flows.
  • the specific processing flow and processing method are not limited by the present disclosure.
  • the first variant data set when obtained, is the variation result of the interval obtained by first processing the variation data of the multiple gene samples, and then the variation results of the interval are combined into a data set, which is the first variant data set.
  • the second variant data set is obtained by merging the first variant data set according to a certain merging rule, and the merging rule can be based on gene chromosome information or other gene information.
  • the specific merging rule is not limited by the present disclosure.
  • Step 102 obtaining a variation quality control model according to the second variation data set, and processing the first variation data set according to the variation quality control model to obtain a first variation detection result corresponding to the first variation data set.
  • the variation quality control model is a model trained to screen out correct variation prediction results. It can be a Gaussian mixture model, a K-means model, or a density clustering model, such as the DBSCAN model (Density-Based Spatial Clustering of Applications with Noise, DBSCAN), the OPTICS model (Ordering points to identify the clustering structure, OPTICS) and other models, or a hierarchical clustering model, such as the BIRCH model (Balanced Iterative Reducing and Clustering Using Hierarchies, BIRCH) and other models, or an affinity propagation model, an aggregation clustering model, a spectral clustering model and other models.
  • the present disclosure does not limit the specific model.
  • the acceleration method for gene detection includes: obtaining a first variation data set and a second variation data set based on a first gene sample set, wherein the first gene sample set includes a plurality of gene sample variation data, and the first gene sample set is obtained by preprocessing the original data; obtaining a variation quality control model based on the second variation data set, and processing the first variation data set according to the variation quality control model to obtain a first variation detection result corresponding to the first variation data set.
  • the present disclosure utilizes temporary interval information to divide the variation detection data into first and second variation data sets, so that in subsequent application quality control, the interval processing is directly oriented to achieve the effect of speeding up parallel computing. Compared with the previous method of re-splitting data and assigning tasks when applying quality control, this method reduces the time consumption of detection and effectively improves the efficiency of population genome analysis and calculation.
  • obtaining the first variant dataset may be achieved by, but not limited to, the following method, as shown in FIG. 2, including the following steps:
  • Step 201 obtaining a gene variation density table.
  • the gene variation density table is obtained through a pre-constructed human genome variation site density database.
  • the general high-quality gene variation data set information is used, and on the other hand, the large population variation information generated by joint variation detection of multiple large population mixed samples is also used.
  • the two aspects of information are combined to construct a human genome variation site density database.
  • the specific method of obtaining gene mutation density is not limited by this disclosure.
  • Step 202 merge the first gene sample set according to the gene variation density table to obtain a first variation data set.
  • the processing of the first gene sample set is to divide the multiple gene sample variation data of the first gene sample set into different intervals according to the gene variation density table, and then perform joint variation detection on the different intervals to obtain the variation data of multiple intervals.
  • the obtained data set consisting of the variation data of multiple intervals is the first variation data set.
  • dividing the intervals it can be based on the gene variation density table, or it can be based on other gene information, or it can be other predefined division rules.
  • the specific division rules are not limited by this disclosure.
  • step 202 when executing step 202 to merge the first gene sample set according to the gene variation density table to obtain the first variation data, it can be implemented by but not limited to the following method, as shown in FIG3, including the following steps:
  • Step 301 Determine multiple intervals of a first gene sample set according to a gene variation density table.
  • the numerical rules for division can be predefined, and the specific division rules are not limited by the present disclosure.
  • Step 302 Process the variation data of the gene samples in the same interval to obtain a plurality of first variation data, and the plurality of first variation data form a first variation data set.
  • the joint variation detection method adopted when processing the genetic sample variation data in the same interval, can be detected by tools related to SNP calling in genetic research, such as the GATK detection tool, the MegaBOLT detection tool, or other related detection tools.
  • the present disclosure does not limit the specific detection tools and detection methods.
  • obtaining the second variant data set may be achieved by but not limited to the following method, as shown in FIG. 4, including the following steps:
  • Step 401 obtaining gene chromosome information.
  • the gene chromosome information is determined by different detection organisms, and the specific chromosome type and number are not limited by the present disclosure.
  • Step 402 Merge the first variant data set according to the gene chromosome information to obtain a second variant data set.
  • the embodiments of the present disclosure may be based on gene chromosome information, and the first joint interval variation data set may be merged according to different chromosome types, or the first joint data variation data may be merged according to different chromosomes.
  • the specific method of using chromosome information is not limited by the present disclosure.
  • the merging process may also be performed based on other gene information, and the specific gene information is not limited by the present disclosure.
  • step 402 when executing step 402 to merge the first variant data set according to the gene chromosome information to obtain the second variant data set, it can be implemented by but not limited to the following method, as shown in FIG5, including the following steps:
  • Step 501 determining multiple intervals of multiple first variation data according to gene chromosome information.
  • the division rules can be predefined, and the present disclosure does not limit the specific division rules.
  • Step 502 Process the first variation data in the same interval to obtain a plurality of second variation data, and the plurality of second variation data form a second variation data set.
  • the embodiments of the present disclosure may be a merging process, and a data set consisting of a plurality of second variant data is the second variant data set.
  • the merging process may also be based on different merging methods or different merging orders.
  • the specific merging rules, specific merging methods and orders are not limited by the present disclosure.
  • the first gene sample set is processed according to the gene variation density table and the gene chromosome information to obtain the first variation data set and the second variation data set.
  • a variation quality control model is obtained according to the second variation data set, and the first variation data set is processed according to the variation quality control model to obtain the first variation data set.
  • the first variation detection result corresponding to the different data set can be achieved by but not limited to the following method, as shown in FIG6, including the following steps:
  • Step 601 Use the second variation data set to train the preset model to obtain a variation quality control model.
  • variation quality control model when obtaining the variation quality control model, it is obtained by training with a comprehensive use of known high-quality variation standard data sets and second variation data sets. During training, different training methods and different training platforms can be used. The specific training methods and platforms are not limited by the present disclosure.
  • Step 602 Screen the first variation data set according to the variation quality control model to obtain a first variation detection result.
  • the embodiment of the present disclosure uses a model for screening, that is, to use a trained variation quality control model to discriminate the data of the first interval data set obtained, so as to eliminate inaccurate data and retain high-quality data.
  • a model for screening that is, to use a trained variation quality control model to discriminate the data of the first interval data set obtained, so as to eliminate inaccurate data and retain high-quality data.
  • the model can be deployed on different computing platforms and can also be called in different ways.
  • the specific model deployment method and the specific model calling method are not limited by the present disclosure.
  • step 601 when executing step 601 to obtain the variation quality control model, it can be implemented by but not limited to the following method, as shown in FIG7, including the following steps:
  • Step 701 obtaining a standard dataset for gene variation detection.
  • the standard data set for gene variation detection is an existing general-purpose high-quality gene variation data set, which can be a HapMap data set, an Omni data set, a dbSNP data set, or other high-quality gene variation data sets.
  • a standard data set When obtaining a standard data set, one or more of them can be obtained.
  • the specific data set and the number of data sets are not limited by the present disclosure.
  • Step 702 training and constructing a variation quality control model based on the second variation data set and the gene variation detection standard data set.
  • step 102 after executing step 102 to obtain a variation quality control model according to the second variation data set, and processing the first variation data set according to the variation quality control model to obtain a first variation detection result corresponding to the first variation data set, further processing of the first variation detection result is also included.
  • the processing may be implemented by, but not limited to, the following method, as shown in FIG8 , including the following steps:
  • Step 801 obtaining gene chromosome information.
  • the gene chromosome information is determined by different detection organisms, and the specific chromosome type and number are not limited by the present disclosure.
  • Step 802 merge the first variation detection results according to the gene chromosome information.
  • the variation detection results in chromosome units can be obtained, and the merging process can also be based on different merging methods or different merging orders.
  • the specific merging rules, specific merging methods and orders are not limited by the present disclosure.
  • the sample is also added.
  • the sample can be added after the variant quality control model processes the first variant data set to obtain the first variant detection result, or after the first variant data set is obtained.
  • the specific time of adding is not limited by the present disclosure.
  • the adding operation can be implemented by but not limited to the following method, as shown in Figure 9, including the following steps:
  • Step 901 Obtain a second gene sample set.
  • the second gene sample set is obtained by preprocessing the original data.
  • the original data that is, the collected samples to be tested, can be a single sample or multiple samples.
  • the specific biological species and the specific number of samples are not limited by the present disclosure.
  • the preprocessing is to process the data of the collected samples in sequence to obtain the variation data of each gene sample.
  • the processing flow may include whole genome sequencing WGS completed by a sequencer.
  • the main steps include data quality control, sequence alignment, sorting, tag deduplication, base quality calibration, variation detection and other related processing processes.
  • the specific processing flow and processing method are not limited by the present disclosure.
  • Step 902 Obtain a third variation data set based on the second gene sample set.
  • Step 903 Process the third variation data set according to the variation quality control model to obtain a second variation detection result corresponding to the third variation data set.
  • processing the third variation data set according to the variation quality control model is the same as the operation of obtaining the first variation detection result in the previous text, and the specific steps are not repeated here.
  • the present disclosure uses temporary interval information to divide the variation detection data into first and second variation data.
  • the data set is then directly processed for interval processing in subsequent quality control applications to achieve the effect of speeding up parallel computing.
  • this method reduces the time consumption of detection and effectively improves the efficiency of population genome analysis and calculation.
  • genetic data analysis acceleration software such as MegaBOLT software
  • MegaBOLT software is used to process the whole genome samples of the project.
  • the specific process is to process and generate multiple genetic sample variation data based on the original sequencing file (FASTQ file) obtained after sequencing each sample, and then perform joint variation detection.
  • FASTQ file original sequencing file
  • this method uses all genetic sample variation data as input at one time to complete variation detection of all samples, and all samples are passed through the variation quality control model to produce the final result.
  • the interval data generated by the joint variation detection step i.e., the first variation data set segmented based on the variation density table
  • the present disclosure performs variation quality control on the first variation data set, and can effectively improve the detection speed through parallel computing.
  • the method of segmenting interval data based on the variation density table ensures the quality of segmentation, thereby ensuring the detection effect.
  • the above two strategies are unique to the method shown in the present patent.
  • FIG10 is a schematic diagram of the overall process of the present disclosure when performing variation detection, including data acquisition and preprocessing, obtaining a joint variation detection data set, and executing a quality control algorithm.
  • FIG11 is a schematic diagram of the present disclosure when performing variation detection, obtaining a joint variation detection data set, and executing a quality control algorithm. Specifically, when performing variation detection on a population genome, the following steps may be performed, but are not limited to:
  • the genome variation record file GVCF of each single sample is obtained by whole genome sequencing (WGS).
  • the whole genome sequencing (WGS) is to use high-throughput sequencing technology to perform whole genome sequencing on individuals or groups to discover information such as sequence or structural variation.
  • the present disclosure proposes to divide by variant density.
  • variation density table is obtained through a pre-constructed human genome variation site density database.
  • general high-quality gene variation data set information is utilized, and on the other hand, large population variation information generated by joint variation detection of mixed samples of multiple large populations is also utilized.
  • the two aspects of information are integrated to construct a human genome variation site density database.
  • the specific method of obtaining gene mutation density is not limited by the present disclosure.
  • the Combine GVCF module when performing joint variation detection, that is, when executing the Joint-calling step, the Combine GVCF module will be used to merge the GVCF data according to the intervals, and the genotype module will be used to perform joint variation detection on the merged GVCF data to obtain the joint variation detection result of the interval.
  • the fusion module (Merge VCF module) of the Joint-Calling step is responsible for merging the joint variation detection results of the interval into 25 chromosome result files and outputting Chr1, Chr2, ..., Chr22, ChrM, ChrX, ChrY.
  • VQSR variation quality control
  • the VCF data of Chr1VCF, Chr2VCF, ...ChrY generated in step 3 will be input into the variation quality control model of the VQSR step (i.e., the VariantRecalibrator module).
  • This model is obtained through machine learning methods, such as a model trained based on a Gaussian Mixed Model (GMM).
  • GMM Gaussian Mixed Model
  • the interval segment data generated by the Joint-Calling step (as indicated by the dotted arrows) will be processed in parallel to generate VQSR VCF results for each interval segment, and then the final result will be obtained by merging the VQSR VCF results for the interval segments.
  • This solution uses temporary interval information during the detection process to obtain the first variant data set and the second variant data set, so that the subsequent quality control can be directly processed for the interval. Since the processing is oriented to the existing interval, on the one hand, it avoids the time consumption of splitting and assigning tasks again in the past, and on the other hand, it also utilizes the information in the detection process, making the detection process steps more united, thereby improving the overall effect of the population genome analysis calculation process.
  • FIG12 is a schematic diagram of the structure of an acceleration device 1200 for gene detection provided by an embodiment of the present disclosure.
  • the acceleration device for gene detection includes:
  • the acquisition unit 1201 is used to obtain a first variation data set and a second variation data set according to the first gene sample set.
  • the processing unit 1202 is used to obtain a variation quality control model according to the second variation data set, and process the first variation data set according to the variation quality control model to obtain a first variation detection result corresponding to the first variation data set;
  • the acquisition unit 1201 includes:
  • the first acquisition module is used to obtain a gene variation density table.
  • the first processing module is used to merge the first gene sample set according to the gene variation density table to obtain a first variation data set.
  • the processing module is further configured to:
  • the gene variation density table multiple intervals of the first gene sample set are determined; the gene sample variation data in the same interval are processed to obtain multiple first variation data, and the multiple first variation data form a first variation data set.
  • the acquiring unit 1201 further includes:
  • the second acquisition module is used to acquire gene chromosome information.
  • the second processing module is used to merge the first variant data set according to the gene chromosome information to obtain a second variant data set.
  • the second processing module is further configured to:
  • multiple intervals of multiple first variation data are determined; the first variation data in the same interval are processed to obtain multiple second variation data, and the multiple second variation data form a second variation data set.
  • the processing unit 1202 includes:
  • the training module is used to train the preset model using the second variation data set to obtain a variation quality control model.
  • the screening module is used to screen the first variation data set according to the variation quality control model to obtain a first variation detection result.
  • the training module is further configured to:
  • the method further includes:
  • the acquisition unit 1201 is also used to acquire gene chromosome information.
  • the processing unit 1202 is further used to merge the first variation detection results according to the gene chromosome information.
  • the method further includes:
  • the acquisition unit 1201 is further used to: acquire a second gene sample set; and obtain a third variation data set according to the second gene sample set.
  • the processing unit 1202 is further configured to process the third variation data set according to the variation quality control model to obtain a second variation detection result corresponding to the third variation data set.
  • a first variation data set and a second variation data set are obtained based on a first gene sample set, wherein the first gene sample set includes a plurality of gene sample variation data, and the first gene sample set is obtained by preprocessing the original data; a variation quality control model is obtained based on the second variation data set, and the first variation data set is processed based on the variation quality control model to obtain a first variation detection result corresponding to the first variation data set.
  • the present disclosure utilizes temporary interval information to divide the variation detection data into the first and second variation data sets, so that in subsequent application quality control, the interval processing is directly oriented to achieve the effect of speeding up parallel computing. Compared with the previous method of re-splitting data and assigning tasks when applying quality control, this method reduces the time consumption of detection and effectively improves the efficiency of population genome analysis and calculation.
  • the electronic device may include a hardware structure and a software module, and implement the functions in the form of a hardware structure, a software module, or a hardware structure plus a software module.
  • a function of the functions may be executed in the form of a hardware structure, a software module, or a hardware structure plus a software module.
  • the electronic device 1300 may be a sequencer, a mobile phone, a computer, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
  • the method proposed in the present disclosure can be applied to a single server, that is, all functions are provided by one server, and the computational task of genetic testing can be performed on this server. Since the amount of data for population genome analysis is large in practice, the method proposed in the present disclosure can also be applied to a computer cluster, which is a distributed computing system composed of multiple servers. In the computational task of genetic testing, the computational task can be assigned to different servers for calculation. Therefore, the electronic device can be a single server or a computer cluster. In other words, the electronic device can be a server, or it can be a server group, and the server group includes at least two servers.
  • the electronic device 1300 may include one or more of the following components: a processing component 1302 , a memory 1304 , a power component 1306 , a multimedia component 1308 , an audio component 1310 , an input/output (I/O) interface 1312 , a sensor component 1314 , and a communication component 1316 .
  • the processing component 1302 generally controls the overall operation of the electronic device 1300, such as operations associated with display, phone calls, data communications, camera operations, and recording operations.
  • the processing component 1302 may include one or more processors 1320 to execute instructions to complete all or part of the steps of the above-mentioned method.
  • the processing component 1302 may include one or more modules to facilitate the interaction between the processing component 1302 and other components.
  • the processing component 1302 may include a multimedia module to facilitate the interaction between the multimedia component 1308 and the processing component 1302.
  • the memory 1304 is configured to store various types of data to support operations on the electronic device 1300. Examples of such data include instructions for any application or method operating on the electronic device 1300, contact data, phone book data, messages, pictures, videos, etc.
  • the memory 1304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read-only memory
  • EPROM erasable programmable read-only memory
  • PROM programmable read-only memory
  • ROM read-only memory
  • magnetic memory flash memory
  • flash memory magnetic disk or optical disk.
  • the power supply component 1306 provides power to the various components of the electronic device 1300.
  • the power supply component 1306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 1300.
  • the multimedia component 1308 includes a screen that provides an output interface between the electronic device 1300 and the user.
  • the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.
  • the multimedia component 1308 includes a front camera and/or a rear camera.
  • the front camera and/or the rear camera may receive external multimedia data.
  • Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
  • the audio component 1310 is configured to output and/or input audio signals.
  • the audio component 1310 includes The audio component 1310 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 1300 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal can be further stored in the memory 1304 or sent via the communication component 1316.
  • the audio component 1310 also includes a speaker for outputting audio signals.
  • I/O interface 1312 provides an interface between processing component 1302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.
  • the sensor assembly 1314 includes one or more sensors for providing various aspects of status assessment for the electronic device 1300.
  • the sensor assembly 1314 can detect the open/closed state of the electronic device 1300, the relative positioning of components, such as the display and keypad of the electronic device 1300, and the sensor assembly 1314 can also detect the position change of the electronic device 1300 or a component of the electronic device 1300, the presence or absence of user contact with the electronic device 1300, the orientation or acceleration/deceleration of the electronic device 1300, and the temperature change of the electronic device 1300.
  • the sensor assembly 1314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • the sensor assembly 1314 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor assembly 1314 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • the communication component 1316 is configured to facilitate wired or wireless communication between the electronic device 1300 and other devices.
  • the electronic device 1300 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR (New Radio), or a combination thereof.
  • the communication component 1316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.
  • the communication component 1316 also includes a near field communication (NFC) module to facilitate short-range communication.
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the electronic device 1300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, graphics processing units (GPUs), computer clusters, microcontrollers, microprocessors, or other electronic components to perform the above methods.
  • ASICs application-specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGAs field programmable gate arrays
  • controllers graphics processing units (GPUs), computer clusters, microcontrollers, microprocessors, or other electronic components to perform the above methods.
  • a non-transitory computer-readable storage medium including instructions
  • the memory 1304 includes instructions that can be executed by the processor 320 of the electronic device 1300 to perform the above method.
  • the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
  • the embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the acceleration method for gene detection described in the above embodiments of the present disclosure.
  • An embodiment of the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, performs the acceleration method for gene detection described in the above embodiment of the present disclosure.
  • Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.
  • computer-readable media include the following: an electrical connection with one or more wirings (control method), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM).
  • the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or processing in other suitable ways as necessary, and then stored in a computer memory.
  • each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
  • the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

Landscapes

  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Genetics & Genomics (AREA)
  • Biotechnology (AREA)
  • Biophysics (AREA)
  • Chemical & Material Sciences (AREA)
  • Molecular Biology (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Analytical Chemistry (AREA)
  • Evolutionary Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)

Abstract

本公开提供一种用于基因检测的加速方法、装置及电子设备，涉及生物信息领域，本公开的方法主要包括：根据第一基因样本集获得第一变异数据集和第二变异数据集；根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果。本公开的技术方案利用临时区间信息，将变异检测数据分为第一、第二变异数据集，从而在后续应用质控时直接面向区间处理以达到提速计算效果。该方法与以往应用质控时重新拆分数据并分配任务的方式相比，减少了检测的时间消耗，有效提高了群体基因组分析计算效率。

Description

一种用于基因检测的加速方法、装置及电子设备 技术领域
本公开涉及生物信息领域，尤其涉及一种用于基因检测的加速方法、装置及电子设备。
背景技术
在生物医学领域，全基因组测序WGS(Whole Genome Sequencing,WGS)是一种常用的基因分析方法，它能快速、低成本地确定生物体的完整基因组序列并检测出其基因组中的变异集合。但当全基因组数据规模上升到万人或十万人规模时，超大型群体基因组分析会面临严重的内存超限和耗时超长问题。因此，如何高效使用计算存储资源来快速准确分析大规模基因组样本是目前需解决的问题。
发明内容
本公开提供一种用于基因检测的加速方法、装置及电子设备，以解决相关技术中的问题，提升群体基因检测的速度。
本公开的第一方面实施例提出了一种用于基因检测的加速方法，该方法包括：根据第一基因样本集获得第一变异数据集和第二变异数据集，其中，第一基因样本集包括多个基因样本变异数据，第一基因样本集为通过对原始数据进行预处理得到；根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果。
在本公开的一些实施例中，获得第一变异数据集包括：获取基因变异密度表；根据基因变异密度表对第一基因样本集进行合并处理获得第一变异数据集。
在本公开的一些实施例中，根据基因变异密度表对第一基因样本集进行合并处理获得第一变异数据集包括：根据基因变异密度表，确定第一基因样本集的多个区间；对处于同一区间的基因样本变异数据进行处理得到多个第一变异数据，多个第一变异数据形成第一变异数据集。
在本公开的一些实施例中，获得第二变异数据集包括：获取基因染色体信息；根据基因染色体信息对第一变异数据集进行合并获得第二变异数据集。
在本公开的一些实施例中，根据基因染色体信息对第一变异数据集进行合并获得第二变异数据集包括：根据基因染色体信息，确定多个第一变异数据的多个区间；对处于同一区间的第一变异数据进行处理得到多个第二变异数据，多个第二变异数据形成第二变异数据集。
在本公开的一些实施例中，根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果包括：利用第二变异数据集对预设模型进行训练，以获得变异质控模型；根据变异质控模型对第一变异数据集进行筛选得到第一变异检测结果。
在本公开的一些实施例中，获得变异质控模型包括：获取基因变异检测标准数据集；根据第二变异数据集和基因变异检测标准数据集训练并构建变异质控模型。
在本公开的一些实施例中，该方法还包括：获取基因染色体信息；根据基因染色体信息对第一变异检测结果进行合并处理。
在本公开的一些实施例中，在根据变异质控模型处理第一变异数据集得到第一变异检测结果之后，或者在获得第一变异数据集之后，该方法还包括：获取第二基因样本集；根据第二基因样本集获得第三变异数据集；根据变异质控模型处理第三变异数据集，得到第三变异数据集对应的第二变异检测结果。
本公开的第二方面实施例提出了一种用于基因检测的加速装置，该装置包括：获取单元，用于根据第一基因样本集获得第一变异数据集和第二变异数据集，其中，第一基因样本集包括多个基因样本变异数据，第一基因样本集为通过对原始数据进行预处理得到；处理单元，用于根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果。
本公开的第三方面实施例提出了一种电子设备，包括：至少一个处理器；以及与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行本公开第一方面实施例中描述的方法。
在本公开的一些实施例中，电子设备为单台服务器或者计算机集群。
本公开的第四方面实施例提出了一种存储有计算机指令的非瞬时计算机可 读存储介质，其中，计算机指令用于使计算机执行本公开第一方面实施例中描述的方法。
本公开的第五方面实施例提出了一种计算机程序产品，包括计算机程序，计算机程序在被处理器执行本公开第一方面实施例中描述的方法。
本公开提供的用于基因检测的加速方法、装置、电子设备及存储介质，包括：根据第一基因样本集获得第一变异数据集和第二变异数据集，其中，第一基因样本集包括多个基因样本变异数据，第一基因样本集为通过对原始数据进行预处理得到；根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果。本公开利用临时区间信息，将变异检测数据分为第一、第二变异数据集，从而在后续应用质控时直接面向区间处理以达到提速并行计算的效果。该方法与以往应用质控时重新拆分数据并分配任务的方式相比，减少了检测的时间消耗，有效提高了群体基因组分析计算的效率。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成本公开的不当限定。
图1为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图2为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图3为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图4为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图5为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图6为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图7为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图8为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图9为本公开实施例提供的一种用于基因检测的加速方法的流程图；
图10为本公开实施例提供的一种执行基因检测时的过程示意图；
图11为本公开实施例提供的一种执行基因检测时的过程示意图；
图12为本公开实施例提供的一种用于基因检测的加速装置的组成框图；
图13为本公开实施例提供的电子设备的结构示意图。
具体实施方式
下面详细描述本公开的实施例，实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，旨在用于解释本公开，而不能理解为对本公开的限制。
在生物医学领域，全基因组测序WGS(Whole Genome Sequencing,WGS)是一种常用的基因分析方法，它能快速、低成本地确定生物体的完整基因组序列并检测出其基因组中的变异集合。但当全基因组数据规模上升到万人或十万人规模时，超大型群体基因组分析会面临严重的内存超限和耗时超长问题。因此，如何高效使用计算存储资源来快速准确分析大规模基因组样本是目前需解决的问题。
现有的检测方式在应用质控算法时，需要先要对检测数据进行拆分，重新进行任务分配，以满足并行计算的要求。但该方式也相应的增加了检测任务处理时的时间消耗，同时也没有联合利用到质控前的检测流程。
为了解决相关技术中存在的问题，本公开利用临时区间信息，将变异检测数据分为第一、第二变异数据集，从而在后续应用质控时直接面向区间处理以达到提速并行计算的效果。该方法与以往应用质控时重新拆分数据并分配任务的方式相比，减少了检测的时间消耗，有效提高了群体基因组分析计算的效率。
如本文所用，术语“样本”通常是指从感兴趣的来源获得或衍生的材料的等分试样，以及通过这些样本产出的标记、标识或分析结果形成的数据、图表等集合。在一些实施方案中，感兴趣的来源是生物或环境来源。在一些实施方案中，感兴趣的来源可以是或包括细胞或生物体，诸如微生物、植物或动物(例如，人)。在一些实施方案中，感兴趣的来源是或包括生物组织或流体。在一些实施方案中，生物组织或流体可以是或包括羊水、房水、腹水、胆汁、骨髓、血液、母乳、脑脊液、耳垢、乳糜、食糜(chime)、一次射出的精液(ejaculate)、内淋巴、渗出物、粪便、胃酸、胃液、淋巴液、粘液、心包液、外淋巴、腹膜液、胸膜液、脓 液、发炎性分泌物、唾液、皮脂、精液、血清、阴垢、痰、滑液、汗液、泪液、尿液、阴道分泌物、玻璃体液、呕吐物，以及/或者它们的组合或一种或多种组分。在一些实施方案中，生物流体可以是或包括细胞内液、细胞外液、血管内液(血浆)、间质液、淋巴液和/或跨细胞液。在一些实施方案中，生物流体可以是或包括植物渗出物。在一些实施方案中，生物组织或样本可以例如通过抽吸、活检(例如，细针或组织活检)、拭子(例如，口腔、鼻、皮肤或阴道拭子)、刮擦、手术、洗涤或灌洗(例如，支气管肺泡、导管、鼻、眼、口腔、子宫、阴道或其他洗涤或灌洗)来获取。在一些实施方案中，生物样本是或包括从个体获得的细胞。在一些实施方案中，样本是通过任何合适的手段直接从感兴趣的来源获得的“初次样本”。在一些实施方案中，如从上下文来看将显而易见的，术语“样本”是指通过处理初次样本(例如，通过去除其一种或多种组分和/或通过向其中添加一种或多种剂)获得的制品。例如，使用半透膜过滤。此类“经处理的样本”可包括例如从样本中提取或通过使初次样本经受一种或多种技术(诸如核酸的扩增或逆转录，某些组分的分离和/或纯化等)而获得的核酸(包括DNA、RNA)、蛋白质或染色质等。
如本文所用，术语“测序仪”，通常指用于确定一个样品的遗传材料的序列。测序仪可以用多种方式并且基于多种技术来发挥作用，包括使用经标记或未经标记的核苷酸通过引物延伸进行测序，如边测序边连接或者焦磷酸测序等，例如使用Sanger双脱氧法、纳米孔或本领域的“NexGen”测序方法中的任一种(例如，使用MGI的测序平台、ROCHE 454测序平台、ILLUMINATM SOLEXATM测序平台、LIFE TECHNOLOGIES/APPLIED BIOSYSTEMS的SOLIDTM测序平台、PACIFIC BIOSCIENCES的SMRTTM测序平台、POLLONATOR Polony测序平台、COMPLETE GENOMICS测序平台、INTELLIGENT BIOSYSTEMS的测序平台、HELICOS测序平台或本领域的任何其它测序仪和系统)实现。
图1为本公开实施例提供的一种用于基因检测的加速方法的流程图。如图1所示，包括步骤101-102。
步骤101，根据第一基因样本集获得第一变异数据集和第二变异数据集。
本公开的实施例该处需要说明的是，所述第一基因样本集，包括多个基因样本变异数据，为通过对原始数据进行预处理得到的。所述原始数据，即为采集到 的待检测的样本，可以是单个样本也可以是多个样本，具体的生物种类，具体的样本数量，本公开不予以限制。所述预处理，是对采集到的样本的数据依次进行处理获取每个基因样本的变异数据，其处理流程可以包含通过测序仪完成的全基因组测序WGS，主要步骤包括测序下机数据质控、序列比对、排序、标记去重、碱基质量校准、变异检测及其他的相关处理流程，具体的处理流程和处理方式，本公开不予以限制。
此外，本公开的实施例该处需要说明的是，所述第一变异数据集，在获取时，是由所述多个基因样本变异数据先经过处理得到的区间的变异结果，后将该区间的变异结果组成数据集，该数据集即为第一变异数据集。所述第二变异数据集，则是由第一变异数据集根据一定的合并规则合并得到的，其合并规则可以根据基因染色体信息，也可根据其他基因信息，具体的合并规则，本公开不予以限制。
步骤102，根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果。
本公开的实施例该处需要说明的是，所述变异质控模型，是为了实现筛选出正确的变异预测结果所训练的模型，它可以是高斯混合模型，也可以是K-均值模型，或是密度聚类模型，如DBSCAN模型(Density-Based Spatial Clustering of Applications with Noise，DBSCAN)、OPTICS模型(Ordering points to identify the clustering structure，OPTICS)等模型，或是层次聚类模型，如BIRCH模型(Balanced Iterative Reducing and Clustering Using Hierarchies，BIRCH)等模型，或是亲和力传播模型、聚合聚类模型、光谱聚类模型等其他模型，具体的模型，本公开不予以限制。
综上，本公开提供的用于基因检测的加速方法，包括：根据第一基因样本集获得第一变异数据集和第二变异数据集，其中，第一基因样本集包括多个基因样本变异数据，第一基因样本集为通过对原始数据进行预处理得到；根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果。本公开利用临时区间信息，将变异检测数据分为第一、第二变异数据集，从而在后续应用质控时直接面向区间处理以达到提速并行计算的效果。该方法与以往应用质控时重新拆分数据并分配任务的方式相比，减少了检测的时间消耗，有效提高了群体基因组分析计算的效率。
进一步的，在本公开的一些实施例中，在执行步骤101根据第一基因样本集获得第一变异数据集和第二变异数据集时，获得第一变异数据集可以通过但不局限于以下的方法实现，具体如图2所示，包括以下步骤：
步骤201，获取基因变异密度表。
本公开的实施例该处需要说明的是，所述基因变异密度表，是通过预构建的人类基因组变异位点密度数据库获得的。在获取该数据库时，一方面利用了通用的高质量基因变异数据集信息，另一方面也利用了对多个大人群混合样本做联合变异检测Joint-Calling产生的大群体变异信息，综合两方面信息以构建人类基因组变异位点密度数据库，具体的基因突变密度获取方式，本公开不予以限制。
步骤202，根据基因变异密度表对第一基因样本集进行合并处理获得第一变异数据集。
本公开的实施例需要说明的是，所述处理第一基因样本集，具体的说，是将第一基因样本集的多个基因样本变异数据根据基因变异密度表划分为不同的区间，然后分别对不同的区间进行联合变异检测以获得多个区间的变异数据，所得的多个区间的变异数据组成的数据集，即为第一变异数据集。在划分区间时，可以根据基因变异密度表，也可以根据其他基因信息，也可以是其他预定义的划分规则，具体的划分规则，本公开不予以限制。
进一步的，在本公开的一些实施例中，在执行步骤202根据基因变异密度表对第一基因样本集进行合并处理获得第一变异数据时，可以通过但不局限于以下的方法实现，具体如图3所示，包括以下步骤：
步骤301，根据基因变异密度表，确定第一基因样本集的多个区间。
本公开的实施例需要说明的是，本公开在此需说明的已在上述步骤阐述，在此不再赘述，利用基因变异密度表确定区间时，可预定义划分的数值规则，具体的划分规则，本公开不予以限制。
步骤302，对处于同一区间的基因样本变异数据进行处理得到多个第一变异数据，多个第一变异数据形成第一变异数据集。
本公开的实施例需要说明的是，在处理同一区间的基因样本变异数据时，所采用的联合变异检测方式，可以利基因研究中SNP calling的有关工具检测，如GATK检测工具，也可以是MegaBOLT检测工具，也可以其他相关检测工具， 具体的检测工具及检测方式，本公开不予以限制。
进一步的，在本公开的一些实施例中，在执行步骤101根据第一基因样本集获得第一变异数据集和第二变异数据集时，获得第二变异数据集可以通过但不局限于以下的方法实现，具体如图4所示，包括以下步骤：
步骤401，获取基因染色体信息。
本公开的实施例该处需要说明的是，所述基因染色体信息，由不同的检测生物所决定，具体的染色体种类及个数，本公开不予以限制。
步骤402，根据基因染色体信息对第一变异数据集进行合并获得第二变异数据集。
本公开的实施例该处需要说明的是，所述根据基因染色体信息，可以是根据不同的染色体种类对第一联合区间变异数据集进行合并，也可以是根据不同的染色体对第一联合数据变异数据进行合并，具体的利用染色体信息方式，本公开不予以限制。此外除了基因染色体信息外，也可以根据其他基因信息进行合并处理，具体是根据何种基因信息，本公开不予以限制。
进一步的，在本公开的一些实施例中，在执行步骤402根据基因染色体信息对第一变异数据集进行合并获得第二变异数据集时，可以通过但不局限于以下的方法实现，具体如图5所示，包括以下步骤：
步骤501，根据基因染色体信息，确定多个第一变异数据的多个区间。
本公开在此需说明的已在上述步骤阐述，在此不再赘述，利用基因变异密度表确定区间时，可预定义划分的规则，具体的划分规则，本公开不予以限制。
步骤502，对处于同一区间的第一变异数据进行处理得到多个第二变异数据，多个第二变异数据形成第二变异数据集。
本公开的实施例需要说明的是，所述处理可以为合并处理，由多个第二变异数据组成的数据集，即为第二变异数据集，合并处理也可以根据不同的合并方法，也可以根据不同的合并顺序，具体的合并规则，具体的合并方法及顺序，本公开不予以限制。
如上所示的，根据基因变异密度表和基因染色体信息对第一基因样本集进行处理，获取第一变异数据集和第二变异数据集后，根据步骤102根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变 异数据集对应的第一变异检测结果时，可以通过但不局限于以下的方法实现，具体如图6所示，包括以下步骤：
步骤601，利用第二变异数据集对预设模型进行训练，以获得变异质控模型。
本公开的实施例该处需要说明的是，在获得所述变异质控模型时，是综合利用已知的高质量变异标准数据集和第二变异数据集训练获得的，在训练时，可以利用不同的训练方法，也可以利用不同的训练平台，具体的训练方法及平台，本公开不予以限制。
步骤602，根据变异质控模型对第一变异数据集进行筛选得到第一变异检测结果。
本公开的实施例该处需要说明的是，所述利用模型进行筛选，即为利用训练好的变异质控模型，对已获得的第一区间数据集的数据进行判别，以达到剔除不准确的数据，保留高质量数据的目的。所述模型应用时，可以部署在不同的计算平台，也可以利用不同方式进行调用，具体的模型部署方式，具体的模型调用方式，本公开不予以限制。
进一步的，在本公开的一些实施例中，在执行步骤601获得变异质控模型时，可以通过但不局限于以下的方法实现，具体如图7所示，包括以下步骤：
步骤701，获取基因变异检测标准数据集。
本公开的实施例该处需要说明的是，所述基因变异检测标准数据集，即为现有通用的高质量基因变异数据集，其可以是HapMap数据集，也可以是Omni数据集，也可以是dbSNP数据集，或是其他高质量基因变异数据集。在获取标准数据集时，也可以获取一个，或是获取其中多个。具体的数据集及数据集数目，本公开不予以限制。
步骤702，根据第二变异数据集和基因变异检测标准数据集训练并构建变异质控模型。
本公开在此需说明的已在上述步骤阐述，在此不再赘述，具体的训练数据组合方式，具体的模型训练方法，本公开不予以限制。
进一步的，在本公开的一些实施例中，在执行步骤102根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果后，还包括对第一变异检测结果的进一步处理，该 处理可以通过但不局限于以下的方法实现，具体如图8所示，包括以下步骤：
步骤801，获取基因染色体信息。
本公开的实施例该处需要说明的是，所述基因染色体信息，由不同的检测生物所决定，具体的染色体种类及个数，本公开不予以限制。
步骤802，根据基因染色体信息对第一变异检测结果进行合并处理。
本公开的实施例该处需要说明的是，进行合并后，可得到以染色体为单位的变异检测结果，合并处理也可以根据不同的合并方法，也可以根据不同的合并顺序，具体的合并规则，具体的合并方法及顺序，本公开不予以限制。
进一步的，在本公开的一些实施例中，还包括对样本的追加。在追加时，可以在变异质控模型处理第一变异数据集得到第一变异检测结果之后追加，也可以在获得第一变异数据集之后追加，具体的追加时间，本公开不予以限制。追加操作可以通过但不局限于以下的方法实现，具体如图9所示，包括以下步骤：
步骤901，获取第二基因样本集。
本公开的实施例该处需要说明的是，所述第二基因样本集，包括多个基因样本变异数据，为通过对原始数据进行预处理得到的。所述原始数据，即为采集到的待检测的样本，可以是单个样本也可以是多个样本，具体的生物种类，具体的样本数量，本公开不予以限制。所述预处理，是对采集到的样本的数据依次进行处理获取每个基因样本的变异数据，其处理流程可以包含通过测序仪完成的全基因组测序WGS，主要步骤包括测序下机数据质控、序列比对、排序、标记去重、碱基质量校准、变异检测以及其他的相关处理流程，具体的处理流程和处理方式，本公开不予以限制。
步骤902，根据第二基因样本集获得第三变异数据集。
本公开的实施例该处需要说明的是，获取第三变异数据集的操作，与获取前文获取第一变异数据的操作一致，具体的步骤在此不再赘述。
步骤903，根据变异质控模型处理第三变异数据集，得到第三变异数据集对应的第二变异检测结果。
本公开的实施例该处需要说明的是，根据变异质控模型处理第三变异数据集，与前文获取第一变异检测结果的操作相同，具体的步骤在此不再赘述。
综上，本公开利用临时区间信息，将变异检测数据分为第一、第二变异数据 集，从而在后续应用质控时直接面向区间处理以达到提速并行计算的效果。该方法与以往应用质控时重新拆分数据并分配任务的方式相比，减少了检测的时间消耗，有效提高了群体基因组分析计算的效率。
相关研究中，在进行基因检测加速时，如自闭症万人基因组项目，是利用基因数据分析加速软件，如MegaBOLT软件，以处理项目的全基因组样本。具体的流程为，根据每个样本测序后得到的原始测序文件(FASTQ文件)，处理生成多个基因样本变异数据，后续再进行联合变异检测。该方法在进行联合变异检测时，是一次性将所有的基因样本变异数据作为输入，以完成所有样本的变异检测，并将全部样本经过变异质控模型，以产生最终结果。
而本实施例中，在进行变异质控步骤时，则充分利用了联合变异检测步骤产生的区间数据(即，基于变异密度表分割的第一变异数据集)，本公开对第一变异数据集进行变异质控，可通过并行计算有效提高检测速度。且，基于变异密度表分割区间数据的方法，保证了分割的质量，从而保证了检测效果。以上两点策略，为本公开专利所示方法所特有的。
下面通过图10、图11所示的具体实施例，对上述图1-9中描述的方法进行举例。
图10为本公开在执行变异检测时的整体过程示意图，包含数据获取及预处理，获取联合变异检测数据集和执行质控算法。图11为本公开在变异检测执行时，获取联合变异检测数据集及执行质控算法时的示意图，具体的，在对群体基因组进行变异检测时，可通过但不限于通过如下步骤：
1.获取单样本的基因组变异记录文件GVCF。
本实施例中，通过全基因组测序(Whole Genome Sequencing,WGS)，获取各个单样本的基因组变异记录文件GVCF。其中，所述全基因组测序(WGS)，是利用高通量测序技术对个体或群体进行全基因组测序，以发现序列或结构变异等信息。
2.通过变异密度表划分区间，分配计算子任务。
本实施例中，在分配计算任务时，由于变异位点在基因组上分布并不均匀，若按以往方法依照平均分配区间。会产生少量任务的严重拖尾现象，造成计算资源浪费和时间消耗，因此本公开提出以变异密度划分。
此外，所述变异密度表，是通过预构建的人类基因组变异位点密度数据库获得的在获取该数据库时，一方面利用了通用的高质量基因变异数据集信息，另一方面也利用了对多个大人群混合样本做联合变异检测Joint-Calling产生的大群体变异信息，综合两方面信息以构建人类基因组变异位点密度数据库，具体的基因突变密度获取方式，本公开不予以限制。
3.执行联合变异检测(Joint-Calling)步骤。
本实施例中，在执行联合变异检测时，即，执行Joint-calling步骤时，将利用合并模块(Combine GVCF模块)，按区间分别合并GVCF数据，并将利用基因型模块(Genotype模块)，对合并后的GVCF数据进行联合变异检测，获得区间的联合变异检测结果。
得到区间的结果后，Joint-Calling步骤的融合模块(Merge VCF模块)，则负责将区间的联合变异检测结果，合并为25个染色体结果文件输出Chr1，Chr2，……，Chr22，ChrM，ChrX，ChrY。
4.执行变异质控(VQSR)步骤。
本实施例中，在实现变异质控(VQSR)步骤时，将把步骤3中生成的Chr1VCF，Chr2VCF，……ChrY的VCF数据，输入VQSR步骤的变异质控模型(即，VariantRecalibrator模块)，此模型是通过机器学习方法，如基于高斯混合模型(Gaussian Mixed Model,GMM)训练得到的模型。
基于该变异质控模型，将并行处理Joint-Calling步骤产生的区间片段数据(即虚线箭头所示)，以分别生成区间片段的VQSR VCF结果，后通过合并区间片段的VQSR VCF结果得到最终的结果。
因此，本方案具有以下有益效果：本方案利用检测过程中的临时区间信息，获得第一变异数据集和第二变异数据集，从而在后续质控时直接面向区间进行处理。由于处理时候是面向已有的区间进行处理的，一方面避免了以往需要再次进行拆分并分配任务的时间消耗，另一方面也利用了检测过程中的信息，使得检测过程步骤的联合性更高，从而提高了群体基因组分析计算流程的整体效果。
图12为本公开实施例提供的一种用于基因检测的加速装置1200的结构示意图。如图12所示，该用于基因检测的加速装置包括：
获取单元1201，用于根据第一基因样本集获得第一变异数据集和第二变异 数据集，其中，第一基因样本集包括多个基因样本变异数据，第一基因样本集为通过对原始数据进行预处理得到；
处理单元1202，用于根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果；
在本公开的一些实施例中，获取单元1201，包括：
第一获取模块，用于获取基因变异密度表。
第一处理模块，用于根据基因变异密度表对第一基因样本集进行合并处理获得第一变异数据集。
在本公开的一些实施例中，处理模块，还被配置为：
根据基因变异密度表，确定第一基因样本集的多个区间；对处于同一区间的基因样本变异数据进行处理得到多个第一变异数据，多个第一变异数据形成第一变异数据集。
在本公开的一些实施例中，获取单元1201，还包括：
第二获取模块，用于获取基因染色体信息。
第二处理模块，用于根据基因染色体信息对第一变异数据集进行合并获得第二变异数据集。
在本公开的一些实施例中，第二处理模块，还被配置为：
根据基因染色体信息，确定多个第一变异数据的多个区间；对处于同一区间的第一变异数据进行处理得到多个第二变异数据，多个第二变异数据形成第二变异数据集。
在本公开的一些实施例中，所示处理单元1202，包括：
训练模块，用于利用第二变异数据集对预设模型进行训练，以获得变异质控模型。
筛选模块，用于根据变异质控模型对第一变异数据集进行筛选得到第一变异检测结果。
在本公开的一些实施例中，所示训练模块，还被配置为：
获取基因变异检测标准数据集；根据第二变异数据集和基因变异检测标准数据集训练并构建变异质控模型。
在本公开的一些实施例中，方法还包括：
获取单元1201，还用于获取基因染色体信息。
处理单元1202，还用于根据基因染色体信息对第一变异检测结果进行合并处理。
在本公开的一些实施例中，方法还包括：
获取单元1201，还用于：获取第二基因样本集；根据第二基因样本集获得第三变异数据集。
处理单元1202，还用于根据变异质控模型处理第三变异数据集，得到所述第三变异数据集对应的第二变异检测结果。
本公开的实施例，在对群体基因变异检测时，根据第一基因样本集获得第一变异数据集和第二变异数据集，其中，第一基因样本集包括多个基因样本变异数据，第一基因样本集为通过对原始数据进行预处理得到；根据第二变异数据集获得变异质控模型，并根据变异质控模型处理第一变异数据集，得到第一变异数据集对应的第一变异检测结果。本公开利用临时区间信息，将变异检测数据分为第一、第二变异数据集，从而在后续应用质控时直接面向区间处理以达到提速并行计算的效果。该方法与以往应用质控时重新拆分数据并分配任务的方式相比，减少了检测的时间消耗，有效提高了群体基因组分析计算的效率。
上述本申请提供的实施例中，对本申请实施例提供的方法及装置进行了介绍。为了实现上述本申请实施例提供的方法中的各功能，电子设备可以包括硬件结构、软件模块，以硬件结构、软件模块、或硬件结构加软件模块的形式来实现上述各功能。上述各功能中的某个功能可以以硬件结构、软件模块、或者硬件结构加软件模块的方式来执行。
图13是根据一示例性实施例示出的一种用于实现上述用于基因检测的加速方法的电子设备1300的框图。例如，电子设备1300可以是测序仪、移动电话，计算机，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
本公开提出的方法可以应用于单台服务器，即通过一台服务器提供所有功能，基因检测的计算任务可以在这一台服务器上进行。由于实际中群体基因组分析数据量较大，本公开提出的方法也可以应用于计算机集群，计算机集群是由多台服务器组成的分布式计算系统，在基因检测的计算任务中可以通过将计算任务分配给不同的服务器来进行计算。因此，电子设备可以是单台服务器或者计算机集群，换言之电子设备可以是服务器，或者可以是服务器组，服务器组中包括至少两个服务器。
参照图13，电子设备1300可以包括以下一个或多个组件：处理组件1302，存储器1304，电源组件1306，多媒体组件1308，音频组件1310，输入/输出(I/O)的接口1312，传感器组件1314，以及通信组件1316。
处理组件1302通常控制电子设备1300的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件1302可以包括一个或多个处理器1320来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件1302可以包括一个或多个模块，便于处理组件1302和其他组件之间的交互。例如，处理组件1302可以包括多媒体模块，以方便多媒体组件1308和处理组件1302之间的交互。
存储器1304被配置为存储各种类型的数据以支持在电子设备1300的操作。这些数据的示例包括用于在电子设备1300上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器1304可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件1306为电子设备1300的各种组件提供电力。电源组件1306可以包括电源管理系统，一个或多个电源，及其他与为电子设备1300生成、管理和分配电力相关联的组件。
多媒体组件1308包括在电子设备1300和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件1308包括一个前置摄像头和/或后置摄像头。当电子设备1300处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件1310被配置为输出和/或输入音频信号。例如，音频组件1310包 括一个麦克风(MIC)，当电子设备1300处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器1304或经由通信组件1316发送。在一些实施例中，音频组件1310还包括一个扬声器，用于输出音频信号。
I/O接口1312为处理组件1302和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件1314包括一个或多个传感器，用于为电子设备1300提供各个方面的状态评估。例如，传感器组件1314可以检测到电子设备1300的打开/关闭状态，组件的相对定位，例如组件为电子设备1300的显示器和小键盘，传感器组件1314还可以检测电子设备1300或电子设备1300一个组件的位置改变，用户与电子设备1300接触的存在或不存在，电子设备1300方位或加速/减速和电子设备1300的温度变化。传感器组件1314可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件1314还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件1314还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件1316被配置为便于电子设备1300和其他设备之间有线或无线方式的通信。电子设备1300可以接入基于通信标准的无线网络，如WiFi，2G或3G，4G LTE、5G NR(New Radio)或它们的组合。在一个示例性实施例中，通信组件1316经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，通信组件1316还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，电子设备1300可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、图形处理器(GPU)、计算机集群、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质， 例如包括指令的存储器1304，上述指令可由电子设备1300的处理器320执行以完成上述方法。例如，非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
本公开的实施例还提出了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，计算机指令用于使计算机执行本公开上述实施例中描述的用于基因检测的加速方法。
本公开的实施例还提出一种计算机程序产品，包括计算机程序，计算机程序在被处理器执行本公开上述实施例中描述的用于基因检测的加速方法。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
在本说明书的描述中，参考术语“一个实施方式”、“一些实施方式”、“示意性实施方式”、“示例”、“具体示例”或“一些示例”等的描述意指结合实施方式或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施方式或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施方式或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施方式或示例中以合适的方式结合。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本发明的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本发明的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理模块的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使 用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(控制方法)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得程序，然后将其存储在计算机存储器中。
应当理解，本发明的实施方式的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤是可以通过程序来指令相关的硬件完成，程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本发明的各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。上述提到的存储介质可以是只读存储器，磁盘或光盘等。
尽管上面已经示出和描述了本发明的实施方式，可以理解的是，上述实施方式是示例性的，不能理解为对本发明的限制，本领域的普通技术人员在本发明的范围内可以对上述实施实施进行变化、修改、替换和变型。

Claims (14)

  1. 一种用于基因检测的加速方法，其特征在于，包括：
    根据第一基因样本集获得第一变异数据集和第二变异数据集，其中，所述第一基因样本集包括多个基因样本变异数据，所述第一基因样本集为通过对原始数据进行预处理得到；
    根据所述第二变异数据集获得变异质控模型，并根据所述变异质控模型处理所述第一变异数据集，得到所述第一变异数据集对应的第一变异检测结果。
  2. 根据权利要求1所述的方法，其特征在于，所述获得所述第一变异数据集包括：
    获取基因变异密度表；
    根据所述基因变异密度表对所述第一基因样本集进行合并处理获得所述第一变异数据集。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述基因变异密度表对所述第一基因样本集进行合并处理获得所述第一变异数据集包括：
    根据所述基因变异密度表，确定所述第一基因样本集的多个区间；
    对处于同一区间的基因样本变异数据进行处理得到多个第一变异数据，所述多个第一变异数据形成所述第一变异数据集。
  4. 根据权利要求1所述的方法，其特征在于，所述获得所述第二变异数据集包括：
    获取基因染色体信息；
    根据所述基因染色体信息对所述第一变异数据集进行合并获得所述第二变异数据集。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述基因染色体信息对所述第一变异数据集进行合并获得所述第二变异数据集包括：
    根据所述基因染色体信息，确定所述多个第一变异数据的多个区间；
    对处于同一区间的第一变异数据进行处理得到多个第二变异数据，所述多个第二变异数据形成所述第二变异数据集。
  6. 根据权利要求1-5中任一项所述的方法，其特征在于，所述根据所述第二变异数据集获得变异质控模型，并根据所述变异质控模型处理所述第一变异数 据集，得到所述第一变异数据集对应的第一变异检测结果包括：
    利用所述第二变异数据集对预设模型进行训练，以获得所述变异质控模型；
    根据所述变异质控模型对所述第一变异数据集进行筛选得到所述第一变异检测结果。
  7. 根据权利要求6所述的方法，其特征在于，所述获得所述变异质控模型包括：
    获取基因变异检测标准数据集；
    根据所述第二变异数据集和所述基因变异检测标准数据集训练并构建所述变异质控模型。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述方法还包括：
    获取基因染色体信息；
    根据所述基因染色体信息对所述第一变异检测结果进行合并处理。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，在根据所述变异质控模型处理所述第一变异数据集得到第一变异检测结果之后，或者在获得所述第一变异数据集之后，所述方法还包括：
    获取第二基因样本集；
    根据所述第二基因样本集获得第三变异数据集；
    根据所述变异质控模型处理所述第三变异数据集，得到所述第三变异数据集对应的第二变异检测结果。
  10. 一种用于基因检测的加速装置，其特征在于，包括：
    获取单元，用于根据第一基因样本集获得第一变异数据集和第二变异数据集，其中，所述第一基因样本集包括多个基因样本变异数据，所述第一基因样本集为通过对原始数据进行预处理得到；
    处理单元，用于根据所述第二变异数据集获得变异质控模型，并根据所述变异质控模型处理所述第一变异数据集，得到所述第一变异数据集对应的第一变异检测结果。
  11. 一种电子设备，其特征在于，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-9中任一项所述的方法。
  12. 根据权利要求11所述的电子设备，其特征在于，所述电子设备为单台服务器或者计算机集群。
  13. 一种存储有计算机指令的非瞬时计算机可读存储介质，其特征在于，所述计算机指令用于使所述计算机执行根据权利要求1-9中任一项所述的方法。
  14. 一种计算机程序产品，其特征在于，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-9中任一项所述的方法。
PCT/CN2023/100431 2023-06-15 2023-06-15 一种用于基因检测的加速方法、装置及电子设备 Ceased WO2024254825A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202380098537.3A CN121175755A (zh) 2023-06-15 2023-06-15 一种用于基因检测的加速方法、装置及电子设备
PCT/CN2023/100431 WO2024254825A1 (zh) 2023-06-15 2023-06-15 一种用于基因检测的加速方法、装置及电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/100431 WO2024254825A1 (zh) 2023-06-15 2023-06-15 一种用于基因检测的加速方法、装置及电子设备

Publications (1)

Publication Number Publication Date
WO2024254825A1 true WO2024254825A1 (zh) 2024-12-19

Family

ID=93851083

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/100431 Ceased WO2024254825A1 (zh) 2023-06-15 2023-06-15 一种用于基因检测的加速方法、装置及电子设备

Country Status (2)

Country Link
CN (1) CN121175755A (zh)
WO (1) WO2024254825A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104462211A (zh) * 2014-11-04 2015-03-25 北京诺禾致源生物信息科技有限公司 重测序数据的处理方法和处理装置
CN109903815A (zh) * 2019-02-28 2019-06-18 北京化工大学 基于特征挖掘的基因翻转变异检测方法
CN112908414A (zh) * 2021-01-28 2021-06-04 中山大学 一种大规模单细胞分型方法、系统及存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104462211A (zh) * 2014-11-04 2015-03-25 北京诺禾致源生物信息科技有限公司 重测序数据的处理方法和处理装置
CN109903815A (zh) * 2019-02-28 2019-06-18 北京化工大学 基于特征挖掘的基因翻转变异检测方法
CN112908414A (zh) * 2021-01-28 2021-06-04 中山大学 一种大规模单细胞分型方法、系统及存储介质

Also Published As

Publication number Publication date
CN121175755A (zh) 2025-12-19

Similar Documents

Publication Publication Date Title
Herring et al. Unsupervised trajectory analysis of single-cell RNA-seq and imaging data reveals alternative tuft cell origins in the gut
Sikkema et al. An integrated cell atlas of the human lung in health and disease
Guo et al. SLICE: determining cell differentiation and lineage based on single cell entropy
Mah et al. Bento: a toolkit for subcellular analysis of spatial transcriptomics data
Rahman et al. Alternative preprocessing of RNA-Sequencing data in The Cancer Genome Atlas leads to improved analysis results
Chen et al. Mpath maps multi-branching single-cell trajectories revealing progenitor cell progression during development
Werner Next generation sequencing in functional genomics
CN105096225B (zh) 辅助疾病诊疗的分析系统、装置及方法
Rashid et al. TASIC: determining branching models from time series single cell data
JP7624929B2 (ja) 遺伝子融合の迅速な検出
Ando et al. An era of single-cell genomics consortia
CN114974432A (zh) 一种生物标志物的筛选方法及其相关应用
Patino et al. Deep learning and computer vision strategies for automated gene editing with a single-cell electroporation platform
Wicker et al. Density of points clustering, application to transcriptomic data analysis
Xiong et al. Chord: an ensemble machine learning algorithm to identify doublets in single-cell RNA sequencing data
Keller et al. Regulation of the dynamic RNA Pol II elongation rate in Drosophila embryos
CN107832584B (zh) 宏基因组的基因分析方法、装置、设备及存储介质
Sun et al. Inferring cell diversity in single cell data using consortium-scale epigenetic data as a biological anchor for cell identity
CN117079714A (zh) 单细胞混样品测序数据的拆分方法和拆分装置
Dong et al. Integrating single-cell datasets with ambiguous batch information by incorporating molecular network features
WO2024254825A1 (zh) 一种用于基因检测的加速方法、装置及电子设备
Cheng et al. PHLOWER leverages single-cell multimodal data to infer complex, multi-branching cell differentiation trajectories
Nguyen et al. Polar Gini Curve: a technique to discover gene expression spatial patterns from single-cell RNA-seq data
Qi et al. Optimizing sample size for supervised machine learning with bulk transcriptomic sequencing: a learning curve approach
Cheng et al. PHLOWER-single cell trajectory analysis using decomposition of the Hodge Laplacian

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23941060

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE