31 results about "Typing methods" patented technology

The invention discloses an HLA (human leukocyte antigen) gene amplification primer based on a nanopore sequencing platform and a typing method, and relates to the technical field of gene engineering, the amplification primer comprises an HLA-A gene amplification primer pair: a forward primer HLA-A-F5; a reverse primer HLA-A-R5; an HLA-B gene amplification primer pair: a forward primer HLA-B-F3; a reverse primer HLA-B-R3; the HLA-DQB1 gene amplification primer pair comprises a forward primer HLA-DQB1-F7, a reverse primer HLA-DQB1-F7 and a reverse primer HLA-DQB1-F7; a reverse primer of HLA-DQB1-R7; the HLA-DRB1 gene amplification primer pair comprises a forward primer HLA-DRB1-F1, a reverse primer HLA-DRB1-F2, a reverse primer HLA-DRB1 A reverse primer (HLA-DRB1-R1); the HLA-DRB3 gene amplification primer pair comprises a forward primer HLA-DRB3-F6, a reverse primer HLA-DRB3-F6, a reverse primer A reverse primer (HLA-DRB3-R8); by designing the specific amplification primer group and combining with the nanopore sequencing length reading technology, the problems of insufficient resolution and the like of the existing typing technology are solved, the typing accuracy and resolution are improved, and the performance is superior to that of the traditional technology; meanwhile, the process is optimized, the limitation of long detection period and the like is broken through, the whole process is rapidly completed, the technical threshold and detection expenditure are reduced, high efficiency, convenience and economy are considered, and support is provided for clinical popularization and scientific research application.

The application discloses a target typing method, device, equipment and storage medium. The target typing method comprises the following steps: performing feature extraction on a plurality of initial images containing a target to be typed, respectively, to obtain initial features of the target in each initial image; fusing the initial features based on a preset correlation relationship between the initial images to obtain target features; and obtaining a typing result of the target by using the target features. The above scheme can improve the accuracy of the typing result.

The invention belongs to the technical field of biological information processing, and provides a cancer typing method and system based on cross-modal attention and variational representation learning, and the method comprises the steps: obtaining the multi-modal medical data of a patient, coding the multi-modal medical data, mapping the multi-modal medical data to a modal specific representation space of a unified dimension, and obtaining the feature representation of a corresponding modal; a multi-head attention mechanism is introduced, for each attention head in the multi-head attention mechanism, an independent mapping space is constructed for each mode, output of the multiple attention heads is spliced on the feature dimension, and through linear transformation, multi-mode fusion representation aggregating cross-mode complementary information is obtained; deducing statistical parameters of potential posteriori distribution represented by multi-modal fusion, and sampling to obtain potential variables; based on the potential variables and the classifier, obtaining a cancer typing result through Softmax; and end-to-end accurate classification is realized.

The application discloses a skin type prediction method for small sample data autonomous learning, and relates to the technical fields of deep learning and medical beauty skin type. The initial model is obtained by a convolutional neural network through a small number of labeled samples, and the subsequent new samples are accepted through the initial model, and whether the new samples have labeling value is judged according to the prediction result of the model, so that only the samples determined to be inaccurate by the model are selected for labeling and retraining. Compared with the existing skin type method, a single model can be used to obtain a more perfect result, the model is continuously iteratively optimized by using the enhanced unit in the actual use process, and the idea of active learning is used to select the samples with greater uncertainty for labeling, so that the number of samples needing expert labeling can be greatly reduced, and the labor cost is reduced. According to the reliability module, when the samples are expanded, the skin type with insufficient reliability is preferred, so that the final typing effect is improved.

The application discloses a diploid typing method based on Hi-C data, comprising obtaining an existing typing assembly result; mapping the assembly result and obtaining a pure region and a hybrid region of a diploid genome; filtering a comparison result of the Hi-C reading and reserving a Hi-C comparison result containing a hybrid variation site; identifying a large section switching existing in the assembly result; and counting the number of Hi-C connections between the sections after cutting, thereby completing the typing of the diploid. The application further discloses a system for implementing the diploid typing method based on the Hi-C data, and an assembly method comprising the diploid typing method based on the Hi-C data. The application filters the Hi-C comparison result through the hybrid variation in the diploid genome, detects whether a large parent switching exists by using the filtered Hi-C comparison result, thereby realizing the final diploid typing method and assembly, and therefore the application has higher reliability and better accuracy.

The application discloses a rehabilitation action recognition and classification method, system, device and storage medium, the method comprising: collecting a three-dimensional coordinate sequence of a human skeleton point corresponding to a target rehabilitation action performed by a user; performing normalization and time alignment processing on the three-dimensional coordinate sequence to generate a standardized posture matrix; extracting principal component features for representing action patterns from the standardized posture matrix; performing unsupervised clustering analysis on the principal component features, and dividing a plurality of action pattern categories according to a clustering analysis result; performing similarity matching on the principal component features and features corresponding to the plurality of different action pattern categories in a typical action pattern database; and determining a specific action pattern category to which the target rehabilitation action belongs according to a similarity matching result. The application improves the objectivity, repeatability and clinical interpretability of rehabilitation action recognition and classification, and expands the applicable scenarios.

The invention discloses an HLA-DRB1 gene high-resolution typing method based on group specific primers, and belongs to the technical field of gene detection. The group of specific primers are respectively designed according to exons 1-4 of the HLA-DRB1 gene, sequences of the specific primers are shown as SEQ ID NO.1-SEQ ID NO.20, the specific primers have good conservative property on allele sequences of the HLA-DRB1 gene, compared with gene sequences of HLA-DRB3, HLA-DRB4 and HLA-DRB5, the specific primers have good specificity, 1, 2, 3 and 4 exons of the HLA-DRB1 site can be effectively amplified, the corresponding exons are sequenced, and the specific primers can be used for detecting the HLA-DRB1 gene. The polymorphic site of the HLA-DRB1 gene is fully covered. Therefore, when further typing is carried out, the resolution and accuracy of HLA-DRB1 genetic typing are effectively improved, and the ambiguous condition of HLA-DRB1 genetic typing is improved.

The invention provides an intelligent montella fracture typing method and device based on image-text multi-modal fusion, and relates to the technical field of medical image typing. The method comprises the following steps: extracting an original high-dimensional feature vector of an image by using a ViT pre-training model, and extracting an original high-dimensional feature vector of a text by using a BERT pre-training model; respectively projecting the original high-dimensional feature vectors to a low-dimensional embedding space to obtain projected image and text features; then the image is input to a feature interaction fusion module, the module learns a shared interaction representation through nonlinear transformation, generates two independent attention weights based on the representation, respectively applies the two independent attention weights to projected image and text features, and finally generates a fusion feature vector; according to the method, the accuracy and comprehensiveness of disease prediction and diagnosis are improved through deep interactive fusion, hierarchical information aggregation and a cost-sensitive learning strategy.

The present application belongs to the technical field of cosmetic safety evaluation, and discloses a human patch test result typing method for cosmetics suitable for sensitive skin, which comprises the following steps: collecting comment data and performing deduplication and noise reduction processing, analyzing the comment data set using a trained RoBERTa-large language model, identifying adverse reaction comments, and calculating adverse reaction scores and adverse reaction rates; performing a patch test and setting a typing line according to the patch test results; extracting product characteristics of the cosmetics; establishing a generalized linear model; testing the likelihood ratio chi-square and significance of each generalized linear model, and screening the best typing of the cosmetics corresponding to the patch test. The method of the present application can effectively evaluate the safety risk of cosmetics for target users.

We will develop a probe set that can process multiple samples simultaneously using sequence capture methods and comprehensively capture genes in the KIR region. [Solution] A probe set for KIR gene typing is provided, each consisting of oligonucleotides having a specific base sequence. Furthermore, a method for KIR gene typing using the probe set is provided.

The invention discloses a gastroesophageal reflux AI auxiliary typing method based on esophageal function and morphological characteristics, and belongs to the technical field of gastroesophageal reflux, a first index parameter is acquired, esophageal functional characteristics are evaluated by using a pre-training model according to the first index parameter, and a functional score is calculated; wherein the first index parameter comprises a high-resolution esophageal power index parameter and an esophageal pH-impedance combined index parameter; obtaining esophageal endoscopic image index parameters, and according to the esophageal endoscopic image index parameters, evaluating the severity of the foraminal hernia defect and cardia relaxation by using the deep learning convolutional neural network prediction model, and calculating a morphological score; comprehensively evaluating the severity of the gastroesophageal reflux according to the functional score and the morphological score, and completing the precise typing of the gastroesophageal reflux. The severity of esophageal dysfunction and morphological defect is effectively evaluated based on a comprehensive index evaluation system, and precise typing of gastroesophageal reflux disease is completed.

This invention provides a highly practical probe set and a method for typing HLA genes using it, which enable efficient and highly accurate simultaneous typing of a large number of samples using the sequence capture method. [Solution] A probe set for HLA gene typing is provided, each consisting of oligonucleotides having a specific base sequence. Furthermore, an HLA gene typing method using the sequence capture method with the probe set is provided.

The invention discloses an accurate auxiliary meningitis typing method based on a machine learning model, electronic equipment and a storage medium, and the method comprises the steps: selecting medical detection items as features, and combining the features to construct a feature subset; constructing a meningitis subdivision discrimination framework, and disassembling meningitis diagnosis requirements into nine mutually independent binary discrimination tasks; taking the feature subset as input, executing each binary discrimination task to construct a training task, and training an independent machine learning model; obtaining a binary discrimination task selected by a doctor and a binary discrimination task selected by the doctor; and respectively calling independent machine learning models for execution, and outputting auxiliary typing discrimination. According to the accurate meningitis typing method based on multi-task discrimination of the machine learning model, clinicians are helped to judge meningitis categories by using a machine learning method, so that accurate and effective diagnosis and treatment are provided for patients in time.

The invention belongs to the technical field of multi-level regional mountain torrent classification and classification methods, and provides a multi-level regional mountain torrent classification and classification method based on a graph neural network and a decision tree. The method comprises the following steps: firstly, collecting mountain torrent disaster-pregnancy data of a target area, and generating a standardized raster data set through resampling, cutting and standardization processing; secondly, introducing a hydrological connectivity relation to construct graph structure data, and defining a node effective neighborhood set; and evaluating the mountain torrent disaster risk by introducing a graph neural network model of an attention mechanism, calibrating an optimal risk threshold and dividing five risk levels. For high-risk and extremely-high-risk areas, a classification and classification method is constructed to divide primary classification and secondary classification, and an optimal classification and classification result is obtained by automatically screening and optimizing rules through comprehensive evaluation criteria. And finally, analyzing the contribution of the mountain torrent disaster-pregnancy factor based on a typing result, and realizing analysis of disaster forming mechanisms of different types of mountain torrents.

This invention discloses an intelligent typing method and system for M protein in immunofixation electrophoresis images, belonging to the field of immunofixation electrophoresis image analysis technology. This invention establishes a double-blind annotation process and an expert knowledge-driven annotation standard with an embedded annotation verification algorithm based on physical constraints of electrophoretic mobility. Vahadane staining normalization and dynamic ROI extraction techniques are used to standardize the images, and intelligent noise suppression is applied to the image data to improve data quality. Through a hybrid neural network deep learning algorithm, the AI ​​model can perform standardized interpretation of electrophoresis images, reducing the influence of human factors and enabling the model to reproduce the specificity and accuracy of expert-level interpretation. This solves the problems of low accuracy due to strong subjectivity in traditional visual interpretation, such as overlapping bands and weak positives, and the low efficiency of seeking expert consultation for complex and difficult cases.

The invention is suitable for the technical field of biology, and provides a giardia genome SNP bar code typing method based on machine learning optimization. According to the method, typing is completed through data acquisition and preprocessing, unsupervised group structure clustering, machine learning feature screening, bar code SNP panel construction, robustness evaluation and detection and interpretation. According to the method, an XGBoost model is trained by taking an unsupervised clustering result as a label, and 50 loci are screened in combination with an SHAP index to form an SNP bar code panel. The resolution ratio of the panel is close to that of whole genome SNP typing only by using a small number of sites, the performance of the panel is superior to that of MLST, and high accuracy is kept under low-quality data such as 15X low depth. Detection modes such as multiple PCR and the like and standardized reports are supported, the process adopts modular design and can be realized in a computer readable storage medium, and an effective tool is provided for giardia public health monitoring and cross-host traceability.

Disclosed are a Parkinson's disease sample feature typing method, a feature typing system, and a sample classification model training method based on a local field potential. The typing method includes: calculating a power spectral density of a Beta-band signal of a local field potential of a sample to obtain an average power spectral density curve, and performing peak analysis on the average power spectral density curve to obtain a peak power spectral density; separately modeling a periodic element and an aperiodic element of an average power spectrum to extract a periodic power spectrum and an aperiodic component; calculating a phase-amplitude coupling feature of the Beta-band signal of the local field potential of the sample; and performing feature clustering analysis, and outputting sample typing results. In the disclosure, a multidimensional data model is constructed, and classification accuracy and reliability are improved.

The invention provides a multi-site sequence typing primer and typing method of serratia marcescens, and belongs to the technical field of molecular detection of pathogenic microorganisms. The invention provides a specific primer group for multi-site sequence typing of serratia marcescens. The specific primer group comprises primer groups designed aiming at seven housekeeping genes: pitA, cyoB, glnA, ftsP, nadR, purR and potD. The invention also provides an MLST typing method of serratia marcescens. The MLST typing method comprises the following steps: extracting genome DNA of a strain to be detected; respectively carrying out PCR (Polymerase Chain Reaction) amplification by using the primer group; and sequencing the amplified product, and comparing the amplified product with a pre-established serratia marcescens MLST standard sequence database to obtain the sequence type of the strain. The invention provides a standardized MLST typing primer and method for serratia marcescens. The standardized MLST typing primer and method have the advantages of accurate typing, good repeatability, digital result, convenience in data sharing among laboratories and the like.

The invention discloses a rotavirus detection primer pair and a typing analysis method and system thereof. The invention relates to a primer pair (containing a forward primer of SEQ ID NO: 1 and a reverse primer of SEQ ID NO: 2) for genotyping of rotavirus VP7, a primer pair (containing a forward primer of SEQ ID NO: 3 and a reverse primer of SEQ ID NO: 4) for genotyping of VP4 and a composition containing the primer pairs. The invention also provides a rotavirus genotyping method which comprises the following steps: extracting rotavirus RNA in a sample, performing reverse transcription to obtain cDNA, performing PCR amplification by using the primer pair, sequencing a product, and comparing a sequencing sequence with a rotavirus reference sequence database to obtain G-type and P-type genotyping results; the invention also provides an automatic typing system for typing analysis of the sequencing sequence of the PCR product. The primer can amplify main epidemic genotypes only through one round of PCR, is convenient to operate and excellent in specificity and detection capacity, is accurate in typing method result, effectively solves the problems of insufficient primer sensitivity, tedious typing and the like in the prior art, and is suitable for rotavirus genotyping and epidemiological monitoring.

The invention belongs to the technical field of cosmetic safety evaluation, and discloses a cosmetic human body patch test result typing method suitable for sensitive skin, which comprises the following steps: collecting comment data and carrying out de-weighting and noise reduction processing, analyzing a comment data set by using a trained RoBERTa-large language model, identifying adverse reaction comments, and classifying the adverse reaction comments. Calculating an adverse reaction score and an adverse reaction rate; performing a patch test, and setting a parting line according to a patch test result; extracting product characteristics of the cosmetics; establishing a generalized linear model; and checking the likelihood bichi square and significance of each generalized linear model, and screening the optimal classification of the cosmetics corresponding to the patch test. According to the method, the safety risk of cosmetics to the target user can be effectively evaluated.

The invention discloses a rehabilitation action recognition and typing method, system and device and a storage medium. The method comprises the steps that a three-dimensional coordinate sequence of human skeleton points corresponding to a target rehabilitation action executed by a user is collected; performing normalization and time alignment processing on the three-dimensional coordinate sequence to generate a standardized posture matrix; extracting principal component features used for representing action modes from the standardized posture matrix; performing unsupervised clustering analysis on the principal component features, and performing division according to a clustering analysis result to obtain a plurality of action mode categories; performing similarity matching on the principal component features and features corresponding to a plurality of different action mode categories in a typical action mode database; and according to a similarity matching result, determining a specific action mode category to which the target rehabilitation action belongs. According to the method, objectivity, repeatability and clinical interpretability of rehabilitation action recognition and typing are improved, and application scenes are expanded.

The invention belongs to the technical field of bioinformatics and gene detection, and particularly relates to a method for realizing high-accuracy and high-resolution human leukocyte antigen HLA typing based on whole exon sequencing data. By incorporating complete exon and intron sequences, different alleles sharing a G-DOMAIN sequence are effectively distinguished, HLA-AP pseudogene sequence correction is combined, typing errors caused by pseudogene interference are effectively avoided, and the anti-interference capability is high. The HLA typing method provided by the invention is adaptive to high and low coverage WES data, can still obtain an accurate typing result for NGS data of fragmented or limited DNA samples, does not need strict coverage screening, and is wide in adaptability. The HLA allele dictionary can be conveniently expanded along with updating of the IMGT / HLA database. According to the HLA typing method, high-resolution typing can be achieved, the typing accuracy of high-coverage NGS data reaches 100%, and the typing precision is high.

The application provides a kind of uterus myoma automatic typing method and device based on deep learning.The method comprises the following steps: constructing semantic segmentation model, input pelvic medical image is divided into mucosa, muscle layer, serosa outside 3 regions;Construct instance segmentation model, segment out uterine fibroids, get uterine fibroids volume V T ;Extract the outline of uterine fibroids, calculate the volume V O Of the uterine fibroids belonging to serosa outside area and the volume V N Belonging to mucosa inside area;Based on V O , V N And V T The uterine fibroids are typed based on FIGO.The whole process of typing uterine fibroids of the application does not need artificial participation, reduces the analysis pressure of imaging department doctors, helps to improve the accuracy and consistency of FIGO typing determination.

The application relates to a method, device and application of a depression biological typing method based on resting-state brain function connection, which can objectively type depression biological subtypes, establish a corresponding relationship between typing and treatment response, realize individual optimal treatment strategy recommendation for patients, improve the treatment response rate and reduce the clinical trial and error cost. The method comprises the following steps: (1) data acquisition and preprocessing; (2) definition of biological subtype clustering and characteristics; (3) subtype verification and standardization; and (4) rapid typing of new patients.

The application provides a knee osteoarthritis typing model training method and device and a typing method, and the method comprises the following steps: constructing a data set by taking information of a patient in a phenotype characteristic as a data sample; taking two-dimensional coordinates obtained by dimension reduction as initial clustering centers, and constructing a minimum spanning tree according to connection lines between the clustering centers; generating an adjacency matrix and a Laplacian matrix according to the connection relationship; calculating the probability of the data sample being distributed to the clustering center according to the distance between the two-dimensional coordinates and the clustering center, and generating a soft distribution probability matrix and a diagonal matrix; solving a pre-set target function based on the above matrices to obtain an updated matrix set; solving the target function based on the updated matrix set, and when the target function value converges, taking the minimum spanning tree topology as a knee osteoarthritis typing model. The application can make the knee osteoarthritis typing result meet the requirements of clinical interpretability, continuous phenotype characteristics and stable and reliable results at the same time.

This invention provides a method and system for dynamic clustering and metabolic response typing based on respiratory quotient (RQ) in relation to nutritional challenges. Specifically, based on changes in metabolic indicators before and after meals in normal-weight and overweight / obese individuals, three types of RQ clusters are identified. The typing model constructed using these three clustering features can effectively classify the metabolic response of the population, thereby further predicting weight loss outcomes after weight loss intervention and also applicable to personalized lifestyle guidance. The typing method and system of this invention have high sensitivity and accuracy, and the indicators used are readily available, showing promising clinical application prospects.

The present disclosure provides a method, system and medium for intelligent typing of chikungunya virus, obtains CHIKV sequence data from a public database, performs quality control, uses an artificial intelligence model to extract typing reference sequences of CHIKV, and then compares the sequence data with the typing reference sequences one by one. If the comparison result of the sequence data and a certain typing reference sequence is similarity>99% and sequence coverage>99%, the sequence information of the typing reference sequence is supplemented to the sequence data, and a typing sequence database is generated. The present disclosure uses an artificial intelligence model to realize automatic extraction, semantic alignment and standardization of multi-source data, solves the bottleneck of data dispersion and metadata loss, realizes intelligent typing of chikungunya virus, encapsulates complex bioinformatics processes into a "one-key" online tool, significantly reduces the technical threshold, enables grassroots personnel to independently complete high-level analysis, and provides real-time, visual molecular evidence and risk prompts for epidemic prevention and control.

The application discloses a primer group, a kit, a typing method and application for rapid typing of porcine delta coronavirus, and relates to the technical field of virus genome detection. The primer group comprises an upstream primer PDCoV-F, wherein the nucleotide sequence of the primer is shown as SEQ ID NO:1; and a downstream primer PDCoV-R, wherein the nucleotide sequence of the primer is shown as SEQ ID NO:2. The primer group is used for amplifying a core genome fragment obtained through screening, the fragment can represent the evolutionary topology structure of the whole genome, the typing resolution is higher than that of a traditional single gene method, and information distortion is avoided; the fragment is short in length, only needs conventional PCR and Sanger sequencing, the cost is reduced by more than 80%, data analysis is simple, and a professional biological information platform is not needed; an operation process is standardized, the flux is high, and the application is suitable for large-scale molecular epidemiological monitoring in a clinic; and the typing result can reflect the virus evolution history and the transmission path, and can provide a reliable and scientific basis for epidemic prevention and control.

The invention belongs to the technical field of bioinformatics, and particularly relates to an HLA typing method based on high-throughput sequencing. According to the method, the aligned HLA sequence is innovatively processed to form an algorithm database with the same length as the sequencing read length, and each basic group of each allele is placed in the absolute coordinate of the whole gene locus through the aligned HLA, so that the allelic gene is obtained. Therefore, the sequence which is obtained after processing and has the same length as the sequencing read length directly has absolute coordinates of one or more HLA gene loci. Meanwhile, high-throughput sequencing data is directly compared with an algorithm database, the base coverage of each absolute coordinate can be directly obtained on the locus, and then the loci are subjected to the steps of locus coincident fragment disassembly, position coincident base disassembly, haploid phasing, candidate sequence construction, database comparison and the like. And obtaining one or more pairs of clear HLA typing sequences according to the clearness of the original data and the mutation position density of the gene locus.

The application belongs to the technical field of biological detection, and particularly relates to a probe-free multiplex SNP typing method, a kit and application thereof. The application proposes a method for realizing multiplex SNP typing without using probes. The method takes melting temperature (Tm) as a discrimination index, distinguishes different allele-specific PCR products by adjusting Tm through differentiation tailing, and thereby identifies the allele types of SNPs. Compared with existing methods, the method greatly reduces reagent cost, experimental time and workload, while maintaining high accuracy and stability. The efficient, scalable and economical characteristics make it expected to play an important role in large-scale genetic screening, crop breeding and clinical typing analysis, and thus have good practical application value.