23 results about "Gene classification" patented technology

The invention discloses a gene identification method based on a mask graph auto-encoder. The method comprises the following steps: 1, acquiring gene interaction data and omics characteristic data and preprocessing the data; 2, masking the processed data, specifically comprising two branches, a node masking module and an edge masking module; 3, inputting the masked network into a graph automatic encoder for training, wherein the graph automatic encoder learns embedded representation of the network by reconstructing nodes and edges of the network; and 4, obtaining low-dimensional embedding of the features through the trained encoder, and finally performing gene classification by using a logic regression classifier. According to the method, the node information and the structure information of the graph are concerned at the same time by respectively masking the nodes and the edges in the network, and the dependence of the feature training model on the label information is reduced in a self-supervised learning mode, so that the genes can be accurately classified.

The present invention discloses a design method and device for an agricultural cultural heritage landscape space database. The method includes the steps of: adopting an object-oriented landscape gene classification mode to define multiple landscape categories and category elements under each landscape category; dividing the agricultural cultural heritage landscape data into spatial data and non-spatial data, and defining corresponding data storage types; digitizing various category elements; establishing an E-R diagram; establishing multiple database layers representing spatial data; constructing a physical model of the agricultural cultural heritage landscape space database, and its data layer is provided with a basic ground object information database and an agricultural cultural heritage landscape special database. The present invention can solve the problems existing in the prior art, such as the inability to conduct systematic dynamic monitoring and management, data systematic analysis, scientific planning and design, etc. for agricultural heritage landscapes.

The application discloses a landscape gene identification method based on machine learning, relates to the technical field of machine learning and data science, and comprises the following steps: constructing a multi-level landscape gene classification architecture, pre-training a machine learning model based on the multi-level landscape gene classification architecture, and obtaining a landscape feature identification model; then, acquiring landscape element data corresponding to a to-be-identified landscape, calling the landscape feature identification model to analyze the landscape element data, and obtaining a landscape index identification result; then, taking the landscape index identification result as the basis, acquiring a first landscape gene identification result by using a feature deconstruction method, acquiring a second landscape gene identification result by using a prototype-variation theory, and acquiring a third landscape gene identification result by using a digital analysis strategy; and finally, taking the three results as a target landscape gene identification result, so that the efficiency and accuracy of landscape gene text identification and extraction are improved, and the application of the landscape gene is facilitated.

To improve estimation accuracy of functional abnormality.SOLUTION: A medical diagnosis support method includes acquiring a medical image of a subject, acquiring variant information including an estimation result of variants of a plurality of genes of the subject by analyzing the medical image, classifying the plurality of genes into one or more co-occurrence groups based on co-occurrence information indicating co-occurrence of variants between genes, determining variants of one or more genes belonging to each of the co-occurrence groups based on the variant information, and estimating a functional abnormality of the subject based on a determination result of the variants of the genes.SELECTED DRAWING: Figure 1

The embodiment of the invention provides a gene data classification method and device based on a fuzzy rough set and incremental learning, and the method comprises the steps: inputting obtained to-be-classified gene expression data into a target gene data classification model; and outputting a target classification result by the target gene data classification model based on the input to-be-classified gene expression data. In the training process of the target gene data classification model, the preset fuzzy rough set model is adopted to screen the gene expression data feature vectors in the gene expression data training sample data set, and only the gene expression feature vectors of which the importance is greater than the preset importance threshold value are reserved to participate in the training of the gene data classification model; the interference of gene expression data with poor contribution degree to the gene classification result on model training can be effectively reduced. Thus, under the condition that important classification information is reserved, the data dimension needing to be processed by the gene data classification model is reduced, and the classification efficiency and accuracy of the gene data classification model can be improved.

The invention relates to the technical field of gene classification, in particular to a longitudinal DNA methylation data-based classification method, which comprises the following steps of: taking collected longitudinal DNA methylation data as sample data, dividing a plurality of data profile matrixes by a time axis, and forming a methylation matrix according to context information of the data profile matrixes; extracting each key site in the methylation matrix by using the stage identifier of the sample data, and identifying the change trend of each key site according to the clustering trajectory of the key sites; based on the change trend of each key site, extracting each differential methylation region, taking each differential methylation region as input, outputting the expression type of each sample data by using the classification model, and calibrating a difference factor according to the data proportion of the expression type in each differential methylation region; according to the difference factor calibrated by each differential methylation region, identifying the execution screening classification of each difference factor; and the accuracy and efficiency of DNA methylation data classification are improved.

The present application is applicable to the field of bioinformatics, and provides an HLA type determination method and device, including: comparing and screening HLA second-generation sequencing data samples after quality control processing with gene features of an HLA type database, and gene classification of the screened data; determining the candidate type range of each gene according to the gene-classified data and the HLA type database; comparing the gene-classified data with a preset gene sequence to determine the difference site; chaining the difference sites into chains, and comparing them with the difference site database to obtain accurate candidate types; determining the HLA type result according to the candidate type range and the accurate candidate type; the present application can directly analyze the HLA type result for normal HLA second-generation sequencing data samples without manual intervention, and will give corresponding prompt information for abnormal data such as HLA new type samples, suspected mixed samples, and data unqualified samples.

Described herein are methods, systems, and compositions for non-invasively diagnosing or detecting a skin disease or disorder. Diagnosing or detecting a non-melanoma skin cancer as provided herein comprises detecting gene expression levels of a set of identified genes and in some instances further detecting mutations in a gene of interest.

The embodiment of the invention discloses a gene classification method and device based on gene expression data and electronic equipment, and belongs to the technical field of bioinformatics and the field of data processing. The method comprises the following steps: determining expression values of genes in different cell clusters to obtain an expression value data set corresponding to the genes; determining a target expression value threshold value of the gene according to the expression value distribution condition in the expression value data set; and classifying the genes in the cell cluster based on the target expression value threshold. According to the embodiment of the invention, the distribution rule of the gene expression values can be utilized, the objectivity and accuracy of biological classification can be improved, meanwhile, fluctuation of the gene expression level caused by the batch effect can be effectively handled, and the consistency of gene classification is ensured.

The present invention provides a method for biological sequence processing and model training, comprising the following steps: S1, obtaining data of biological gene sequences and integrating the data; S2, preprocessing the data, traversing the read biological gene sequences, and filtering out the biological gene sequences that meet the requirements; S3, constructing a data set required for training the model, and fine-tuning the data set according to the number of each category of data in the data set to ensure that the scales of various types of data in the data set are roughly equal; S4, performing processing on the quantity balance of various types of data in the data set and the length balance of gene data to obtain a training set; S5, using the training set to train a model with a reverse complementary network. The method proposed by the present invention can save time on the basis that the accuracy is similar to that of traditional gene classification and recognition methods, and can correctly predict some genes that cannot be correctly classified by traditional biological methods.

This invention provides a species gene classification system, method, apparatus, electronic device, and storage medium, belonging to the field of integrated circuit technology. It includes: a preprocessing module for converting a first serial current signal corresponding to a gene of a species to be tested into a hash vector representing that gene; a content-addressable memory (MAP) for performing vector-matrix multiplication on the hash vectors to obtain multiple first cumulative currents; the MAP is an RRAM array structure, and its conductance is positively correlated with a reference hash vector, where each reference hash vector represents a gene from a species gene pool; and a first comparison module for comparing the various first cumulative currents to determine the species to which the gene belongs. This invention achieves species gene classification through in-memory computation, reducing data movement and eliminating the need for complex algorithms to correct noise, thereby accelerating system operation, reducing sequencing time, and lowering system energy consumption.

The present application relates to the technical field of biomedical detection, and particularly relates to an intelligent transcriptome analysis system based on a maternal-fetal interface biomarker. The system comprises a maternal-fetal RNA low-temperature storage module, a maternal-fetal genome sequencing calculation module, a transcriptome differential expression determination module and a transcription differential expression network construction module, can obtain a maternal-fetal interface biological blood sample set and perform RNA extraction and low-temperature storage to generate a maternal-fetal blood RNA low-temperature sample group; by constructing a maternal-fetal blood RNA sample library and performing single-end sequencing calculation and reference gene mapping screening, a maternal-fetal RNA reference genome is generated; based on the maternal-fetal RNA reference genome, differential expression genes are determined, target gene clustering and enrichment analysis are simultaneously performed, the gene pathway distribution corresponding to each gene classification is obtained, and gene expression network analysis is performed to generate a maternal-fetal target gene expression network. The present application can analyze the gene pathway network between maternal-fetal target genes.

The invention relates to the technical field of biology, and particularly discloses a typing and prognosis prediction model construction method based on HR < + > / HER2-LOW breast cancer gene classification. According to the application, clinical pathological characteristics and biological characteristics of the HR < + > / HER2-low breast cancer are comprehensively analyzed, an internal molecular typing system is established, specific molecular treatment targets of all subtypes are identified, a combined treatment scheme is optimized, and'classified treatment 'is developed to accurately treat the HR < + > / HER2-low breast cancer.

The invention discloses a gene function classification method and a gene function classification device based on a Sension-BERT model and a KMeans model. The method comprises the following steps: obtaining data required by a model, wherein the data required by the model is listed subsequently; through pre-training and task fine tuning, the SBERT can better capture the fine-grained semantic difference in the gene function description, and the data is input into the pre-trained SBERT to generate Sensor Embedding; and continuously inputting the Sensor Embedding into the KMeans model for training, and adjusting parameters through an elbow method to obtain an optimal K value (a classification cluster number). Based on the established gene function summary knowledge base, a reliable method is provided for gene classification through a modeling method combining an SBERT deep learning model and a KMeans unsupervised machine learning model.

The embodiment of the present application provides a gene data classification method and device based on fuzzy rough sets and incremental learning. The method inputs the acquired gene expression data to be classified into a target gene data classification model, and the target gene data classification model outputs a target classification result based on the input gene expression data to be classified. During the training process of the target gene data classification model, a preset fuzzy rough set model is used to screen the gene expression data feature vectors in the gene expression data training sample data set, and only the gene expression feature vectors with an importance greater than a preset importance threshold are retained to participate in the training of the gene data classification model, which can effectively reduce the interference of gene expression data with a poor contribution to the gene classification result on the model training. In this way, the data dimension required to be processed by the gene data classification model can be reduced while retaining important classification information, which helps to improve the classification efficiency and accuracy of the gene data classification model.

The invention relates to the technical field of biological gene detection, and particularly discloses a meriones unguiculatus SNP molecular marker combination and application thereof. The meriones unguiculatus SNP molecular marker combination disclosed by the invention comprises at least one of 219 SNP molecular markers, the physical positions of the 219 SNP molecular markers are determined by performing sequence alignment on whole genome sequencing with the coverage rate of 10 * on the basis of meriones unguiculatus, and the site information of the 219 SNP molecular markers is shown in a table 1. The meriones unguiculatus SNP molecular marker combination provided by the invention is used for detecting the SNP genotyping of the meriones unguiculatus, and has the properties of novelty, stability, economy and high efficiency.

The present invention provides a gene classification method, system and device based on multi-label feature selection, the method comprising: obtaining a gene expression data set, performing feature selection on the gene expression data set using a multi-label feature selection model based on missing gene data, and obtaining a feature subset of the gene expression data set; training a gene classification model using the feature subset of the gene expression data set, and obtaining a trained gene classification model; classifying the genes to be classified based on the feature subset of the gene data to be classified using the trained gene classification model, and obtaining labels of the gene data to be classified. The present invention adopts a gene classification method based on multi-label feature selection, completes feature selection of multi-label gene data based on missing data, considers all dependencies between gene labels and features, and completes gene classification based on the feature subset after feature selection, thereby fundamentally solving the problem of low accuracy of existing multi-label gene classification.

The invention discloses a tumor gene classification method based on a variable precision fuzzy rough set, and relates to the technical field of mining and bioinformatics crossing, and the method comprises the following steps: constructing a variable precision fuzzy rough set model based on a pseudo-overlap function, and defining a fuzzy positive domain and fuzzy dependency degree used for measuring the correlation degree between attributes and decisions; providing a feature selection algorithm based on the model, the rough fuzzy set and the fuzzy dependency degree; a feature selection algorithm is combined with an intelligent classifier to be applied to tumor gene classification; according to the method, the variable-precision fuzzy rough set model based on the pseudo-overlap function is provided, so that the processing capability of fuzzy information is enhanced, the uncertainty of a fuzzy relationship in a discourse domain can be flexibly dealt with, a solid theoretical basis is provided for accurately depicting the association between attributes and decisions, and the adaptability and expression capability of complex fuzzy data are improved.

The invention discloses an animal and plant data classification method and device, electronic equipment and a storage medium, and the method comprises the steps: after obtaining a plurality of pieces of animal and plant data to be classified, extracting feature data from each piece of animal and plant data, the feature data comprising real object feature data, environment feature data and gene feature data; the animal and plant data are classified according to the physical feature data and the environment feature data, a plurality of entity classification categories are obtained, and each entity classification category comprises a plurality of animal and plant data; and classifying the animal and plant data of each entity classification category according to the gene feature data to obtain a plurality of gene classification categories, and classifying the animal and plant data according to the gene classification categories. According to the method, comprehensive classification is carried out through the object features, the environment features and the gene features, so that classification deviation is avoided, and the classification accuracy is improved.

This paper provides a method for predicting the risk of immune-related adverse events (irAEs) from immune checkpoint inhibitor (ICI) therapy. ICIs have emerged as promising treatments for many cancer types. However, these therapies can induce unpredictable and potentially serious autoimmune toxicities, termed irAEs. The method involves classifying T cell receptor β genes as productive or repair TCR β genes and calculating a tolerant fraction (TF) score. TCR β gene classification indicates the relative presence of non-tolerant T cells, which are more likely to recognize autoantigens after treatment with ICI therapy. The relative presence of tolerant T cells indicates the risk of irAEs.

Methods to improve the selection of breeding individuals as part of a breeding program are provided in which optimized estimation data sets are constructed by selecting candidates for phenotyping, for which genotypic information is also available, from a candidate set and inputting them into the estimation data set and then evaluating accuracy of genomic estimated breeding values for each candidate (i.e. genomic prediction accuracy). The optimized estimation data set is then used as a model to determine genomic estimated breeding values of breeding individuals based purely on genotypic information.

The invention relates to the technical field of biomedical detection, in particular to an intelligent transcriptome analysis system based on maternal-fetal interface biomarkers. The system comprises a maternal-fetal RNA low-temperature storage module, a maternal-fetal genome sequencing calculation module, a transcriptome differential expression determination module and a transcriptome differential expression network construction module, and can obtain a maternal-fetal interface biological blood sample set and perform RNA extraction and low-temperature storage to generate a maternal-fetal blood RNA low-temperature sample set; the method comprises the following steps: constructing a maternal and fetal blood RNA sample library, and carrying out single-ended sequencing calculation and reference gene mapping screening to generate a maternal and fetal RNA reference genome; carrying out differential expression gene determination based on the maternal and fetal RNA reference genome, carrying out target gene clustering and enrichment analysis to obtain gene pathway distribution corresponding to each gene classification, and carrying out gene expression network analysis to generate a maternal and fetal target gene expression network. The method can be used for analyzing a gene pathway network between maternal and fetal target genes.

A method of identifying a bicycle gene involves determining for a candidate gene a series of gene structure-based predictor variables, and applying a bicycle gene classifier including the predictor variables to determine whether the candidate gene is identified as a bicycle gene. The gene structure-based predictor variables can be selected from the following: (i) total gene length (base pair, bp); (ii) total length (bp) of coding exons; (iii) first coding exon length (bp); (iv) last coding exon length (bp); (v) number of internal exons in phase 0); (vi) number of internal exons in phase 1; (vii) number of internal exons in phase 2; and (viii) mean internal exon length (bp).