11 results about "Gene recognition" patented technology

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.

This application relates to the field of gene recognition technology, and provides a method and related equipment for identifying pathogenic genes based on abnormal expression. The method includes: for each target gene, calculating tail enrichment statistics in two tail directions based on the grouping tag values ​​of all signal vectors to characterize the abnormal expression of the target gene at the low or high expression end; determining the optimal tail enrichment direction from the two tail directions based on the two tail enrichment statistics; calculating the tail boundary shift degree of the target gene according to the optimal tail enrichment direction; calculating the significance p-value of each target gene; identifying multiple pathogenic genes from all target genes based on all significant p-values; and performing pathogenicity analysis based on the tail boundary shift degree and optimal tail enrichment direction of all pathogenic genes to obtain the pathogenic gene identification result. The method of this application can improve the accuracy of pathogenic gene identification.

The application discloses a plant salt-alkali-resistant gene recognition method and system, in particular to a plant salt-alkali-resistant gene recognition method and system based on machine learning, which aims at solving the problem of low accuracy of plant salt-alkali-resistant functional gene recognition caused by high false positive rate and false negative rate of the recognition result of the salt-alkali-resistant gene recognition method which depends on the recognition of plant homologous genes, and comprises the following steps: obtaining a plurality of plant protein sequences known to be salt-alkali-resistant genes or not; obtaining a feature vector of the plant protein sequence; constructing a C4.5 algorithm model, training the C4.5 algorithm model with the feature vector, outputting whether the gene is a salt-alkali-resistant gene, and obtaining the trained C4.5 algorithm model; executing S2 on the plant protein sequence to be recognized to obtain a feature vector, inputting the feature vector into the trained C4.5 algorithm model, and obtaining whether the plant protein sequence to be recognized contains a salt-alkali-resistant gene. The system executes any step of the method. The application belongs to the field of gene recognition.

The present application relates to the technical field of bioinformatics and oncology, and particularly relates to a tumor driver gene identification system fusing multi-omics data and graph neural network, which comprises a data preprocessing module, a heterogeneity feature fusion module, a dynamic gene graph construction module, an improved graph neural network identification module, and a result verification and optimization module. Through standardizing the multi-omics raw data, the heterogeneity features are weighted and fused by using the attention mechanism, the dynamic gene co-expression network is constructed by combining the tumor development time series data and the clinical information, the driver gene identification is performed by using the graph attention network with embedded residual connection and multi-scale feature extraction, and the closed-loop optimization is realized by using the wet experiment data and the clinical sample feedback. The deep fusion and dynamic modeling of multi-dimensional data are realized, the accuracy, specificity and generalization ability of the driver gene identification are significantly improved, and the present application can be widely applied to the early diagnosis of tumors, the research and development of targeted drugs, and the formulation of individualized treatment plans.

This invention discloses a molecular marker and its application that breaks the linkage between smooth, hairless male sterility and co-segregation of watermelon fertility genes, aiming to solve the technical problem of the current lack of methods for identifying and characterizing major watermelon fertility genes. This application develops a molecular marker that breaks the linkage between smooth, hairless male sterility and co-segregation of watermelon fertility genes (based on the watermelon 97103 reference genome V2 version, which contains a genomic region related to male sterility in the 27.94-27.95 Mb region on chromosome 8; watermelons with deletions or partial deletions of this genomic region exhibit male sterility), and designs the corresponding primer pair BY2-3. Applying this molecular marker for marker-assisted selection breeding enables faster and more accurate targeted genetic improvement of watermelon fertility, thereby shortening the breeding cycle.

Embodiments of the present application relate to a pathogenic gene identification method, device, equipment and storage medium. The method comprises: performing phenotype feature matching on a target to-be-diagnosed case and a candidate reference case to obtain a phenotype matching result; obtaining a target reference case of the target to-be-diagnosed case from the candidate reference case according to the phenotype matching result; and generating a pathogenic gene identification result of the target to-be-diagnosed case according to a case pathogenic gene of the target reference case. The technical solution of the embodiments of the present application can improve the information utilization rate and the robustness to atypical phenotypes in rare disease pathogenic gene identification, and realize efficient and accurate pathogenic gene identification.

The application provides a tissue-specific expression gene identification method and system based on three-dimensional space transcriptome, and belongs to the field of gene identification. The method comprises the following steps: obtaining three-dimensional space transcriptome data of a target biological individual at multiple continuous development stages, wherein the three-dimensional space transcriptome data comprises cell three-dimensional coordinates, cell annotation data and gene expression information; calculating a comprehensive tissue-specific score of each gene by using at least two parameters in a spatial expression concentration, a cell composition correction specificity parameter, a cross-development phase stability parameter and a significance parameter; and identifying genes of the target biological individual based on the corresponding comprehensive tissue-specific score of each gene to obtain tissue-specific expression genes. The application can effectively improve the identification accuracy of tissue-specific genes.

The application discloses a high-perturbation gene priority ranking system, which comprises a gene interaction network, a hub gene identification module, a knockout perturbation initialization module and a perturbation propagation network.

This application discloses a method, apparatus, device, and medium for predicting pathogenic genes based on phenotypic fingerprinting. This method, executed by a computer, systematically integrates and quantifies the association information between genes and multi-dimensional phenotypes, constructing gene-specific phenotypic fingerprints at the population level. This allows for a more comprehensive capture of the complex effects of genes across different phenotypic dimensions. Furthermore, it calculates gene-centered multi-phenotypic scores using gene phenotypic fingerprints, transforming the multi-dimensional clinical phenotypic information of the target subject into gene-centered quantitative scores at the object level. Utilizing the observed phenotypes of the target subject, it achieves two key outputs: assessment of the risk of carrying pathogenic variants and priority ranking of candidate genes. This enables an objective and efficient evaluation of the fit between each candidate gene and the actual phenotype of the target subject. By introducing phenotypic fingerprinting and combining it with a multi-phenotypic scoring mechanism, this application significantly improves the efficiency and objectivity of identifying pathogenic genes for complex diseases, possessing significant clinical application value.