38 results about "Gene prediction" patented technology

The invention provides a pathogenic driver gene prediction method based on biological network fusion and related equipment. The method comprises the following steps: acquiring data of various driver genes for training; constructing an initial gene relationship map based on protein interaction, gene sequence similarity, KEGG pathway co-occurrence, a gene co-expression mode and semantic similarity of a gene ontology, and embedding various human driven gene data for training into each node in the initial gene relationship map to obtain various gene relationship maps; performing dynamic adjustment on each gene relationship map through edge discarding, feature discarding and difficult sample recognition enhancement to obtain an adjusted gene relationship map for training the constructed pathogenic driving gene prediction model to obtain a trained pathogenic driving gene prediction model; inputting the target driver gene data into the trained pathogenic driver gene prediction model for prediction to obtain a prediction result; and the accuracy and robustness of pathogenic driver gene prediction are improved.

The application discloses a gene editing system CRISPR-Cas12p and application thereof. Based on microbial genomes and metagenomic data, the CRISPR-Cas12p protein of the CRISPR-Cas protein family is obtained by preliminary screening by using a Prodigal gene prediction tool, a Pfam database and HMMER software, and a gene editing system CRISPR-Cas12p is constructed. PAM preference and interference function identification show that the editing system has a PAM preference of 5'-TTC-3', can effectively realize targeted cutting by using long transcripts and double RNA hybrid chain transcripts respectively, and can realize editing of a target gene in prokaryotic and eukaryotic cells. The CRISPR-Cas12p gene editing system obtained by the application has a small protein component, is beneficial to delivery, can realize gene editing in prokaryotic and eukaryotic cells, and has a wide application prospect.

The application relates to a method for predicting gene mutation based on deep learning using multi-modal slices, image block division is performed on a digestive tract HE slice, and based on the image block division result, each image block of the digestive tract HE slice is classified into a cancerous region; the digestive tract HE slice and an immunohistochemical slice are registered; based on the digestive tract HE slice and the registered immunohistochemical slice, a gene mutation prediction training sample set is constructed, a multi-instance learning model is trained, the training standard is whether a gene is mutated, and a gene mutation prediction model is obtained; gene mutation prediction is performed according to the obtained gene mutation prediction model, a model for predicting gene mutation in combination with multi-modal pathological data of a patient is used, high specificity of the model is ensured, compared with a pathological gene prediction model using single modal data, more modal data is introduced, and the prediction accuracy is effectively improved.

The invention relates to the technical field of gene detection, in particular to an opioid analgesic drug gene detection method based on multiple targeted amplification, which comprises the following steps: extracting DNA from a peripheral blood sample; the method comprises the following steps: setting a primer pool aiming at a preset site of a specific gene related to opioid drugs, and carrying out multi-targeted amplification sequencing by using the primer pool to obtain sequencing data; comparing the sequencing data with a human reference genome to obtain a data comparison rate, and judging the eligibility of the multi-target amplification sequencing process according to the data comparison rate; performing variation detection on the qualified sequencing data, identifying the base type of each SNP site, and determining the genotype of the subject in combination with a dbSNP database; and inputting the genotype and clinical data into a pre-trained multi-gene prediction model, and obtaining the medication guidance of the subject for using the opioid drugs. The gene detection efficiency is improved.

This invention provides a gene prediction and identification method, apparatus, device, and storage medium, belonging to the field of gene annotation and prediction. The method includes: acquiring the gene text to be annotated and a set of promoter-terminator pairs; preprocessing the gene text to generate a raw genome sequence; searching the raw genome sequence for base sequences that fuzzy search matches the set of promoter-terminator pairs to generate a base sequence to be aligned; and comparing the base sequence to be aligned with base sequences in a bioinformatics database based on the BLAST gene alignment method to generate gene prediction and identification results. This invention, by separating base sequences from promoter-terminator pairs and then performing BLAST gene sequence alignment, achieves coarse gene localization followed by BLAST gene sequence alignment, providing a method for predicting new genes, improving alignment efficiency and comprehensiveness, as well as the accuracy and comprehensiveness of gene prediction results.

Provided are a gene prediction method and apparatus, a computer device, and a computer readable storage medium. The method comprises: acquiring a template gene sequence, and a genetic gene sequence and a free gene sequence which correspond to a subject under test (step S102); determining a target gene site in the genetic gene sequence and the free gene sequence (step S104); extracting feature data corresponding to the target gene site, wherein the feature data is used for representing attribute features of the target gene site, and the feature data comprises first input data and second input data (step S106); acquiring a target gene prediction model, wherein the target gene prediction model comprises a first network, a second network, and a third network, and an output of the first network and the second network is an input of the third network (step S108); and respectively inputting the first input data and the second input data into the first network and the second network to obtain a gene prediction result outputted by the third network and corresponding to said subject (step S110).

The present application relates to the technical field of artificial intelligence and deep learning, in particular to a tomato salt tolerance prediction method and system based on deep learning, specifically as follows: obtaining a tomato salt tolerance genome, inputting it into a tomato salt tolerance prediction system based on deep learning for detection, sequentially passing through a salt-tolerant small sample gene recombination module, an epigenetic gene multi-granularity mining module, a heterogeneous salt-tolerant gene feature integration module, a salt-tolerant feature point fusion module and a tomato salt tolerance gene prediction module, and calculating the probability of having relevant tomato salt tolerance genes in the input tomato salt tolerance genome. The present application improves the prediction accuracy and generalization ability of salt tolerance genes under complex genetic background, and provides an intelligent prediction method for tomato salt-tolerant variety breeding.

The invention provides a dairy cow ketosis regulatory gene prediction system based on multi-omics analysis and machine learning, which belongs to the technical field of molecular breeding and disease prevention and control, and comprises a data acquisition and preprocessing module, a feature set establishment module, a machine learning model establishment module and a result evaluation module, the method comprises the following steps: integrating dairy cow genome, transcriptome and metabolome data, screening candidate regulatory genes through whole genome association analysis, gene differential expression analysis, cis-eQTL positioning and co-positioning analysis, and constructing a gene expression feature set; core regulation genes are screened through L1 regularization penalty by means of a Lasso model, weights are distributed, model parameters are optimized in combination with grid search and cross validation, and model performance is evaluated through an ROC curve and an AUC value. According to the invention, an integrated technical system from gene screening to risk prediction is constructed, efficient screening of the core regulation gene and accurate prediction of ketosis risk are realized, and the economic loss of breeding is effectively reduced.

Provided are a gene prediction method and apparatus, a computer device, and a computer readable storage medium. The method comprises: acquiring a template gene sequence, and a genetic gene sequence and a free gene sequence which correspond to a subject under test (step S102); determining a target gene site in the genetic gene sequence and the free gene sequence (step S104); extracting feature data corresponding to the target gene site, wherein the feature data is used for representing attribute features of the target gene site, and the feature data comprises first input data and second input data (step S106); acquiring a target gene prediction model, wherein the target gene prediction model comprises a first network, a second network, and a third network, and an output of the first network and the second network is an input of the third network (step S108); and respectively inputting the first input data and the second input data into the first network and the second network to obtain a gene prediction result outputted by the third network and corresponding to said subject (step S110).

The invention provides an analysis method and system for virus metagenome sequencing data, and relates to the field of biological information.The method comprises the steps that quality filtering is conducted on original sequencing data, and filtered data is obtained; according to the filtered data, a sequence is assembled through a De Bruijn graph and an overlapping layout, and a virus metagenome sketch is constructed; comparing the virus metagenome sketch with a known virus database to identify known virus types; and identifying a new virus by combining the unknown sequence which is not compared with the virus sequence through clustering analysis so as to realize the sequence comparison of the virus metagene. By improving data quality and accuracy, enhancing virus identification and classification capability, improving variation detection and function annotation efficiency and optimizing gene prediction and community structure analysis, analysis of virus metagenome sequencing data is realized.

The application relates to the technical field of pathogenic gene prediction, and provides a pathogenic gene prediction method based on whole-transcriptome correlation research and related equipment. The method provided by the application comprises the following steps: calculating a splicing percentage matrix of each gene according to an RNA-seq sample; obtaining a genotype matrix of each gene and a genotype matrix of each splicing factor; constructing a first prediction model based on the genotype matrix of all splicing factors and all splicing percentage matrices, and obtaining a predicted splicing percentage matrix corresponding to all splicing factors by using the first prediction model; constructing a second prediction model based on the predicted splicing percentage matrix and the genotype matrix of all genes, and obtaining a final predicted splicing percentage matrix of all genes by using the second prediction model; and performing pathogenicity analysis according to the final predicted splicing percentage matrix of all genes to obtain a gene pathogenicity prediction result. The method provided by the application can improve the accuracy of pathogenic gene prediction.

The application discloses a method for eRNA transcription identification, regulation target prediction and function annotation based on high-throughput transcriptome sequencing data, and is characterized in that the method comprises the following steps: identifying part of non-coding RNA in which a transcription start site is located in an enhancer region as eRNA; obtaining eRNA-related protein coding genes which simultaneously exist in an eRNA-protein coding gene co-expression network and an eRNA-centered regulation network, constructing an eRNA-protein coding gene relationship network, and extracting protein coding genes which are directly connected or closely connected to the eRNA, so as to predict potential regulation targets of the eRNA; and finally, performing function enrichment analysis on the potential regulation targets of the eRNA, so as to obtain the results of eRNA function annotation, and the method has the advantages of wider application range, and can be applied to all eRNAs and more accurately obtain the action forms between the eRNA and the protein coding gene.

The invention relates to the technical field of biology, in particular to a cotton fiber initial key regulatory gene prediction method which comprises the following steps: collecting cotton ovule samples at different development time points for in-situ capture and transcription library construction and sequencing to obtain spatial transcription matrixes of different samples; performing data dimension reduction and clustering processing on the spatial transcription matrixes of different samples to obtain spatial slice information and UMAP dimension reduction images; according to the spatial slice information and the UMAP dimensionality reduction image, marking fiber-related and non-fiber-related cell groups, and extracting an SCT expression matrix; carrying out random stratified sampling based on the extracted SCT expression matrix, dividing the SCT expression matrix into a training set and a test set, and then training data of the training set by adopting a random forest algorithm to obtain a prediction model; and based on the prediction model and in combination with co-expression network analysis, obtaining an initial key regulation gene of the cotton fiber. By using the method, the initial key regulation gene of the cotton fiber can be quickly and accurately obtained.

The invention discloses a method, a system, equipment, a medium and a program for predicting a disulfide death regulatory gene based on large-scale expression map correlation, and belongs to the technical field of disulfide death regulatory gene prediction. An expression residual error of a transcriptome gene expression matrix formed by converting human large-scale gene expression map data is calculated by using a PEER method, and the expression residual error is used for replacing a gene expression quantity, so that a whole genome gene expression residual error matrix is obtained. Then calculating expression correlation between each gene and a known disulfide death regulation factor; and taking the correlation of the disulfide death regulatory factors as a weight factor of weighted average correlation, and calculating the weighted average correlation of the whole genome gene and the known disulfide death regulatory factors to obtain the disulfide death characteristics of the whole genome gene. And the first 1% of the gene with the highest disulfide death characteristic is used as a potential disulfide death regulating gene. The method can predict the dithiodeath tendency of various cancer types and the difference of dithiodeath characteristics in different tissues and organs.

The invention relates to the field of bioinformatics, and discloses a space transcriptome gene expression prediction method and system, a terminal and a storage medium, and the method comprises the steps: segmenting a histological image into small blocks according to capture sites, obtaining the image, gene expression and position coordinates of each small block, and respectively learning gene features and image features, designing a loss function to capture potential correlation between the two modals, completing alignment between the two modals, and performing weighted aggregation on gene expressions of a plurality of gene features most similar to the image features to obtain corresponding predicted gene expressions. According to the method, the potential relationship between the histological image and the gene expression is captured, and the gene expression is predicted through the histological image by utilizing the potential relationship, so that the gene prediction accuracy is remarkably improved.

The application discloses an adaptive multi-channel graph neural network disease gene prediction model and a prediction method, and the method comprises the following steps: S1, through unified arrangement, standardized mapping and quality control of PPI network, disease seed genes and GWAS prior information, a candidate disease gene prediction input system for a low seed scene is established; S2, according to the candidate disease gene prediction input system for the low seed scene, a disease network representation and feature system for the low seed scene is constructed; S3, an adaptive multi-channel graph neural network model AdaMC-GNN for the low seed scene is constructed, and model parameters are updated and the model is trained; and S4, the disease network representation and feature of the low seed scene are input into the trained adaptive multi-channel graph neural network model AdaMC-GNN for the low seed scene, priority ranking of the candidate disease is obtained, and through disease level gating mechanism, local network propagation, cross-disease migration and GWAS prior evidence are fused, and whole genome ranking of sleep-related chronic disease candidate pathogenic genes is realized.

The application relates to the technical field of gene analysis, and provides an Alzheimer disease gene prediction method and equipment based on alternative splicing, which comprises the following steps: performing difference analysis on the expression amount of all genes and the expression amount of transcripts to obtain expression amount difference characteristics, expression amount difference characteristics and expression proportion difference characteristics of the genes, and performing difference analysis on alternative splicing events of all sample gene signals to obtain alternative splicing difference characteristics of each gene; splicing the expression amount difference characteristics, the transcript expression amount difference characteristics, the expression proportion difference characteristics and the alternative splicing difference characteristics of each gene to obtain final characteristics of each gene; constructing a function correlation network according to the final characteristics of all genes; and performing gene disease prediction on the function correlation network to obtain the probability that each gene is related to Alzheimer disease. The method can improve the accuracy and reliability of Alzheimer disease gene prediction.

The invention discloses a gene prediction and functional peptide recognition method based on multi-feature fusion, and relates to a gene prediction and functional peptide recognition method. The invention aims to solve the problems of low efficiency and high cost caused by incapability of automatically extracting features in a traditional prediction method; most models depend on local sequence features and cannot fully capture potential biological activity signals of sequences, so that information is not fully considered. The system comprises a feature extraction module of a gene prediction part, a multi-feature fusion module, a convolutional neural network module, a Transform encoder module, a classification prediction module and a protein translation and storage module. The functional peptide recognition part comprises a peptide sequence representation module, a Bert module, a CNN module, a Bi-LSTM module and a feature fusion and classification module; constructing a data set; and evaluating the model. The invention belongs to the technical field of bioinformatics.

This invention relates to a biomarker for predicting treatment response to immunotherapy and a gene prediction model utilizing the same, wherein the gene prediction model utilizing the biomarker is based on the expression patterns of key genes that reveal the characteristics of a patient's tumor-microenvironment, thereby predicting treatment response, thus avoiding unnecessary surgery and determining the optimal treatment regimen.

The invention discloses a hereditary disease candidate gene sorting method and device based on heterogeneous graph embedding, and relates to the field of biological information. The method comprises the following steps: constructing a phenotype-gene heterogeneous network, and determining an edge weight in the heterogeneous network according to an association frequency of genes and phenotypes in a clinical medical record; capturing heterogeneous neighbor nodes based on meta-path weighted random walk according to the types of the neighbor nodes, and obtaining node embedding in the heterogeneous network; and according to the node embedding corresponding to the phenotypic node and the node embedding corresponding to the gene node, evaluating the possibility that the candidate gene is a pathogenic gene, and according to an evaluation result, sorting the priority of the candidate gene. Through the method, heterogeneous information in a biological network is effectively captured, the priority ranking accuracy of candidate genes is improved, the historical medical record data is introduced to generate the edge weight, and the expression ability of a heterogeneous graph and the credibility of a virulence gene prediction result are improved.

The invention discloses a drug-resistant gene and resistance category prediction method based on sequence characteristics and a protein language model. The method comprises the following steps: 1, constructing an amino acid data set and a drug-resistant gene data set; 2, calculating mutual information, conditional mutual information, Fourier power spectrum characteristics, dipeptide composition, interval amino acid pair composition, an ESM2 matrix, mutual information, interval amino acid pair composition, a triple matrix, a tagged ESM2 matrix and an untagged ESM2 matrix; 3, constructing a drug-resistant gene prediction network to obtain a drug-resistant gene prediction score; and 4, constructing a drug-resistant gene resistance category prediction network to obtain a drug-resistant gene resistance category prediction score. According to the method, efficient and accurate prediction of the drug-resistant gene and the resistance category thereof can be realized, and meanwhile, the practicability and the reliability of the method are verified when the method is applied to real genome data.

The invention discloses a prognosis model for predicting cervical cancer based on autophagy-related genes and a construction method of the prognosis model, and belongs to the technical field of biomedicine. The model contains four characteristic genes related to prognosis of cervical cancer: BCL2, SPNS1, TM9SF1 and TP73, and the characteristic genes can become biological markers related to cervical cancer; the calculation formula of the prognosis model is as follows: risk score = (-0.411 * BCL2 gene expression quantity) + (0.753 * SPNS1 gene expression quantity) + (0.669 * TM9SF1 gene expression quantity) + (-0.398 * TP73 gene expression quantity). The prognosis model provided by the invention can evaluate the prognosis of the cervical cancer patient, improve the prognosis prediction capability of the cervical cancer patient, effectively identify the high-risk patient, assist in predicting the curative effect of immunotherapy, detect and intervene the high-risk patient earlier in clinic, improve the survival rate and life quality of the patient, and improve the clinical application prospect. A reference is provided for individualized diagnosis and treatment of cervical cancer; and tests and external verification prove that the model is stable and effective.

The invention provides a method for cloning a broad-spectrum resistance gene ETD1 of rice blast through map-based cloning. The method comprises the following steps: phenotypic screening and population construction: extracting DNA from screened individuals; constructing a DNA pool; performing high-throughput sequencing; controlling data quality; performing comparison and variation detection; analyzing variation sites; performing correlation analysis; and predicting candidate genes. The broad-spectrum resistance gene ETD1 cloned by the method has a nucleotide sequence as shown in SEQ ID NO: 1, and / or a cDNA sequence of the gene is as shown in SEQ ID NO: 2, and / or a coding protein of the ETD1 gene has an amino acid sequence as shown in SEQ ID NO: 3, and the gene belongs to a super-efficient allele of OsCNGC13, obtains stronger calcium ion transport capacity, and can be used for preparing a calcium ion transport agent. The function of remarkably accelerating cell calcium ion influx is realized. Therefore, the rice resistance can be improved by normal expression or overexpression of the gene in a gene knockout type plant, and the rice blast resistance can be positively regulated and controlled.

The invention discloses a pathogenic gene prediction method and device based on phenotypic fingerprints, equipment and a medium. The method is executed by a computer, systematic integration and quantification are carried out on associated information between genes and phenotypes of multiple dimensions, phenotype fingerprints with specific genes are constructed on the group level, and complex effects of the genes on different phenotype dimensions can be captured more comprehensively; a multi-phenotype score value taking genes as the center is calculated through gene phenotype fingerprints, that is, multi-dimensional clinical phenotype information of a target object is converted into quantitative scores taking the genes as the center on the object level, and two types of key output of pathogenic variation carrying risk assessment and candidate gene priority ranking are achieved through observation phenotypes of the target object; and the integrating degree of each candidate gene and the actual phenotype of the target object can be objectively and efficiently evaluated. According to the method, phenotype fingerprints are introduced, a multi-phenotype scoring mechanism is combined, the efficiency and objectivity of complex disease pathogenic gene recognition are remarkably improved, and the method has important clinical application value.

The present application provides a forest functional gene prediction and regulation analysis method and system based on a generative large model, belonging to the technical field of bioinformatics. The present application solves the problem that existing gene large models mostly use unconditional or weak conditional mask language modeling methods, do not introduce forest breeding targets as explicit conditional variables into the model training process, and are difficult to realize breeding target-oriented functional gene prediction. The method includes: input collection; feature encoding and vector condition construction; conditional generative model input; construction of functional gene counterfactual regulation latent space; functional gene prediction and regulation direction inference; regulation path generation; target shape constraint judgment; potential space functional gene prediction and regulation direction judgment. The system includes a data and condition input layer, a conditional generative pre-training and encoding layer, a core generative large model layer, a counterfactual regulation and generative inference layer, a result and decision support layer, and a model inference log and instability evaluation module.

The application relates to the technical field of genome selection, and provides a multi-omics genome selection method and application thereof in livestock and poultry breeding, which comprises the following steps: obtaining reference population data and target population data and carrying out pretreatment; training an optimal linear unbiased prediction model and an elastic network model by using the reference population data; inputting cis-single nucleotide polymorphism site genotype data of the target population into the trained gene expression prediction model to obtain predicted gene expression of each individual in the target population; estimating the cis-heritability of each gene based on the reference population data, and screening gene prediction expression data greater than a cis-heritability threshold; integrating the screened gene prediction expression data and genome data to construct a multi-omics genome selection model, and obtaining a genome breeding value of each individual based on the multi-omics genome selection model. The application can adapt to genetic regulation structure differences of different genes and obtain high-quality prediction results.

The invention belongs to the field of gene prediction, and discloses a livestock and poultry breeding value prediction method based on model evaluation and a related device.The method comprises the steps that firstly, genome historical data is preprocessed to form a training set; adopting parallel cross validation to synchronously train a plurality of statistical basic models, and outputting prediction accuracy indexes of each model under different characters; then, combined with economic weights of breeding target traits, comprehensive selection indexes of all the models for specific samples are calculated; and finally, screening the model with the highest index as an optimal prediction model to estimate a breeding value. According to the method, data feature changes are responded through comprehensive selection indexes, and it is ensured that the model is adaptively optimized under the condition of small groups or complex characters. And finally, the precision stability and the practical value of breeding value prediction in livestock breeding are remarkably improved.

The invention discloses a plant breeding method and device based on a two-channel convolutional neural network. The method comprises the following steps: determining a target plant, a plurality of specified compounds in the target plant and a plurality of SNP sites in the specified compounds; screening out a plurality of first tag SNP sites for covering the whole genome from the plurality of SNP sites, and determining each first tag SNP site as a general feature of a general information channel input into each gene prediction model; screening out first candidate SNP loci corresponding to different specified compounds from the plurality of SNP loci, and determining the first candidate SNP loci corresponding to the different specified compounds as prior characteristics of prior information channels input into each gene prediction model; and based on the general characteristics, each prior characteristic and each gene prediction model, predicting the content corresponding to each specified compound, and performing breeding feasibility analysis on the target plant according to the predicted content.

The invention relates to a pathogenic fungus generic genome analysis method, device and equipment and a readable storage medium. The method comprises the following steps: obtaining to-be-analyzed sequencing genome data containing a plurality of contig sequences, removing the contig sequences of human and bacteria in the sequencing genome data to obtain cleaned sequencing genome data, performing gene prediction on the cleaned sequencing genome data to obtain a gff protein sequence file corresponding to the cleaned sequencing genome data, and analyzing the gff protein sequence file according to the gff protein sequence file. And finally, performing generic genome clustering analysis on the gff protein sequence file to obtain a clustering analysis result of sequencing genome data. According to the method, the to-be-analyzed sequencing genome is subjected to cleaning of human and bacterial sequences, only fungal gene sequences are reserved, the cleaned data are further predicted, so that the corresponding gff protein sequence file is obtained, clustering analysis is executed on the basis of the gff protein sequence file, and the accuracy and integrity of analysis are improved.

The invention relates to the technical field of artificial intelligence and deep learning, in particular to a tomato salt tolerance prediction method and system based on deep learning, and the method specifically comprises the following steps: obtaining a tomato salt tolerance genome, and inputting the tomato salt tolerance genome into the tomato salt tolerance prediction system based on deep learning for detection; and calculating the probability of related tomato salt-tolerant genes in the input tomato salt-tolerant genome through a salt-tolerant small sample gene recombination module, an epigenetic gene multi-granularity mining module, an isomeric salt-tolerant gene feature integration module, a salt-tolerant feature point fusion module and a tomato salt-tolerant gene prediction module in sequence. The prediction precision and generalization ability of the salt-tolerant gene under the complex gene background are improved, and an intelligent prediction method is provided for tomato salt-tolerant variety breeding.