15 results about "Gene interaction network" patented technology

The invention relates to the technical field of biological information, and provides a whole genome selection method, device and equipment of a graph neural network and a storage medium, and the whole genome selection method of the graph neural network comprises the following steps: mapping single nucleotide polymorphism (SNP) to a gene level, and converting the SNP into a gene embedding vector; constructing a gene interaction network based on preset multi-source biological priori knowledge; inputting the target character into a graph neural network model to obtain a predicted value of the target character output by the graph neural network model; wherein the graph neural network model is determined based on a gene embedding vector and a gene interaction network. According to the method, the SNP is mapped to the gene level, and the gene interaction network is combined, so that the prediction result has clear biological significance; and the gene interaction network is constructed based on the preset multi-source biological priori knowledge, so that interaction information between genes can be fully utilized, and the accuracy of target character prediction is improved.

The invention discloses a multi-layer heterogeneous network unicellular organism network inference method based on meta-path enhancement, which mainly comprises a gene regulation knowledge base enhanced multi-layer heterogeneous network construction module for integrating an external gene interaction network and multiple omics data such as scRNA-seq, scATAC-seq, ST and the like; constructing a single-cell multi-omics multilayer heterogeneous network containing cell-cell, cell-gene and gene-gene relationships, and fusing spatial constraints to consider cell positions and tissue structures; and the feature enhancement module based on the meta-path explores complex semantics of the network by designing a multi-hop meta-path mode, designs an adaptive multi-view learning framework and a multi-round enhancement mechanism, and optimizes feature representation by using cell-gene interaction and cross-modal attention fusion. The unicellular biological network can be effectively deduced, the deduction accuracy and biological interpretation are remarkably improved, the method plays an important role in understanding the cell biological process, developing and treating diseases and the like, has good expandability, and can further integrate multi-modal omics data such as proteomics and metabonomics.

The invention is suitable for the technical field of bioinformatics, and provides a gene interaction network analysis system and method based on symbology dynamics. The method comprises the steps of original gene data preprocessing, dynamic gene interaction network construction, network dynamic state symbol coding, symbol sequence feature analysis, analysis strategy dynamic adjustment, key information identification and result output. The system comprises corresponding function modules. According to the method, a symbolic dynamics theory and gene interaction network analysis are fused, a gene network dynamic process is converted into a symbol sequence through an exclusive symbol coding algorithm, network dynamic characteristics are extracted by means of methods such as symbol entropy calculation and symbol pattern recognition, and meanwhile, a dynamic adjustment analysis strategy is introduced; according to the method, a dynamic self-adaptive analysis system is constructed, dynamic changes of gene expression and regulation relationships are accurately described, the recognition accuracy of key interaction relationships, key nodes and key paths of a complex network is improved, and the method has important theoretical value and practical application prospects.

The application belongs to the technical field of picture processing, and particularly relates to a picture generation method based on mutation data, a generation system and a cancer metastasis prediction method. Step one: constructing a pathway image by using the functional similarity of pathways on a gene interaction network; step two: constructing a patient characteristic image; the prediction method further comprises: training a prediction model by using the constructed patient characteristic image, and predicting the metastasis of mutation data by using the trained prediction model. The application aims to solve the problems of lacking high-performance generation of patient characteristic pictures based on single nucleotide variation and the technical problems of cancer metastasis prediction and determination.

A method for simultaneously deducing single-cell pseudo time, velocity field and gene interaction comprises the following steps: preprocessing a single-cell RNA sequencing data set of cell development with multiple branches, clustering different cell types, constructing a piecewise linear model, optimizing the piecewise linear model by adopting an expectation maximization algorithm, and calculating the single-cell pseudo time, velocity field and gene interaction. Deduced pseudo time of each cell, a gene interaction matrix of the dynamic network and single cell velocity field visualization on a pseudo time chart are obtained. According to the method, a segmented ordinary differential equation model is introduced to reconstruct an RNA velocity field and pseudo time of a cell and an interaction network between genes. By iteratively optimizing a connection matrix between genes and pseudo time of the cells, the prediction precision of dynamic change of the cells can be remarkably improved, cell state transition can be accurately deduced, and a key gene regulation and control relationship can be accurately detected.

The invention discloses a multi-gene interaction network prediction method and system based on a graph neural network. The method comprises the following steps: S1, acquiring multi-source biological data; s2, carrying out pretreatment; s3, constructing a gene map; s4, fusing the edge weight matrix and the node feature matrix in the gene map through a dynamic attention mechanism, and outputting a refined feature set; s5, acquiring an optimal hyper-parameter set by using a Bayesian optimization algorithm; s6, based on the gene map and the optimal hyper-parameter set, training the attention enhancement map neural network to obtain a multi-gene interaction network prediction model; and S7, predicting the interaction relationship of the unknown gene pair by using the multi-gene interaction network prediction model, and outputting a result. According to the method, the gene map is constructed through multi-source data fusion, the gene association information is enriched, the multi-head attention map neural network is introduced to automatically learn the interaction weight, the hyper-parameters are dynamically adjusted in combination with Bayesian optimization, and the prediction accuracy and model universality of the multi-gene interaction network are improved.

This invention provides a multi-to-multi drug screening method for CRISPRa / i GPCR libraries based on a three-dimensional spatial hybrid screening model and its applications, belonging to the field of biomedical technology. The method includes the following steps: Step (1): Constructing a screening cell pool; Step (2): Classifying the drugs to be screened; Step (3): Constructing a drug hybrid screening model; Step (4): Grouping drugs according to mutually perpendicular X, Y, and Z planes, with drugs in each plane mixed to form independent pools; Step (5): Processing each pool into a cell pool; Step (6): Detecting and analyzing the changes in sgRNA abundance in each pool; Step (7): Decoding to determine the drug-GPCR interaction pairs. This invention offers higher screening throughput, realizes a multi-target, multi-drug screening mode, reduces costs and time, and enables large-scale research on drug-gene interaction networks, which is of great significance for drug research and development.

The invention discloses a queen bee breeding value evaluation and core population selection method based on multi-omics data, and relates to the technical field of bee genetic breeding and multi-omics data application, and the method comprises the steps: obtaining candidate queen bee genome, intestinal microbiome and host transcriptome data; analyzing data and screening disease-resistant related core microbial markers, immune genes and bacterium-gene interaction network characteristics; by taking the characteristics as input, constructing a machine learning model to calculate a disease-resistant genome-microbiome combined breeding value; combining the breeding value, a core group genetic coefficient and an intestinal flora diversity index to construct a comprehensive selection index; according to the method, accurate evaluation of disease-resistant breeding values is achieved through multi-omics fusion and machine learning, genetic relationship and flora diversity optimization selection are combined, the disease resistance and genetic diversity of the core populations are improved, and a scientific basis is provided for queen bee breeding.

The invention discloses an intelligent autumn pear whole genome association analysis system based on deep learning, and relates to the technical field of gene deep learning, which comprises the following steps: collecting genotype data and phenotype data of autumn pears, obtaining a standardized data set through preprocessing, converting the standardized data set into a matrix form by adopting an image coding method, and carrying out correlation analysis on the whole genome of the autumn pears; extracting spatial features, and generating image data; analyzing the interaction among the multiple-effect gene identification data by adopting a graph convolutional network, obtaining gene interaction characteristics, identifying gene clusters participating in the same biological process, and generating a gene interaction network; and combining the gene interaction network with a deep convolutional neural network, analyzing the relationship between the genotype data and the phenotype data, obtaining deep feature data, identifying the gene locus of the pyrus ussuriensis, and generating a key gene locus analysis scheme. According to the method, the accuracy of genome correlation analysis is effectively improved, and important support is provided for gene research and accurate breeding of pyrus ussuriensis.

The invention relates to the technical field of environmental microbial toxin detection, in particular to a qPCR technology-based algal toxin production gene detection analysis method and system, and the method comprises the following steps: generating an original amplification curve; outputting an effective amplification curve after the PCR inhibition effect is eliminated; obtaining an algae toxin-producing gene database, performing dynamic baseline correction on the effective amplification curve, and outputting a baseline correction curve; calculating a second derivative of the baseline correction curve and positioning a global maximum point; based on the global maximum value point, determining a self-adaptive threshold value, and calculating a Ct value representing the expression level of the target gene; obtaining a toxin expression profile database, and constructing a gene interaction network based on the Ct value; the gene interaction network is analyzed, and the toxin production potential state is judged; and integrating the effective amplification curve, the Ct value, the gene interaction network and the toxin production potential state to generate a detection report. According to the method, the accuracy and the reliability of detecting the toxin-producing genes of the algae are remarkably improved.

The application provides a transcription factor target gene relationship prediction method, system, device and medium, and the method comprises the following steps: obtaining DNA sequences of transcription factors and DNA sequences of target genes of a to-be-predicted species and encoding to obtain encoded sequences; obtaining protein and genetic interaction network data and transcription factor target gene interaction network data of the to-be-predicted species; constructing a graph neural network model based on the encoded sequences, the protein and genetic interaction network data and the transcription factor target gene interaction network data, and performing model training to obtain a trained graph neural network model; and predicting unknown transcription factor target gene interaction relationships of the to-be-predicted species by using the trained graph neural network model. The application can avoid the problems of a large number of missing values of gene expression data and inaccurate binding site prediction; meanwhile, large-scale transcription factor-target gene potential relationship prediction can be realized according to the topological structure of an existing gene regulation network.

A kind of anti-cancer cell sensitivity prediction method, system, equipment and medium of fusion gene network relationship, method includes: the vector of the expression amount of each gene of cell line is as the original gene expression feature of cell line, compressed low-dimensional hidden vector is used as the gene expression feature of cell line by using self-encoder, graph self-encoding is carried out to gene interaction network to obtain gene interaction feature, gene network feature is calculated according to gene expression feature and gene interaction feature, the feature of each atom in drug compound molecule is obtained by establishing drug compound molecular graph, and the predicted anti-cancer cell sensitivity is obtained according to EIGA model;System, equipment and medium are used to realize a kind of anti-cancer cell sensitivity prediction method of fusion gene network relationship;The present application fully considers the interaction relationship between genes and the topological structure in compound molecule by designing new algorithm, realizes the anti-cancer cell sensitivity prediction on cell line and single cell level.

The application belongs to the technical field of biometric recognition, and relates to a key pathogenic factor screening method based on deep embedding and gene network constraint. The method first acquires a gene expression matrix; a gene interaction network corresponding to the gene expression matrix is constructed to generate a sparse adjacency matrix and a sparse mask matrix; a graph variational autoencoder model with gene network constraint is constructed, the input of the model is the gene expression matrix, the sparse mask matrix M is used in the form of element-level multiplication to limit the weight connection of the encoder, the decoder reconstructs the input gene expression matrix according to the latent structure characteristics, and a multi-task prediction module at the output end predicts the infection stage probability distribution and pathogen load through parallel classification branches and regression branches; the constructed model is trained; feature attribution analysis is performed on the input genes according to the task output of the model, the importance scores of the genes are calculated, and a key gene candidate set is generated. The method significantly improves the biological rationality and stability of the screening result.

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.

The invention belongs to the technical field of biological feature recognition, and relates to a key pathogenic factor screening method based on deep embedding and gene network constraint, and the method comprises the steps: firstly obtaining a gene expression matrix; constructing a gene interaction network corresponding to the gene expression matrix, and generating a sparse adjacent matrix and a sparse mask matrix; a graph variational auto-encoder model constrained by a gene network is constructed, the input of the model is a gene expression matrix, an encoder adopts a sparse mask matrix M to limit weight connection in the form of element-level multiplication, and a decoder reconstructs the input gene expression matrix according to potential structural features. A multi-task prediction module at an output end predicts probability distribution and pathogen load of an infection stage through parallel classification branches and regression branches; the constructed model is trained; feature attribution analysis is conducted on input genes according to task output of the model, importance scores of all the genes are calculated, a key gene candidate set is generated, and the biological rationality and stability of screening results are remarkably improved through the method.