84 results about "Gene expression matrix" patented technology

A gene regulation inference method based on causal diagram embedding and conditional cellular network relates to the technical field of gene regulation network prediction, and comprises the following steps: 1, obtaining a gene expression matrix from scRNA-seq, and generating a causal diagram; 2, generating a local feature embedding matrix of a gene by using a graph neural network model based on a causal graph and a known gene regulation and control network graph; 3, constructing a CCSN based on scRNA-seq, converting the CCSN into gene connectivity vectors, and integrating the gene connectivity vectors of all cells to form a CNDM as a global feature matrix; 4, integrating the local feature embedding matrix and the global feature matrix to form a final gene feature matrix; 5, screening a core gene from the gene feature matrix, and constructing a regulation edge matrix; and 6, inputting the regulatory edge matrix into a gene link prediction module to realize inference of the gene regulatory network. By applying the method, the causal relationship and the cell specificity can be integrated, the core gene is effectively screened, the feature fusion is optimized, and the accuracy and the biological interpretation of network inference are improved.

The invention discloses a spatial transcriptome data spatial domain identification method based on multi-space self-supervised contrast learning, and the method comprises the steps: carrying out the modeling to generate a spatial neighborhood graph, keeping the graph structure unchanged, disorganizing node features, and carrying out the data enhancement, thereby obtaining an enhanced graph; constructing an encoder based on a graph neural network, extracting spatial transcriptome data fused with spatial information and gene information to obtain potential embedding, and sending the potential embedding into a multi-space generator to generate multiple groups of rich graph feature representations; fusing graph feature representation and potential embedding to obtain refined representation, reconstructing a gene expression matrix through a decoder, and adding contrast learning loss and reconstruction loss as a total objective function; and updating network parameters by adopting an Adam optimizer according to the obtained total objective function to complete spatial transcriptome spatial domain identification. Spatial transcriptome data are fully mined from global and local angles, and accurate spatial domain identification is realized.

The invention discloses a spatial transcriptome data analysis method based on artificial intelligence, and belongs to the technical field of spatial transcriptomics data analysis. Firstly, self-adaptive normalization and hypervariant gene screening preprocessing are carried out on original gene expression data; then constructing a hierarchical map integrating spatial proximity and transcription similarity, and ensuring the connectivity and robustness of the map through a dynamic radius pruning and neighborhood inheritance strategy; dividing positive and negative sample sets based on the atlas, and inputting a type modulation contrast graph auto-encoder for training; and finally, spatial domain identification and downstream function analysis are completed based on the low-dimensional potential representation or reconstructed gene expression matrix output by the model. The method effectively improves the accuracy and stability of spatial domain recognition, adapts to multi-technology-source data, enhances the biological interpretability of model output, and can be widely applied to biomedical scenes such as tumor microenvironment analysis and organ development research.

The invention discloses a cell interaction identification method based on cell space transcriptome data, which comprises the following steps: constructing cell pairs according to cell space proximity, and calculating an interaction signal matrix and space information of each pair of cells by combining a ligand-receptor database; then generating cell pair embedding representation by using a graph neural network, calculating the similarity between cell pairs, and calculating the similarity between cells based on a gene expression matrix; updating the similarity matrix through iteration until convergence to obtain a final similarity matrix between cells and between cell pairs; and clustering the similarity matrix, and constructing a cell type and cell pair type model, thereby realizing accurate cell interaction identification. According to the method, space and expression information can be fully utilized, inter-cell heterogeneity and context specificity interaction can be captured, the analysis precision and biological authenticity of a cell communication network are improved, and an effective tool is provided for research on tissue development, disease mechanisms, immune response and the like.

This invention belongs to the field of bioinformatics and relates to a single-cell trajectory inference method based on adaptive feature selection. First, an initial gene expression matrix is ​​obtained through data preprocessing and screening for highly variable genes. Second, a two-dimensional evaluation strategy is employed to calculate the scores of highly variable genes with gene expression variability and the trajectory importance score related to differentiation trajectories. Then, a dynamic weight fusion mechanism is introduced, adaptively adjusting the fusion weights of the two scores based on performance feedback, and highlighting key genes through nonlinear enhancement. Next, an intelligent inflection point detection algorithm adaptively determines the optimal number of features. Finally, trajectory inference is performed based on a variational autoencoder model reconstructed from feature subsets, and a performance-driven feature selection closed loop is formed through multiple rounds of iterative optimization. This invention achieves high-precision, adaptive single-cell trajectory inference, solving the technical problems of single feature selection and fixed weights in traditional methods.

The invention relates to a structural network-genetic map biological network model for predicting ischemic stroke and a construction method thereof, and the method comprises the steps: extracting and calculating seven multi-scale morphological features and pairwise Pearson correlation coefficients among the features from T1 weighted imaging data and diffusion tensor imaging data; constructing a 308 * 308 morphological similarity network matrix and a brain network module for identifying ischemic stroke neural dysfunction; 1782 sampling points are extracted from the Airy human brain map, and each sampling point comprises expression data of 10185 genes; the method comprises the following steps: mapping space coordinates of AHBA sampling points to a cortex package of a Desikan-Killiany map, carrying out normalization processing to output 308 * 10185 brain region gene-by-gene expression matrixes, and constructing a structural network-gene map biological network model for predicting ischemic stroke by adopting a partial least square regression method and a bootstrap method. Compared with the prior art, the model determines the specific molecular mechanism related to the phenotypic structure change of ischemic stroke injury, and the stroke occurrence probability is predicted according to the specific molecular mechanism.

The invention belongs to the technical field of biomedical engineering, and discloses a gene regulatory network optimization method based on a diffusion model, which comprises the following steps: acquiring gene data of cells under a steady state condition, and constructing a gene expression matrix according to the gene data; injecting Gaussian noise into the gene expression matrix based on a diffusion model method to generate a series of noisy data sequences; performing noise estimation and structure estimation on the noisy data sequence by a noise estimator and a structure estimator based on a gene regulation and control network, and performing reverse denoising processing according to the noise estimation and the structure estimation to obtain gene structure estimation after reverse denoising; performing structure optimization on the gene structure estimation after reverse denoising by adopting an acyclic constraint function and a regularization substitution method; and outputting the optimized gene structure estimation. According to the method, the regulation and control relation between the genes is accurately recognized from high-dimensional gene expression data, and the modeling precision of the regulation and control relation between the genes is improved.

The invention relates to the technical field of biomedical detection and bioinformatics, and discloses a detection method and system for social anxiety disorder risk assessment, and the method comprises the steps: obtaining transcriptome data of a peripheral blood sample of a to-be-detected object, and carrying out preprocessing and normalization to obtain a standardized gene expression matrix; extracting minimum gene set expression data containing 10 genes such as HSF5 and FADS2, and performing Z-score standardization processing by using the solidified model parameters; calling a preset weight coefficient and an intercept item to perform linear weighting and probability conversion calculation on the standardized data to obtain a disease prediction probability of the subject; and carrying out risk layering according to the optimal critical value and generating an auxiliary diagnosis report. According to the method, stable features are screened through a machine learning algorithm, the scoring model is constructed, subjectivity of traditional clinical diagnosis is overcome, and objective, quantitative and automatic evaluation of social anxiety disorder risks is achieved.

The invention discloses a gene regulatory network prediction method and system based on explicit correlation modeling, and the method comprises the steps: obtaining a gene expression matrix of single-cell RNA sequencing data and an adjacent matrix of a prior regulatory graph constructed based on prior knowledge, and inputting the matrixes into a graph neural network model; wherein the graph neural network model is configured to perform explicit modeling on a link in the prior regulation and control graph through an intra-layer message passing space and an inter-layer message passing space so as to obtain link representation; predicting whether a regulation relation exists between the gene pairs through a classifier on the basis of link characterization so as to deduce a gene regulation network; wherein the architecture of the graph neural network model is adaptively determined through an automatic architecture search algorithm according to input data. According to the framework provided by the scheme, modeling link representation is displayed in the message passing process, the regulation and control relation of the gene pair is inferred by MLP based on link embedding, utilization and organization of complex connection information of the prior regulation and control graph are enhanced from the source, and the inference accuracy is effectively improved.

The present application relates to the technical field of bioinformatics and artificial intelligence, in particular to a virtual cell construction method and system, the method comprising: taking single cell gene expression matrix and perturbation condition data as input data; constructing an encoding network based on a structural causal model to obtain latent representation, and constructing a perturbation variable according to the perturbation condition data, modeling the latent representation and the perturbation variable to obtain decoupled latent representation; constructing a continuous time evolution path from an initial distribution to a target distribution based on a flow matching model, and determining state changes according to the decoupled latent representation; numerically solving the continuous time evolution path to output virtual cell expression data. The present application is used to solve the problems of causal aliasing, insufficient distribution out-of-distribution generalization ability, unstable generation process and difficulty in counterfactual reasoning in the existing single cell perturbation prediction method.

The application discloses a kind of screening methods and application of pivot gene related to sheep muscle fatty acid content, to solve the technical problems that local sheep breed sample quantity is limited, traditional single gene analysis method is difficult to analyze fatty acid metabolism regulation from network level.This application carries out transcriptome sequencing to multiple months of muscle tissue of Gangba sheep, constructs gene expression matrix, using weighted gene co-expression network analysis (WGCNA) Combined with module characteristic gene and fatty acid phenotype correlation screening strategy, the pivot gene significantly positively correlated with muscle fatty acid content is obtained.The screening method can construct a robust co-expression network under limited sample size, systematically identify the functional module and core gene related to the content of fatty acids such as linoleic acid, and reveal the dynamics of fatty acid metabolism at different ages, and the method can be extended to other plateau livestock;The screened pivot gene can be used as a molecular breeding marker for early selection of Gangba sheep, and the breeding cycle is shortened.

The invention discloses a cell communication analysis method and system based on single cell transcriptome data. The cell communication analysis method based on the single cell transcriptome data comprises the following steps: data input, standardized screening, stratified analysis and visual output. By means of CellPhoneDB and CellChat software, a cell-cell communication network is established by integrating gene expression with a signal ligand and a receptor according to a single-cell gene expression quantity matrix, and a visual analysis result is provided.

The invention discloses a gene regulation and control network prediction method based on line graph attention and Transform. The method comprises the following steps: firstly, acquiring a gene expression matrix and a gene regulation prior network, and preprocessing the gene expression matrix; then, selecting gene nodes from the gene regulation prior network, and constructing a closed subgraph by taking a target gene node pair as a center; converting the closed sub-graph into a line graph, and constructing a line graph node feature matrix; finally, a gene regulation and control network prediction model is constructed, and the model comprises a graph attention neural network, a Tannformer encoder and a multi-layer perceptron; the graph attention neural network extracts gene local spatial features by using the line graph and the line graph node feature matrix; the Tannform encoder extracts global spatial features of the gene by using the gene expression matrix; and splicing the gene local spatial features and the gene global spatial features, and predicting regulation edges of the spliced features through a multi-layer perceptron. According to the method, the key regulation relation can be distinguished more effectively in the gene regulation network with high noise and sparse structure.

This invention relates to a method for assessing the quality of single-cell sequencing data, which addresses the current difficulty in evaluating the differences in data quality after applying different single-cell sequencing data imputation algorithms without the participation of real samples. The method includes the following steps: First, two single-cell sequencing data imputation algorithms are prepared. Then, a synthesis matrix based on the statistical characteristics of real data is created and normalized preprocessed. The normalized gene expression matrix is ​​input into the two imputation algorithms to be evaluated, and the output feature vectors are extracted to set an optimization function. The gene expression matrix is ​​optimized using the optimization function, and then the optimized matrix is ​​denormalized to obtain the imputed gene expression profile. Finally, the obtained gene expression profile is input into the two algorithms to be evaluated to obtain two sets of predicted feature vectors. The data quality difference value can be calculated using these feature vectors. This invention can accurately assess the data quality difference between two data imputation algorithms without the participation of real samples.

The invention discloses a spatial transcriptome data feature extraction method and system based on a hierarchical variational auto-encoder, and the method comprises the steps: carrying out the preprocessing of a to-be-processed gene expression matrix, obtaining the preprocessed data, and constructing an adjacent matrix of a sparse graph structure based on the preprocessed data; inputting the preprocessed data into a hierarchical variational auto-encoder model for processing, and outputting comprehensive potential representation; and carrying out downstream analysis by utilizing the comprehensive potential representation, wherein the downstream analysis comprises spatial domain identification, batch effect correction, trajectory analysis and differential gene expression analysis. According to the method, the feature extraction efficiency of the spatial transcriptomics data is remarkably improved.

The invention relates to the technical field of cell recognition, and discloses a rare cell population recognition method, device and equipment and a storage medium, and the method comprises the steps: obtaining an original gene expression matrix, preprocessing the original gene expression matrix to obtain a target gene expression matrix, and constructing a cell leaf node graph and a K neighbor graph; integrating the cell leaf node graph and the K neighbor graph to obtain an enriched cell leaf node graph; performing node embedding on the enriched cell leaf node graph to map all target cells in the target gene expression matrix to a target dimension embedding space to obtain a cell embedding vector set; and performing clustering analysis and neighbor error analysis on all target cells in the cell embedding vector set, and identifying a rare cell population. According to the scheme, the limitation of single-dimension information is overcome, the complex relationship between cells can be more comprehensively and deeply described from two complementary perspectives of a functional mechanism and a phenotype state, and the recognition accuracy of a rare cell population is improved.

The invention provides a bladder cancer subtype classification system and molecular typing method based on machine learning, and the molecular typing method comprises the steps: firstly obtaining transcriptome data and survival information of bladder cancer tissue of a patient, extracting data from a preset amino acid metabolism related gene set, and constructing a gene expression matrix; then, clustering the patients by adopting an unsupervised clustering algorithm, and determining at least two types of amino acid metabolism molecule subtypes in combination with a stability index; thirdly, carrying out survival difference analysis on different subtypes, screening out differential expression genes related to survival outcomes, constructing a survival prediction model based on the differential expression genes, and calculating amino acid metabolism scores of the patients; finally, the patients are grouped according to the scores, and molecular typing based on the amino acid metabolism characteristics is completed. According to the invention, stable and accurate typing of the bladder cancer patient is realized.

The invention discloses an inference method and device of a gene regulation network, equipment and a storage medium, relates to the technical field of bioinformatics, solves an intercellular regulation relation matrix through a matrix decomposition framework provided by a bilateral self-characterization model, and can provide more accurate causal relation inference for intercellular regulation. The method comprises the following steps: acquiring a first gene expression matrix and a second gene expression matrix; taking the first gene expression matrix as input, performing regulation relation prediction by adopting different gene regulation inference algorithms, and constructing a global gene regulation adjacency matrix; embedding the global gene regulation adjacency matrix and the second gene expression matrix into a bilateral self-characterization model, and carrying out first solving calculation through the bilateral self-characterization model to obtain an intercellular regulation relation matrix; and on the basis of a set cell type, carrying out second solving calculation according to the second gene expression matrix and the intercellular regulation relation matrix to obtain a gene regulation network of the set cell type.

The application discloses a method for analyzing B lymphocyte BCR characteristics based on single-cell multi-omics sequencing. The method collects samples of patients in different disease states for single-cell sequencing, constructs a single-cell gene expression matrix based on single-cell transcriptome sequencing data and carries out cell type annotation, assembles BCR sequences based on single-cell immunome sequencing data and identifies BCR chain composition genes, then evaluates and identifies the stable BCR expression rate of each cell subpopulation, evaluates the clonal state of each cell subpopulation in different disease states, analyzes the BCR assembly and single-gene use preference of each sample in different disease states, and the BCR assembly and V-J gene pair use preference. The application has important significance for the mechanism analysis of specific viral infection hosts and the research and development of specific vaccines and drugs.

The invention provides a space transcriptome cell type identification and annotation method based on dimension reduction and downsampling, and relates to the technical field of biological information analysis. Comprising the following steps: S101, providing a spatial transcriptome gene expression matrix and a single cell transcriptome gene expression matrix annotated with cell types; the cell type comprises two levels, the first level is a cell large class, and the second level is a cell subtype; s102, splitting the single cell transcriptome gene expression matrix according to cell subtypes, clustering cells of the same cell subtype, and generating a meta-cell gene expression matrix; s103, identifying the cell category of each spatial site in the spatial transcriptome marker gene expression matrix; and S104, identifying the cell subtype of each spatial site in the spatial transcriptome marker gene expression matrix under each cell large class one by one. According to the technical scheme, the calculation amount in the analysis process is greatly reduced, the analysis efficiency is improved, and the accuracy and stability of annotation are improved.

This invention discloses a single-cell transcriptome data processing method based on a Siamese network autoencoder, comprising: receiving single-cell gene expression matrix data from multiple experimental batches and performing quality control and standardization; constructing positive and negative sample pairs based on cell biological type annotation; constructing a Siamese network autoencoder model, which includes a shared encoder, a decoder, and a contrastive learning module, wherein the shared encoder contains two encoder branches with identical structures and shared weights; performing end-to-end training of the Siamese network autoencoder model using a contrastive loss function and a reconstruction loss function based on InfoNCE; and using the trained shared encoder to encode the cells to be processed to obtain a low-dimensional biological feature representation after removing batch effects. The single-cell transcriptome data processing method based on a Siamese network autoencoder provided by this invention effectively removes batch effects, preserves true biological differences, and improves the quality of data integration.

The invention belongs to the field of bioinformatics, and relates to a high-precision elastic network transcription factor targeting relationship prediction method. The method comprises the following steps: firstly, acquiring single cell transcriptome sequencing data, and extracting a gene expression matrix and potential transcription factor information; secondly, constructing a high-resolution latent time grid, and performing fine-grained division on a single cell cycle; secondly, introducing an elastic network hybrid regularization mechanism, performing sparsification on the gene expression model by using L1 regularization, and meanwhile, retaining core transcription factor characteristics with a collaborative regulation effect by using L2 regularization; then, carrying out iterative optimization based on an RNA kinetic equation, and calculating a regulation weight of a transcription factor on a target gene and a cytodynamic rate; and finally, outputting a high-confidence-coefficient gene regulatory network atlas. According to the method, high-precision, high-robustness and anti-noise targeting relation prediction is realized, and an important calculation and analysis tool is provided for revealing a gene regulation and control mechanism of a cell development bottom layer and accurately searching key disease targets.

The application discloses a biomarker mining model training method and device and related equipment, comprising: providing a number of biological sample corresponding transcriptome original data and sample phenotype category label, obtaining a gene expression matrix from the transcriptome original data, processing the matrix to obtain a high-dimensional gene expression feature vector, inputting the high-dimensional gene expression feature vector corresponding to each biological sample into a biomarker mining model, the biomarker mining model obtains the confidence value of each sample phenotype category based on the high-dimensional gene expression feature vector, and predicts the sample phenotype category based on the confidence value. The application extracts features from transcriptome data, uses the feature vector and the corresponding sample phenotype category label as training data for training, sets a confidence calculation in the trained model, realizes quantitative evaluation of the importance of gene features, determines the marginal influence of single gene feature change on the prediction result, and thus determines the biomarker.

This invention relates to the fields of bioinformatics and computational biology, specifically to a method and system for integrating single-cell transcriptome data based on explicit decoupling and optimal transport. First, multiple batches of single-cell gene expression matrices are preprocessed. Then, a deep residual autoencoder maps the input data to a structured latent representation, explicitly segmenting it into biological feature components and batch noise components. These components are then completely separated through joint optimization using multiple loss functions. High-quality nearest neighbor pairs are selected as anchors based on a clean biological feature space. A generative adversarial network is constructed using these anchors as training samples. An optimal transport regularization term is introduced into the generator loss function, and the Wasserstein distance between distributions is minimized using the Sinkhorn algorithm, achieving accurate and geometrically smooth distribution alignment. Finally, the corrected gene expression data or low-dimensional embedding representation is output. This invention achieves efficient integration of data from different batches, platforms, and species.

This application discloses a method, apparatus, electronic device, and readable storage medium for detecting the cellular composition of biological samples, applicable to the field of biomedical technology. The method includes performing single-cell transcriptome sequencing on the biological sample to be tested to obtain single-cell sequencing results; generating a cell gene expression matrix by analyzing the single-cell sequencing results; and determining the cell types contained in the biological sample by performing single-cell bioinformatics analysis on the cell gene expression matrix. This application enables low-cost, high-throughput, accurate, and quantitative one-step detection of the cellular composition of biological samples.

The invention provides a complication prediction method, a complication prediction model training method and electronic equipment. The method comprises the following steps: acquiring free ribonucleic acid cfRNA sequencing data of a to-be-detected sample; obtaining a gene expression matrix according to the cfRNA sequencing data; inputting the gene expression matrix into a pre-trained complication prediction model; performing feature extraction on the gene expression matrix by using a feature extraction module of the complication prediction model to obtain feature data; and predicting the feature data by using a classification module of the complication prediction model to obtain a prediction result corresponding to the sample. According to the method, the prediction precision of the gestational complications can be improved.

The application discloses a kind of based on joint adjacency matrix spatial transcriptome data clustering method, belong to computer science and bioinformatics field.The method constructs a fusion SPOT-SPOT space adjacency matrix, SPOT-GENE expression matrix and GENE-GENE gene co-expression network matrix, to realize the adaptive alignment of multi-modal data in structure.On this basis, by introducing the graph auto-encoder with residual connection and multi-task learning mechanism, joint learning node low-dimensional embedding and model parameters, finally realize the accurate identification of spatial functional domain.The application constructs a complete technical process from multi-source data integration, graph structure modeling, feature learning to spatial domain identification, can accurately analyze the spatial organization mode and functional state of cell in tissue sample, provides a powerful computing tool for developmental biology, tumor microenvironment and other researches.

The invention relates to the technical field of cell classification, in particular to a multi-scale attention mechanism and mask self-coding fused scRNA-seq data clustering analysis model construction method, a clustering analysis method and a related device, and the method comprises the steps: obtaining a plurality of scRNA-seq data sets; and training the initial network model by using the data set, and obtaining an scRNA-seq data clustering analysis model based on the loss function. According to the method, mask perturbation is performed on an original gene expression matrix, data missing and noise conditions are simulated, the de-noising ability of the model and the robustness of potential expression are improved, the complex dependency relationship between the gene and the cell is captured from different levels by means of a multi-scale attention mechanism, the model can more deeply analyze the internal structure of the gene expression data, and the accuracy of the model is improved. High-quality low-dimensional cell representation is provided for a clustering task, a reconstruction matrix is output based on a mask auto-encoder, high-quality low-dimensional representation suitable for a downstream clustering task is generated, and clustering accuracy is improved.

The invention discloses a single-cell gene completion method based on a sparse perception diffusion model, and belongs to the technical field of gene expression completion, and the method comprises the following steps: carrying out forward noise addition diffusion on an original single-cell gene expression profile to obtain a noise sample; constructing a sparse correction resampling diffusion model; and inputting a noise sample into the sparse correction resampling diffusion model, and outputting a complete single-cell gene expression matrix after gene completion through a multi-step reverse denoising process. The complementation normal form provided by the invention can generate originally missing gene entries in an expression profile, perceive and correct sparse distribution deviation, provide consistent and reliable over 30k gene input for a basic model, and improve the robustness of the expression profile. Double constraints of geometric rearrangement and sparse correction are adopted, gene expression integrity and sparse structure authenticity are considered, and high-fidelity reconstruction of extreme deletion expression is realized.

The application discloses a differential gene identification method based on non-parametric test. Gene expression matrices of an experimental group and a control group are obtained. An MMD unbiased empirical estimation between gene expression level sequences of genes in the experimental group and gene expression level sequences of the genes in the control group is calculated as an original MMD unbiased empirical estimation of the genes. Gene expression levels in the gene expression level sequences of the genes in the experimental group and the control group are combined and then randomly shuffled and rearranged, and an MMD unbiased empirical estimation is calculated as a new MMD unbiased empirical estimation. The significance parameter of the genes is calculated, and the differentially expressed genes are determined according to the significance parameter. The method does not depend on specific data distribution assumptions, can more flexibly process data sets with few time points or large gene expression level fluctuations, is suitable for various types of gene expression data, and improves the flexibility and applicability of analysis.