58 results about "Cell clustering" patented technology

The invention discloses a spatial transcriptomics cell clustering method based on multi-scale contrast learning. The method comprises the following steps: S1, carrying out data preprocessing; s2, performing graph construction by using the processed data; s3, performing data enhancement; s4, extracting cell gene expression information by using GCN; s5, enriching node information by using a ContraNorm layer; and S6, further learning information by using multi-scale image comparison learning, and performing biological analysis by using final information obtained by learning. According to the method, computer-aided cell type analysis is utilized, a large amount of high-quality data is not needed, only gene expression data and cell space position information data are utilized, which cells belong to the same category can be predicted, and more effective information is provided to help researchers to identify the onset of cancer and the development of diseases.

The invention discloses an scRNA-seq cell clustering method based on multi-scale feature fusion. The scRNA-seq cell clustering method comprises the following steps: 1, acquiring and preprocessing an scRNA-seq data matrix; 2, using a ZINB-based auto-encoder to extract global expression features, and constructing ZINB loss; 3, constructing a cell-cell adjacency matrix based on a Gaussian kernel function, extracting local structure features by using a graph automatic encoder, and constructing graph loss; and 4, fusing the global expression features from the ZINB auto-encoder and the local structure features from the graph auto-encoder by using a double-end attention mechanism. 5, the cells are clustered based on a self-optimization clustering method, and clustering loss is constructed. And 6, performing clustering result analysis by using t-SNE. According to the method, scRNA-seq data can be well processed, multi-scale features are fused, tag prediction is more accurate, and analysis of complex biological characteristics of single cell data is facilitated.

The invention provides a cell specific transcription factor regulatory network analysis method and a visualization platform, and relates to the technical field of bioinformatics, the method comprises the following steps: constructing a gene regulatory network through a GRNBoost2-cisTarget-AUCell-Cell GRN workflow based on a transcription factor in combination with a motif database; screening a direct regulation relationship in combination with the database, and calculating an activity score of a regulator in each cell; based on activity scores and cell type annotation results, grouping the single cell data by using a unified manifold approximation and projection (UMAP) dimensionality reduction method and a Leiden clustering algorithm, and displaying the following results through an interactive visualization tool: a cell clustering UMAP graph, performing color marking according to cell types; a UMAP graph and a heat map of transcription factor regulator activity; according to the visual map of the gene regulation and control network, transcription factors and target genes are distinguished through node shapes, and regulation and control relations are marked through line weights and colors. According to the invention, an accurate regulation and control network can be provided.

The invention discloses an animal single cell data cell type annotation method, which is characterized by comprising the following steps: collecting Bulk RNA-seq data of purified cell types in various tissues and organs of a specific animal, and integrating the Bulk RNA-seq data into a reference data set after preprocessing; the method comprises the following steps: acquiring single-cell RNA-seq original data, screening the single-cell RNA-seq original data to obtain high-quality cells, screening high-variation genes from the high-quality cells, processing the high-variation genes, extracting principal components, performing dimensionality reduction on the principal components, and performing cell clustering based on a dimensionality reduction result to obtain cell clusters; and calculating expression similarity between the cell clusters and the reference data set based on the high-variation genes, determining initial cell types of the cell clusters according to a similarity result, and carrying out iterative tuning on the initial cell types with similar scores to obtain a final cell type annotation result. The method provides efficient and accurate technical support for animal single cell research.

The invention relates to a multi-model fusion and knowledge base enhancement-based cell clustering prediction system and method, and the system comprises the following modules: a comprehensive knowledge base construction module, a knowledge base enhancement module, a knowledge base enhancement module, a knowledge base enhancement module, a knowledge base enhancement module, a knowledge base enhancement module and a knowledge base enhancement module. Constructing a species-tissue-cell group three-level knowledge sub-library; when cell dimension reduction clustering analysis is carried out, firstly, an existing knowledge database is used, key identification genes and modes are transmitted into a large model, and scoring is carried out through the large model; secondly, performing significance scoring on each cell cluster based on a specific algorithm, and performing accuracy evaluation and optimization on a grouping result by applying a grouping accuracy evaluation algorithm; in addition, a large amount of data is sorted in combination with a large model RAG and a large model fine tuning technology, and the large model is adjusted in combination with an artificial correction prediction result, so that the prediction accuracy is improved; and the calculation resources and the calculation efficiency of the model are reduced through a large model rectification technology.

The invention discloses a single cell clustering statistics significance test method and system based on manifold learning, and the method comprises the following steps: obtaining original single cell data, carrying out the standardization processing of the original single cell data, and removing the deviation and noise in the data; performing dimension reduction on the standardized data by using a manifold learning method; dividing the dimension reduction data based on a pre-calculated clustering label, and performing hierarchical clustering on the divided data to obtain a hierarchical tree; hypothesis testing is carried out step by step from the bottom to the top of the hierarchical tree by adopting a Monte Carlo simulation method, and whether the clusters are combined or not is determined according to a hypothesis testing result; and finally, taking the combined hierarchical tree as a single cell clustering correction result. According to the method, the reliability and the accuracy of the clustering statistical test can be improved, and unnecessary group splitting and misjudgment can be avoided.

The invention discloses a lightweight optimal clustering selection method for scRNA-seq data. The lightweight optimal clustering selection method comprises the following steps: 1, acquiring and preprocessing an scRNA-seq data matrix; 2, performing layer-by-layer dimensionality reduction on data by using a multi-layer perceptron encoder to obtain a low-dimensional feature matrix; and 3, constructing an undirected cell map, and enhancing and removing cell map noise through an NE network. And 4, reconstructing features by using graph convolution, inputting the low-dimensional feature matrix and the cell graph into a simplified graph convolution module, and updating the reconstructed feature matrix round by round. And 5, carrying out cell clustering on the characteristic matrix after each round of updating by using self-optimization clustering to obtain cell representation. And 6, judging and evaluating the clustering performance of the current round, storing an optimal clustering result, and carrying out feature reconstruction and self-optimization clustering of the next round. And 7, outputting and analyzing final optimal feature information. According to the method, scRNA-seq data can be well processed, low-dimensional embedded features can be extracted, tag prediction is more accurate, the requirement for hardware resources is low, and an efficient method is provided for analyzing biological characteristics of single cell data.

A method for designing a beam hopping pattern of a low-orbit satellite belongs to the field of low-orbit satellite communication, and comprises the following steps: dynamically clustering ground cells by using a hybrid clustering cell clustering algorithm according to the service requirements of the cells in a beam hopping scene, and enabling the cells in the same cluster to approach as much as possible on the basis of load balancing; dividing user satisfaction indexes into three levels to guide three dynamic operations; selecting an optimal individual to generate a progeny by using the overall user satisfaction of all cells in the whole beam hopping period; performing individual gene crossover by using the community user satisfaction of each cluster; performing individual gene variation by using the user satisfaction of a single cell; and fine tuning of beam power is carried out when each beam of the beam hopping pattern is served in the same time slot. According to the method, load balancing and geographic position compactness are comprehensively considered, the same-frequency interference is reduced, the resource utilization efficiency is improved, the calculation overhead is reduced, and the overall calculation efficiency is improved.

The application relates to the technical field of artificial intelligence, in particular to a cell clustering method, device and electronic equipment. The method comprises the following steps: acquiring MDT data coverage boundary maps of a plurality of cells within a first preset time and network index change data of the plurality of cells within a second preset time; performing first clustering on the cells with similar coverage form features of the MDT data coverage boundary maps and similar time distribution features of the network index change data, to obtain cells with different cluster labels; acquiring user number change data of the plurality of cells within a third preset time; and performing second clustering on the cells with similar spatiotemporal distribution features of the user number change data in the cells with different cluster labels. The cell clustering method, device and electronic equipment provided in the application can solve the technical problem that the existing cell clustering / classification method is not good in effect.

The invention discloses a structure-driven single cell transcriptomics immune cell annotation system and method, and the system comprises a data loading and preprocessing module which is used for loading a marker table and data after single cell clustering, and extracting the expression characteristic statistic of each cluster from the marker table and data to form a characteristic matrix; the basic structure annotation module is used for carrying out preliminary structure annotation on peripheral blood mononuclear cells and tissue samples; the tissue extension annotation module is used for completing structure extension and refinement under tissue expression drift on the basis of preliminary structure annotation according to a sample structure annotation requirement from peripheral tissues; and the structure dimension auxiliary annotation module is configured to integrate the dimension reduction coordinates and the adjacency graph information after being triggered, and perform spatial consistency verification and auxiliary correction on the low-confidence annotation result. According to the method, an automatic annotation function with high accuracy, strong controllability and good interpretability can be realized, and the method has high interpretability and robustness.

This specification describes a framework that includes one or more feature extractors (models) and a cluster component for clustering. The framework supports (1) offline, image-based, unsupervised clustering, which replaces time-consuming manual gating, and (2) online, image-based single-cell sorting. During training, one or more cell image datasets, with or without ground truth, are used to train the one or more feature extractors. The feature extractors are based on neural networks containing several convolutional layers. Once trained, the feature extractors are used to extract cell image features for unsupervised cell clustering and sorting. Additionally, after the feature extractors are trained, they can be further refined using additional datasets.

The invention provides a determination method of signal channels of a cell subset and a cell model, a prescription efficacy prediction method and a related device, and relates to the technical field of traditional Chinese medicines. The method comprises the following steps: performing low-depth single cell transcriptome sequencing and cell grouping and annotation analysis on a disease sample and a normal control sample, screening cell subgroups of which the quantity proportion is remarkably changed in the disease sample, and performing gene expression data aggregation analysis and signal path enrichment analysis, thereby obtaining the disorder signal path of the disease-related cell subgroups. Based on the corresponding relation between the disease-related cell subpopulation and the cell model of the traditional Chinese medicine effect, the cell model and the imbalance signal channel for predicting the efficacy of the prescription are determined, and applications such as quantitative prediction of the efficacy of the prescription with the reversal of the disease signal channel as the core are further developed.

The application discloses a battery cell fault diagnosis method and device, and relates to the technical field of batteries. According to the charging voltage of a battery cell, the sum of the absolute values of MN of a to-be-tested cell and the Euclidean distance are calculated, the sample entropy-scale factor curve slope of the to-be-tested cell is calculated according to the sampling time of the charging voltage, the first Hamming closeness of the sum of the absolute values of MN, the Euclidean distance and the sample entropy-scale factor curve slope of the to-be-tested cell to the normal cell clustering center is calculated, the second Hamming closeness of the sum of the absolute values of MN, the Euclidean distance and the sample entropy-scale factor curve slope of the to-be-tested cell to the fault cell clustering center is calculated, and if the second Hamming closeness is greater than the first Hamming closeness, the to-be-tested cell is judged to be faulty. The battery cell fault is comprehensively diagnosed from three dimensions.

The invention provides a spatial transcriptome signal enhancement method and device, electronic equipment and a storage medium. The spatial transcriptome signal enhancement method comprises the following steps: clustering cells in a target slice based on spatial transcription data of the target slice to obtain a cell cluster set; determining candidate cells of the target cells according to a preset distance threshold; determining first gene expression data of the candidate cells and second gene expression data of the target cells from the spatial transcription data; and combining the first gene expression data and the second gene expression data to enhance the gene expression of the target cell. The embodiment of the invention can provide a simple spatial transcriptome signal enhancement method.

The application relates to a single-cell Hi-C clustering method and system based on contact number weight smoothing and feature fusion, which comprises the following steps: (1) data preprocessing; (2) contact number weight-based smoothing; using a weight matrix to quantify the influence of different neighbor fragments on a target chromosome fragment; (3) restart random walk smoothing; using a restart random walk algorithm to perform smoothing processing on the chromosome contact matrix after the contact number weight-based smoothing processing; (4) contact binarization; (5) principal component extraction; using KPCA to perform dimension reduction and generate cell embedding; (6) feature fusion; (7) spectral clustering; using a spectral clustering algorithm to realize cell clustering. The single-cell Hi-C clustering method provided by the application is obviously superior to existing clustering methods, greatly improves the clustering effect when a large-scale single-cell Hi-C data set is processed, and can identify cell types with a small number of cells in the data set.

The invention relates to the technical field of data analysis, in particular to an integrated analysis method and system for multi-source single cell transcriptome data. The method comprises the following steps: converting all gene names of single cell transcriptome data from different sources into a unified version, and filtering source specific genes; a specific background gene pool is constructed, pollution genes are identified, and background RNA pollution is eliminated; calculating the average sequencing depth of each sample cell, and performing sequencing depth correction on each sample cell; based on transcriptome data of single cells from different sources, cell types are identified through cell grouping and characteristic gene expression quantity analysis, and each cell type is obtained; and constructing anchor point cells for each cell type, and correcting the deep equilibrium cell expression profile of the same cell type to obtain an integrated cell expression profile. The accuracy of data integration analysis of the single cell transcriptome is improved, and the influence of batch effect caused by multiple sources on other subsequent analysis is reduced.

The application belongs to the field of single cell clustering methods, and provides a single cell clustering method and system based on consistency matrix scoring, multiple consistency matrices are obtained after combined dimension reduction based on gene expression data, each consistency matrix is clustered to obtain a corresponding clustering result; the f-value of each consistency matrix is calculated by using a scoring method in combination with the consistency matrix and the corresponding clustering result, the consistency matrix corresponding to the highest f-value score is the optimal consistency matrix; based on the obtained optimal consistency matrix, a distance matrix between cells is constructed, and the final clustering result is obtained by using hierarchical clustering on the distance matrix between cells. The indirect distance between cells is fully utilized, and the clustering effect is improved.

The construction method of the digital cell basic model disclosed by the invention comprises the following steps: inputting single cell transcription sequencing data and related biological characteristics, and respectively encoding and integrating the data into node characteristics and edge characteristics of a cell map; inputting the formed cell graph into GNN, and adopting a message passing mechanism to jointly learn feature representation of nodes and edges; learning a global relationship among genes in the cell map through an attention mechanism, and outputting feature representation of the genes; and coding based on the feature representation of the gene to obtain a cell feature vector. According to the digital cell basic model CGCompass provided by the invention, pre-training is carried out on five million pieces of human single cell sequencing data, so that information of biological significance of genes and information of interaction between the genes can be learned; biological cell downstream tasks such as cell clustering, cell classification, single-gene disturbance prediction and bulk gene knockout prediction can be effectively completed through two modes of fine tuning and zero sample reasoning.

The invention discloses a single cell clustering analysis method and tool, and relates to the technical field of single cell sequencing data analysis. The method comprises the following steps: step 1, subdivision clustering: extracting a specific cell cluster from a Seurt object, carrying out secondary clustering under different resolutions and PCA dimension settings, and carrying out reclassification on cells by utilizing dimension reduction of Seurt and a neighborhood detection algorithm so as to identify a hidden subgroup structure; and step 2, label mapping and integration: a clustering result after subdivision is mapped back to an original Seurt object, a new refinedcluster column is created, an original clustering label and a new label coexist, and different clustering schemes are allowed to be flexibly switched in analysis. According to the method, the self-defined clustering resolution and the PCA dimension are supported, and parameters can be flexibly adjusted according to different data sets and research targets; the subdivided subgroup labels are seamlessly integrated with the original Seurt objects, and original clustering information is reserved at the same time, so that subsequent analysis is facilitated; a visualization function which is perfectly compatible with Seurt is provided, and visual display and comparison of subdivision results are supported.

This invention discloses a cross-modal cell alignment method for pathological images in non-registerable scenarios. The method acquires H&E and mIF stained images and their data-augmented views corresponding to spatial anatomical locations; constructs H&E modality processing branches, mIF modality processing branches, and a reverse self-attention module; and sequentially performs three-stage progressive training: intra-modal contrastive pre-training based on the data-augmented view; using mIF modality-level semantic aggregation tokens from the same spatial anatomical location as positive samples and mIF modality-level semantic aggregation tokens from different spatial anatomical locations as negative samples, achieving H&E to mIF modality-level semantic alignment through contrastive learning; inputting the aligned H&E modality-level semantic aggregation tokens and the projected H&E cell feature embedding set into the reverse self-attention module, and achieving unsupervised cell-level semantic alignment by minimizing the Hungarian matching loss; finally, the output H&E cell features semantically aligned with mIF are embedded into a refined set, which can be directly used for downstream pathological analysis tasks such as high-precision cell clustering.

The invention belongs to the technical field of bioinformatics and data mining, and discloses a single cell transcriptome sequencing data clustering method and system.The method comprises the steps that single cell transcriptome sequencing data are preprocessed, and preprocessing comprises data dimension reduction; constructing a stable pellet space based on the dimensionality-reduced data, wherein the pellet space is composed of a plurality of pellets covering the single cell sample; performing maximum pellet splitting on pellets in the stable pellet space to further refine the pellet set; the correction distance between the pellets and the balls is calculated to construct a correction distance matrix, and the correction distance integrates the Euclidean distance between the centers of the pellets and the radius information of the pellets and the balls; based on the corrected distance matrix, clustering the pellets by adopting a density clustering algorithm to obtain clustering labels of the pellets; and mapping the clustering labels of the pellets to the single cell samples covered by the pellets to generate a final single cell clustering result. According to the method, efficient, accurate and robust cell grouping is realized.

The invention relates to the technical field of data processing, in particular to a cell factor detection data processing method and system and a storage medium. The method comprises the following steps: acquiring original single cell cytokine detection data; performing cytokine secretion amount analysis on the original single cell cytokine detection data, and performing multi-cell-cytokine matrix construction to obtain a cytokine secretion characteristic matrix; carrying out secretion mode typing degree difference calculation on the cell factor secretion characteristic matrix to generate a cell dynamic heterogeneous distribution diagram; performing cell subset center tracking according to the cell dynamic heterogeneous distribution diagram to obtain cell detection subset data; and carrying out subpopulation cell clustering processing on the cytokine secretion characteristic matrix through cell detection subpopulation data to obtain cytokine subpopulation characteristic data. According to the method disclosed by the invention, the cell subpopulation is identified by finely analyzing the single cell data, so that the characteristic quantification of the cytokine secretion heterogeneity is realized.

The embodiment of the invention provides a cell subset division optimization method and device based on a single cell clustering result. The method is applied to the technical field of medical data analysis, and comprises the following steps: performing clustering analysis on single-cell RNA sequencing data according to a preset initial clustering resolution to obtain a plurality of cell subgroups after preliminary clustering; performing differential expression analysis on each cell subset obtained by preliminary clustering to obtain a differential expression gene quantity corresponding to each cell subset; and under the condition that the cell subgroups with the differential expression gene quantity lower than a preset threshold value exist in all the cell subgroups obtained by the preliminary clustering, performing automatic iteration merging on the cell subgroups obtained by the preliminary clustering until the differential expression gene quantity of all the merged cell subgroups is not lower than the preset threshold value. And outputting an optimized cell subset division result. According to the method, the accuracy of cell subset division and the efficiency of single cell data analysis are improved, and the biological rationality and interpretability of an analysis result are improved.

The invention relates to a method for detecting and / or identifying BAFF + DNT cells and application thereof, and belongs to the technical field of cell detection. According to the present invention, the anti BAFF monoclonal antibody is combined with the flow cytometry to characterize the BAFF protein expression efficiency of the DNT cell, and the DNT cell is positioned through the CD3, the CD4 and the CD8 so as to achieve the synchronous detection of the cell activity, the DNT cell grouping and the BAFF positive rate; the kit has the characteristics of high sensitivity, strong specificity, short detection period, less cell sample consumption, low false positive rate, high quality control standardization degree and suitability for GMP production.

The present invention belongs to the technical field of single-cell RNA sequencing technology, and relates to the fields of data mining, artificial intelligence, algorithm optimization, and single-cell multi-omics. In particular, it relates to a method for improving the clustering accuracy of single-cell multi-views, which includes the following steps: calculating and obtaining multi-view data {V<supgt;m< / supgt>}; constructing a multi-perspective similarity graph {S<supgt;m< / supgt>} by applying k-nearest neighbors; obtaining a weighted graph by weighting different views: optimizing {S<supgt;m< / supgt>}, w, and U; constructing H according to {S<supgt;m< / supgt>}; optimizing the structure graph A and normalizing it; fusing the weighted graph and the structure graph, and using the constructed symmetric normalization matrix T; through the normalized Laplacian matrix L and applying the k-means algorithm to the eigenvector F, finally the data points are divided into c clusters of different cell types. The advantage of this patent is that it improves the clustering accuracy of single cells through multiple technologies.

The invention belongs to the technical field of single cell clustering, and particularly relates to a single cell clustering method and system based on multi-granularity Transform. In order to solve the problems of insufficient cell genome relation extraction, limited clustering accuracy and the like in scRNA-seq data, the method provides a multi-granularity feature learning framework, hierarchical Token division is carried out on gene expression data, multi-level association from local gene collaboration to a global function module is captured by utilizing an attention mechanism, and the clustering accuracy is improved. And thus, cell global representation with higher discrimination is constructed. Furthermore, by introducing a cluster contrast learning mechanism, feature collision possibly caused by negative sample pairs in traditional contrast learning is avoided, and the clustering friendliness of a feature space is enhanced.

The application discloses a single-cell RNA sequence data clustering method based on a robust residual graph convolutional network, and comprises the following steps: determining a data set: selecting several public single-cell RNA sequence data sets; single-cell RNA sequence data preprocessing: performing cell and gene screening operations on the single-cell RNA sequence data set; network construction: constructing a single-cell RNA sequence data clustering network based on a robust residual graph convolutional network; network training: inputting the single-cell RNA sequence data into the constructed network for network training, and evaluating the current clustering performance by four clustering evaluation indexes after the training is completed; and cell clustering: inputting the single-cell RNA sequence data into the trained clustering network to obtain a clustering result. The application can make high-accuracy clustering on single-cell RNA sequence data in view of the noise problem existing in the single-cell RNA sequence data, and can be used for single-cell type annotation and recognition.

The invention relates to the technical field of infrared focal plane detector performance testing, and discloses a blind pixel clustering analysis-based infrared focal plane detector failure mechanism determination method, which comprises the steps of test preparation, response data acquisition, blind pixel identification, clustering analysis and failure mechanism inference. According to the method, on one hand, blind pixel recognition is completed by collecting the multi-dimensional original response data and combining multi-threshold judgment, and the accuracy of a blind pixel sample is ensured; and on the other hand, a multi-feature parameter set is formed by extracting the output level average value, the noise root-mean-square value and the detection response rate of the blind element, feature parameters are classified and combined by means of a clustering model to lock a core feature combination, and a failure mechanism type is inferred by combining a preset clustering cluster and failure mechanism mapping relation. The accuracy and the standardization degree of failure mechanism diagnosis are improved, meanwhile, reliability evaluation of the infrared focal plane detector is completed synchronously, and the actual requirements of detector failure root accurate positioning and reliability evaluation are met.

The present invention relates to the technical field of cell clustering, and discloses a method for clustering single-cell RNA sequencing data. The present invention extracts the content information of single-cell RNA sequencing data based on the self-encoding module of ZINB, and reconstructs the gene expression matrix and data distribution through ZINB decoding; secondly, uses the graph self-encoding module to capture the high-order structural information between cells, and extracts the structural information between cells by performing graph convolutional network processing on the cell-cell graph; through the attention fusion mechanism, the self-encoding module based on ZINB and the graph self-encoding module are fused and embedded layer by layer, effectively fusing the feature representation of gene expression information and structural information into the same representation, enhancing the clustering performance; finally, the present invention adopts a self-supervised strategy to integrate the self-encoding module based on ZINB and the graph self-encoding module into a unified framework, and effectively performs end-to-end clustering training and synchronous optimization on these two modules, thereby improving the clustering performance.

The present invention relates to a high-precision single-cell clustering method and system based on marker genes and ensemble learning, including: Step 1: Feature extraction; using a feature extraction algorithm and a dimensionality reduction algorithm to reduce the dimensionality of the cell expression matrix and extract cell features; each element in the cell expression matrix corresponds to the expression of a gene / transcript in a given cell; Step 2: Inner-layer clustering; the expression matrix after feature extraction is used as input and applied to the inner-layer clustering method; the inner-layer clustering method includes the single-cell clustering method SNN-Cliq and the self-organizing mapping method SOM of deep learning; Step 3: Calculate the consensus matrix; use the clustering-based similarity partitioning algorithm CSPA to calculate the consensus matrix C; Step 4: Consensus clustering; construct a graph c according to the consensus matrix C, where the nodes Node in the graph c represent cells, and the weight edge of the edge represents the probability that two nodes are in the same partition.