34 results about "Single cell transcriptome" patented technology

This document provides a high throughput method for the creation of AAV vectors and / or promoter sequences with high efficiency and / or specificity for multiple cell types.

A single-cell transcriptome-guided multimodal synergistic injectable magnetically responsive biomimetic hydrogel system, its preparation method, and its application are described. This hydrogel platform is a three-level composite system of "matrix-microsphere-nanoparticle": the primary structure is a photocrosslinked methacryloyl hyaluronic acid three-dimensional network matrix; the secondary structure is GelMA microspheres loaded with MTPT nanoparticles prepared by microfluidic control; and the tertiary structure consists of bevacizumab and magnetite nanoparticles dispersed in the HAMA matrix. The MTPT nanoparticles have a mesoporous silica core, which is sequentially coated with temozolomide, a polydopamine coating, and a T7 targeting peptide. Under the activation of an alternating magnetic field, Fe3O4 generates a magnetothermal effect, which not only achieves local hyperthermia but also accelerates the time-sequential release of bevacizumab and MTPT, synergistically exerting the effects of chemotherapy, anti-angiogenic therapy, and hyperthermia.

The application provides a single-cell transcriptome cell type automatic annotation method and device based on consensus voting, electronic equipment and storage medium, relates to the field of medical biotechnology, and integrates a plurality of initial annotation results obtained by a plurality of cell type annotation methods by applying an ensemble learning strategy, so as to reduce errors that may exist in a single annotation method, and improve the accuracy and robustness of cell type annotation. In addition, the method uses single-cell transcriptome data of a sample, combines rich prior knowledge and strong reasoning ability of a large language model, and has the ability to discover rare cell types, so as to effectively identify rare cell types, widen the application range of cell type annotation, and improve the general tissue annotation capability of cell types.

This invention discloses a method and system for single-cell transcriptome cell type annotation based on deep learning, belonging to the field of bioinformatics data processing technology. The method includes five steps: data quality control preprocessing, Transformer cell encoder pre-training, graph attention network cell relationship modeling, hierarchical classification annotation, and zero-shot transfer annotation. This invention deeply couples Transformer representation learning with graph attention networks, obtains general representations through masked gene prediction pre-training, enhances rare cell type features using KNN graphs and graph attention message passing, improves recognition accuracy by adopting a hierarchical classification architecture from main lineage to subtype, and supports zero-shot cross-modal annotation based on text description.

Embodiments of the present application disclose a pan-cancer cell recognition model training method, device, equipment and storage medium. The method comprises selecting transcriptome test data of a plurality of preset cancer types according to a preset ratio of normal cells and malignant cells to construct an initial data set; obtaining a preset number of high variable genes in the transcriptome test data of the initial data set as training features to obtain a training set; based on a binary classification label, performing label annotation on the transcriptome test data in the training set to generate a binary classification label system test data set; taking the pre-training weight of a preset base model as an initialization parameter, mounting a binary classification head at the top layer of a transformer layer, and performing parameter fine-tuning on the preset base model based on the binary classification label system test data set to obtain a pan-cancer cell recognition model. The scheme of the embodiments of the present application can realize accurate identification of benign and malignant cells in pan-cancer single-cell transcriptome data.

This invention discloses a high-throughput screening method based on cytokinesis for bidirectional recognition of TCR and pMHC. The method involves displaying both pMHC and TCR on the cell membrane, with the TCR simultaneously fused with the MS2 phage capsid protein for capturing barcode and MS2 RNA. The two cell types are co-cultured, and cytokinesis-mediated membrane transfer occurs between cells exhibiting bidirectional TCR and pMHC recognition. Cells displaying pMHC are isolated and collected for single-cell transcriptome sequencing analysis. The sequencing results are grouped according to different pMHCs, and the corresponding TCR is determined using the barcode sequence, thus identifying the TCR that specifically recognizes pMHC bidirectionally. This high-throughput screening method based on cytokinesis for bidirectional specific recognition of TCR and pMHC overcomes, to some extent, the limitations of existing technologies in terms of screening throughput, physiological relevance, and bidirectional matching ability.

The application discloses a paclitaxel treatment response prediction method and system for triple-negative breast cancer patients, and the method comprises the following steps: obtaining single-cell transcriptome data, bulk transcriptome data and paclitaxel sensitivity data of triple-negative breast cancer patients before and after treatment and preprocessing; constructing a regression model of immune microenvironment and tumor response, calculating the response score of immune cell subgroups, screening key immune cell subgroups related to paclitaxel treatment response, performing differential expression analysis on the pre-treatment sample, constructing a paclitaxel IC50 prediction model, and dividing the sample into a high-sensitivity group and a low-sensitivity group; constructing a treatment response prediction model and outputting a prediction result. The technical scheme integrates the dynamic changes of the immune microenvironment, the transcriptome characteristics and the drug sensitivity data, realizes accurate prediction of the paclitaxel treatment response of the triple-negative breast cancer patients before treatment, and provides a scientific basis for formulating an individualized treatment plan.

This invention discloses a method, system, and device for single-cell transcriptome clustering based on deep autoencoders. The method includes: data preprocessing and feature engineering, construction of a deep autoencoder network, design of a multi-task loss function, model training and feature extraction, dimensionality reduction visualization, and spectral clustering analysis. The system includes: a data preprocessing module, a deep autoencoder module, a loss function calculation module, a model training module, a dimensionality reduction visualization module, a clustering analysis module, and an evaluation module. This invention significantly improves the clustering accuracy of single-cell data by introducing a contrastive learning mechanism and optimizing the clustering strategy.

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.

This invention discloses the application of P4HB as a target in the preparation of therapeutic drugs for metastatic pleural and peritoneal effusions in multiple cancer types. Through combined single-cell transcriptomics and proteomics analysis, this invention revealed that P4HB is significantly overexpressed in metastatic pleural and peritoneal effusion lesions. Multiplex immunofluorescence and immunohistochemistry were used to perform in situ tissue validation in clinical samples of pleural and peritoneal effusions from breast cancer, lung cancer, gastric cancer, colorectal cancer, and ovarian cancer, clarifying the differential expression characteristics of P4HB in metastatic tumor cells and its correlation with poor prognosis. In patient-derived organoid models, targeting and inhibiting P4HB activity with small molecule inhibitors significantly reduced organoid growth capacity and survival rate, and showed a synergistic sensitizing effect on chemotherapeutic drugs. This invention reveals the use of P4HB as a therapeutic target for metastatic pleural and peritoneal effusions in multiple cancer types, providing a new target and direction for drug development in precision medicine.

This invention relates to the fields of bioinformatics and precision oncology medicine, specifically disclosing a single-cell analysis system and method based on precise typing and treatment prediction of the lung cancer immune microenvironment. The system includes a data preprocessing and quality control module, a lung cancer-specific cell annotation module, an immune microenvironment typing module, a clinical efficacy prediction module, and a visualization report generation module. These modules form a complete technical chain from raw data to clinical efficacy prediction. Furthermore, this invention provides a scheme for precise typing and treatment prediction of the lung cancer immune microenvironment matching this system. This invention can take single-cell transcriptome data (which can integrate spatial transcriptome data) from lung cancer patients as input, process it through a series of specific computational modules, and finally output immune microenvironment typing results and treatment response prediction results with clear clinical guidance significance, solving the problems of unclear typing, fragmented processes, and insufficient clinical translation capabilities in existing technologies.

The application discloses a kind of single-cell transcriptome analysis methods and application of Crohn's disease creeping fat microenvironment, belong to the field of biological medicine technology.The method is by obtaining the single-cell and batch transcriptome data of mesenteric adipose tissue of Crohn's disease patient and healthy control, constructs relevant gene set and carries out data quality control, clustering and cell annotation;Mesenchymal stem cells are subpopulation identified, abundance analysis and function typing, combined with signal path analysis and cell communication analysis, and the key factor of regulating creeping fat microenvironment is screened out.The application first systematically analyzes the cell heterogeneity and MSC subpopulation characteristics of Crohn's disease creeping fat microenvironment, and determines the key signal path and regulating molecule, which can provide efficient and reliable technical means for the pathogenesis research, treatment target screening and creeping fat related molecule identification of Crohn's disease, and has high scientific research and clinical application value.

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.

The application discloses a single-cell transcriptome analysis method, system and storage medium, relates to the technical field of biological statistical data analysis, and comprises the following steps: receiving single-cell transcriptome sequencing data and analysis parameters corresponding to a current analysis task, and determining a hash value corresponding to the analysis parameters; comparing the hash value with a preset hash value, and determining whether a target preset hash value matching the hash value exists; if yes, taking an analysis result associated with the target hash value as a target analysis result of the current analysis task; if no, analyzing the single-cell transcriptome sequencing data based on the analysis parameters, generating the target analysis result, associating the target analysis result with the hash value, and outputting the target analysis result. The application realizes cache reuse and version isolation of single-cell transcriptome analysis results by calculating and comparing the hash value of the analysis parameters, and solves the technical problem that researchers need to repeatedly calculate due to result coverage in traditional analysis.

This invention relates to the field of biological aging assessment technology, specifically a method for assessing cellular aging based on proteomics data and machine learning. The method includes: constructing a cell type-specific candidate feature set based on single-cell transcriptomics data; obtaining a protein feature matrix based on plasma proteomics data; constructing independent machine learning-based cell type-specific aging prediction regression models for each cell type, using age as the response variable and the protein feature matrix as input; inputting the proteomics data of the sample to be predicted into the corresponding cell type-specific aging prediction model to obtain the predicted lifespan and the lifespan difference characterizing cellular aging for different cell types. This invention achieves quantitative assessment of the aging degree of different cell types in different organs under in vivo conditions by constructing a functional mapping bridge between single-cell transcriptomics and plasma proteomics.

This invention discloses a biomarker for evaluating the efficacy of tuberculosis treatment and its application. The biomarker includes the SPP1 gene and / or the TREM2 gene. This invention proposes for the first time that the gene expression characteristics or proportional changes of two macrophage subsets with opposing functions and spatial distributions in tuberculous granulomas—namely, SPP1-highly expressed macrophages in the core region (pro-inflammatory / antibacterial) and TREM2-highly expressed macrophages in the peripheral region (regulatory / repair-oriented)—can be used as novel biomarkers for evaluating the efficacy of tuberculosis treatment. By monitoring the dynamic changes in characteristic transcriptional profiles (such as the SPP1 and TREM2 gene sets) derived from these two cell types in tissues or peripheral blood before and after treatment using single-cell transcriptomics and other technologies, the treatment response can be sensitively and accurately assessed, providing a novel tool based on cellular functional status for the precision medical management of tuberculosis.

The application discloses a method for evaluating the curative effect of traditional Chinese medicine in colorectal cancer by fusing network representation and deep learning. The application accurately identifies disease core driver genes through single-cell transcriptome differential analysis and protein-protein interaction network topology centrality index, simultaneously extracts the structural characteristics of traditional Chinese medicine ingredients by graph isomorphism network, constructs traditional Chinese medicine-compound isomorphism network, and extracts the isomorphism topological representation of traditional Chinese medicine by network representation algorithm. The one-dimensional convolutional neural network is used to deeply mine the protein sequence nature semantic features of disease gene sequence, so that the protein features and the end dimension of traditional Chinese medicine are aligned. Finally, the cross-modal joint vector is constructed through feature splicing, and the intervention probability output by the full connection neural network is used to realize the scoring of the candidate drug. The application establishes a direct and quantitative connection between the traditional Chinese medicine intervention space and the single-cell pathological mechanism, realizes the end-to-end evaluation of the anti-colorectal cancer efficacy of traditional Chinese medicine, and can be applied to the fields of traditional Chinese medicine screening and individualized drug administration scheme making.

The application discloses a screening and detection method based on a nuclear male sterility gene of oil flax, and belongs to the technical field of molecular biology and plant breeding. The method comprises the following steps: performing single-cell transcriptome sequencing on anther tissues of oil flax flower buds in multiple periods of development, and identifying differentially expressed genes of tapetum cells and microsporocyte cell groups before meiosis; performing homologous alignment on the differentially expressed genes of the cell groups and an Arabidopsis thaliana nuclear male sterility gene set, and screening nuclear male sterility candidate genes of the oil flax; designing overlapping primer pairs for long fragment PCR amplification and sequencing according to the candidate genes, and obtaining sequence difference sites between sterile lines and fertile lines; designing a high-resolution melting curve detection primer group for amplification reaction according to the sequence difference sites, and distinguishing the genotypes of the sterile lines and the fertile lines according to the peak type difference of the melting curves.

This invention discloses a method and application for screening polymorphic genetic markers of disease resistance traits in livestock, relating to the fields of animal molecular genetics and genome breeding technology. This invention uses single-cell transcriptome sequencing to locate key cell subpopulations for disease resistance, and then conducts targeted eQTL analysis on these purified subpopulations. This addresses the shortcomings of relying on mixed samples, which leads to a lack of cell type specificity in markers. Immune cells are grouped using single-cell transcriptome sequencing, and key cell subpopulations in the disease resistance response are screened using pivotal scoring. Cell sorting technology is then used to purify these subpopulations, ensuring that subsequent eQTL analysis is conducted only on these core subpopulations. This process clearly distinguishes the specific cell types involved in the genetic variation, enabling the screened eQTL markers to be directly associated with disease resistance regulatory mechanisms. This achieves a precise correspondence between markers and cell functions, eliminating the interference of mixed samples on marker specificity and giving the markers clear cell type specificity and functional targeting.

The application belongs to the technical field of bioinformatics, single-cell multi-omics and artificial intelligence, and discloses a tea tree hair phenotype prediction method and system based on machine learning. The method comprises the following steps: firstly, the development trajectory of tea tree epidermis and hair cells is finely analyzed by using single-cell transcriptome sequencing (scRNA-seq), and hair-specific expression gene clusters are accurately positioned. Combined with a high-density genetic map, the hair-specific expression genes screened at the single-cell level are subjected to expression quantitative trait locus (eQTL) mapping, 111 core single nucleotide polymorphism (SNP) sites most significantly related to hair development are strictly screened from the whole genome, and a Core-111 feature set with extremely reduced dimension is constructed. Subsequently, a variety of regression algorithms are evaluated in parallel, and an arithmetic mean ensemble learning model with ridge regression and gradient boosting regression as base learners is constructed.

Provided herein include methods, compositions, isolated cells, cell models, and kits suitable for use in profiling various cell types in amnion including amnion epithelial cells, amnion mesenchymal cells, fibroblasts, macrophages, as well as amnion stem cells including amnion epithelial stem cells and amnion mesenchymal stem cells. The present disclosure also discloses novel markers for various cell types in human amnion, including marker genes, transcription factors and signaling molecules associated with various stages of amniotic development. The methods, cell models, and gene signatures disclosed herein can be used for a variety of research, diagnostic, or therapeutic applications.

This invention discloses an integrated method for identifying and functionally annotating metaprograms in tumor single-cell transcriptomes, belonging to the fields of bioinformatics, tumor biology, and single-cell transcriptome sequencing. This invention aims to address the problems of unstable metaprogram identification, significant technical artifact interference, and fragmented functional annotation in existing technologies. Based on multi-rank nonnegative matrix factorization, it systematically extracts co-expression modules at different scales from the tumor single-cell expression matrix. Robustness screening ensures the consistency and reliability of the obtained metaprograms under multiple factorizations and cross-sample conditions. Furthermore, it performs systematic functional analysis of the metaprograms to reveal the multi-dimensional functional states of tumor cells. This method improves the stability and biological interpretability of tumor metaprogram identification, providing a new technical means for tumor heterogeneity research and the discovery of precision therapeutic targets.

The application relates to the technical field of biological information, in particular to a single-cell transcription gene gene regulation network inference method, model, system and storage medium. A correlation vector of each gene pair in to-be-measured single-cell transcription gene data is determined, and each gene pair is represented in the form of a histogram; time characteristics in the correlation vector are captured through a time sequence convolution network, and space characteristics in the histogram are captured through a convolution network; the time characteristics and the space characteristics are weighted and fused to obtain fused characteristics; and a gene regulation network inference result of the to-be-measured single-cell transcription gene data is predicted based on the fused characteristics. The application aims to solve the problem of how to predict single-cell transcriptome data in a gene regulation network.

This invention relates to a tumor efficacy evaluation system and the application of single-cell transcriptome sequencing in tumor efficacy evaluation. The tumor efficacy evaluation system includes: a sample acquisition module for acquiring paraffin-embedded samples of lesions at different stages from the same patient being evaluated, the paraffin samples containing tumor tissue; an information acquisition module for acquiring corresponding tumor microenvironment information based on each paraffin sample, the tumor microenvironment information including cell type-related information; and an analysis module for analyzing and comparing the tumor microenvironment information to obtain cellular information for tumor efficacy evaluation. The tumor efficacy evaluation is realistic, accurate, and comprehensive. This invention also discloses the application of single-cell transcriptome sequencing in tumor efficacy evaluation.

The application relates to a single cell perturbation prediction method based on a flow matching and mixed expert architecture. Single cell transcriptome data and perturbation information are acquired, input into a pre-trained single cell variational autoencoder, compressed to obtain low-dimensional latent representations of control group and perturbation group cells, and then optimal transport pairing is used to construct a mapping between the two groups of cells to obtain a target velocity vector of the flow matching model. Subsequently, a mixed expert enhanced flow matching generation model is built, the mapping relationship and the velocity vector are used as training data, prior knowledge is combined to form a physical-biological dual constraint loss function to complete training, and a perturbation prediction model is obtained. Finally, actual single cell transcriptome data is encoded into latent representations, and the model can output the complete evolution trajectory of the cell to the target perturbation. Compared with the prior art, the application has the advantages of breaking the limitation of unpaired data and establishing a mapping relationship conforming to physical and biological laws.

This invention discloses GmEXO70 Application of genes in enhancing soybean resistance to nematodes. This invention is the first to discover and validate a gene encoding the EXORDIUM protein through single-cell transcriptome analysis. GmEXO70 It is specifically and highly expressed in the syncytia of disease-resistant soybean varieties, and its expression is strongly induced by nematode infection. Overexpression was confirmed by constructing an overexpression vector and transforming soybean hairy roots with Agrobacterium rhizogenes. GmEXO70 It can significantly increase the expression level of this gene in roots. Further resistance evaluation showed that, compared with the empty vector control, overexpression significantly increased the expression level of this gene. GmEXO70 In the root system, the proportion of nematodes developing to the J3 / J4 stage was significantly reduced, with most nematodes arresting at the J2 stage. Furthermore, immunofluorescence in situ hybridization directly confirmed at the transcriptional level that... GmEXO70 The gene was specifically enriched in nematode-induced syncytia. This invention provides a new key gene for soybean nematode resistance breeding. GmEXO70 .

The present application relates to the technical field of plant tissue protoplast separation, and in particular to a preparation method and application of Phyllostachys edulis root tip protoplast. The preparation method comprises the following steps: collecting root tips of Phyllostachys edulis spring bamboo shoots as raw materials; washing the raw materials with 0.6-0.8M mannitol, and then placing the washed raw materials in an enzymatic solution for enzymolysis for 2.5-3.5h to obtain a protoplast single cell suspension; centrifuging the protoplast single cell suspension at 40g-60g, removing the supernatant, resuspending the cells with mannitol, and obtaining a cell resuspension; mixing the cell resuspension with a sucrose solution with a mass concentration of 18-22%, and then centrifuging at 40g-60g to obtain the protoplast. The preparation method can obtain protoplast with high cell activity and pure background, and can meet the use requirements of Phyllostachys edulis root single cell transcriptome sequencing library construction, and has great significance for Phyllostachys edulis root single cell sequencing.

This invention discloses an in vitro detection method and kit for assisting in the screening of systemic lupus erythematosus (SLE) patients suitable for BCMA-CD19 dual-target CAR-T therapy. Based on single-cell transcriptome sequencing, this invention identifies a plasma cell subset that exhibits high XBP1 / JCHAIN ​​expression but low CD19 expression after CD19 single-target therapy. This method uses qPCR to quantitatively detect the mRNA levels of AIM2, XBP1, JCHAIN, and immunoglobulin heavy chain constant region genes in PBMCs, and calculates the BCR category switching score using an exponential operational model. Patients exhibiting high expression of AIM2 or plasma cell markers and a BCR score >1.5 (indicating IgG / IgA dominance) are considered suitable for dual-target therapy. This method effectively identifies individuals at risk of single-target therapy escape and can be used to assess the quality of immune reconstitution after treatment.