31 results about "Cell localization" patented technology

The invention discloses a handwritten table structure recognition and Excel cooperative processing method and system, relates to the technical field of computer vision, and comprises the steps of image preprocessing, table structure recognition, cell positioning, content recognition, Excel template analysis and text mapping. The system preprocesses the input image; respectively extracting horizontal and vertical lines based on morphological operation, and identifying a logic rank range of the merged cells; calculating a cell pixel bounding box through the cross points, and carrying out logic sorting and interference filtering; independently cutting each cell and calling a handwriting OCR (Optical Character Recognition) engine to extract text content; matching a preset Excel template according to the header or the code, and analyzing the coordinates of the combined and non-combined cells of the Excel template; and accurately mapping the identification content to the corresponding position of the Excel based on the row and column logic sequence numbers by taking the anchor point cell as a reference, and generating a spreadsheet. According to the method, the problems of inaccurate merging cell recognition, content dislocation and the like are effectively solved, and the electronization precision and efficiency of the handwritten form are remarkably improved.

Methods of tagging cells with unique oligonucleotide “zipcode” constructs are provided. By these methods and associated compositions, cells in a multicellular structure such as a tissue section can be tagged with a construct, the unique composition of which is associated with the cells position in the multicellular structure. Subsequently, the multicellular structure can be dissociated into single cells and a single cell transcriptome analysis performed, as well as other types of single cell analyses. By preserving positional information in the analyzed single cells, biological processes within the tissue can be mapped. By these methods, the effects of the local environment surrounding a cell on its state and various functions can be elucidated, and intra-tissue processes can be mapped and observed. Likewise, coordinated actions by multiple cells within a tissue can be mapped and tracked over time.

High levels of nuclear NMT1 are associated with longer relapse free survival in ERα positive breast cancer patients. Both low levels of cytosolic and nuclear NMT1 correlated to very poor clinical outcomes. NMT2 also plays an important function in breast cancer signalling, regulated through phosphorylation. For example, NMT2 phosphorylation status is a key element in the progression of ER+ breast cancer cells. Specifically, nuclear localization of NMT2 is associated with poor outcomes in breast cancer patients.

The present application relates to the technical field of gastric cancer, and discloses a tumor cell quantification analysis method and system based on gastric cancer CLDN18, which comprises the following steps: presetting candidate points on a pathological section image; generating foreground and background auxiliary points for cell labeling points, and constructing a structured supervised target; extracting multi-scale semantic features through a pre-trained pathological large model, and generating an aggregated feature map through downsampling alignment and fusion operations; adaptively reconstructing candidate point features using implicit feature interpolation technology; predicting position offset and class confidence based on candidate point features, and determining cell position and class through threshold screening and offset optimization; optimizing the model in combination with an auxiliary point supervision mechanism, and outputting objective quantification results. The present application can significantly improve the positioning accuracy and classification consistency of CLDN18 positive tumor cells, and reduce the workload of doctors.

A method for detecting cell positioning anomalies is disclosed. Control plane signaling data packets are collected associated with multiple cells of a communications network. Distance and azimuth values for individual communication sessions are calculated for each cell. A machine learning model is executed using various communication parameters as input to generate a classification for each cell. A list identifying which cells are experiencing anomalies is generated.

The invention provides a single-cell space transcriptome cell localization and type deconvolution algorithm based on feature decoupling. A deep learning technology is utilized to carry out single-cell pseudo-space reconstruction and space transcriptome cell type deconvolution. The algorithm combines feature decoupling and cross-domain transfer learning methods, and specifically comprises encoder feature decoupling, feature transfer, single-cell pseudo-space prediction and space transcriptome cell type composition prediction. According to the method, cross-domain transfer learning is applied to simultaneous prediction of single-cell pseudo-space and space transcriptome cell type composition for the first time, and the model is constructed by using gene transcriptome data. In the embodiment, the Pearson's correlation coefficient between the predicted distance between the paired cells in the single cell space and the distance between the paired cells in the real space reaches 0.75, and the Pearson's correlation coefficient between the predicted space transcriptome cell type composition and the real cell type composition reaches 0.79; the method successfully realizes efficient prediction of single cell pseudo-space and space transcriptome cell type composition, and provides a new thought and method for the field of solving cell heterogeneity.

The present disclosure relates to computer-implement techniques for cell localization and classification. Particularly, aspects of the present disclosure are directed to accessing an image for a biological sample, where the image depicts cells comprising a staining pattern of a biomarker; inputting the image into a machine learning model; encoding, by the machine learning model, the image into a feature representation comprising extracted discriminative features; combining, by the machine learning model, feature and spatial information of the cells and the staining pattern of the biomarker through a sequence of up-convolutions and concatenations with the extracted discriminative features from the feature representation; and generating, by the machine learning model, two or more segmentation masks for the biomarker in the image based on the combined feature and spatial information of the cells and the staining pattern of the biomarker.

The invention relates to a cell counting method, and relates to the technical field of cell image analysis, a neural network model directly processes clear and discrete point coordinates from input to output, does not need complex composite loss, directly outputs instance-level coordinates, and basically completely eliminates background noise accumulation caused by density map integration. The invention further provides a query point generation mechanism for intelligently distributing calculation resources according to the actual distribution density of the cells, the counting speed is greatly increased while high precision is guaranteed, and the dilemma that a traditional method is redundant in calculation or unstable in matching is fundamentally solved. According to the method, each query point is creatively enabled to simultaneously query feature maps from different levels of the convolutional neural network. Therefore, the neural network model makes a final decision, the low-level detail features, the middle-level structural features and the high-level semantic features can be organically and adaptively fused, and the cell positioning precision and robustness are greatly improved.

The present invention provides a kind of rubber tree HbMAX2 gene, its nucleotide sequence is as shown in SEQ ID NO:1.The present invention clones and obtains rubber tree HbMAX2 gene from rubber tree for the first time, and this gene subcellular localization is in cell nucleus, and is expressed in all tissues of rubber tree, wherein the expression amount in flower and leaf is significantly higher than other tissues, and the expression amount in rubber tree high-yield germplasm is higher than low-yield germplasm, explanation HbMAX2 may be involved in the latex synthesis process of rubber tree, further study shows, this gene can improve the viability of yeast under oxidative stress, and illustrates the regulatory function of this gene on abiotic stress.The present invention provides new candidate gene for the research of improving aspects such as yeast and plant stress resistance, and is of great significance to in-depth study of rubber tree genetic improvement breeding.

A cell cultivation apparatus for cultivating microorganisms and growing cells at high density is provided. The apparatus includes a membrane comprising multiple surface features on a first side of the membrane for cell placement. The surface features comprising one or more compartments within which a cell can be located. The membrane includes a material that is at least partially permeable to gas. A second side of the membrane defines a gas region. The second side of the membrane is separated from the first side of the membrane by the membrane. The apparatus further includes a media region for receiving media. The compartments are configured to at least partially reduce media flow shear forces on one or more cells in the compartments. The surface features may be ridges, protrusions, fins, wells, and / or posts.

Methods of treating heart disease by modulating the cellular localization of the beta isoform calcium / calmodulin dependent protein kinase II delta (CaMKIIδ) via the disruption of post-transcriptional phosphorylation.

The present application relates to a single-cell protein subcellular localization model based on weakly supervised multi-instance learning, and relates to the technical field of biological information. The model comprises a cell feature extractor, an image branch, a cell branch and a class-aware adaptive pruning module. The cell feature extractor is used to encode single-cell images into single-cell feature vectors. An image-level classifier in the image branch is used to output an image-level protein subcellular localization prediction result according to the image-level feature representation. A cell-level classifier in the cell branch is used to output a single-cell-level protein subcellular localization prediction result according to the single-cell feature vector. The class-aware adaptive pruning module generates single-cell pseudo labels through several label sources. The model of the present application can solve the problems of cell label noise and class long-tail distribution under weak supervision, thereby realizing more accurate and stable single-cell localization prediction and providing a powerful tool for single-cell heterogeneity analysis.

A method and system for seeding cells on a well plate is disclosed. According to the present disclosure, a cell concentrating device is used that positions the cells at a particular location on the bottom floor of each well. The cell concentrating device improved sensitivity and uniformity when conducting analysis on the cells.

The invention relates to the technical field of biomedicine, in particular to a sepsis marker screening method based on a peripheral blood mononuclear cell gene co-expression network, and the method comprises the following steps: obtaining a sample; carrying out batch RNA sequencing, differential expression analysis, weighted gene co-expression network analysis, cross analysis and protein interaction network analysis on the sample, and screening hub genes; performing function enrichment analysis and immune cell infiltration analysis on the hub gene, and screening out a core gene; and carrying out expression verification and clinical correlation analysis on the hub gene. Starting from the overall perspective of a gene network, the screened Hub gene has higher biological significance and reliability, through cross screening of WGCNA and differential expression analysis, the range of candidate genes is greatly narrowed, the screening efficiency and accuracy are improved, bioinformatics analysis, scRNA-seq cell localization and protein level experimental verification are integrated, and the screening method has the advantages that the screening efficiency is greatly improved, and the screening cost is reduced. A complete evidence chain is formed, and the credibility of the marker is ensured.

The invention relates to a computer-implemented method for creating a searchable indexed data structure for biological sequence data. The invention further relates to searching in said data structure for any given biological sequence data or associated information. The invention relates to a computer-implemented method comprising: a. providing biological sequence input data, b. decomposing the biological input data into non-overlapping portions, c. indexing each portion of the biological input data with at least one associated information of said portion comprised within or provided with the biological input data, thereby creating a two-tiered index for each portion. The method may further comprise d. receiving at least one query from a user, wherein the query comprises biological sequence information, language-based prompts and / or queries regarding the metadata comprised within or provided with the biological input data. The method may further comprise e. providing at least one output comprising at least one biological sequence information, biological sequence identifier and / or metadata of one or more portions of the biological sequence input data corresponding to the query. The invention further relates to the use of the method of the invention for identifying tissue and / or cell localized expression of at least one nucleic acid, such as a gene, and / or protein of interest. The method further relates to a data structure and a computer-readable medium comprising a data structure, such as a database, constructed according to the invention.

The present application relates to the technical field of genetic engineering, and particularly relates to a MdHEMH2 gene for promoting apple anthocyanin synthesis and application thereof. The present application uses molecular biology means to screen a gene MdHEMH2 capable of regulating apple anthocyanin accumulation from apples. Through GUS reporter gene expression, biological information analysis, subcellular localization, transient and stable genetic expression and other tests, it is proved that the MdHEMH2 gene plays a positive regulation role in the accumulation of anthocyanin induced by ALA, and has the function of promoting the accumulation of apple anthocyanin. In addition, exogenous ALA can induce the expression of MdHEMH2 gene and participate in the accumulation of apple anthocyanin. The use of MdHEMH2 gene can improve fruit quality and provide a molecular basis for breeding new plant varieties.

A method of determining presence of biomarkers in a sample comprises receiving an image of the sample, the image comprising a plurality of cell-cross segments; dividing the image into a plurality of two-dimensional grid segments, each of the plurality of two-dimensional grid segments comprising a plurality of cell segments; determining, for each of the plurality of two-dimensional grid segments, a corresponding z-level of a cell contained within the segment; correcting a segment-quantified biomarker expression for each of the cells contained within each of the plurality of grid segments by regressing out z-level information; and returning a corrected expression approximating a complete biomarker expression for each of the cells contained within each of the plurality of grid segments as if a biomarker expression of an entirety of each of the cells contained within each of the plurality of the grid segments had been measured.

The invention relates to the technical field of gastric cancer, and discloses a gastric cancer CLDN18-based tumor cell quantitative analysis method and system, and the method comprises the steps: presetting candidate points on a pathological section image; foreground and background auxiliary points are generated for the cell labeling points, and a structured supervision target is constructed; extracting multi-scale semantic features through a pre-trained large pathological model, and generating an aggregation feature map through down-sampling alignment and fusion operation; adopting an implicit feature interpolation technology to adaptively reconstruct candidate point features; based on candidate point features, predicting position offset and category confidence, and determining cell positions and categories through threshold screening and offset optimization; and combining with an auxiliary point supervision mechanism optimization model, and outputting an objective quantification result. According to the scheme, the positioning precision and classification consistency of the CLDN18 positive tumor cells can be remarkably improved, and the workload of doctors is reduced.

This invention discloses a deep learning-based method and related equipment for locating and counting cells in *Scenedesmus* (a type of algae). The method first acquires microscopic images of *Scenedesmus* populations and labels the cell locations to form a set of labeled cell points. Then, a *Scenedesmus* cell counting network is constructed, including a backbone network, density branches, and regression branches, to extract features from the images and model the spatial distribution of cells. Enhanced images are generated by preprocessing the microscopic images, and the network is trained using the labeled information as supervision. After model training, new microscopic images are input into the network to obtain initial cell location and counting results. Furthermore, by incorporating the biological prior constraint that the number of cells in a *Scenedesmus* population is even, the initial counting results are post-processed and corrected, finally outputting the cell location and counting results. This invention enables automatic location and accurate counting of cells in *Scenedesmus* populations, exhibiting high recognition accuracy and application value.

This invention belongs to the field of biomedical technology and discloses an in vitro evaluation method for GBM drug delivery systems based on tumor organoid chips. This method uses a PDMS tumor organoid chip as a carrier, co-culturing GBM cells and human umbilical vein endothelial cells to localize and culture GBM cells within the chip chamber. A biomimetic blood-brain barrier is constructed within the microchannels, and a perfusion system continuously maintains the cell growth microenvironment. After in vitro drug administration to the test drug delivery system, its anti-GBM effect is quantitatively detected from three dimensions: proliferation, invasion, and spheroidization. This invention can highly simulate the in vivo GBM tumor microenvironment and blood-brain barrier structure, achieving precise, real-time, and dynamic in vitro efficacy evaluation, while significantly reducing reliance on animal experiments, improving the reliability of results and experimental throughput. It provides an efficient and standardized platform for preclinical screening and mechanism of action research of anti-GBM drug delivery systems, and has significant scientific research value and clinical translational significance.

The application discloses a multi-omics integration method and system for identifying a key autocrine signal loop and core candidate genes in pancreatic cancer. The method comprises the following steps: acquiring and preprocessing batch transcriptome, proteome, single-cell RNA sequencing and spatial transcriptome data; identifying core candidate genes through multi-method cross screening and machine learning robustness sorting; locating the core genes to the target cell subpopulation by using single-cell data and analyzing the regulation mechanism thereof; identifying the autocrine signal loop participated by the core genes in the target subpopulation based on cell communication network analysis; and verifying the spatial co-localization and co-activity of the loop by using spatial transcriptome data. The application systematically connects the whole-chain analysis of molecular discovery, cell localization, function analysis and interaction verification, significantly improves the accuracy and reliability of the identification of key factors and autocrine loops, and provides new targets and complete evidence chain for pancreatic cancer targeted therapy.

The present disclosure relates to computer-implement techniques for cell localization and classification. Particularly, aspects of the present disclosure are directed to accessing an image for a biological sample, where the image depicts cells comprising a staining pattern of a biomarker; inputting the image into a machine learning model; encoding, by the machine learning model, the image into a feature representation comprising extracted discriminative features; combining, by the machine learning model, feature and spatial information of the cells and the staining pattern of the biomarker through a sequence of up-convolutions and concatenations with the extracted discriminative features from the feature representation; and generating, by the machine learning model, two or more segmentation masks for the biomarker in the image based on the combined feature and spatial information of the cells and the staining pattern of the biomarker.

The invention relates to the technical field of medical research, in particular to a method for evaluating the invasive growth mode of hepatocellular carcinoma based on multiple pathological staining technologies, which comprises the following steps: taking liver tissue, pretreating a specimen, preparing a slice, and obtaining a specimen slice; dyeing the specimen sections by using hematoxylin-eosin dyeing, and analyzing the dyeing condition; the method comprises the following steps: respectively carrying out masson staining and specific immunohistochemical staining on a key junction region of a specimen section on the basis of a staining condition, and evaluating an invasive growth mode of hepatocellular carcinoma, so that the invasive growth mode of hepatocellular carcinoma is evaluated by carrying out multi-dimensional observation and analysis on the junction region of hepatocellular carcinoma tissue and multiple adjacent structures; three pathological technologies of basic morphology, fibrosis evaluation and specific cell localization immunohistochemical staining are combined, mutual verification is carried out, the limitation of a single technology is made up, and a new pathological basis is provided for accurately knowing the growth characteristics and invasion potential of hepatocellular carcinoma and formulating an individualized diagnosis and treatment strategy.

The invention discloses a staining cell positioning method and system for pathological diagnosis, and relates to the technical field of pathological image analysis, global positioning parameters corresponding to cell images in a reference area are obtained, and the cell images in the reference area are positioned in a layer-by-layer expansion mode from the reference to the edge by taking a cluster as a unit. And sequentially calibrating global positioning parameters of all the local observation clusters except the outermost edge region, performing joint correction and coordinate mapping on each cell image in the whole pathological section based on the initial imaging parameters and the global positioning parameters of each local observation cluster, and outputting global positioning information of all stained cells in the whole pathological section. According to the positioning method, through precise calibration of local features and imaging parameters and progressive collaborative calibration of global positioning parameters, the accuracy and reliability of cell positioning are further improved, so that more precise cell positioning information is provided for pathological diagnosis, and a clinician is assisted to make a more efficient diagnosis decision.

The application relates to a lightweight cell positioning method and system, which comprises the following steps: inputting an image to be processed into a cell positioning model; wherein the cell positioning model is a model obtained after lightweight processing, and a differential convolution and an attention module are introduced into the cell positioning model; in the front end of an initial stage, gradient information of an image is enhanced through differential convolution to obtain a feature map containing the gradient information; in each subsequent stage, multi-channel convolution is performed on the feature map, and the feature map is adaptively optimized through the attention module to obtain an optimized feature map; and cell positioning information is obtained based on the optimized feature map. According to the scheme, the attention module is introduced into the cell positioning model, the cell positioning model can pay attention to dense cell parts in a scene, lightweight processing is performed, the calculation cost of the cell positioning model is reduced, and the cell positioning model can be applied to more low-computing-power scenes.

This invention discloses a method, apparatus, device, and medium for identifying cervical exfoliated cell slides. The method includes: acquiring a first cervical exfoliated cell slide image at a first preset resolution; identifying and segmenting a single-cell image and a cell cluster image at the first preset resolution; classifying and predicting cells in the single-cell image and cell cluster image at the first preset resolution, respectively, to obtain prediction results for different categories of positive cells; acquiring a second cervical exfoliated cell slide image at a second preset resolution; identifying and segmenting a cell cluster image at the second preset resolution in the second cervical exfoliated cell slide image; and inputting the cell cluster image at the second preset resolution into a pre-trained cascaded cell classification model to obtain the target cervical exfoliated cell slide identification result. This invention enables rapid cell localization and improves the accuracy and efficiency of cervical exfoliated cell slide identification.

Provided are systems and methods for positioning cells in proximity to pores of an electroporation chip. Cell positioning in proximity to pores of an electroporation chip may be achieved using centrifugal forces to improve transfection efficiency.

The invention provides a three-dimensional space transcriptome high-throughput detection method utilizing a tissue expansion technology and a multicolor hybridization chain reaction and application. According to the method, a sample is processed by adopting a secondary embedding method, high-throughput and low-crosstalk detection of a plurality of genes is realized in a single-round reaction by utilizing a pure-color modified and double-color modified hybridization chain reaction coding strategy, and multi-round detection is realized by utilizing a DNA enzyme elution signal. In addition, the invention also provides a decoding algorithm, so that gene expression and molecular space subcellular localization characteristics thereof can be rapidly and accurately detected and analyzed. The method disclosed by the invention can be applied to thick-sheet tissues exceeding 100 microns, is simple and rapid to operate and high in sensitivity, specificity and resolution, and has important application value in the fields of target multiple detection, multi-omics analysis, molecular diagnosis and the like.

The invention discloses an atopic dermatitis key autophagy gene screening method based on transcriptomics and machine learning, and the method comprises the following steps: collecting AD transcriptome and single cell data, preprocessing, and screening differential expression genes; candidate genes are obtained through three-order screening of WGCNA analysis, autophagy gene intersection and differential gene filtering; eight machine learning algorithms are adopted, a model is screened and optimized through residual error and AUC double standards, and core genes are taken to be intersected to obtain key autophagy genes; four-dimensional verification of diagnostic performance, immune infiltration, single cell localization and causal relationship is carried out; targeted drugs are predicted and validated. The four key genes RELB, TP53INP2, TNFSF10 and PRKCB are screened out, the average AUC of a validation set reaches 0.872, four high-affinity drugs are matched, the problems that in the prior art, screening accuracy is low, validation is not systematic, and conversion performance is poor are solved, and technical support is provided for accurate diagnosis and treatment of AD.