56 results about "Gene Feature" patented technology

The invention is applicable to the technical field of clinical medicine, provides a clinical multi-modal cancer drug response prediction method based on feature reconstruction, constructs a clinical multi-modal model for drug response prediction of diffuse large B-cell lymphoma, and aims to predict the drug response of diffuse large B-cell lymphoma by integrating gene sequencing and clinical multi-modal data. And accurate drug reaction prediction is realized. The model adopts an end-to-end multi-stage processing flow: firstly, extracting gene features through TransP-Net, and processing multi-modal clinical data by using a clinical information encoder; then, pseudo-gene features are generated through a clinical-genome filling module to deal with the data missing problem; and finally, multi-modal deep fusion is realized through a clinical information decoder, and a prediction result is output. According to the method, data characteristics and working processes in a real clinical environment are fully considered, two conditions of complete gene data and missing gene data can be processed at the same time, and the method has a good clinical transformation prospect and application value.

Described herein are gene features that provide prognosis, diagnosis, treatment and molecular subtype classification of cancer by genomic and epigenomic profiling, including immune checkpoint regulators such as Programmed Death Ligand 1 (PDL-1). Using the methods and compositions described herein, specific and sensitive detection of biomarkers of interest is provided. Such biomarkers indicate disease pathogenesis, which provides opportunities for selection of treatments, including treatment regimens intended to overcome tolerance mechanisms.

The invention relates to the technical field of medical treatment, and discloses a lung cancer personalized treatment scheme recommendation method and system and a storage medium. The method comprises the following steps: acquiring clinical and molecular indexes of a patient, and constructing a simplified feature set; distributing weights for treatment targets according to the simplified feature set, constructing and optimizing a scheme evaluation matrix, and generating a preliminary scheme sorting list; through threshold screening and patient feature matching degree verification, a verified scheme set is obtained; the schemes are classified based on gene mutation and driver gene features, and classified optimization scheme subsets are obtained; constructing an interaction model to analyze interaction influence of toxic and side effects and life quality on curative effects, and dynamically adjusting scheme scores; and if the score is lower than a threshold value, triggering iterative optimization, obtaining a scheme list after iteration, and further determining an optimal treatment scheme according to treatment collaboration and target balance. According to the method, intelligent and closed-loop optimization from multi-source data to personalized treatment decision is realized, and the personalization and accuracy of a treatment scheme are improved.

The invention relates to the field of medicine and the field of machine learning, in particular to a gene feature recognition method based on comparative learning and related equipment thereof. The method comprises the following steps: firstly, acquiring a target gene feature vector, and inputting the target gene feature vector into a pre-trained ovarian cancer gene feature recognition model, so that the ovarian cancer gene feature recognition model outputs a corresponding gene feature recognition result; wherein the ovarian cancer gene feature recognition model is obtained through training by the following steps: acquiring a plurality of sample gene data; performing characterization processing on each sample gene data to obtain a corresponding sample feature vector; performing feature space mapping on the plurality of sample feature vectors to obtain a remapped feature space; constructing a decision forest model based on the remapping feature space; and performing optimization iteration on the model parameters of the decision forest model to obtain the ovarian cancer gene feature recognition model. According to the invention, the accuracy of ovarian cancer gene feature recognition can be improved.

The application provides a HBV inhibitor screening method based on a molecule-gene interaction constraint graph convolution network. In view of the limitation of a traditional drug discovery method in processing complex biological data, the application is based on a constructed compound library verified by anti-HBV in-vitro activity, a plurality of gene targets associated with the corresponding compound and an interaction network thereof, a graph data processing capacity of a graph convolution network model is used, and a molecule-gene interaction constraint graph convolution network model is constructed. The model combines an interaction matrix of a target protein corresponding to the gene, a gene feature matrix and a compound activity label, and effectively predicts the biological activity category of the compound. The specific steps include data processing, graph data generation, graph convolution network model training, hyperparameter optimization and model evaluation. The model parameter AUC value is 0.97, and the model effect is good. The application provides a new path and idea for virtual screening of anti-HBV drugs, and has potential application value.

The invention belongs to the technical field of cell data processing, and relates to a single cell gene characterization system and method based on deep learning. The system comprises a gene information input module, a data processing module, a context sensing interpolation module, a gene feature fusion module, a deep representation learning and joint optimization module and a cell typing and differentiation track inference module. The input module integrates a data source; the processing module preprocesses and enhances the original expression matrix; the interpolation module performs weighted interpolation by using a conditional Gaussian graph model; the gene feature fusion module generates a gene module activity matrix through 1 * 1 convolution and the like; the fusion module fuses the sample meta-information with the active matrix, the sequencing depth and the gene feature vector; the depth representation module captures high-dimensional dependence through a multi-layer Transform network, and generates cell high-order potential representation; the typing module outputs a cell population division and differentiation trajectory based on the deduced pseudo-time trajectory. The method has the beneficial effects that cell expression characteristics are recovered under high sparseness and noise, and a new way is provided for cell type identification and the like.

The invention relates to the field of biological detection, and discloses a method for analyzing prognosis gene characteristics of glioma based on machine learning. The method comprises the following steps: acquiring prognosis gene expression data and pathological variable data corresponding to a glioma evaluation sample; determining a prognostic gene score of the prognostic gene expression data based on a pre-constructed prognostic scoring model; and analyzing the prognosis risk of the neuroglioma evaluation sample according to the prognosis gene score and the pathological variable data to obtain a prognosis risk analysis result. The problems that an existing neuroglioma prognosis evaluation method is insufficient in accuracy and lacks a quantitative analysis model are solved.

A method for identifying cell subpopulations associated with disease phenotypes, belonging to the biomedical field. To identify cell subpopulations associated with disease phenotypes, this invention collects single-cell RNA sequencing data of the disease to obtain a single-cell expression matrix, collects the bulk expression matrix of the disease and corresponding phenotypic tags, and downloads human protein-protein interaction data to construct a protein-protein interaction network; extracts gene signature features of cells and samples and maps them to the protein-protein interaction network to form corresponding cell modules and sample modules; calculates the distance between each cell module and each sample module, and determines a set of multiple sample modules as the sample module set of the disease phenotype; calculates the distance between cell modules and the sample module set of the disease phenotype; creates a background distance distribution to evaluate the statistical significance of the distance between cell modules and the sample module set of the disease phenotype, and identifies cells whose distance to the sample module set of the disease phenotype is significantly smaller than the background distance distribution.

The application provides a carbon source intelligent screening method and device for strengthening microbial degradation of emerging pollutants, and belongs to the technical field of pollution control. The method adopts a carbon source screening model constructed and trained based on coupling of a large language model and machine learning, intelligently screens based on gene characteristics of microorganisms in a microbial community and candidate carbon source characteristics to obtain an advantage specific carbon source of functional microorganisms, and can screen the advantage specific carbon source for promoting growth of the functional microorganisms, so that the functional microorganisms are directionally enriched in the microbial community, the in-situ emerging pollutant degradation capacity of the microbial community is improved, and the treatment effect of the emerging pollutants is further improved.

Provided herein are compositions, systems, and methods for ranking cancer drugs for treating a subject's cancer cells, where a plurality of gene signatures (each with a plurality of gene signature genes) with associated cancer drugs are processed with raw mRNA expression levels for genes in the sample. The processing (e.g., by computer) can comprise: i) applying a normalization algorithm to generate normalized mRNA expression values for signature genes, ii) applying a median finding algorithm to the normalized mRNA expression values in each of the plurality of drug gene signatures to generate a plurality of median values, and iii) applying a ranking algorithm such that the median values are ranked from highest value to lowest value (or vice versa), with the highest value being associated with the most effective cancer drug, or most effective combination of two cancer drugs.

The application relates to a single cell recognition method and a storage medium, wherein the single cell recognition method comprises the following steps: obtaining single cell original gene expression data, a gene label control table and pre-training prior gene feature data; obtaining correction data based on the single cell original gene expression data, generating a cell supervision label, combining the gene label control table to construct a single cell gene set activity matrix; generating a training data set based on the above matrix, label, prior data and correction data, inputting the training data set into a classifier and a reconstruction module of an initial cell deep learning network, obtaining a classification result and a constructed activity matrix; obtaining a total loss by weightedly combining a label loss and a reconstruction loss, iteratively training a gradient in a reverse direction, and generating a cell deep learning network; inputting the correction data into the network, inferring a cell fusion embedding result, and further obtaining a single cell recognition result. Through the application, the problem of low single cell recognition accuracy is solved.

The invention provides a gene feature selection method. Relates to the technical field of data mining. The method comprises the following steps: taking high-dimensional medical gene expression data to be analyzed as a search space; generating a population in the search space, and constructing an elite archive for storing a Pareto optimal solution; storing the Pareto optimal solution of the current population into an elite file; based on the difference between the occurrence frequency of the gene feature combination in the elite archive and the occurrence frequency of the gene feature combination in the current population as an information gain, selecting a high-quality gene feature combination in the elite archive to replace a non-high-quality gene feature combination in the current population so as to iteratively update the current population; when the number of times of continuous non-updating of the elite archive exceeds a stagnation threshold value, performing local redundant gene feature elimination operation and local gene feature replacement operation on the elite archive; judging whether a preset termination condition is met or not, and if not, returning to update; and if so, outputting the optimal gene feature combination in the elite archive. And gene feature selection with low gene number and high precision can be realized.

A computer-implemented method for calculating an individual's tailored Polygenic Risk Score is based on known genetic information. A dataset is provided related to a reference panel including genetically characterized individuals with known disease status and diversified global ancestry. An individual-specific genetic reference group of individuals is selected as a subset from the reference panel. Genetic distances of the individual from each of the reference panel individuals are computed; each being the individual's genetic distance from a respective reference panel individual. Individuals of the individual-specific genetic reference group based on the individual's computed genetic distances are selected. The individual's basic Polygenic Risk Score for a disease is calculated to provide the individual's disease risk prediction. An ancestry-based background PRS contribution is determined. The ancestry contribution is removed from the individual's calculated basic Polygenic Risk Score to obtain the individual's tailored Polygenic Risk Score and provide a disease risk prediction.

The invention provides a method for predicting spatial gene expression, electronic equipment and a medium. The method comprises the following steps: acquiring a to-be-detected pathological histological image; extracting a first visual feature of the to-be-detected pathological histological image; converting the first visual feature into a first visual feature vector based on a preset projection model; based on the first visual feature vector, searching in a preset gene feature library according to a preset matching model to obtain a first gene feature vector matched with the first visual feature vector; and obtaining space gene expression of the to-be-detected pathological histological image based on the first gene feature vector.

The application relates to the technical field of biological information data analysis, and discloses an intelligent identification method and system for rapid genotyping diagnosis of gene polymorphism. The method comprises the following steps: acquiring multi-source gene sequencing data and preprocessing to generate a structured gene feature set; constructing a multi-modal data fusion model, defining a multi-dimensional analysis space of sequence axes, function axes, variation axes and environment correlation axes; performing genotyping identification simulation based on the model to generate a preliminary genotyping strategy; and dynamically optimizing the preliminary genotyping strategy by using a self-adaptive feature selection algorithm to generate a multi-source collaborative genotyping strategy. By means of multi-modal data fusion and self-adaptive optimization, the application improves the efficiency and accuracy of genotyping diagnosis of gene polymorphism, can adapt to different populations and environments, optimizes resource utilization and reduces costs, and has important application value in the fields of biomedical research and disease diagnosis.

The invention provides a spatial transcriptome data clustering method based on modal conflict modulation, and relates to the technical field of biological information, and the method comprises the steps: carrying out the preprocessing of original spatial transcriptome data, and constructing a spatial diagram and a gene diagram; performing cross propagation learning of gene features and spatial features by using a graph convolutional network and taking the gene expression feature matrix, the spatial graph and the gene graph as input; in the training process, random masking is carried out on the space diagram, the gene is embedded and projected to a unit hypersphere, the reconstruction probability of masked connection is calculated based on the projected features, and a reconstruction loss function is constructed by using Jensen-Shannon divergence; and combining the reconstruction loss, the gene expression reconstruction loss and the spatial feature reconstruction loss to construct a total loss function training graph convolutional network. According to the technical scheme, the problem that the node distinguishing capability in the space transcriptomics data is weak is solved.

This invention relates to the field of medical data processing technology, and in particular to a method and apparatus for predicting the survival of cancer patients. The method includes: acquiring molecular pathological examination results, histopathological examination results, and radiological imaging results of a target cancer patient; extracting features from the molecular pathological examination results, histopathological examination results, and radiological imaging results to obtain gene features, pathological image features, and MRI image features; fusing and stitching the gene features, pathological image features, and MRI image features to obtain a final fused feature; and predicting the actual survival range of the target cancer patient based on the final fused feature. This solves the problems of existing cancer survival prediction methods that often rely on single-modal information such as pathological images or radiological images, resulting in limited predictive performance and generalization ability, and making it difficult to provide sufficient and comprehensive reference for doctors and patients.

The invention discloses a curative effect prediction marker screening method, a curative effect prediction method and device, a storage medium and a program product. The curative effect prediction marker screening method comprises the following steps: preprocessing sample data; screening out differential expression genes related to treatment response from the preprocessed sample data; constructing a classifier model according to the gene features of the differential expression genes; and evaluating the performance of the constructed classifier model, and selecting a curative effect prediction marker according to an evaluation result.

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

The present application relates to the technical field of artificial intelligence and deep learning, in particular to a tomato salt tolerance prediction method and system based on deep learning, specifically as follows: obtaining a tomato salt tolerance genome, inputting it into a tomato salt tolerance prediction system based on deep learning for detection, sequentially passing through a salt-tolerant small sample gene recombination module, an epigenetic gene multi-granularity mining module, a heterogeneous salt-tolerant gene feature integration module, a salt-tolerant feature point fusion module and a tomato salt tolerance gene prediction module, and calculating the probability of having relevant tomato salt tolerance genes in the input tomato salt tolerance genome. The present application improves the prediction accuracy and generalization ability of salt tolerance genes under complex genetic background, and provides an intelligent prediction method for tomato salt-tolerant variety breeding.

The invention relates to a single cell data enhanced representation method and device and a storage medium. The method comprises the following steps: acquiring an original counting matrix and a gene module data set of single cell gene expression; performing gene feature conversion based on the original counting matrix to obtain a gene feature matrix; determining a cell module activity matrix based on the gene feature matrix, the original counting matrix and the gene module data set; processing the gene feature matrix through a gene encoder to generate a gene implicit vector, and processing the cell module activity matrix through a module encoder to generate a module implicit vector; performing interactive fusion by taking the gene implicit vector and the module implicit vector as input of a cross attention fusion model and taking the weighted sum of the first loss item and the second loss item as an optimization target to obtain an output fusion implicit vector; and projecting the fusion implicit vector to a target embedding space to generate single cell enhanced representation. Implicit vectors are integrated through a cross attention fusion model, and the interpretability of unicellular organisms is improved.

This gene set analysis device is provided with a relationship estimation unit 14 for identifying a biological phenomenon that is estimated to be related to a gene set to be analyzed, wherein the estimation is performed on the basis of the similarity between a gene set feature vector that is formed by integrating constituent gene feature vectors respectively related to a plurality of genes constituting the gene set and each of phenomenon feature vectors that are feature vectors of various biological phenomena (e.g., GO term). The gene set analysis device is configured such that a biological phenomenon that is estimated to be related to the gene set to be analyzed can be identified by estimating the relationship between the gene set and the biological phenomenon on the basis of the similarity with the feature vectors even when a gene of which the relationship with the biological phenomenon is unknown is included in the gene set regardless of whether the gene set is in a large scale or in a small scale. In addition, the gene set analysis device is also configured such that a biological phenomenon that is significant for the gene set can be identified by performing the vector analysis in consideration of information on all of genes constituting the gene set of interest.

Described herein are gene signatures providing prognostic, diagnostic, treatment and molecular subtype classifications of cancers through genomic and epigenomic profiling, including immune checkpoint regulators such as programmed death ligand 1 (PDL-1). Using methods and compositions described herein, specific and sensitive detection of biomarkers of interest is provided. Such biomarkers are indicative of disease pathogenesis, which provides opportunity for selection of treatment, including treatment regimes directed at overcoming resistance mechanisms.

This invention proposes a pre-trained paradigm for genome characterization and gene regulation analysis, including: acquiring gene expression, genome sequence, and regulatory factor expression data from biological samples; standardizing gene expression data; segmenting and encoding genome sequence and regulatory factor expression data; using masked self-supervised learning to encode two types of sequence feature representations separately through a sequence coding model; aligning and fusing features using an attention fusion mechanism to generate cell type-specific genome region representations, predicting gene expression levels, and optimizing model parameters; and performing gene regulatory network inference or genome function prediction based on the optimized model's genome region representations to obtain gene regulatory relationship analysis results. This invention achieves precise fusion of gene features and accurate prediction of expression levels, improving the accuracy of gene regulatory relationship analysis and providing an efficient method for genome function research.

The invention discloses a monkey pox virus triple fluorescence PCR nucleic acid detection kit, a detection method and application. The kit adopts a single-tube triple detection system and comprises (a) a monkey pox virus universal detection primer probe group and a targeted F3L and G2R gene conserved region; (b) a Clade Ib subtype detection primer probe group which targets D14L and A36R gene deletion feature regions; (c) a Clade II subtype detection primer probe group, which is used for targeting J2R and D18L gene feature sequences; and (d) an internal standard detection group which targets the human RNase P gene. By optimizing the concentrations of the primers and probes and four-channel fluorescent labels (FAM universal type, VI-Clade Ib, ROX-Clade II and CY5 internal label), single-tube synchronous detection is realized. The leak detection risk is reduced by adopting a double-target redundancy design, virus screening and subtype identification (Clade Ib / II) can be completed through single detection, and an internal standard system monitors the quality of a sample in the whole process. The kit is suitable for clinical early diagnosis, epidemic prevention and control and strain traceability.

The application provides a gene set and kit for evaluating the curative effect after allogeneic hematopoietic stem cell transplantation of hematopathy, and belongs to the field of gene detection. The application develops a new post-transplantation curative effect evaluation panel detection design method. The panel comprises: 1. single nucleotide polymorphism (SNP) sites characteristic of individual genetic characteristics, which can be used for graft implantation evaluation; 2. high-frequency mutation sites of blood tumor hotspot genes, which can be used for MRD detection and disease state evaluation; and 3. HLA gene characteristic SNP sites on the short arm of human chromosome 6, which can be used for HLA gene typing, combined with the state of graft implantation, to analyze the occurrence of HLA-loss. The technical scheme of the application can solve the above-mentioned multiple contents of post-transplantation curative effect evaluation at one time, is more accurate and sensitive than the previous detection method, and can greatly reduce the detection cost and shorten the clinical report time.

The application discloses a caries risk assessment method, device and storage medium, which are applied to the technical field of oral image processing, and the method acquires multi-source data corresponding to a caries sample to be evaluated, wherein the multi-source data at least includes oral image data and gene data; risk alleles of multiple gene sites related to caries susceptibility; the gene data is numerically encoded to obtain gene features; the oral image data is subjected to feature extraction to obtain oral image features; the gene features and the oral image features are subjected to feature fusion to obtain fusion features; and the fusion features are subjected to caries risk assessment to obtain a caries risk assessment result of the caries sample to be evaluated, so that the accuracy of caries risk assessment can be improved.

The invention relates to a single cell identification method and a storage medium, and the method comprises the steps: obtaining single cell original gene expression data, a gene tag comparison table and pre-training prior gene feature data; correction data is obtained based on single-cell original gene expression data, cell supervision tags are generated, and a single-cell gene set activity matrix is constructed in combination with a gene tag comparison table; based on the matrix, the label, the prior data and the correction data, generating a training data set, and inputting the training data set into a classifier and a reconstruction module of the initial cell deep learning network to obtain a classification result and a structure activity matrix; carrying out weighted combination on label loss and reconstruction loss to obtain total loss, and carrying out reverse conduction gradient iterative training to generate a cell deep learning network; and inputting correction data into the network, and reasoning to obtain a cell fusion embedding result so as to obtain a single cell identification result. According to the invention, the problem of low single cell identification accuracy is solved.

The invention relates to the field of bioinformatics, and discloses a space transcriptome gene expression prediction method and system, a terminal and a storage medium, and the method comprises the steps: segmenting a histological image into small blocks according to capture sites, obtaining the image, gene expression and position coordinates of each small block, and respectively learning gene features and image features, designing a loss function to capture potential correlation between the two modals, completing alignment between the two modals, and performing weighted aggregation on gene expressions of a plurality of gene features most similar to the image features to obtain corresponding predicted gene expressions. According to the method, the potential relationship between the histological image and the gene expression is captured, and the gene expression is predicted through the histological image by utilizing the potential relationship, so that the gene prediction accuracy is remarkably improved.

This invention relates to the field of artificial intelligence technology and discloses a disease prediction system for primary Sjögren's syndrome based on gene polymorphism. The system consists of a gene data acquisition module, a feature processing server, an artificial intelligence prediction server, and medical and follow-up terminals. By performing quality control, functional site screening, and three-valued dose encoding on genotype data, structured gene features are constructed, and multimodal input features are generated by combining clinical phenotype and environmental exposure information. The system employs a multimodal counterfactual interpretation-Transformer model to quantify feature contributions, locate perturbation intervals, and perform counterfactual optimization inference, thereby outputting risk prediction values ​​and risk levels. This system effectively improves the accuracy and interpretability of gene polymorphism risk prediction, enables traceable and transparent risk assessment, and supports population risk identification and individualized prevention management.