436 results about "Expression data" patented technology

The invention provides a cell type and cell abundance identification method and system based on cross-modal training, relates to the field of image processing, and aims to solve the problems that the existing identification technology mostly depends on non-standard factors such as manual labeling position annotation information and the like, abundant morphological modes in a tissue pathological image are not fully utilized, and the identification accuracy is poor. And the identification reliability and accuracy are influenced. The method comprises the following steps: acquiring spatial transcriptomics data matched with pathological image-gene expression, and preprocessing the spatial transcriptomics data to obtain high-expression gene expression data, local image blocks, cell types and abundance tags; constructing a cross-modal joint representation learning model, and inputting high-expression gene expression data and local image blocks into the model for training; and predicting a to-be-predicted histological image based on the trained model. According to the method, the problems in the prior art are solved, the capability of predicting the cell abundance from the histological image is improved, and the spatial distribution of fine-grained cell types is fully revealed.

The invention discloses an emotion recognition method based on electroencephalogram (EEG) and expression data, which combines fusion analysis of electroencephalogram (EEG) signals and facial expression data, and provides an innovative solution for the complexity and accuracy of emotion recognition. The method comprises the following specific implementation steps: 1, finding an optimal frame in an expression video by using multi-instance learning, extracting global visual features by adopting Swin Transform, and realizing dimension reduction and balance representation of cross-modal information through a cross attention mechanism; 2, preprocessing the electroencephalogram signal by using band-pass filtering and a fast ICA algorithm, and extracting effective features by using PSD; and 3, designing a fusion module based on Transform, combining the characteristics of the two modes, and giving full play to the complementary advantage of the modes. Experimental results show that 94.85% of classification accuracy is achieved in four types of emotion classification tasks, and compared with an existing method, the accuracy is remarkably improved.

The invention discloses a drug resistance prediction method and system based on comparative learning and multi-modal fusion, and the method comprises the steps: firstly generating a molecular map and a molecular fingerprint based on the SMILES of a target drug, and extracting the molecular features of the drug through a comparative learning model constructed through combining a map attention network and a map convolution network; and then, acquiring protein expression, gene expression and metabolic expression data from the target tissue cells, extracting modal features through a deep convolutional network, a Transform encoder and a multi-dimensional attention network, and realizing adaptive fusion of the multi-modal features through a heterogeneous interactive attention mechanism. And finally, jointly inputting the fused multi-modal features and drug molecular features into a multi-layer sensor to realize high-precision prediction of the drug resistance of cells to drugs. By introducing a contrast learning and multi-modal feature fusion mechanism, the characterization capability and prediction precision of the model are effectively improved, and efficient and reliable support can be provided for drug screening and clinical decision making.

The invention discloses a causal gene regulation network inference method based on a directed graph attention network, and belongs to the technical field of graph representation learning and system biology. According to the method, an initial directed causal graph is constructed by using prior regulation and control information, expression data is used as initial features of nodes in the graph, and then two directed graph attention networks are used for respectively learning embedded expressions of genes as source nodes and target nodes in the directed causal graph; meanwhile, learning feature information of genes implied in the expression data by using a residual network; and finally, calculating the probability of the potential directed regulation relationship based on transcription factor embedding, target gene embedding and self-embedding of the gene. According to the method, the gene regulation network is learned and modeled from the perspective of the directed regulation relationship, and the inference accuracy of the potential directed regulation relationship is improved.

A system and method for processing genomic data using dynamic latent manifolds that transforms multi-modal genomic datasets into geometric representations within a curved manifold space. The system receives genomic datasets including DNA sequences, genetic variants, and expression data, then extracts biological features and assesses importance using trained neural networks. Manifold curvature values are computed based on biological significance, and genomic data is embedded as geometric structures where semantic relationships are represented through distance and curvature properties. The system generates compression pressure fields that influence processing decisions and computes optimal geodesic paths through the manifold to minimize cognitive action functionals. Adaptive compression rates are determined for different genomic regions based on geometric properties and biological importance. The manifold structure evolves through use, strengthening frequently accessed pathways while applying thermodynamic decay to unused concepts. The system supports hierarchical organization across biological scales, reversible navigation, and federated learning capabilities that enable privacy-preserving collaboration.

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 belongs to the technical field of medical pathological images, and particularly relates to a multi-instance multi-task learning pan cancer biomarker prediction method and system, and the method comprises the steps: obtaining a full-view digital pathological image and pan cancer biomarker expression data of a solid tumor patient; performing preprocessing and feature extraction based on the full-view digital pathological image to obtain a pathological feature data set; based on the pathological feature data set, inputting the pathological feature data set into a twin multi-example full convolutional network model for training to obtain pathological low-dimensional features, and calculating an attention score corresponding to each pathological feature in combination with a linear attention mechanism; and in combination with each pathologic low-dimensional feature and the corresponding attention score, calculating to obtain a pathologic depth feature, and inputting the pathologic depth feature into a multi-task classification prediction model for classification prediction to obtain a prediction result of each biomarker in the pan cancer.

The invention provides a crop whole genome prediction method and system based on machine learning, and the method comprises the steps: firstly obtaining a gene expression data set of a target crop in a plurality of growth cycles, the gene expression data set containing a plurality of gene sequence samples composed of genetic markers and phenotypic character data; performing feature extraction on the gene expression data set to obtain gene association features and growth character features, performing fusion prediction on the gene association features and the growth character features by using a preset machine learning model to generate fusion prediction features, and determining a whole genome prediction result according to the fusion prediction features. The whole genome prediction result can indicate character expression trends of crops in different environments, and finally, an adaptability optimization strategy is generated based on the whole genome prediction result and fed back to a crop cultivation system, cultivation parameter adjustment is triggered, crop cultivation precision and intelligence are achieved, and the cultivation efficiency and crop adaptability are improved.

The invention discloses a single-cell drug causal gene discovery method and system based on adversarial transfer learning, and relates to the technical field of drug sensitivity prediction.The method comprises the steps that a source domain data set and a target domain data set are obtained, an adversarial transfer model is constructed, and the adversarial transfer model is trained and optimized according to the source domain data set and the target domain data set; obtaining a single-cell drug sensitivity prediction result; modeling single-cell gene expression data, combining a k-adjacent matching algorithm and a single-cell drug sensitivity prediction result to obtain an anti-fact value, and further calculating a hybrid effect and a difference effect; and calculating the causal effect based on the hybrid effect and the difference effect, and screening out the causal gene of the single-cell drug. On one hand, the key problem of lack of drug sensitivity labeling data in single cell analysis is solved, on the other hand, the causal gene is successfully found, and an important clue is provided for deep understanding of a drug action mechanism.

The invention discloses an emotion recognition analysis method for expression data based on artificial intelligence, and relates to the technical field of image recognition, the method comprises the steps: collecting the facial contour of a target person, constructing a facial model, selecting a plurality of traction points corresponding to the facial model, and carrying out the combination according to the corresponding emotions of the traction points, and obtaining a combined point cloud of a plurality of corresponding emotions; establishing a pull line relationship between the combined point clouds of the plurality of corresponding emotions and the face model; collecting face emotional expression video image data of the target person in a preset time period, and fitting the face emotional expression video image data with the face model to obtain a fitting model; and based on the face model in the fitting model, obtaining a combined point cloud of a corresponding emotion through a pull line relationship. According to the method, the emotion recognition data can be embodied and cleared, the emotion types which do not correspond to the target person can be deleted and selected in the dynamic analysis process of the face emotion expression video image data of the target person, and the accuracy of emotion type recognition can be ensured.

The invention discloses a fragrance preference degree detection system and method based on facial micro-expressions. The system comprises a data acquisition module and a detection module, the data acquisition module is used for creating a test scene and acquiring facial micro-expressions of a subject in a test process to obtain micro-expression data; the detection module is used for constructing feature vectors according to the micro expression data; when a plurality of evaluation steps exist in the test process, respectively constructing the feature vectors according to the evaluation steps; predicting the feature vector through a trained neural network model to obtain a detection result; the method can recognize the facial micro-expression based on the evaluation video, and achieves the detection of the preference degree according to the micro-expression data in the whole evaluation process.

The invention relates to the technical field of artificial intelligence interaction, in particular to a full-life-cycle AI accompanying agent system and method.The full-life-cycle AI accompanying agent system comprises a core engine layer, a business service layer, a basic tool layer, a data layer and an interface layer, and the full-life-cycle AI accompanying agent method comprises the steps that multi-modal data, including biological signals, behavior data, voice data, expression data and environment data, of a user are collected; constructing a user digital twinborn model, and updating model parameters through a weighted learning algorithm; identifying a user cognition development stage, and dynamically adjusting interaction complexity and an expression mode; emotional connection is established, and resonance feedback is generated through multi-mode emotional recognition and memory retrieval; according to the method, interaction memory is stored, cross-stage retrieval is realized, data management is performed by adopting a hierarchical memory architecture, and accurate judgment of a cognitive stage is realized by synchronously collecting multi-dimensional data such as behavior tracks, language texts and biological signals of a user and combining a development psychology theoretical model to construct a feature association map.

The invention discloses a time sequence data alignment method and device, equipment and a medium, and relates to the technical field of artificial intelligence, the method comprises the following steps: using a feature extraction model and a pre-training language model to perform feature extraction on obtained time sequence gene expression data and text data, and further obtaining corresponding time sequence gene features and text features; and combining a target aggregation loss function and a training feature extraction model to obtain a trained feature extraction model aligned with different features so as to determine a final multi-modal model, thereby solving the problems that the requirements of time dynamic change and cross-modal semantic alignment are difficult to consider at the same time, a flexible mechanism is lacked to capture and integrate time sequence gene expression data, and the accuracy of the time sequence gene expression is improved. The technical problem that the multi-modal information fusion and alignment precision is poor is solved, and the technical effects of capturing the internal law and trend of data changing along with time, deeply mining semantic information and contextual relationships in texts, more comprehensively understanding and processing information and fully utilizing complementarity among different modal information are achieved.

A decoder includes circuitry and memory coupled to the circuitry. In operation, the circuitry: decodes expression data indicating information expressed by a person; generates a person equivalent image corresponding to the person through a neural network according to the expression data and at least one profile image of the person; and outputs the person equivalent image.

The invention discloses an old people abnormal expression recognition method based on gradient covariance analysis. The method comprises the steps of old people expression data set construction, time sequence optical flow feature-based facial expression region screening, abnormal expression enhancement loss estimation, gradient covariance-based facial expression region feature enhancement, micro-expression model training and micro-expression model testing. Aiming at the problems that the expression movement of the elderly is not obvious and the abnormal expression is easy to neglect, the facial expression key region is positioned by using the time sequence optical flow feature, the abnormal expression is introduced to enhance the loss so as to punish the leak detection condition, the back propagation gradient of the loss and the covariance thereof are calculated, and the region with larger covariance has more obvious feature change, so that the detection accuracy is improved. According to the method, facial expression region features based on gradient covariance are fully considered, key region analysis is enhanced, and the accuracy of abnormal expression recognition of the old people is effectively improved.

The invention relates to the technical field of language barrier evaluation, and discloses a deep learning-based language barrier executive intervention effect evaluation method. The method comprises the following steps: acquiring real-time voice data and facial expression data of a language barrier patient in intervention training through a multi-modal data acquisition device to form an original behavior feature set; performing acoustic feature hierarchical analysis on the voice data by adopting a time sequence feature extraction network to generate a voice time sequence feature vector; performing micro-expression dynamic capture on the expression data through a three-dimensional convolutional neural network to generate an expression state feature vector; inputting the two types of vectors into a multi-modal feature fusion layer to carry out cross-modal correlation analysis, and generating a comprehensive behavior evaluation matrix; on the basis of the matrix, an intervention effect analysis model driven by an attention mechanism is adopted, a behavior improvement degree index of the current intervention stage is calculated, accurate evaluation of the intervention effect is achieved, and support is provided for dynamic adjustment of language barrier rehabilitation intervention.

The invention discloses an interpretable cancer survival prediction method based on multi-modal data fusion, and the method comprises the following steps: carrying out the preprocessing of a full-section pathological image, and obtaining an image feature matrix; preprocessing a pathological report text corresponding to the pathological image, and constructing a text feature matrix; preprocessing the high-dimensional gene expression data of the patient to generate a plurality of survival-related gene modules and feature vectors thereof; performing dynamic fusion on the obtained multi-modal features through a self-adaptive multi-modal expert hybrid module to obtain final fusion feature representation; and training a deep learning model by using fusion feature representation in combination with a negative log-likelihood loss function and a Cox proportional risk model, and performing prognosis analysis on the cancer patient. According to the explainable cancer survival prediction method based on multi-modal data fusion, the prediction accuracy is improved, good model interpretability is achieved, and biomarkers closely related to cancer prognosis can be automatically recognized.

The invention discloses a variable polyadenylation dynamic analysis method and device. The method comprises the following steps: acquiring initial space transcriptome data and an initial space bright field image; performing first preprocessing on the initial space transcriptome data to obtain target space transcriptome data; performing second preprocessing on the initial space bright field image to obtain a target space bright field image; performing data analysis and integration processing to obtain spatial variable polyadenylation data, spatial gene expression data and spatial cell distribution dynamic data; constructing a gene expression regulation network; generating an integrated analysis result; performing space-time analysis to obtain a space-time analysis result; performing trajectory analysis to obtain a trajectory analysis result; performing disease process analysis to obtain a disease process analysis result; and generating a variable poly-adenosine acidification dynamic analysis result. According to the invention, dynamic analysis of variable polyadenylation is realized, the accuracy is improved, and multi-angle biological understanding is provided. The method can be applied to the technical field of gene analysis.

The invention relates to the technical field of biological information, in particular to a brain glioma microenvironment formation key molecular mechanism analysis method, which comprises the following steps: calling expression data to analyze a cell marker sequence to construct a segmentation interval, calculating a candidate factor expression direction to judge trend consistency, identifying expression aggregation difference to construct a split node section, and constructing a subsection; according to the method, partitions are constructed on the basis of marker expression syn-position, judgment is carried out in combination with candidate factor expression directions and marker trends, factor collaboration features are constructed according to the number of trends consistent times, and the semantic sorting information is generated by analyzing the channel change trends to generate drift scores, evaluating multi-label output stability screening key factors and analyzing literature word order positions. Identifying and expressing an aggregation and split structure, guiding a functional pathway to perform trend analysis in a scoring interval and construct a dynamic trajectory, judging label stability and empowerment according to pathway scoring difference, and determining a factor semantic position in combination with a literature word order structure to realize integrated support of regulation and control information and literature evidence.

The invention discloses a colorectal cancer prognosis model construction method based on fatty acid metabolism related genes, and belongs to the technical field of biomedicine, and the colorectal cancer prognosis model construction method comprises the following steps: S1, obtaining transcriptome data of a colorectal cancer diagnosis individual from a TCGA database; s2, performing difference analysis on fatty acid metabolism related gene expression data of the colorectal cancer tissue and the normal tissue, and screening out differentially expressed genes; s3, performing single-factor Cox regression analysis on the differentially expressed genes, and screening out genes related to colorectal cancer prognosis; according to the construction method of the colorectal cancer prognosis model based on the fatty acid metabolism related genes, provided by the invention, the tumor immunotherapy reactivity is evaluated by introducing TIDE scores, and the prior art is improved, so that the immune escape potential and the immunotherapy effect of tumor subtypes are analyzed. The prognosis of a colorectal cancer patient is effectively predicted, and a new molecular marker is provided for personalized treatment of the colorectal cancer.

The invention discloses a single cell subtype sample generation method, system, device and medium, and relates to the technical field of single cell subtype sample generation, the method comprises the following steps: obtaining a plurality of omics data; the omics data comprises a single cell genome, transcriptome sequencing expression data, clinical metadata and cell type annotation data; learning a meta-path graph of single-cell RNA sequencing data and clinical metadata through graph network data conversion, and learning representation of nodes and edges on the meta-path graph; a self-adaptive condition graph diffusion convolution model ACGDC model is constructed; inputting representations of nodes and edges into an adaptive condition graph diffusion convolution model through a graph network data conversion module, and sampling new single cell sample seeds in a Gaussian distribution space; decoding the single cell sample seeds to generate a new single cell subtype sample through a condition control sample generation method; according to the method, various high-quality single cell subtype samples can be efficiently generated.

The invention discloses a miRNA and disease relation prediction system and method based on causal feature selection. According to the system, the accuracy of miRNA and disease relation prediction is improved through a plurality of modules such as data acquisition, negative sample selection, feature selection and causal analysis, model training and evaluation and the like. The data acquisition module is used for acquiring miRNA expression data and disease characteristics from a biomedical database; the negative sample selection module is used for grouping unknown miRNA-disease relationships through k-means clustering and randomly selecting negative samples; the feature selection module adopts a causal feature selection algorithm to construct a Markov blanket so as to screen out miRNA features directly related to disease states, and redundancy is reduced; the model training module uses a single machine learning algorithm for training, and optimizes the model performance through cross validation; and finally, the evaluation module evaluates the model effect through indexes such as AUROC and AUPR. According to the method, the accuracy of miRNA and disease relation prediction is remarkably improved, and important support is provided for medical research.

The invention discloses a schizophrenia risk structure variation identification and function evaluation method based on three-generation sequencing, and relates to the field of molecular biology, whole genome sequencing is performed on peripheral blood DNA of a patient through three-generation sequencing, multi-tool joint detection is adopted, multi-sample results are integrated, and a high-confidence SV data set is generated; through cross-queue comparison, the patient specific SV is screened, and the high-risk potential pathogenic SV is identified in combination with an SV priority ordering tool SVJudge. By combining transcription factor binding analysis, SCZ drug target data and histocyte specific expression data, the influence of SV on gene regulation is evaluated, and the potential action mechanism of SV in SCZ is analyzed. The SCZ risk gene is screened based on SVJudge scoring and patient carrying conditions, the genetic risk and pathogenic mechanism of the SCZ are analyzed and verified through pathway enrichment, a protein interaction network and a functional module, and a new technical means and theoretical basis are provided for genetic research of the SCZ.

The invention provides a gene module analysis method and device, equipment and a storage medium, and relates to the technical field of space transcriptomics. The method comprises the steps of obtaining space-time group chip expression data, performing linearization processing, and performing sliding window cutting to obtain a plurality of window units arranged according to a space sequence; calculating gene function activeness and constructing a matrix; clustering and grouping are carried out to obtain window groups; performing difference analysis screening on the window groups to obtain a difference expression gene set; and performing gene module analysis to obtain a functional gene module. According to the method, through an integrated processing flow of structure linearization, sliding window cutting, activeness quantification, clustering analysis and module identification, fine extraction and function reconstruction of spatial expression information in the curled tissue are realized under the condition that an additional algorithm or external data is not introduced; and the practicability and research value of the spatial omics data in a complex organization structure are improved.

The invention provides a campus emotion risk individual assessment method and system based on expression recognition, and the method comprises the steps: collecting monitoring image data for recognition, and obtaining recognized individual expression data and related information data; performing processing according to the individual expression data to obtain group emotion data; correcting the individual expression data according to the group emotion data to obtain individual negative emotion data; and evaluating an emotion risk target individual according to historical statistics of the individual negative emotion data. According to the method, group emotional abnormity can be accurately eliminated in a group scene, the individual emotional risk degree is objectively judged, and the accuracy of identifying the campus emotional risk target is improved.

The invention belongs to the technical field of emotion evaluation. The emotion evaluation method comprises the steps that a video frame of a played video in a preset time period and an expression frame of micro-expression change of a user when the user watches the video are obtained, and the expression frame represents the facial expression of the user recorded by a frame of image; performing corresponding matching on the video frame and the expression frame to obtain to-be-analyzed data; inputting the to-be-analyzed data into a target convolutional neural network to obtain a micro-expression data analysis result; and obtaining an emotion evaluation result of the user according to the micro-expression data analysis result. Through the method, the related characteristics of the expression change are analyzed to summarize the emotional state of the testee when the testee receives the test, and a reasonable reference analysis material is provided for related services of psychological assessment.

The invention provides a disease marker epitope prediction and antibody screening method, which belongs to the technical field of disease markers, and comprises the following steps: firstly, establishing a training data set containing a known antigen-antibody compound structure and disease tissue expression data; and obtaining target protein sequence information through liquid chromatography-mass spectrometry analysis and carrying out sequence comparison. And then a deep convolutional neural network is utilized to extract sequence features, and surface exposure sites are identified by combining secondary structure prediction and solvent accessibility analysis. After the features are integrated with sequence evolution conservative properties, a prediction model is constructed by using a random forest classifier. The method comprises the following steps: carrying out molecular dynamics simulation on a prediction result, screening first 10% of candidate sequences through a comprehensive scoring function and K-means clustering, and finally determining an antigen epitope sequence with the strongest binding activity through verification of an antigen chip and a fluorescence labeled antibody system, so that the technical problem that specific antigen epitopes are difficult to accurately predict and recognize in the prior art is solved.

The invention relates to the technical field of biomedicine, in particular to a method for constructing a plasma ctDNA organ distribution characteristic spectrum of advanced colorectal cancer. The method comprises the following steps: collecting a peripheral blood sample at multiple time points, separating plasma by adopting a double-centrifugal method, and extracting circulating tumor DNA (Deoxyribose Nucleic Acid); carrying out whole exome sequencing based on ctDNA to obtain genome variation information and calculating variation allele frequency, and synchronously detecting the expression quantity of immune-related proteins by adopting an Olink proteomics technology; integrating the genome data, the protein expression data and the clinical pathological features, and constructing a multi-dimensional feature data matrix; and taking the organ metastasis condition confirmed by iconography as a supervision label, training a model by applying a machine learning algorithm, screening key prediction factors, constructing a quantitative prediction model, and finally generating a visual organ metastasis tendency prediction map. According to the method, early and accurate prediction of the advanced colorectal cancer organ metastasis tendency is realized through multi-omics data collaborative analysis and machine learning modeling.

Provided is a method for screening myocardial therapeutic targets for ischemic heart failure by using single-cell sequencing, which method comprises the following steps: S1, sample preparation; S2, construction of a single-cell expression matrix; S3, cell quality control; S4, cell type annotation; S5, cell communication analysis; and S6, co-expression network analysis. The provided method for screening myocardial therapeutic targets for ischemic heart failure by using single-cell sequencing comprises performing single-cell sequencing on hearts of healthy mice and IHF mice, screening for cell types with significant differences in cardiac transcriptional profiles of the healthy mice and IHF mice, then exploring interaction characteristics of various types of cells in malignant fibrotic IHF hearts, revealing potential regulatory modules and pathways related to malignant myocardial fibrosis in single-cell expression data of IHF hearts, and performing screening to obtain Pdgfb and Tnfsf12 genes which can be used as therapeutic targets for treating myocardial fibrosis in ischemic heart failure.

The invention discloses an RNA (Ribonucleic Acid) binding protein enrichment analysis method based on single cell expression profile data, which comprises the following steps of: writing an interactive online Web application program by using Shiny, carrying a data visualization tool, and using an RBP (Reactive Binding Protein)-gene database as a database; the method is specially designed for single cell data, different single cell data can be integrated for enrichment analysis, and expression profiles and RBP dynamic changes in single cells can be effectively captured and analyzed; rBP enrichment analysis is customized for single cell data, a single group and multiple groups of single cell expression data are preprocessed, including normalization processing, and a statistical model is used to evaluate enrichment significance at each time point, so that the analysis accuracy and biological correlation are improved; a dynamic visualization tool is provided, the dynamic visualization tool comprises a customizable network diagram, an interactive bar diagram and detailed table display, and a user can adjust a plurality of parameters of a view according to needs and directly download images and data from an interface.