380 results about "Omics data" patented technology

A spatial omics multi-modal fusion method under a single cell level comprises the following steps: extracting spatial morphological characteristics of differential expression genes and cell nucleuses from spatial transcriptome data, single cell sequencing data and histological images, and realizing field adaptation among different platforms by using a conditional variation auto-encoder. And based on a probability inference model, fusing spatial transcriptome expression, unicellular omics and morphological characteristics, and jointly inferring the type and gene expression level of each cell. A spatial cell network is constructed through a graph attention mechanism, and spatial diffusion and recognition of cell types in a full slice range are realized. In combination with a multi-omics enhancement module, undetected gene and protein expression is completed based on expression similarity, and prediction consistency is improved through spatial correction. According to the method, high-resolution reconstruction of single-cell multi-omics information in a three-dimensional space is realized, the information coverage and spatial resolution of spatial omics data are improved, and an efficient and low-cost solution is provided for spatial biology and precise medical research.

The invention discloses a metabonomics data batch correction method based on multi-kernel learning, and belongs to the cross technical field of bioinformatics and analytical chemistry. According to the method, the multi-kernel learning technology is utilized, the advantages of different kernel functions are fused in a self-adaptive mode, a model conforming to data reality is constructed, complex drift characteristics of metabolite signals are accurately captured, and efficient and accurate normalization processing of metabonomics data is achieved. Compared with traditional data standardization methods such as SVR and LOESS, the method has the advantages that the performance is excellent in the aspect of reducing the metabolite peak intensity variability, and the data stability is remarkably improved. In the subsequent multivariate statistical analysis, the classification accuracy is greatly improved, the comparability among different batches of data is also remarkably enhanced, reliable data support can be provided for discovery of disease biomarkers, and the method plays a key role in large-scale metabonomics research.

The invention discloses a colorectal cancer drug relocation method based on multi-omics integration. The system comprises a multi-omics data acquisition and preprocessing module, a tumor microenvironment analysis module, a specific disease network construction module, a multi-dimensional drug relocation module and a result evaluation module. And the tumor microenvironment analysis module comprises cell heterogeneity identification, cell map construction, cell annotation and tumor cell subset annotation. The specific disease network construction module comprises tumor feature expression program extraction, expression program screening, meta-program construction, clinical related meta-program recognition and specific disease protein interaction network construction. And the multi-dimensional drug relocation module comprises a module for identifying diseases by using a random walk algorithm, carrying out drug screening based on disturbance data, carrying out drug screening based on network proximity and carrying out comprehensive drug relocation. From the perspective of single cell data, element programs related to colorectal cancer survival are excavated, corresponding modules are designed, and the efficiency and precision of colorectal cancer targeted drug screening are improved.

The invention discloses a dynamic identification method for unusual cells before young tumors based on multi-omics data, and relates to the technical field of cell unusual identification. A dynamic correlation intensity matrix and a cumulative effect contribution matrix are constructed, a differentiation screening strategy is implemented according to individual response characteristics, and the unusual cells before young tumors are identified. And the abnormal dynamic high-fidelity identification of the young tumor pre-cells is realized. And aiming at individuals of different response types, an instant path, a long-term path or a double-path fusion strategy is respectively adopted, key behavior data is accurately screened, and the input quality is improved. According to the method, redundant interference is effectively eliminated, the simulation capability of the model on key processes such as immunosuppression and DNA damage accumulation is enhanced, the biological rationality and prediction precision of a cell state evolution sequence are remarkably improved, and the problems of model response lag, low calculation efficiency and output distortion caused by data noise in the prior art are solved; and a reliable technical support is provided for early warning and individualized intervention of precancerous lesions.

The invention discloses a cerebral apoplexy high risk group positioning evaluation system based on multi-modal data, and relates to the technical field of medical information science, the cerebral apoplexy high risk group positioning evaluation system comprises a cerebral apoplexy prevention and control management platform, and the cerebral apoplexy prevention and control management platform is in communication connection with the following modules: a multi-modal data acquisition and integration module, the multi-modal data collection module is used for collecting multi-modal data related to cerebral apoplexy from multiple channels and carrying out preprocessing operation on the collected multi-modal data. By integrating clinical data, image data, omics data and terminal health data, multi-dimensional information related to the cerebral apoplexy can be comprehensively captured, particularly, cerebral vessel digital twin is utilized to simulate hemodynamic characteristics, a plurality of data sources are fused in combination with a graph neural network, high-risk groups can be recognized more accurately, and the accuracy of cerebral apoplexy recognition is improved. The accuracy and reliability of risk prediction are remarkably improved, the problem of missing detection caused by dependence on a single data source in a traditional method is solved, and more powerful support is provided for early intervention.

The invention discloses an AI-based gene data analysis system. The system comprises a plurality of omics data matrixes; local association pattern mining is performed on the multi-omics data matrix through a 1D-CNN one-dimensional convolutional neural network, a topological structure of a gene network is identified through continuous coherence analysis, dynamic weights are allocated to sequence features and a topological feature matrix by using a dynamic attention mechanism, and weighted multi-scale feature vectors are output; establishing a multi-modal fusion model based on a Transform architecture to fuse the multi-scale feature vectors, performing fine adjustment on the adaptive disease data set by using the general genome feature of a pre-training model, and outputting a fused feature vector; and inputting the fusion feature vector into an MLP multilayer perceptron for disease risk prediction, generating a disease risk prediction index in combination with an SHAP algorithm, and generating an auxiliary decision scheme according to the prediction index. And the accuracy and generalization ability of disease risk classification are effectively improved.

The invention discloses a dual-channel fusion cancer drug response prediction method, and belongs to the technical field of biological information. The method aims at solving the problems that an existing prediction method is only limited to intra-modal feature extraction, and a complex nonlinear cooperative relation between a drug and cancer cells is difficult to capture. Multi-omics data, drug molecular structure information and cancer cell line drug reaction data are integrated from databases such as CCLE, GDSC and PubChem, and unified input features are formed through standardization and feature construction. Introducing a hierarchical double-attention conversion network into the first channel to carry out characterization learning on the multi-modal features of the drug and the cell line, and constructing a high-order attention neighbor interaction graph convolutional network in the second channel to capture graph structure information of cancer drug response. And carrying out adaptive weighting on output results of the two channels by using a PPO-based fusion module so as to realize a dynamic optimal decision. And finally, generating a drug sensitivity prediction result of the cancer cell line through a classification predictor.

The invention discloses a diabetes cognitive impairment method based on metabonomics analysis and prediction, and relates to the technical field of biological information, and the method comprises the following steps: S1, obtaining metabonomics data and immunomics data from a peripheral blood sample of a diabetic patient, extracting relevant time sequence data aiming at glucose metabolism, and calculating the glucose metabolism related time sequence data; processing the sequence data by adopting a time sequence analysis algorithm to obtain time sequence change characteristics; s2, constructing a cross-omics interaction network according to time sequence change characteristics, integrating an incidence relation between metabolite concentration and immune factor expression, and setting a dynamic interaction mode; according to the diabetes cognitive impairment method based on metabonomics analysis and prediction, through multi-omics data integration and dynamic network analysis, the precision and reliability of diabetes cognitive impairment mechanism analysis are remarkably improved, and a theoretical basis is provided for precise intervention.

The invention discloses a multi-omics cancer subtype recognition method, system and device based on density sensing cluster structure guide contrast learning and a medium, and belongs to the technical field of bioinformatics and artificial intelligence crossing. The method comprises the following steps: acquiring and preprocessing multi-omics data; constructing an omics specific auto-encoder and learning potential representation; constructing a density sensing cluster block in the potential space; constructing a cross-omics positive and negative sample pair based on cluster block sample overlapping; difficult negative sample mining; constructing a cluster block level cross-omics contrast learning target, and training and updating; a self-supervised soft refinement mechanism is introduced to dynamically enhance a cluster structure; and carrying out multi-loss joint optimization and model iteration training. According to the method, the robustness and the stability of a cancer subtype recognition result can be improved, high-dimensional, multi-source and multi-noise multi-omics data can be efficiently modeled and analyzed, good generalization ability and application potential are achieved, and reliable technical support can be provided for cancer subtype research, patient stratified analysis and precise medical aid decision making.

The invention discloses a multi-omics data integration and classification method, system and device based on hierarchical attention, and is applied to the field of precise medical big data analysis. The method comprises the following steps: firstly, generating feature embedding and feature importance scores through a plurality of parallel feature-level attention modules; then, embedding and inputting all the characteristics of the omics into a unified omics-level attention module, and generating omics embedding and omics importance scores; and finally, a classification prediction task is executed based on omics embedding, and a classification result is output for disease classification. The invention completely abandons a traditional dependency graph convolutional network and an integration normal form of variants of the dependency graph convolutional network, and provides a universal hierarchical attention integration architecture. The framework supports classification tasks of any complex diseases, is not limited by omics data types and combination modes, not only is remarkably superior to a traditional integration normal form in classification performance, but also shows a unique negative generalization distance, and proves that the framework has excellent generalization ability. Meanwhile, features and omics importance scores automatically output by the model provide a powerful analysis tool for biomarker discovery and precise diagnosis and treatment of complex diseases.

The invention relates to a multi-modal data processing method based on generative adversarial and dynamic gating fusion, and the method comprises the steps: carrying out the preprocessing of multi-modal medical data, inputting the data obtained through the preprocessing into a framework based on generative AI and dynamic gating fusion, and carrying out the pre-training, and obtaining a data processing model; preprocessing the multi-modal medical data corresponding to the specific task, and performing fine tuning and transfer learning on an input data processing model obtained by preprocessing to obtain a prediction result; images and omics data of different dimensions are mapped to a unified 128-dimensional feature space through a generative AI model, and scale normalization and semantic alignment are achieved; an MoE architecture and a gating network are introduced, expert weights are dynamically adjusted according to modality existence, and adaptive fusion under modality deficiency is supported; according to the method, a feature space full combination and generation type modal complementation strategy is designed, modal missing samples are allowed to participate in training and reasoning, and the sample utilization rate is remarkably increased.

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.

The invention relates to a hepatocellular carcinoma gene knockout target library based on multiple omics and a screening method of the hepatocellular carcinoma gene knockout target library, and the gene knockout target library for precise treatment of hepatocellular carcinoma is finally obtained through data collection and integration, data screening and target verification in sequence. According to the invention, through multi-omics data integration and bioinformatics analysis, key driving genes of hepatocellular carcinoma are systematically screened, and the important effects of the genes in occurrence, development, metastasis, drug resistance and immune escape of hepatocellular carcinoma are disclosed; the genes not only deepen the understanding of the hepatocellular carcinoma molecular mechanism, but also provide important theoretical basis and potential intervention targets for the development of targeted therapy and personalized therapy strategies.

The invention discloses a double-domain RAG-driven multi-omics fusion pathology analysis system, and belongs to the technical field of artificial intelligence of medical data. Pathology image feature data and structured multi-omics data of a patient are fused in a semantic layer through a multi-modal fusion module, a semantic layer fusion result is obtained, and a comprehensive representation vector of the patient is generated; the double-domain retrieval module obtains internal reference evidence corresponding to a hospital case knowledge base and external reference evidence corresponding to an external medical literature knowledge base; the consistency gating fusion module analyzes the consistency of the internal reference evidence and the external reference evidence, and fuses the internal reference evidence and the external reference evidence to obtain a fused credible evidence; and the report generation module generates a medical auxiliary report with an evidence chain based on a large language model according to the semantic layer fusion result and the credible evidence. According to the embodiment of the invention, the interpretability and credibility of the diagnosis conclusion can be enhanced.

The invention relates to the crossing field of artificial intelligence technology and bioinformatics, and discloses a pig feed efficiency prediction model and system based on multi-omics data. Modulating a neural differential equation which runs on a priori knowledge graph and is realized by a graph neural network by using the matrix so as to solve and generate a continuous evolution trajectory of an individual physiological state; and finally, aggregating the tracks, combining the constraint matrix, and outputting a feed efficiency prediction value through a second preset model. The invention further provides a corresponding prediction system which comprises a static constraint module, a dynamic core module and a prediction module. According to the method, static genetic constraint and dynamic physiological process simulation are combined, genetic differences among different individuals can be reflected, and the biological consistency and individualization precision of a prediction model are improved.

The present disclosure relates to predicting genomic instability status in biological samples using machine learning techniques with comprehensive genomic and immune profiling (CGIP) data. Particularly, aspects are directed towards performing a genomic instability test on a biological sample. Then, multi-omics data for the subject are obtained by DNA sequencing and RNA sequencing assays, including genomic alteration data for a first set of genes and expression data for a second set of immune genes. The multi-omics data are input into a machine learning model having a tree-based architecture, which is configured to analyze features by traversing paths from root nodes to terminal nodes in each tree based on values generated from the data. The model predicts a genomic instability status, which is then provided via a user interface notification or as part of a testing report.

The invention discloses a laying hen genetic disease molecular marker screening system based on data fusion and AI prediction, the system comprises six modules, a multi-omics data acquisition module obtains laying hen genome and transcriptome data, and a FineDataLink data fusion module carries out feature alignment and association mapping to generate a fusion feature matrix; the dynamic time sequence diagram neural network processing module constructs a time sequence association diagram and outputs a time sequence feature vector, and the attention enhancement deep forest analysis module evaluates feature importance and outputs a screening result; the federal variation auto-encoder modeling module constructs a federal training framework to generate a molecular marker probability distribution model, and finally the molecular marker screening output module extracts key molecular markers. The system realizes deep fusion of multi-omics data and efficient application of an AI algorithm through multi-module cooperation, improves the molecular marker screening efficiency and accuracy, and provides technical support for disease-resistant breeding of laying hens.

The invention relates to the technical field of bioinformatics, in particular to a method for typing acute respiratory distress syndrome biological subtypes. The method comprises the following steps: a) acquiring multi-omics data and carrying out standardized preprocessing; the multi-omics data comprises transcriptomics data, proteomics data and metabonomics data of a biological sample source; b) constructing a similarity network of each group by using a similarity fusion network (SNF), and obtaining a uniform sample similarity matrix through multi-group network fusion and iteration; multiple collaborative principal component analysis (MCIA) is adopted to carry out dimension reduction on multi-omics data so as to realize visualization of a clustering result; carrying out multi-omics joint discrimination modeling under the guidance of SNF clustering by using a data integration analysis (DIABLO) method so as to identify key feature variables; and carrying out biological subtype classification based on the clustering result of the steps.

Systems and methods for processing spatial transcriptomic data and generating insights related to cell and tissue status. The systems and methods include spatial clustering, integration of a plurality of tissue sample data, and integration of scRNA-seq data with spatial transcriptomic data. The systems and methods combine graph self-supervised contrast learning and graph neural networks to perform spatial transcriptomics data processing.

The invention provides a space transcriptomics organization space domain intelligent identification method based on a Graph Transform. The method comprises the following steps: reading a space transcriptomics data file; extracting features in the histological image data by adopting a pre-trained deep learning model; setting a spatial distance threshold value; acquiring spatial position data of each sampling point according to a set spatial distance threshold value, and constructing an adjacent matrix; combining the gene expression data, the adjacent matrix and the histological image features to obtain a normalized feature matrix; performing dimensionality reduction on the normalized feature matrix by adopting PCA; inputting the feature matrix subjected to dimension reduction processing into a feature learning model to obtain a comprehensive feature representation; clustering the obtained feature representations by adopting a Leiden algorithm to obtain a spatial domain classification result; according to the invention, deep fusion of multi-modal information is realized through a Graph Transform architecture, spatial distribution rules and functional characteristics of cells can be captured at the same time, and a systematic solution is provided for analyzing a complex structure of a tissue microenvironment.

The invention provides a multi-view space transcriptomics clustering method based on sharing-specific information mining. The technical problems that in an existing space domain recognition method, robustness of a single view is insufficient, multi-view information fusion is insufficient, and description of data statistical characteristics is not accurate are solved. According to the technical scheme, the method comprises the following steps: S1, acquiring and preprocessing original data of a spatial transcriptome; s2, constructing a sharing-specific decomposition coding network; s3, using a ZINB expression decoder, a structure decoder and a Student's t distribution clustering module to construct a multi-task loss function; and S4, outputting a spatial domain division result based on the trained network. According to the method, the spatial domain recognition precision and robustness are remarkably superior to those of an existing method, the data statistical characteristics and biological significance can be accurately described, stable support is provided for tissue function analysis and tumor microenvironment research, and the analysis quality and application value of spatial transcriptomics data are effectively improved.

The invention belongs to the technical field of gene identification, and discloses a method for integrating multi-omics data to enhance genome prediction and candidate gene identification, candidate gene identification is verified through multi-layer evidence integration, and the verification comprises priority ordering based on gene contribution scores, function enrichment analysis, generic genome network verification and CRISPR / Cas9 experimental verification. Evaluation on a corn population (n = 174) containing complete genomics, transcriptomics, translational omics and proteomics maps shows that the framework is remarkably improved in grain character prediction and is improved by 2.9-12.3% compared with a genome selection baseline, and meanwhile candidate genes verified by experiments are recognized. The invention further verifies the universality of the framework to five traits on an arabidopsis thaliana population, and provides an open source software platform to promote the practical application of the framework in a breeding plan.

The invention discloses a construction method of a single-cell multi-omics data analysis system based on a containerization technology, and the construction method of the single-cell multi-omics data analysis system based on the containerization technology comprises the following steps: constructing a single-cell multi-omics analysis modular toolkit; a production mirror image is constructed on the high-performance cluster through a Single container engine, and deployment of a production environment is completed; a single-cell multi-omics automatic analysis platform is built through a snakemake process engine; and a JupyterLab interactive analysis platform for exploratory analysis of the single-cell multi-omics data is constructed. According to the single-cell multi-omics data analysis system construction method based on the containerization technology, the data acquisition link in the analysis process is accelerated, an automatic working process is formed to solve the problem of complex process, and the actual requirements of multiple users on a high-performance computing cluster for scientific exploration and analysis of single-cell data are met.

The invention provides a Wuzhishan pig organ multi-omics data space integration and analysis method, and belongs to the technical field of data statistics and analysis, the method comprises the following steps: S1, experiment design and Wuzhishan pig organ sample standardization preparation; s2, independently collecting and preprocessing multi-omics data of Wuzhishan pig organs; s3, multi-omics data standardization and batch effect correction; s4, labeling and calibrating spatial dimension information; s5, spatial specificity correlation modeling of the multi-omics data is carried out; s6, carrying out integrated clustering analysis on the spatial multi-omics data; s7, performing function annotation and path enrichment analysis on the clustering feature clusters; and S8, analyzing the spatial specific molecular mechanism and constructing a multi-omics data spatial integration database. According to the method, spatialization and systematization analysis of the Wuzhishan pig organ multi-omics data is achieved through collaborative optimization of the HHO-IK-means-BI three algorithms, and technical support is provided for experimental zoology research and conversion of medical application.

The invention discloses a space transcriptome and space metabolome integration method based on deep learning. The method comprises the following steps: firstly, acquiring original space transcriptomics data and original space metabonomics data of a biological tissue, and performing data preprocessing to obtain a preprocessed biological tissue data set; then, aligning space metabonomics data in the preprocessed biological tissue data set to space transcriptomics data, unifying data resolution, obtaining corrected space metabonomics data, and updating the biological tissue data set; and finally, generating to-be-integrated sample data from the newest biological tissue data set, inputting the to-be-integrated sample data into the spatial multi-omics data integration model, and outputting final joint embedding by the model, so that cross-modal and cross-sample effective integration of the data can be realized. According to the method, the problems of form and resolution inconsistency and batch effect caused by technical difference of ST and SM data are solved, and high-precision and interpretable spatial multi-omics integration analysis is realized.

The invention discloses a microfluidic multi-organ tumor chip targeted drug test AIGC system, and relates to the technical field of medical drug test information processing. The microfluidic multi-organ tumor chip targeted drug test AIGC system comprises a multi-omics data acquisition module for acquiring and preprocessing disturbance response data and dynamic expression data; the disturbance response pre-screening module is used for carrying out strength evaluation on drug action strength and reconstructing channel mapping; the characteristic space reconstruction module is used for performing action analysis on the whole medicine action state and dynamically adjusting a liquid medicine blending rule; the drug effect prediction module is used for predicting and evaluating the response degree of the organoid under the intervention of the specific drug and deducing the individualized drug effect intensity; and the feature augmentation self-closed loop module constructs a negative supervision signal and dynamically corrects a disturbance perception and feature embedding path. The problems that current multi-omics data is high in dimension, large in redundancy and large in noise, key features are difficult to extract under limited samples, and model generalization is difficult to maintain are solved.

The invention discloses a newborn rare disease intelligent screening and diagnosis system based on multi-omics data fusion, relates to the technical field of medical data processing, and aims to solve the technical problems that a traditional diagnosis method is long in time consumption and low in accuracy and cannot meet the requirement for rapid and accurate diagnosis of newborn rare diseases. The data acquisition module is used for acquiring clinical omics data from a doctor's advice database through a neonatal medical record, and acquiring blood samples to acquire gene data and metabonomics data and marking when the medical record records that the neonatal suffers from a rare disease; the data processing module is used for preprocessing the clinical omics data according to the neonatal medical record to obtain a training set and a test set, and preprocessing the gene data and the metabonomics data according to the blood sample; and the diagnosis module is connected with the data processing module. By constructing a three-level modular architecture, the problem of missed diagnosis caused by traditional multi-source data isolated analysis is effectively solved, and the accuracy rate of newborn rare disease diagnosis is remarkably improved.

The invention discloses an early pancreatic cancer prediction and risk stratification system based on artificial intelligence, and belongs to the technical field of medical health data analysis and artificial intelligence. The system comprises a multi-omics data adaptive fusion module, a longitudinal health trajectory coding module, a biomarker combination discovery module, a risk prediction and dynamic layering module and a closed-loop feedback optimization module, and a data confidence index generated by the multi-omics fusion module directly affects the attention weight of longitudinal trajectory coding. Longitudinal track coding adopts a bidirectional long-short-term memory network to extract time sequence characteristics, a biomarker discovery module recognizes a synergistic marker combination through a Transform mechanism, a closed-loop feedback module dynamically adjusts parameters of each module according to a prediction result, and clinical verification shows that the prediction accuracy of the system reaches 85%, the I-stage diagnosis rate is improved by 60%, diseases are discovered 8-12 months in advance, and the diagnosis efficiency is improved. The method is obviously superior to the prior art.

The invention discloses a laying hen genetic disease knowledge graph construction and intelligent decision support system. The system comprises a genetic disease weak supervision graph extraction module, a disease multi-factor diagnosis module, a group health risk clustering module, a multi-omics graph analysis module, a genetic disease knowledge graph construction module and an intelligent decision support module. According to the system, laying hen genes, physiological indexes, breeding environments and multi-omics data are collected through gene sequencing and the like, a gene disease association graph is generated through weak supervision graph extraction, a disease diagnosis result is generated through multi-factor diagnosis, health risk grades are divided through risk clustering, and an association graph is generated through multi-omics analysis; and a genetic disease knowledge graph is constructed, and an intelligent decision scheme is generated in combination with real-time data and an algorithm. The system improves the accuracy of laying hen genetic disease prevention and control and the intelligent level of breeding management, guarantees the economic benefits of breeding, and is suitable for large-scale breeding scenes of laying hens.

The invention belongs to the technical field of biological information, and particularly relates to a cancer molecular subtype recognition method based on self-adaptive pellet multi-view image clustering. The method comprises the following steps: acquiring a multi-omics data set of cancer molecules, and constructing a pellet set for each kind of omics data in the multi-omics data set; constructing a biological network structure chart according to the particle ball set; fusing the biological network structure diagrams of the omics data to obtain a unified graph; inputting the unified graph into a pre-trained heterogeneous graph neural network for processing to obtain a cancer molecular subtype recognition result; according to the method, multi-scale biological structure features in multiple omics data can be captured at the same time, collaborative optimization of molecular network topology and patient characterization is achieved, and therefore the accuracy of cancer molecular subtype recognition results is improved.