74 results about "Biological network" patented technology

The invention is applicable to the technical field of biological information, and provides a drug target prediction method based on a graph neural network, which comprises the following steps of: respectively taking a drug and a target node as a core, and automatically extracting local sub-graphs of the drug and the target node to capture local context information of the nodes in a complex biological network; taking different types of edges as feature information and fusing the feature information into a feature learning process, dynamically adjusting contribution degrees of the different types of edges to node representation through an attention mechanism, introducing residual connection and a normalization processing strategy, and fusing node features; and performing deep mining on the fused node features by using a two-layer graph convolutional network, and calculating a potential interaction prediction score between the drug and the target. The invention further provides a drug target prediction model based on the graph neural network. According to the method, independent feature extraction and training are carried out on predicted drugs and target spots, and the accuracy and richness of node representation are effectively improved while the flexibility of the model is kept.

The invention provides a micro-flow field measurement method of a mechanical biological net port flowmeter, and belongs to the technical field of micro-flow field measurement, and the micro-flow field measurement method comprises the following steps: firstly, constructing a net port cavity digital model, and realizing micro-flow field high-resolution characterization by using fluorescent particle tracing liquid and a laser confocal system; and recording a fluid movement track and processing original data by applying a track optimization function under the condition that the microfluidic driving system generates a constant pressure gradient. And solving fluid pressure distribution by adopting an orthogonal grid system and a Navier-Stokes equation, and processing speed field and pressure distribution data by utilizing a pre-trained micro-flow field analysis neural network model. Finally, the flow and pressure relation curve is obtained by calculating the flow flux of the cross section of the network port, a micro-flow field measurement correction coefficient table is generated, and the technical problems that in the prior art, the accurate measurement difficulty of the biological network port micro-flow field is large, and multi-scale flow characteristic representation is insufficient are solved.

The invention relates to an oncogene prediction method based on graph variation self-coding, and belongs to the field of bioinformatics. The method is based on a dual-path neural network framework: a main path processes an original network and features enhanced by a variational auto-encoder (VAE) by using a graph attention network (GAT) so as to capture a complex relationship between nodes; the auxiliary path generates an auxiliary network and features containing global information through an APPNP algorithm, and the auxiliary network and features are aggregated through GraphSAGE to retain structural information. The model introduces jump connection and residual connection to relieve gradient disappearance and enhance feature complementarity. And finally, integrating dual-path information output prediction through a linear layer. The method is verified on a plurality of biological network data sets, the prediction accuracy, robustness and hidden relation recognition capability are remarkably improved, and a reliable tool is provided for cancer research.

The invention discloses a construction method and application of a multi-scale and multi-level regulation and control network, and relates to the field of biological information.The construction method comprises the following steps that firstly, 20 databases about interaction among protein, transcription factors, enhancer super enhancers, ncRNA and metabolites are collected; 2, performing quality control on each database, and annotating a specific disease physiological state to each regulation and control relationship; 3, integrating molecular regulation and control relationships among different levels according to biological logic; 4, a bidirectional random walk algorithm is adopted to cooperate with a multi-level biological network to predict and mine potential drug treatment targets; the regulation and control network constructed by the method has a multi-level structure and a specific disease physiological state, the dynamic regulation and control network conforming to the real disease physiological state can be constructed, and the method can be applied to mining potential drug targets and exploring pharmacological mechanisms.

The invention relates to a medical simulation experiment method and device for acting apoptosis vesicles on primary cartilage cells based on cell line culture, and the method mainly comprises the following steps: S1, co-culture system construction, S2, multi-dimensional observation and analysis, and S3, operation risk assessment. In the step S1, primary cartilage cells, primary immune cells and cell line culture apoptosis vesicles are co-cultured; s2, carrying out multi-dimensional observation and analysis on the influence of apoptosis vesicles on cells; and S3, mainly constructing a multi-dimensional risk scoring system, and carrying out risk grade division by applying a biological network model. The invention aims at simulating and evaluating the influence of cell line culture apoptosis vesicles on primary cartilage cells in vitro and the interaction between the cell line culture apoptosis vesicles and primary immune cells, so that an experimental basis is provided for subsequent clinical application.

The invention provides a drug-target correlation prediction method based on a hierarchical representation learning framework, and the method comprises the steps: screening high-information-density nodes based on a dynamic fluctuation threshold value, reducing low-noise nodes, and reconstructing topological connection according to a virtual edge weight formula; performing tensor splicing on the drug molecular features extracted by the dynamic neighborhood search framework and the protein semantic features generated by the denoising auto-encoder to form drug-protein pair joint feature representation; a multi-head attention mechanism is utilized to allocate dynamic weights for multi-view features based on drug-protein pairs, multi-view feature vectors are spliced, after key information is screened through the attention mechanism, the key information is input into a full-connection neural network, and a correlation prediction value is output based on the full-connection neural network. The association prediction method solves the problems that the prediction precision of the model on the complex biological interaction is poor, and the understanding ability of the model on the multilevel feature learning association in the complex biological network is seriously limited.

The invention belongs to the technical field of bioinformatics, particularly relates to a computer simulation and regulation method and system for beef cattle fat metabolism, and aims to solve the problems of excessive fat deposition, low feed conversion efficiency, difficulty in multi-objective optimization and the like in existing beef cattle breeding. A multi-scale biological network model is constructed, a computer simulation and prediction engine is developed, an intelligent intervention strategy optimization engine is designed, and implementation and feedback optimization are carried out. By reducing unnecessary fat deposition, improving the feed conversion efficiency and improving the beef quality, the economic benefit of beef cattle breeding is remarkably improved, the requirements of consumers for high-quality and safe beef products are met, and the method has important value for promoting intelligent upgrading and sustainable development of the beef cattle industry.

The invention is applicable to the technical field of knowledge migration, and provides a graph domain adaptive node classification method based on instance learning, which comprises the following steps of: acquiring a source domain data set with a mark and a target domain data set without a mark; the representation of the source domain data set and the representation of the target domain data set are learned through a GNN model, modeling is conducted on the source domain data set and the target domain data set, and embedded vectors of the source domain data set and the target domain data set are obtained; the embedded vectors of the target domain data set are classified through KNN, and target domain category pseudo labels are obtained; performing fine-grained instance contrast learning on embedded vectors of the source domain graph data set and the target domain graph data set; and after classification is finished, displaying a final classification result of the target domain graph data set. According to the method, the defects of an existing graph domain adaptation technology in cross-domain tasks are overcome, and the method has wide applicability and can be applied to graph data analysis tasks in various cross-domain scenes, such as social network analysis, recommendation systems, knowledge graphs and biological networks.

The invention discloses a drug-disease interaction prediction method and device, a medium and a product, and relates to the field of intelligent medical treatment. Firstly, drug data, disease data and biological data are acquired; carrying out preprocessing and feature extraction on the drug data to obtain drug molecular features; extracting target spot features based on the biological data; inputting the drug molecular features and the target features into a first full-connection neural network for predicting a drug-target interaction relationship; generating drug biological network characteristics based on the drug-target interaction relationship; performing preprocessing and feature extraction on the disease data to obtain disease features; training a second full-connection neural network based on the drug-biological network features and the disease features, and obtaining a drug-disease interaction prediction model after training is completed; the drug-disease interaction is predicted by using the drug-disease interaction prediction model, and the prediction efficiency and accuracy can be improved.

The present invention discloses a drug-target prediction method based on a graph-attributed neural network, comprising the following steps: S1, constructing a multi-source heterogeneous biological network and uniquely identifying drugs, proteins, and diseases; S2, calculating the similarity between any two diseases based on the disease module theory of the human protein-protein interaction network; S3, using each biological entity pair and the corresponding similarity value as a training sample for the graph attention neural network representation learning phase; S4, using the training samples to drive the graph attention neural network learning to obtain a representation vector for each entity; and S5, using the trained drug-target prediction model to predict drug-target interactions. This invention reduces the dependence of deep learning models for drug-target interaction prediction on training samples, thereby improving prediction performance.

The invention discloses a drug relocation method and system based on heterogeneous knowledge and structure fusion, and belongs to the technical field of medical care informatics. The method comprises the following steps: constructing a biomedical domain knowledge heterogeneous graph; generating disease knowledge embedding and drug knowledge embedding corresponding to a target drug-disease pair based on the biomedical domain knowledge heterogeneous graph; generating disease structure embedding and drug structure embedding corresponding to the target drug-disease pair by constructing a drug-drug similarity network, a disease-disease similarity network and a drug-disease association network; and based on disease knowledge embedding, drug knowledge embedding, disease structure embedding and drug structure embedding, obtaining a drug relocation result. According to the method, complex biological network characteristics are accurately captured and complex entity information is finely modeled through an innovative drug relocation model, so that accurate drug relocation is realized.

The invention provides a pathogenic driver gene prediction method based on biological network fusion and related equipment. The method comprises the following steps: acquiring data of various driver genes for training; constructing an initial gene relationship map based on protein interaction, gene sequence similarity, KEGG pathway co-occurrence, a gene co-expression mode and semantic similarity of a gene ontology, and embedding various human driven gene data for training into each node in the initial gene relationship map to obtain various gene relationship maps; performing dynamic adjustment on each gene relationship map through edge discarding, feature discarding and difficult sample recognition enhancement to obtain an adjusted gene relationship map for training the constructed pathogenic driving gene prediction model to obtain a trained pathogenic driving gene prediction model; inputting the target driver gene data into the trained pathogenic driver gene prediction model for prediction to obtain a prediction result; and the accuracy and robustness of pathogenic driver gene prediction are improved.

The invention discloses a biological data anomaly detection method based on semantic information fusion, and relates to the technical field of computer processing, and the method comprises the following steps: S01, constructing biological entity nodes and relation edges through a depth map neural network, generating an adjacency matrix and a node attribute matrix, aggregating node neighbor information by using a message passing mechanism, and generating a node attribute matrix; a biological network architecture model is obtained; s02, constructing a semantic fusion space based on a large model, analyzing deep semantic information and node association information of nodes, and synthesizing a few abnormal node candidate sets; and S03, adding the composite node candidate sets into the original data set one by one through an edge generator, and inputting the composite node candidate sets into a reinforcement learning module for screening. According to the method, classification and risk assessment of biological data are optimized by utilizing large-model semantic analysis and biological network construction, so that abnormal biological data can be quickly identified through multi-source data fusion and deep learning analysis in the early stage of virus transmission, and accurate detection and intelligent early warning are realized.

Systems for inferring spatially-varying regulatory networks, such as gene regulatory networks, are provided. Optimization processes are performed and include regularization minimization processes that rely on one or both of a smoothly-changing minimization process and a sparsely-changing minimization process, for example to learn sparsely- or smoothly-changing Gaussian Markov random fields (GMRF). The systems are further able to convert spatially-varying data, such as spatial transcriptomic data, into spatio-temporal regulatory networks.

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.

The invention discloses a multi-layer heterogeneous network unicellular organism network inference method based on meta-path enhancement, which mainly comprises a gene regulation knowledge base enhanced multi-layer heterogeneous network construction module for integrating an external gene interaction network and multiple omics data such as scRNA-seq, scATAC-seq, ST and the like; constructing a single-cell multi-omics multilayer heterogeneous network containing cell-cell, cell-gene and gene-gene relationships, and fusing spatial constraints to consider cell positions and tissue structures; and the feature enhancement module based on the meta-path explores complex semantics of the network by designing a multi-hop meta-path mode, designs an adaptive multi-view learning framework and a multi-round enhancement mechanism, and optimizes feature representation by using cell-gene interaction and cross-modal attention fusion. The unicellular biological network can be effectively deduced, the deduction accuracy and biological interpretation are remarkably improved, the method plays an important role in understanding the cell biological process, developing and treating diseases and the like, has good expandability, and can further integrate multi-modal omics data such as proteomics and metabonomics.

The invention discloses a mountain river aquatic organism network health evaluation method, and relates to the technical field of ecological environment. Comprising the following steps: establishing a mountain river aquatic organism network health evaluation index system which comprises an index layer, a criterion layer and a target layer; calculating mountain river aquatic organism network index layer data; determining a comprehensive weight coefficient of data of each index layer, and calculating a health index of a criterion layer; determining the comprehensive weight coefficient of the health index of each criterion layer, and calculating the total health index of the target layer; and according to the total health index value, determining the grade category of the health state of the aquatic organism network in the mountain river. The method can objectively evaluate the health state of the aquatic organism network of the mountain river, and provides a scientific basis for ecological protection and treatment of the high mountain river.

The invention belongs to the technical field of drug-target relationship prediction, and relates to a prediction method and device for interaction between a drug and a target, and a storage medium. The method comprises the following steps: constructing a heterogeneous biological network diagram based on drugs, targets, diseases, side effects and interaction of the drugs, the targets, the diseases and the side effects, and obtaining an initial feature vector of each node; taking the drug nodes and the target nodes as target nodes, and obtaining four types of neighbor nodes and four types of meta path nodes of the target nodes; performing feature extraction on the initial feature vectors of the four types of neighbor nodes of the target node and the four types of meta-path nodes to obtain a neighbor view embedding representation and a meta-path view embedding representation; projecting the neighbor view embedded representation and the meta-path view embedded representation into a query vector, a key vector and a value vector, and calculating a cross attention value; based on the neighbor view embedded representation, the meta-path view embedded representation and the cross attention value of each target node, obtaining a fusion representation; and performing interaction prediction of the drug node and the target node based on the fused representation.

The invention relates to a structural network-genetic map biological network model for predicting ischemic stroke and a construction method thereof, and the method comprises the steps: extracting and calculating seven multi-scale morphological features and pairwise Pearson correlation coefficients among the features from T1 weighted imaging data and diffusion tensor imaging data; constructing a 308 * 308 morphological similarity network matrix and a brain network module for identifying ischemic stroke neural dysfunction; 1782 sampling points are extracted from the Airy human brain map, and each sampling point comprises expression data of 10185 genes; the method comprises the following steps: mapping space coordinates of AHBA sampling points to a cortex package of a Desikan-Killiany map, carrying out normalization processing to output 308 * 10185 brain region gene-by-gene expression matrixes, and constructing a structural network-gene map biological network model for predicting ischemic stroke by adopting a partial least square regression method and a bootstrap method. Compared with the prior art, the model determines the specific molecular mechanism related to the phenotypic structure change of ischemic stroke injury, and the stroke occurrence probability is predicted according to the specific molecular mechanism.

The invention discloses a mountainous river aquatic organism network degeneration pathogenesis diagnosis method, and relates to the technical field of ecological environment. Comprising the following steps: determining a mountainous river aquatic organism network health external influence factor, and establishing a mountainous river aquatic organism network pathogenesis diagnosis index system; according to the mountainous river aquatic organism network pathogenesis diagnosis index system, constructing a mountainous river aquatic organism network health pathogenesis diagnosis model; according to the mountainous river aquatic organism network health pathogenesis diagnosis model, calculating the influence intensity of each mountainous river aquatic organism network health external influence factor; and according to the influence intensity calculation result of the external influence factor of the health of the mountain river aquatic organism network, diagnosing and analyzing the pathogenesis of the mountain river aquatic organism network. According to the invention, the main pathogenesis of the aquatic organism network of the mountain river can be accurately identified, and the pertinence and effectiveness of ecological protection and treatment of the mountain river are improved.

The invention relates to the technical field of pharmaceutical informatics, in particular to a method for discriminating a drug combination type based on a directed regulation network, which comprises the following steps: acquiring regulation data of a drug to a target, and constructing a drug-target directed regulation network; determining a drug regulation type according to the drug-target directed regulation network, calculating the action intensity of each node by combining attenuation characteristics, and judging whether the node is a positive regulation node or a negative regulation node; respectively classifying into a positive node set to obtain a negative node set; obtaining the shortest network distance between two different node sets; and for the double-drug combination, dividing a positive node set and a negative node set of the first drug and the second drug, and respectively calculating a positive relative distance and a negative relative distance to realize the judgment of the drug combination type. According to the method, drug-target and target-target action directions and action types are fully considered, and the constructed directed regulation biological network contains more action information and is closer to the real drug action condition.

The present invention provides a biological network link prediction algorithm SSL-Bio based on self-supervised graph representation learning. The provided biological network link prediction algorithm SSL-Bio is based on a graph convolutional neural network, uses graph data augmentation to generate two different views for the biological network, and solves the problem of inaccurate biological network link prediction caused by sparse biological networks, long-tail distribution, and high noise by setting appropriate self-supervised tasks, realizes link prediction for multiple biological networks, and improves prediction accuracy.

The application discloses a drug repositioning method and system based on heterogeneous knowledge and structure fusion, and belongs to the technical field of medical care informatics. The method comprises the following steps: constructing a biomedical field knowledge heterogeneous graph; based on the biomedical field knowledge heterogeneous graph, generating disease knowledge embedding and drug knowledge embedding corresponding to a target drug-disease pair; by constructing a drug-drug similarity network, a disease-disease similarity network and a drug-disease association network, generating disease structure embedding and drug structure embedding corresponding to the target drug-disease pair; and based on the disease knowledge embedding, the drug knowledge embedding, the disease structure embedding and the drug structure embedding, obtaining a drug repositioning result. The application accurately captures complex biological network characteristics and finely models complex entity information through an innovative drug repositioning model, so that accurate drug repositioning is realized.

The present invention discloses an automatic gene function prediction system based on graph neural networks and contrastive learning, comprising: a data import module for loading multiple biological network data and corresponding protein sequences and preprocessing the data; a data enhancement module for enhancing each biological network data using graph perturbations; a gene representation training module for obtaining corresponding gene representations using graph neural networks and contrastive learning; and a gene function prediction module for using support vector machines to predict whether a gene has certain specific gene functions. The present invention uses graph neural networks rather than traditional deep learning networks to fully extract information from biological network data, while using contrastive learning to capture data distribution and generate semantically rich representations, effectively improving the effectiveness of subsequent gene function prediction.

The invention relates to a disease similarity prediction method and system based on multivariate data fusion, and the method comprises the steps: collecting gene network data, miRNA network data, a disease-gene incidence matrix and a disease-miRNA incidence matrix, and forming a unified heterogeneous biological network; extracting and generating a multi-modal feature set through the graph convolutional network and the improved graph attention network; the independent weight of each feature in the multi-modal feature set is calculated through a multi-layer perceptron, gene view angle embedding and miRNA view angle embedding of the disease are generated in combination with the incidence matrix and serve as model input training, and a lightweight bilinear tower model is obtained; model parameters are optimized through an alternate training strategy and a regularization mechanism inspired by ReconBoost, an optimized lightweight bilinear tower model is obtained, and a similarity prediction result of the target disease pair is obtained. The defects of multivariate data integration, sparse data processing and prediction stability in the prior art are effectively overcome.

The invention discloses a biological entity multivariate association prediction system combining linear and nonlinear fusion matrix factorization, which relates to the technical field of biological entity multivariate association prediction and comprises a multivariate biological entity input module, a cross-modal feature extraction module, a dual-channel fusion matrix factorization module, a dynamic feature fusion device and a multivariate association prediction engine. According to the method, the limitation of a traditional biological entity association prediction method is broken through by fusing linear and nonlinear matrix decomposition technologies, and a dynamic feature fusion mechanism realizes optimal combination of cross-modal features through adaptive weight adjustment, so that the problem of insufficient flexibility of a traditional static fusion strategy is overcome; in addition, the system adopts a three-dimensional tensor modeling technology, a unified prediction framework of multiple types of associations such as gene-disease, drug-target, metabolite-pathway and the like is realized, heterogeneity characteristics of biological associations can be effectively maintained, and compared with the prior art, the analysis capability of a complex biological network is remarkably improved.

The application provides a drug-target correlation prediction method based on a hierarchical representation learning framework, in the method, high information density nodes are screened based on a dynamic fluctuation threshold, low noise nodes are reduced, and topology connection is reconstructed according to a virtual edge weight formula; drug molecule features extracted by a dynamic neighborhood search framework and protein semantic features generated by a denoising autoencoder are spliced in a tensor level to form joint feature representation of a drug-protein pair; a multi-head attention mechanism is used to assign dynamic weights to multi-view features based on the drug-protein pair, multi-view feature vectors are spliced, key information is screened through the attention mechanism, and then the full connection neural network is input, and a correlation prediction value is output based on the full connection neural network. The correlation prediction method solves the problems that the prediction accuracy of the model for complex biological interactions is poor, and the understanding ability of the model for multi-level feature learning correlation in a complex biological network is severely limited.

A biological network mimic for investigating subcellular structures and their interaction with biomolecular condensates is presented. The mimic is a stimulus-responsive polymer and a non-responsive polymer in an aqueous two-phase system (ATPS). One effective mimic is an aqueous two-phase system (ATPS) that combines poly (N-isopropylacrylamide) (PNIPAM) and dextran (DEX). The ATPS mimic, displays ultrasensitive thermo-induced aqueous liquid-liquid phase separation and liquid-solid phase separation (AqLL-LS PS2). Diverse structures, including networks, hollow spheres, and spinodal decomposition-like patterns, are generated by regulating component concentrations and temperatures. These structures are thermally reconfigurable. Networks can melt fused in sarcoma (FUS) condensates. The mimics provides methods to examine potential treatments of neurode-generative diseases by dissolving pathologically relevant biomolecular condensates.

The application provides a forestry carbon sink project full life cycle measurement method and system based on digital twinning, relates to forestry carbon sink measurement, and comprises the following steps: acquiring multi-source heterogeneous basic data such as forest three-dimensional skeleton topology, carbon dioxide flux time sequence, mycorrhizal network distribution and meteorological data, coupling forest digital gene and ecological process tensor to generate a digital gene tensor field; then obtaining a double-path carbon flux field of dominant conduit transmission and implicit mycorrhizal transfer through carbon transmission inversion driven by a conduit bundle network; constructing a carbon sink phase change field based on a stability boundary constraint by analyzing a carbon sink phase change critical point; obtaining a carbon re-allocation map regulated by a biological network through a cross-scale carbon re-allocation path deduction; and finally outputting an optimized and adjusted carbon sink evaluation value through full life cycle carbon sink entropy optimization measurement processing. The application realizes the transformation from static estimation to dynamic simulation of carbon sink measurement, and significantly improves the accuracy and reliability of full life cycle evaluation of a carbon sink project.

This invention relates to the field of bioinformatics technology, specifically a method for mining key multi-omics molecules and pathways based on a heterogeneous graph framework. The steps of this method are as follows: (1) Constructing an integrated biological knowledge graph. (2) Using various machine learning algorithms to convert the original multi-omics data into a multi-dimensional machine learning attribute matrix. (3) Extracting specific multi-layer knowledge networks related to specific diseases from the integrated biological knowledge graph. (4) Matching the preprocessed machine learning attribute matrix with the specific multi-layer knowledge network. (5) Based on the complete network structure, capturing key molecular information using a graph convolutional neural network with an attention mechanism equipped with a purifier. (6) Using a community detection algorithm to extract functional modules from the trained network. This method relies on a biological knowledge graph, interconnects biological networks with experimental data through a heterogeneous graph deep learning model, and combines a graph structure variational autoencoder and an optimized graph convolutional neural network to achieve information optimization and deep mining.