106 results about "Protein Interaction Networks" patented technology

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 provides a rapid quantitative analysis method for an outer vesicle proteome, and belongs to the technical field of quantitative analysis of the outer vesicle proteome. According to the rapid quantitative analysis method for the outer vesicle proteome, firstly, a high-quality outer vesicle sample is obtained through low-speed centrifugation, ultra-speed centrifugation and membrane filtration; and obtaining proteome data by utilizing two-dimensional electrophoresis and mass spectrometry. Then, a mathematical model equation set is constructed for preliminary analysis, a protein interaction network is optimized through an embedded game optimization index model, and feature extraction and quantitative analysis are conducted through a convolution parameter adaptive function and a residual network deep learning model; finally, a quantitative analysis result containing the protein expression level and the function importance is generated in combination with the multi-dimensional protein expression contribution index, and the technical problem that in the prior art, in the rapid quantitative analysis process of the outer vesicle proteome, the protein component complexity is high, and consequently the quantitative precision is low is solved.

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 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 biological signal transduction pathway analysis method based on a protein network, which comprises the following steps: acquiring omics data, and preprocessing the omics data to obtain preprocessed omics data; constructing a cell specific protein interaction network according to the preprocessing omics data; extracting topological structure characteristics from the cell specific protein interaction network; obtaining a signal transduction path according to the topological structure features and a network topological feature prediction model; and obtaining a signal transduction path analysis result according to the signal transduction path. According to the method, multi-omics data and a machine learning algorithm are combined, a complex signal transduction mechanism can be revealed from a global perspective, and the prediction accuracy is improved.

The invention discloses a disease-related anomaly localization protein prediction method based on deep learning, and the method comprises the steps: carrying out the protein prediction based on the proteomics expression data of normal and disease samples and a known protein interaction network in a normal state; respectively constructing a protein interaction network under the activity characteristics of the sample pathway and the disease state; the proteomics expression data and the pathway activity characteristics are fused through a cross attention mechanism, and protein characterization characteristics with pathway perception ability are constructed; respectively predicting protein subcellular localization under the normal and disease states by using a graph attention network model based on the protein characterization characteristics and the protein interaction network corresponding to the normal and disease states; disease-related abnormal localization proteins are identified by comparing predicted protein subcellular localization in normal and disease states. The method can efficiently and accurately identify the abnormal localization protein related to the disease, and has important scientific research value and application prospect.

The present invention discloses a method for predicting drug-drug interactions based on secure multi-party computing, comprising the following steps: S1, obtaining a drug-drug interaction network, a drug-protein interaction network, a drug-disease association network, and a drug-side effect association network; S2, calculating Jaccard similarity based on different drug features to obtain similar features between all drugs, and using principal component analysis technology to reduce the dimensionality of all drug similarity features; S3, dividing each user's private feature data into four parts, encrypting them using secret sharing technology, and sending them to four servers using an additional secret sharing mechanism; S4, inputting the four parts of feature data into a preset private deep learning model to predict drug-drug interactions. The present invention enables high-quality collaboration between pharmaceutical companies and research institutions without leaking drug privacy information, thereby improving drug-drug interaction prediction.

The application provides a method for analyzing the synergistic mechanism of hepatotoxicity and nephrotoxicity of non-steroidal anti-inflammatory drugs. The method comprises the following steps: preliminary toxicity prediction of NSAIDs and collection of toxicity target points, collection of liver and kidney disease target points, then cross and screening of the target points to obtain core target points and common core target points of NSAIDs induced liver and kidney diseases, and then constructing a protein interaction network of the common core target points; enrichment analysis of the common core target points to obtain the common action pathway of NSAIDs induced liver and kidney diseases; finally, further screening of the common core target points to obtain the key target points of NSAIDs induced liver and kidney diseases, and verification by using molecular docking technology. Compared with the traditional method, the advantages of the method are: first, the method does not depend on large-scale patient clinical data and a large number of animal or cell experiments, avoiding the ethical controversy in animal experiments and human experiments; second, the method can identify the potential cross-pathway and synergistic toxicity mechanism when a compound triggers multiple diseases, which is helpful for more comprehensive evaluation of the toxicity risk of NSAIDs.

The embodiment of the invention provides a drug optimization method and system based on the overall effect of a protein network. The method comprises the following steps: constructing a protein interaction network related to a target disease, and dividing each protein target into a risk protein set and a protection protein set; respectively calculating first binding affinity data of the candidate drugs and each protein target in the risk protein set, and generating a first network comprehensive score based on the first binding affinity data; respectively calculating second binding affinity data of the candidate drugs and each protein target in the protection protein set, and generating a second network comprehensive score based on the second binding affinity data; calculating network confrontation scores of the candidate drugs according to the first network comprehensive score and the second network comprehensive score; and determining whether the candidate drug is a preferred drug based on the network adversarial score. The method can overcome the defect that a single-target drug is insufficient in curative effect due to a network compensation effect, so that safer and more effective candidate drugs are screened out.

The invention discloses a PPI prediction method based on a dynamic hypergraph, and belongs to the technical field of PPI prediction, and the method comprises the steps: carrying out the sampling of a hyperedge through employing the learned hyperedge feature distribution P (Xe | Xv) according to a protein-protein interaction network G = (V, E), and obtaining an initial hyperedge feature matrix Xe; protein node features are mapped to a hyperedge feature space, an attention coefficient is calculated by adopting an attention mechanism, front Kn node features are aggregated, hyperedge features are updated through a multi-layer perceptron and feature splicing, and finally a model is optimized through back propagation; calculating the correlation between the nodes and hyperedges, and distributing each node to the first Ke hyperedges with the highest attention coefficient; and updating node features by combining Fourier transform and regularization terms with the weight matrix. According to the method, the complexity of the protein interaction network is effectively processed through the dynamic hypergraph, and the prediction precision is remarkably improved.

The disclosure provides a traditional Chinese medicine efficacy evaluation method and device based on a node-weighted network, equipment and a storage medium. The method determines target disease protein targets and corresponding target weights based on the comprehensive scoring results of candidate disease protein targets by a public database and a large language model. When determining the protein targets of medicinal materials and the corresponding protein target weights of medicinal materials, the prescription ratio, chemical component information, and the interaction probability between the chemical components and the protein targets of each medicinal material in the traditional Chinese medicine prescription to be evaluated are comprehensively considered. The target disease protein targets and the corresponding disease protein target weights, as well as the protein targets of medicinal materials and the corresponding protein target weights of medicinal materials, are added to a pre-constructed protein interaction network. The obtained node-weighted network focuses on the real pharmacological basis, effectively improves the network biological interpretation, and the multi-dimensional network index determined accordingly is used to evaluate the regulation effect of the traditional Chinese medicine prescription to be evaluated on the target disease, which is more accurate.

The invention discloses core components, targets and action mechanisms of Zhibai Dihuang pills / decoction for treating early diabetic nephropathy based on a directed PPI network and a plurality of network centrality algorithms. Core components and targets of the Zhibai rehmannia pill / decoction for treating diabetic nephropathy are determined through the steps of screening active components of the Zhibai rehmannia pill / decoction, collecting target information corresponding to the active components, collecting disease related targets, obtaining drug-disease intersection genes, constructing a directed protein interaction network and the like. The action mechanism of the Zhibai rehmannia pill / decoction for treating diabetic nephropathy is researched. The invention provides a scientific theoretical basis for the treatment of diabetic nephropathy by the Zhibai Dihuang pill / decoction, and provides a new method for the clinical treatment and scientific research of the Zhibai Dihuang pill / decoction on diabetic nephropathy.

The invention discloses a method for drawing a human full-coverage protein interaction network based on digital PCR next-generation sequencing. After the advanced pedestrian 293T cell line obtains mRNA, a modified random primer or an oligo-dT primer is adopted to obtain a cDNA library; carrying out homogenization treatment on the human cDNA library; the method comprises the following steps: transforming plasmids of a BACTH bacteria double-hybrid system to obtain transformed plasmids; carrying out homologous recombination on the transformed plasmids of the sample library and the double-impurity system, and introducing into escherichia coli for screening to obtain positive PPI clones of the library with interaction; and carrying out digital PCR-based next-generation sequencing on the screened clones to draw the human full-coverage protein interaction network. The method is suitable for performing high-throughput screening after thousands of positive PPI combinatorial clones are obtained by'library-to-library 'bacteria or yeast double hybrids, identifying the same cell bar code cDNA combinatorial pairs, and realizing PPI network identification in different species, among species and in hybridization technology system extensive scenes.

This invention discloses a molecular docking analysis method for obtaining core targets based on the RCSB database, comprising: screening drug-disease-immunity intersection targets through multiple databases; screening core targets through protein interaction network analysis and multi-topology algorithms; obtaining core target structure files from the RCSB database and downloading active ingredient structure files from the PubChem database; performing molecular docking through the CB-DOCK2 database; screening effective binding pairs using binding energy as an indicator and visualizing the results; and finally outputting the results through functional annotation and pathway enrichment analysis. This method improves the accuracy of core target screening and the reliability of molecular docking through multi-database integration, multi-algorithm collaboration, and multi-dimensional evaluation, forming a complete technical chain and providing efficient technical support for the analysis of the mechanisms of action of traditional Chinese medicine compound prescriptions.

The present invention discloses a method, device, terminal, and medium for predicting synthetic lethal gene pairs based on a graph convolutional neural network. The synthetic lethal gene pair prediction method includes: obtaining protein structural features based on protein structure data; obtaining protein sequence features based on protein sequence data; obtaining protein functional features based on a protein-protein interaction network; merging and standardizing the protein structural features, sequence features, and functional features to obtain the gene features of the primary protein-producing genes; obtaining interactions between genes, and training a synthetic lethal gene pair prediction model based on a graph convolutional neural network using the gene interactions and gene features; obtaining a final feature representation for each gene based on the trained synthetic lethal gene pair prediction model, and predicting whether two genes form a synthetic lethal gene pair based on the final feature representation. This method improves the efficiency of feature extraction and the ability to predict gene interactions.

The application relates to a cancer driver gene explainable identification method based on trust calibration and prototype learning, and relates to the technical field of biological information identification. A gene graph is constructed by fusing a protein interaction network and gene multi-omics characteristics, and part of nodes are labeled. Label-aware message passing is performed through a trust calibration encoder, the neighborhood is split into a labeled part and a non-labeled part for independent calibration, and node embedding is adaptively fused. An angle margin prototype classifier is used to construct a class prototype on a hypersphere, the decision boundary is expanded, and a prediction result is output. A pivot node self-supervised regularizer is introduced, center nodes are screened from labeled driver genes, positive constraints are applied to neighbor non-labeled nodes, negative penalties are applied to non-neighbors, and a supervised boundary is maintained when non-labeled data is used. Finally, a structured explanation module is used to reuse the internal evidence of the model, a verifiable explanation is provided for prediction, and the unification of high precision and credible explanation is realized.

The invention relates to a novel chemical cross-linking agent with mass spectrum fragmentable trehalose disaccharide as a skeleton structure and a preparation method thereof. The cross-linking agent disclosed by the invention has the following characteristics: 1) trehalose disaccharide is used as a skeleton structure, so that the cross-linking agent has excellent biocompatibility; 2) the trehalose skeleton has a pair of symmetrical mass spectrum fragmentable glucosidic bonds, so that a cross-linked peptide fragment can be simplified into a conventional peptide fragment modified by a cross-linking agent fragment; 3) the enrichment of the cross-linked peptide fragment can be realized by the trehalose skeleton under the condition of not adding an enrichment handle; and 4) active groups of the cross-linking agent comprise but not limited to a plurality of reactive groups such as succinamide ester, diaziridine, phenylsulfonyl fluoride, hydrazide group, amino group, hydroxylamine group and the like, and chemical cross-linking of a plurality of amino acids except lysine is realized. The trehalose cross-linking agent disclosed by the invention is applied to the field of proteomics, and provides technical support for realizing large-scale analysis of a protein complex in a complex sample, spatial structure analysis of protein and a protein-protein interaction network.

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

Methods and systems for generating drug repurposing predictions for a disease caused by a pathogen, such as a novel pathogen, are provided. A multi-modal system includes a protein-protein interaction network (PPI), a graph neural network (GNN), a diffusion module, a proximity module, and an aggregation module. The GNN is configured to predict new edges between candidate drug nodes and disease nodes in an embedded representation of the PPI to produce a decoded embedding space. The diffusion module is configured to determine a proximity distance for pairs of nodes in the PPI, and the proximity module is configured to determine a proximity distance for pairs of nodes in the PPI, each pair comprising a pathogen-protein node and a drug-protein node. A ranked list of candidate drugs predicted to be effective in treatment of the disease based on candidate drug lists generated by the other modules is generated by the aggregation module.

The application discloses a method for predicting different metabolic states of cells in cancer and metabolic characteristic subtypes of the cells based on a metabolite-protein interaction network, and the method comprises the following steps: (1) identifying the classification and metabolic state of the cells: preprocessing data, filtering low-quality cells; performing twice principal component analysis according to key genes; performing twice dimension reduction clustering on the cells respectively; (2) predicting metabolic characteristic subtypes of a queue according to the proportion of different metabolic states of cells in the sample. The method can identify the metabolic state of the cells and metabolic subtypes, and provides a new perspective for cancer research.

The present invention discloses a method for analyzing the liver toxicity differences between proton pump inhibitors and H2 receptor antagonists based on network toxicology. The method of the present invention comprises the following steps: mining the action targets of drugs and liver toxicity disease risk genes in a database, constructing a protein interaction network of the drug-induced liver injury disease module DILI, and performing GO biological function and KEGG pathway enrichment analysis on the risk genes; overlapping the drug targets and the DILI disease module and analyzing the drug liver toxicity mechanism; calculating the proximity degree between the drug and the DILI disease module by using a network proximity strategy; and finally performing molecular docking on the drug molecule and the core target. The method of the present invention reveals that H2 receptor antagonists have stronger liver toxicity than proton pump inhibitors, explores the mechanism of potential liver injury of drugs, and provides a reference for the subsequent liver toxicity research of drugs.

The invention discloses a method for analyzing an action mechanism of acanthopanax for treating non-small cell lung cancer based on network pharmacology, molecular docking and molecular dynamics simulation, and relates to a pharmacology mechanism research method, and the method comprises the following steps: S1, screening active ingredients; s2, acquiring a disease target; s3, constructing and analyzing a compound-target spot-disease network; s4, constructing a protein interaction network; s5, performing KEGG pathway enrichment analysis and GO function enrichment analysis to explore a specific anti-non-small cell lung cancer mechanism; s6, construction and analysis of a chemical component-target-pathway-disease network of the acanthopanax senticosus; s7, exploring the mechanism by molecular docking; and S8, evaluating the binding stability of the protein-ligand complex through molecular dynamics simulation. According to the method, the enrollment threshold of network pharmacology is simplified; according to the used method, data is directly mined in each database, and network pharmacology, molecular docking and molecular dynamics simulation are combined, so that the content is more layered, and the action mechanism of the chemical components of the acanthopanax senticosus for treating the non-small cell lung cancer can be accurately analyzed.

The invention relates to a solanaceae stress resistance multi-omics database, a construction method thereof, equipment and a medium. A construction method of a solanaceae stress resistance multi-omics database comprises the following steps: S10: downloading solanaceae plant multi-omics original data, and obtaining a standardized metabolic pathway annotation file; s20, filtering low-quality sequences, unifying metadata naming rules, and performing semantic standardization processing; s30, performing differential expression gene analysis and screening, constructing a gene-metabolite co-expression network, and generating a visual map; s40: constructing a MySQL relational database to store structured data such as gene expression and metabolites, and establishing a gene-metabolite-protein interaction network model; and S50, implementing a composite index to accelerate high-frequency query, performing database horizontal fragmentation according to species classification, and deploying middleware to realize distributed data transparent access. According to the solanaceae stress-resistant multi-omics database and the construction method, equipment and medium thereof, a special database system supporting high-throughput data management and deep mining is constructed.

A method for establishing and predicting a chemical potential biological target point model, the method for establishing comprising: obtaining a protein interaction network and transcriptome data containing differential genes under the influence of a chemical; diffusing the differential scores of the differential genes to adjacent gene nodes along the protein-protein interaction network to obtain diffused differential gene nodes; calculating the average shortest distance between each gene node and the diffused differential gene nodes; sorting the gene nodes in the protein interaction network based on the average shortest distance to obtain a target protein prediction list; adjusting the diffusion parameters until the target protein prediction list meets a first prediction accuracy condition; and selecting a cutoff value of the target protein prediction list that meets the first prediction accuracy condition so that the target protein prediction list before the cutoff value meets a second prediction accuracy condition. The prediction model can quickly and accurately predict potential biological target points.

The invention discloses a combined product based on NanoBiT luciferase three fragments, a method and application. The combination comprises a first fusion protein, a second fusion protein, and a third fusion protein. According to the combined product, NanoBiT luciferase is divided into three fragments, the three fragments are fused with different protein fragments, it is ensured that all the fragments of NanoBiT luciferase are integrated into a protein interaction network, therefore, non-specific signals are reduced, the biological authenticity and reliability of experimental results are improved, and compared with a traditional NanoBiT luciferase two-fragment system, the combined product has the advantages that the combined product is simple in structure and convenient to use, and the application range is wide. The light-emitting signal of protein interaction is obviously enhanced, and a more accurate tool is provided for in-vitro research of protein interaction.

A traditional Chinese medicine intelligent screening method based on network targeting comprehensive indexes belongs to the technical field of traditional Chinese medicine intelligent screening. The method comprises the following steps: constructing a target set A and a protein interaction network database corresponding to each traditional Chinese medicine; constructing a disease core gene set B based on a protein interaction network; calculating a network targeting comprehensive index based on the target point set A and the disease core gene set B; calculating the network targeting comprehensive index of each traditional Chinese medicine and then performing ascending sorting, wherein the smaller the network targeting comprehensive index is, the stronger the network targeting relevance between the traditional Chinese medicine and the disease is; and matching the traditional Chinese medicines according to the obtained ascending order, and generating a structured and explainable final recommendation report. According to the method, the disease-related gene identification accuracy is improved, the biological interpretation of the result is enhanced, the standardized processing of integrating multi-source data into intelligent recommendation is realized, and the urgent demand of efficient and accurate screening in modern research of traditional Chinese medicines is met.

The invention discloses an action mechanism analysis method of an external medicine for treating liver cancer ascites, and relates to the technical field of medicines. Comprising the following steps: screening active ingredients and related targets of a medicine through network pharmacology; predicting liver cancer ascites related disease targets; constructing an intersection target point network of active ingredient target points and disease target points, and performing protein interaction network analysis; carrying out GO function and KEGG pathway enrichment analysis on the intersection target spot; establishing a medicine, component, disease, target spot and pathway network; the binding activity of the core target and the active component is verified through molecular docking; establishing a liver cancer ascites model through animal experiments, and performing efficacy verification; network pharmacology and animal experiment data are integrated, and a drug action mechanism is analyzed. According to the invention, active ingredients, target spots and pathways of the medicine are rapidly screened through network pharmacology, so that the earlier-stage research period is greatly shortened; animal experiment design is standardized, samples can be processed in batches, and the method is suitable for high-throughput drug screening.

The invention provides a network pharmacology-based large model generated traditional Chinese medicine prescription curative effect evaluation method and system, and the method comprises the steps: employing a machine learning model to generate candidate prescriptions, and obtaining all known active components of each traditional Chinese medicine in the prescriptions; predicting human body protein targets corresponding to the patient based on the known active components, and gathering all the human body protein targets to obtain a prescription target set P; obtaining human body protein targets related to the corresponding diseases, and gathering all the human body protein targets corresponding to the diseases to obtain a disease target set D; constructing a protein-protein interaction network; inputting the prescription target point set P and the disease target point set D into a protein-protein interaction network, and constructing a connected sub-network; calculating curative effect indexes of the connected sub-networks; and optimizing the prescription based on the curative effect index to complete the curative effect evaluation of the traditional Chinese medicine prescription. According to the method, calculation and experiments are closely combined, the blindness and the cost of experimental verification are remarkably reduced through a calculation priority strategy, and the research and development efficiency is improved.

The present invention provides a method for reconstructing a weighted protein interaction network and a method for predicting protein complexes. The method for reconstructing a weighted protein interaction network comprises: step S1: checking the weight consistency index of the link weight matrix of a given weighted protein interaction network; step S2: keeping the edge conditions of the original weighted protein interaction network unchanged, selecting the entire original weighted protein interaction network as a training set, and reconstructing the weight information in the edges of the original weighted protein interaction network only through a link weight prediction algorithm based on a weight perturbation model and a latent factor model to obtain a new weighted protein interaction network. After adopting the above technical solution, data enhancement of the protein interaction network is achieved, the protein interaction network is optimized, and the prediction effect of the protein complex is improved.