81 results about "Disease Association" patented technology

The present invention provides a method for diagnosing a disease or disorder associated with aberrant GSK-3β expression and / or activity or for determining the predisposition of a subject to the disease or disorder. In particular, the methods of the present invention comprise detecting a marker that comprises one or more polymorphisms and / or one or more allelic variants of a glycogen synthase kinase 3β gene. The present invention also relates to a method for identifying new markers that are diagnostic of a disease or disorder associated with aberrant GSK-3β expression and / or activity. Furthermore, the present invention relates to methods of identifying and producing candidate compounds for the treatment of a disease or disorder associated with aberrant GSK-3β expression and / or activity.

The invention discloses a method and a system for predicting the association relationship between a disease and LncRNA. The method comprises the steps: the LncRNA-miRNA association relationship and the miRNA-disease association relationship are obtained from a known database, and a LncRNA-miRNA-disease interaction network is constructed according to the two relationship; a disease hyper-expressionprofile and a LncRNA hyper-expression profile are constructed based on the LncRNA-miRNA-disease interaction network; the prediction model of the disease and LncRNA association relationship is trainedaccording to the disease hyper-expression profile and the LncRNA hyper-expression profile by using LncRNA similarity computing and disease similarity computing based on the RBF neural network; and the LncRNA-disease association pairs of the candidate samples are predicted by using the prediction model. The most promising LncRNA disease association for further experimental verification is provided, the potential disease-related LncRNA can be effectively mined from the mass biological data, the cost and the expense of the biological experiment can be reduced and the research progress in the bioinformatics field can be accelerated.

The invention discloses a miRNA-disease association predicting method based on double random walk models. The method is characterized by comprising the following steps of 1), acquiring a known miRNA-disease association dataset, and establishing an adjacent matrix which is associated with miRNA-disease; 2), respectively constructing Gaussian interaction attribute kernel similarity matrix of the miRNA and the disease; 3), constructing a miRNA function similarity matrix and a disease meaning similarity matrix; 4), integrating similarities of the disease and the miRNA by means of a similar networkfusion algorithm; and 5), predicting the miRNA-disease association relation by means of the double random walk models. The miRNA-disease association predicting method has advantages of low cost and short time consumption. Furthermore the predicting precision of the miRNA-disease association predicting method is higher than that of existing methods.

An embodiment of the invention provides a relation predicating method, a device and electronic equipment. The relation predicating method comprises the steps of fusing a plurality of medicament single-attribute similarity networks, a plurality of target single-attribute similarity network and a plurality of disease single-attribute similarity networks, thereby obtaining a fused medicament similarity network, a fused target similarity network and a fused disease similarity network; constructing a three-element heterogeneous network according to the fused medicament similarity network, the fusedtarget similarity network and the fused disease similarity network; predicting the network node of the three-element heterogeneous network, and obtaining a first association relation which comprisesa first medicament-target association relation, a second medicament-disease association relation and a first target-disease association relation. Therefore medicament-target-disease three-element association relation information can be sufficiently mined. The similarity networks of multiple attributes of medicament, disease and target are fused. Accuracy reduction of the predication result causedby eccentricity caused by a single attribute is prevented.

The invention discloses an intelligent hospital guide method and an intelligent hospital guide device. The intelligent hospital guide method includes generating symptom lists according to acquired patient information and pathogenic sites; screening diseases according to selected disease parameters and generating inquiry problems; carrying out sorting according to answers to the inquiry problems and the possibility of the diseases; querying consultation departments corresponding to the selected diseases; transmitting acquired names of the consultation departments. The intelligent hospital guide method and the intelligent hospital guide device have the advantages that the intelligent hospital guide device is combined with technical means such as databases, information matching and intelligent search, and accordingly hospital guide processes in actual scenes can be effectively simulated in the aspect of disease association and screening; the integral hospital guide processes contain intact contents and are meticulously classified; systems are high in automation and intelligent degree, accordingly, the hospital guide efficiency and accuracy can be greatly enhanced, the process experience is concise and smooth, and the intelligent hospital guide method and the intelligent hospital guide device are high in user operation friendliness.

The invention discloses a computer-assisted ultrasonic diagnosis method for a left atrium / left auricle thrombus. The technical scheme includes that data mining technology, a pattern recognition theory and medical clinical information are combined, a gray-scale video and a real-time three-dimensional dynamic video serve as research objects, all-dimensional information in an image is accurately acquired, potential disease association rules in the image information are mined, and multiclass characteristics are comprehensively analyzed to obtain a detection method for automatically detecting and classifying the left atrium / left auricle thrombus. A thrombus recognition method can avoid missed diagnosis and misdiagnosis caused by subjective reasons such as inadequate experience or visual fatigue of doctors, and patients with suspected left atrium / left auricle thrombi clinically detected by transesophageal echocardiography can be confirmed as early as possible, so that the patients without thrombosis can receive cardioversion treatment of atrial fibrillation as early as possible. The method is simple and convenient to operate and high in practicability, and has important guiding significance for diagnosis and treatment of the left atrium / left auricle thrombus and ventricular fibrillation.

The embodiment of the application relates to a miRNA-disease association prediction method, a system, a terminal and a storage medium. The method comprises the following steps of: constructing a miRNA-disease association matrix, a miRNA similarity matrix and a disease similarity matrix according to miRNA-disease related data; constructing a heterogeneous network according to the miRNA-disease association matrix, the miRNA similarity matrix and the disease similarity matrix; learning topological information of the heterogeneous network by adopting a neural network, calculating optimal parameters of the heterogeneous network through topology preservation, and reconstructing the heterogeneous network according to the optimal parameters; the reconstructed heterogeneous network is the correlation score matrix of miRNA and diseases. The embodiment of the application solves the problems of high cost and time consumption of a biological experiment method, improves the effect of miRNA-disease association prediction, has practicability, and can be used for association prediction between diseases without known association and miRNA.

The invention discloses a drug recommendation method, an electronic device and a storage medium. The method comprises the following steps: acquiring a disease set; acquiring disease association data according to the disease set; acquiring disease matching data of each drug; calculating a drug matching coefficient of each drug according to the disease association data and the disease matching dataof each drug; recommending drugs whose matching coefficients meet recommending conditions. Based on the correlation coefficients between different diseases and the disease matching coefficients between specific drugs and various diseases, the drug matching coefficients between the drugs and the disease set input by a demander are comprehensively evaluated, the link between the diseases is taken into account, the effect of the drugs on various diseases is also considered, and recommending results are more accurate. Moreover, the disease association data and the disease matching data of the drugs can pool wisdom and are scientific and transparent, and new drug data can be conveniently populated.

The invention discloses an lncRNA-miRNA-disease association method based on fusion similarity. The method comprises the following steps: constructing an lncRNA-miRNA-disease network; calculating the functional similarity of the fused lncRNA; calculating and integrating disease semantic similarity; obtaining a weight matrix of the miRNAs between the miRNA-lncRNAs and a weight matrix of the miRNAs between the miRNA-diseases according to a weight distribution algorithm; obtaining a miRNA-lncRNA association score matrix according to the fused lncRNA with similar functions, the miRNA-lncRNA adjacency matrix and the weight matrix of miRNA-lncRNA between the miRNA-lncRNAs; integrating the disease semantic similarity, the miRNA-disease adjacency matrix and the weight matrix of miRNAs among miRNA-diseases to obtain a miRNA-disease association score matrix; integrating the two incidence matrixes to obtain an incidence score matrix Smld; and predicting the Smld by using the prediction model. Theunknown incidence relation hidden under the data is revealed through the multi-aspect data relation.

The invention discloses a circRAN-disease association predicating method based on a network model. The method is characterized by comprises the following steps of 1), acquiring a circRNA-disease association data set, and constructing an adjacent matrix A which is related with circRNA-disease association; 2), constructing a circRNA Gaussian interaction attribute kernel similarity matrix KC; 3), constructing a disease Gaussian interaction attribute kernel similarity matrix KD; and 4), performing circRNA-disease association matrix according to a network consistency projection model. The method has low cost and can improve circRNA-disease association prediction precision.

The invention discloses a drug activity prediction method and application thereof. The method comprises the following beneficial effects: step one, targets of human on-market or under-study drugs andtreatment activity information are collected by inquiring drug target interaction database information; step two, searching for a plurality of virulence gene databases, collecting disease associationgenes, and according to activity rates of drugs corresponding to the disease association genes, different assignment values of disease association genes of different database sources are given; step three, feature attributes of the drug targets and the disease association genes are built; step four, a machine learning prediction model is constructed; step five, a model prediction result is evaluated; and step six, a drug with activity to a specific disease is predicted. According to the invention, the drug activity prediction method can be used as a GPS in the drug discovery field; disease association genes can be identified efficiently; the effective guidance is provided for prediction, research and development of active drugs; and a novel method and idea is provided for the drug discovery field in future.

The invention discloses an enteric microorganism detection data analysis method, an automatic interpretation system and a medium. The method comprises the following steps: acquiring enteric microorganism sequencing data of a user; extracting sample data from the sequencing data, and filtering the sample data; performing species annotation classification and function annotation classification on the filtered sequencing data to obtain an annotation result; performing conventional analysis on the annotation result, wherein the conventional analysis comprises diversity analysis and probiotics content and pathogenic bacteria content analysis; and obtaining a flora function and disease association database, and based on the annotation result, automatically interpreting the conventional analysisresult according to the flora function and disease association database. According to the method, analysis and interpretation can be automatically executed, so that the working pressure is reduced, the generated analysis results are diversified in form and good in readability, the requirements of users are met, process and batch operations are conveniently carried out, and the workload of manual interpretation is small, visual and convenient.

The invention discloses a microRNA-disease association prediction method based on a multi-mode stacking automatic coding machine. The method comprises: forming microRNA sequence features and disease semantic similarity features; constructing a microRNA-protein-disease network, a microRNA-mRNA-disease network and a microRNA-lncRNA-disease network, and respectively obtaining network adjacent characteristics between microRNA and protein, between disease and protein, between mRNA and lncRNA and between disease and lncRNA by using a LINE network embedding method; mining, by using a multi-mode stacking automatic coding machine, the advanced abstract features of four features (self attribute features, protein network adjacent features, mRNA network adjacent features and lncRNA network adjacent features) of microRNA and diseases, thereby reducing the time complexity of a model and improving the prediction accuracy of the model; and training and predicting the processed features by using a CatBoost classifier, and taking an average value of prediction scores of the four features as a final prediction score. According to the method, the problems of high time consumption and high cost of a traditional biological experiment method are solved, so that a better classification effect is achieved, and the potential incidence relation between microRNA and diseases is predicted with higher accuracy.

The invention discloses a brand new distributed and privatized miRNA-disease association prediction method, which is characterized in that firstly, DPMDA collects, analyzes and estimates matrix factors representing the relationship between miRNAs and diseases, and the prediction accuracy is improved through exchanging information between distributed data sets; secondly, DPFMDA only needs positivesamples, the performance is not easy to be affected by the data sparsity, and the matrix factors from the distributed data set are used for generating a common reference factor; and thirdly, the DPFMDA is a distributed and privatized framework which perfectly realizes and promotes the cooperation between different biomedical databases. The biomedical research will benefit from the prediction results.

The invention discloses a non-coded RNA and disease association prediction method based on sparse subspace learning and belongs to the field of system biology. The method comprises steps of 1, constructing an adjacency matrix associated with non-coded RNA-diseases, and then respectively calculating Gaussian spectrum kernel similarity of the non-coded RNA and Gaussian spectrum kernel similarity ofthe diseases; 2, calculating a graph theory characteristic matrix and a statistic characteristic matrix according to two similarity matrixes and an adjacent matrix, further constructing a target function and solving a mapping matrix G; and 3, solving non-coded RNA-disease association pair relationship score prediction matrixes, and performing sorting to give the final prediction result. The methodis advantaged in that a graph theory, a statistical method and a machine learning method are fused, the information of a negative sample in the non-coded RNA-disease associated data can be effectively utilized, the non-coded RNA with significant correlation to disease occurrence and development can be efficiently, accurately and quickly predicted, and problems of long time consumption and high cost of a biological experiment method are effectively solved.

The invention discloses a non-coding RNA and disease relationship prediction method based on Hessian regular non-negative matrix factorization, and belongs to the field of system biology. The method mainly comprises the following three steps: 1, respectively calculating Gaussian spectrum kernel similarity of non-coding RNA and Gaussian spectrum kernel similarity of diseases; 2, calculating a prediction score of the non-coding RNA-disease association pair by using an iterative solution algorithm; 3, sorting the scores according to the calculated non-coding RNA-disease association, and giving afinal prediction result. According to the method, the internal manifold structure of the data is described meticulously through Hessian regularization, so that the information of a negative sample iseffectively utilized; the l2, 1 norm constraint and the approximate orthogonal constraint ensure the group sparsity of the coding matrix, and the influence of noise data can be weakened. According tothe method, a relatively reliable prediction result can be obtained, and the problems of long consumed time and high cost of a biological experiment method are effectively solved.

The invention provides a method for predicting a potential lncRNA disease based on a random walk target convergence set technology. The method comprises the following steps of: combining known long-non-coding RNA-disease association with long-non-coding RNA comprehensive similarity and disease comprehensive similarity to construct a heterogeneous network, so that the defect that a walking processcannot be started by adopting a traditional method based on RWR under the condition that no known long-non-coding RNA-disease association exists is overcome. Then, each node in the heterogeneous network establishes own TCS according to the network distance information, so that the particularity of different nodes in the walking process can be reflected, the prediction is more accurate, and the consumed time is less. Furthermore, by considering that for a given random walker, when the TCS has reached the final convergence state, some nodes may still not be included in the TCS, but are actuallyassociated with the TCS, and it is ensured that the prediction result is not missed.

The invention discloses a miRNA-disease association prediction method and device based on graph neural network fusion multi-view information, and the method integrates miRNA-disease-related multi-omics data to construct a plurality of views, not only considers a plurality of homogeneous similarity networks, but also considers a heterogeneous bipartite network, extracts node features on all views in combination with a graph neural network and multi-view learning, captures dependency between global features and local features through a discriminator, and can better capture the complex nonlinear relation between miRNA and diseases.

The invention discloses a miRNA-disease association identification method and system based on fusion attributes. The method comprises the following steps: firstly, calculating functional similarity between any two miRNAs in a disease database, constructing an miRNA network undirected graph according to the functional similarity, calculating an aggregation coefficient between any two different miRNAs, and fusing the functional similarity and the aggregation coefficient between the two miRNAs to obtain a combined weight; secondly, calculating the weight of each miRNA vertex according to the combined weight, performing descending sort on each miRNA according to the weight, and screening out potential miRNAs related to diseases according to a descending sort result. The method is simple to implement; on the basis of fusing two attributes of topology attributes and function similarity, the miRNA nodes are weighted and sequenced in a descending order, and then potential correlation between miRNA and diseases is predicted by means of a disease database related to human miRNA and by means of a sequenced result, so the miRNA-disease correlation identification accuracy is improved, and valuable clues can be provided for medical diagnosis.

The invention belongs to the field of bone marrow cell morphology detection, and particularly relates to a disease association method of a bone marrow cell morphology automatic detection system. According to the technical scheme, the disease association method of the bone marrow cell morphology automatic detection system comprises the following steps: S1, counting and recognizing cells in a screening area; and S2, putting the cell screenshots with abnormal sizes, shapes, dyeing and structures into an auditing system for artificial description. According to the invention, the disease association is developed by combining the data of the bone marrow image and the blood image and the morphological characteristics of abnormal cells; the screened diseases are high in accuracy, a large amount oftime of doctors is saved, the workload of the doctors is reduced, the diagnosis efficiency of the doctors is improved, the problem that a final report is restricted by the professional level of people can be avoided, a stable and standard diagnosis conclusion can be obtained finally, and therefore the overall diagnosis level is improved.

The invention discloses a self-avoiding random walk-based disease-associated miRNA prediction method and system. According to the method of the invention, self-avoiding random walk is adopted to traverse a disease-miRNA bipartite graph, and the association degree of two nodes is measured through the ratio of two attributes (the transition probability and average step size of the two nodes) of theself-avoiding random walk, and therefore, the association between a disease and miRNAs is realized. The method can be used for both an unweighted miRNA-disease bipartite graph and a weighted miRNAs-disease bipartite graph. With the method adopted, disease-associated miRNAs can be accurately predicted based on known miRNA-disease association information, a large number of pathogenic miRNAs can be predicted at one time, and problems such as high cost and time-consuming performance of a biological experimental method can be solved.

Methods and constructs are provided that are predictive of a subject's susceptibility to developing a metabolic disorder, such as obesity. The disclosed naturally-occurring SNPs located upstream of the NPY2R gene can be used as targets for the design of diagnostic reagents and the development of therapeutic agents, as well as for disease association and linkage analysis. In particular, the SNPs of the present invention are useful for identifying an individual who is at an increased or decreased risk of developing metabolic disorders, such as obesity and diabetes, and for early detection of the disease, for providing clinically important information for the prevention and / or treatment of metabolic disorder, and for screening and selecting therapeutic agents. The SNPs disclosed herein are also useful for human identification applications. Methods, assays, kits, and reagents for detecting the presence of these polymorphisms and their encoded products are provided.

The invention discloses a miRNA-disease association prediction method and system based on tensor decomposition. The method comprises the following steps: using tensors to represent complex relationships among miRNA-disease, miRNA-gene and gene-disease, in the tensor decomposition process, exploring a complex biological mechanism in combination with auxiliary information, then integrating an alternating direction multiplier method (ADMM) framework and an optimization strategy of a conjugate gradient (GC) method to solve an objective function to obtain a miRNA-gene-disease association scoring tensor, converting the association scoring tensor into a miRNA-disease association scoring matrix, and evaluating method performance through the miRNA-disease association scoring matrix so as to provide an effective result for acquiring disease association miRNA. Experiments show that the method provided by the invention has good prediction performance, and can provide an effective result for acquisition of the disease-associated miRNA.

The invention aims to overcome the defects in the prior art, and provides a sample imbalance-oriented multi-disease classifier design method, which comprises the following steps: dividing medical casedata into a plurality of case sample subsets according to disease categories, and performing a feature selection method of a disease association rule on each sample subset; selecting a feature vectorof the case sample subset, iteratively and randomly updating the adoption probability on the premise that the imbalance degree is an upper limit threshold value, equalizing the case sample subset, training a weak classifier of each sample subset, and calculating the classification effect of the weak classifier; and finally, determining whether the iterative generation of the multi-disease classifier is finished or not by judging whether the difference value of the macro-F1 meets an iterative convergence threshold or not.

The invention belongs to the field of bone marrow cell morphology detection, and particularly relates to a bone marrow cell morphology automatic detection system and a working method thereof. According to the technical scheme, the bone marrow cell morphology automatic detection system comprises a printer and further comprises a central control module, a scanning structure and a man-machine interaction structure. The scanning structure is in communication connection with the central control module; the man-machine interaction structure is in communication connection with the central control module; the printer is in communication connection with the central control module; the scanning structure comprises a transmission device, a light source box and an image acquisition device; and the transmission device is arranged on the light source box and is rotationally connected with the light source box. The system integrates scanning, automatic detection, human interaction and disease association, performs full-automatic detection on bone marrow cell morphology, and avoids the problems of large detection workload, poor repeatability and easy misdiagnosis of disease conditions during manual detection.

According to the miRNA-disease association prediction method based on the attention mechanism, unknown miRNA-disease association is searched on the basis of known association data, and a foundation is laid for disease diagnosis and medicine research and development. The method comprises the following steps: firstly, obtaining initial feature representation of miRNA and diseases by utilizing a Gaussian profile kernel similarity function; embedding and longitudinally splicing miRNA and disease characteristics in the sample to form a sequence with only two nodes as the input of the encoder, an encoder being composed of a sub-attention module and a feedforward neural network module, and adding a residual module behind each sub-module in order to ensure the effectiveness of a result; and finally, using the output of the encoder as the score associated with the input prediction of the MLP decoder; and determining an optimal parameter through specific loss function back propagation.

The invention discloses a GHP and GCN fused Chinese and western medicine relocation method and system and a storage medium. The relocation method comprises the following steps: collecting multi-source and multi-mode heterogeneous data; gHP-GCN Chinese and western medicine relocation model construction specifically comprises the steps of global heterogeneous pharmacological network GHP construction, global heterogeneous pharmacological network and graph convolutional neural network fusion to form a GHP-GCN model, and "monarch, minister, assistant and guide" and "node semantic neighbor" dual weighted constraint optimization of the GHP-GCN model; constructing a training set and learning and reasoning a GHP-GCN model; contribution degree calculation and result analysis; and verifying and optimizing a result. The method can be applied to Chinese and western medicine relocation research, can predict potential and new drug-target protein / gene, target protein / gene-disease and drug-disease association, identifies new drug targets and new disease-associated pathogenic genes, and discovers and confirms drugs having potential treatment effects on diseases and integration effects and synergistic mechanisms thereof. A scientific basis is provided for explaining the effectiveness of Chinese and western medicine treatment and drug discovery.

The invention discloses an efficient prediction method for a circRNA and disease association relationship. The method comprises the following steps: 1, downloading circRNA data and disease data from a database website; 2, calculating a circRNA Gaussian kernel similarity, a circRNA gene similarity, a circRNA sequence similarity, a disease Gaussian kernel similarity and a disease semantic similarity which are respectively a matrix CIS, a matrix CGS, a matrix CES, a matrix DIS and a matrix DSS; 3, constructing a circRNA comprehensive similarity matrix CS, and constructing a disease comprehensive similarity matrix DS; 4, obtaining similarity matrixes CRS and DRS by using a restart random walk algorithm; 5, respectively splicing the CRS, the DRS and the A, and performing feature extraction by using a PCA algorithm to obtain feature matrixes CF and DF; 5, constructing a heterogeneous adjacency matrix Acd according to CS, DS and the adjacency matrix A; constructing a heterogeneous feature matrix CD according to the CF and the DF; 6, finally, performing classification prediction on the Acd and the CD by using a graph convolutional neural network. The method provided by the invention is a brand-new method for predicting the association of circRNA and diseases.

The present invention discloses a method and system for predicting the relationship between disease and LncRNA, comprising: obtaining LncRNA-miRNA-related relationship and miRNA-disease relationship from a known database, and constructing a LncRNA-miRNA-disease interaction network based on the two; LncRNA-miRNA-disease interaction network, construct disease super-expression profile and LncRNA super-expression profile; according to disease super-expression profile and LncRNA super-expression profile, use LncRNA similarity calculation and disease similarity calculation based on RBF neural network, train A prediction model for the association between disease and LncRNA; use the prediction model to predict the LncRNA-disease association pair of candidate samples. The present invention provides further experimental verification of the most promising LncRNA disease association, can effectively mine potential disease-related LncRNAs from massive biological data, reduce the cost and overhead of biological experiments, and accelerate the research progress in the field of bioinformatics.