104 results about "Gene prediction" patented technology

The invention discloses a method for obtaining disease potentially-associated genes based on multi-source information fusion. The method comprises the following steps of: predicting disease-associated genes found based on uncorrelated literature knowledge, predicting disease-associated genes based on functional similarity, predicting disease-associated genes based on a regression prediction model, respectively scoring associated genes obtained through prediction of disease-associated genes found based on uncorrelated literature knowledge, prediction of disease-associated genes based on functional similarity and prediction of disease-associated genes based on a regression prediction model, establishing preliminary analysis to the associated genes, and fusing results obtained in all steps to obtain a final judgment result to determine the disease potentially-associated genes.

The invention discloses a sequence characteristic analysis method for forecasting a miRNA target gene. The method comprises the steps of constructing related characteristics of 27 miRNA-target point pairing sequences on the basis of a CLASH experiment data set, and forming a characteristic set comprising 84 characteristic values by combining traditional characteristic; and performing machine learning by using a random forest model, and constructing a miRNA target gene forecast model to perform miRNA target gene recognition. The model constructed according to the method has the advantages of high accuracy, sensitivity, specificity and precision, and the miRNA target gene can be relatively and accurately forecasted.

The present invention relates to a method for selecting a gene intended to predict the prognosis for a cancer, to the selected gene for predicting the prognosis of cancer and to a kit for predicting and a method for predicting metastasis in breast-cancer patients by using the same. In the present invention, a straight forward method is used to achieve high-reliability prediction of the patient's prognosis by analysing for the genetic characteristics of early stage breast cancer, and thus the present invention can be used to advantage in prognosis diagnosis which can reduce unnecessary anticancer therapy.

The invention relates to a miRNA function recognition method based on multi-genomics, and relates to a miRNA function recognition method based on multi-genome. The present invention aims to solve theproblem of low accuracy of miRNA function recognition in the prior art. The method of the invention comprises: analyzing differentially expressed genes through gene expression profiles; constructing disease-or drug-related protein networks; selecting functional modules of the constructed protein network related to disease or drug; performing enrichment analysis of the selected functional modules to determine the key genes in the functional modules; analyzing differentially expressed miRNAs by miRNA expression profiles to predict the target genes of differentially expressed miRNAs; performing construction of miRNA-regulated disease-or drug-related protein networks; performing functional enrichment analysis on the nodal genes of the constructed miRNA-regulated disease or drug-related proteinnetwork to identify the function of miRNA. The invention is used in the field of bioinformatics.

The invention provides a maize single panicle weight main effect QTL, as well as an acquisition method and application thereof. The QTL comprises qEW-1, qEW-2, qEW-3, qEW-4 and qEW-5. The method comprises the following steps: configuring cross combination by taking a high-yield early-maturity maize inbred line SG5 as a female parent and a maize inbred line SG7 with relatively poor yield trait as a male parent, and constructing an F2 genetic group of the cross combination; performing GBS sequencing-basing typing on the F2 genetic group, and performing genotyping by combining differential SNP validated based on SG5 and SG7 parents; investigating the yield trait of single F2 panicle, performing QTL analysis on the F2 single panicle yield trait by utilizing a winQTLcart2.5 software composite interval mapping method, and analyzing the chromosome region of the main effect QTL and the genetic effect. According to the method, a theoretic base is provided to excavating and controlling the maize single panicle weight main effect QTL and linked marker, a molecular marker closely linked with the target QTL is acquired, and foundation is laid to maize single panicle yield trait QTL candidate gene prediction, cloning and molecular mark assisted breeding.

The invention discloses an exogenous miRNA regulatory target gene prediction method containing three-dimensional free energy. In order to improve traditional sequence matching characteristics, statistical characteristics of the three-dimensional energy in a seed area and statistical characteristics of a spatial distribution penalty function at binding sites are newly provided, the characteristicsof the seed area binding sites represent the specific matching information of the binding sites, so that a constructed feature input vector is more accurate and more practical, and therefore the accuracy of miRNA target spot prediction is improved.

The invention discloses a method for screening MicroRNAs of nilaparvata lugens with effect on oryza sativa resistance adaptability, and relates to the bioengineering technology. The method comprises the following steps: (1) sample collection; (2) sequencing of small RNA; (3) pretreatment of sequencing raw data; (4) sequence alignment; (5) new miRNA prediction; (6) analysis of miRNA differential expression; (7) prediction of differential miRNA target genes; (8) synthesis of miRNA mimic, miRNA inhibitor and control chain; (9) microinjection and artificial feeding of miRNA mimic and miRNA inhibitor to nilaparvata lugens and verification of the function of miRNAs; (10) preliminary study on oryza sativa resistance adaptability change of the nilaparvata lugens after microinjection and artificialfeeding. Small RNAs of two nilaparvata lugens groups are deeply sequenced with a high-throughput sequencing technology, and are analyzed, identified and predicted according to subsequent bioinformatics, differences between the two nilaparvata lugens groups on insect-susceptible oryza sativa TN1 and insect-resistant oryza sativa YHY 15 are compared, the miRNA associated with host resistance adaptability is analyzed, screened and discovered, and the new method is provided for oryza sativa insect-resistant breeding.

The invention discloses a method for rapidly identifying cashmere cycle development. The goat miRNA is identified comprehensively, the differential expression profiles of goat skin follicle in different growth periods (growth period, rest period, and regression period) are compared so as to screen out miRNA of differential expression; a technology of fluorescent quantitation is adopted to verify the result; through target gene prediction and transcript profile difference comparison, the gene for modulating follicles is searched, the functions of miRNA is determined; and finally the miRNA-263 is the specific miRNA for cycle development of follicles. Through identifications, people find that the miR-263b is accord with the cashmere cycle development rule; the target gene modulated by miR-263b is part of key gene in the cashmere cycle development pathway; the change of expression of miR-263b can precisely represents the specific periods of cashmere, and thus miR-263b can be used to indicate the periods. So miR-263b has an important value on research and application, and can be used as a novel reference for prognosis judgment of cashmere cycle development.

The present invention provides for the identification of genes that are expressed in tumors that are responsive to a given therapeutic regime and whose expression correlates with responsiveness to that therapeutic regime. One or more of the genes of the present invention can be used as markers to identify patients that are likely to be successfully treated by a therapeutic regime.

The invention relates to the field of gene detection technologies and biomedicine, in particular to a breast cancer patient recurrence risk 20 gene prediction model based on breast cancer single-celltranscriptome sequencing analysis and an establishment method and application thereof. The model is composed of 20 genes of CEBPD, SERPINA1, CD24, ERRFI1, BCL3, DSTN, BTG2, SERTAD1, SPINT1, BAMBI, LIMCH1, NFIA, SKP1, DHRS7, ODF3B, KRT7, ZFP36, CEBPB, BHLHE40 and UGDH. The breast cancer patient recurrence risk 20 gene prediction model provided by the invention provides more accurate judgment for long-term prognosis of a breast cancer patient, and provides a basis for selection of a postoperative adjuvant therapy scheme of the patient, so that individualized accurate treatment is realized, and meanwhile, a new research perspective is provided for research of breast cancer tumor stem cells.

The invention is applicable to the technical field of cross-computer science and bioinformatics, and provides a metagenome gene analysis method, device and equipment and a storage medium. The method comprises the steps of screening and assembling each set of received sequencing data, generating assembling data corresponding to the sequencing data, generating predicted genes of each set of sequencing data by performing gene prediction on the assembling data, constructing a gene dictionary according to the predicted genes, clustering the gene dictionary according to the abundance of each gene inthe gene dictionary, classifying and assembling each set of screened sequencing data according to clustered gene clusters, and generating and outputting genes of metagenomes. Accordingly, on the condition that no existing biological gene is adopted as a reference genome, gene analysis of the metagenome is achieved, the limit caused by the reference genome is avoided, and the gene analysis accuracy of the genome is effectively improved.

The invention relates to a prediction method for a target gene of long-fragment non-coding RNA of forest tree, and belongs to the technical field of molecular genetics. The prediction method for the target gene of the long-fragment non-coding RNA of the forest tree, provided by the invention, comprises the following steps of 1) obtaining a lncRNA sequence of the forest tree; 2) obtaining a target gene of the lncRNA subjected to preliminary screening by utilizing a blast prediction method; 3) obtaining a target gene of the lncRNA subjected to secondary screening by utilizing an RNAplex prediction method; and 4) detecting tissue specific expression modes of the lncRNA and the target gene of the IncRNA subjected to the secondary screening in the step 3), calculating expression correlation of the lncRNA and the target gene of the lncRNA, and determining an interaction relationship between the lncRNA and the target gene of the lncRNA. According to the prediction method, the action fragments of the lncRNA and the target gene of the lncRNA can be efficiently and stably detected, and the accuracy of predicting the target gene of the lncRNA of the forest tree can be remarkably improved.

The invention discloses a smart city intelligent rail vehicle fault gene prediction method and system, and the method comprises the steps: collecting the vibration data Xh (0) = [e1, e2, e3,..., en] belongs to R of a train part, and enabling e1, e2,..., en to represent the vibration information of each sampling point on a train; encoding the vibration data into a DNA sequence, extracting features of the DNA sequence, and permuting and combining the features to form a predictable DNA sequence, namely a candidate vehicle part fault gene; and training an ESNs deep echo state network by using the candidate vehicle part fault gene to obtain a prediction model. The method and system can accurately predict the vehicle fault.

The invention discloses a method for carrying out ceRNA prediction based on miRNA target gene prediction and related expression analysis. The method is characterized by comprising the following steps:carrying out correlation analysis on a ceRNA action pair; screening potential ceRNA relationship pairs according to the number of common MERs; evaluating the regulation and control function of the miRNA on a pair of competitive lncRNA-mRNA by adopting two scoring modes according to the expression correlation of the miRNA and the ceRNA to the three; and obtaining results of statistical test significance, and sorting the results according to scores. The method for carrying out ceRNA prediction based on miRNA target gene prediction and related expression analysis has the advantages that after the ceRNA is preliminarily analyzed, the inter-gene expression correlation is analyzed according to an actual sequencing result, and the result is screened; different target gene prediction methods areadopted for animals and plants, so that ceRNA prediction analysis can be performed; and information in a common database is integrated, and the reliability of an analysis result is improved.

The invention relates to a method for predicting a microRNA target gene, which is suitable for predicting the target gene of the microRNA located in the gene coding region. The present invention includes the following procedures: step 1, establishing the coding region sequence database of the organism to be studied; step 2, performing sequence comparison with the coding region sequences of other species to find conserved segments; step 3, designing a target gene prediction program and compiling and debugging; step 4, for each microRNA, scan the coding regions of all genes, and obtain binding sites from conserved sequences; step 5, statistics and query of target genes; step 6, experimental verification. The method has the advantages of simple implementation, high reliability of results, and can meet the needs of prediction of target genes in most microRNA coding regions.

The invention discloses an Alzheimer's disease related gene prediction method. The method includes the following steps that: data information is obtained; FPKM values expressed by splicing isoforms are calculated, the splicing isoforms are screened, so that FPKM1 values are obtained; the splicing isoforms are screened; samples are clustered, and outliers are eliminated; the scale-free networks, topology overlap matrixes and node dissimilarity matrixes of the samples are constructed, and clustering and merging are performed; a network edge file is generated through transformation; an undirectednetwork is generated, screening is performed, so that splicing isoforms with network structure differences are obtained; modules are merged, the differences of the modules are judged, splicing isoforms with differences are obtained; and the union of the splicing isoforms with network structure differences and the splicing isoforms with differences is obtained, and a final result is obtained. Withthe method of the invention adopted, the related genes and splicing isoforms of the Alzheimer's disease can be predicted, and data support and theoretical basis can be provided for subsequent work.

The present invention designs a method for using literature mining technology to study the relationship between virus and human protein expression regulation, including the following main steps: step 1, predicting the direct target gene from microRNA; step 2, predicting the direct target protein from the above target gene; Step 3, use literature mining technology to construct a protein-protein interaction database; Step 4, use the constructed protein interaction database to screen out the indirect target protein and indirect target gene of microRNA from the direct target protein; Step 5, through the experiment Validation of indirect target genes of microRNAs. The feature of this method is that an "indirect" target gene model is proposed, and the literature mining technology is introduced to screen out the real microRNA target genes that are difficult to detect by conventional methods.

The invention discloses a drug sensitivity prediction method, electronic equipment and a computer readable storage medium, and relates to the technical field of drug detection. The method comprises the steps: acquiring gene sequencing data and drug feature data of cancer cell tissue to be trained, pre-processing the gene sequencing data according to the drug feature data to obtain gene sample data, performing verification processing according to the gene sample data and the drug characteristic data to obtain a prediction model and a gene prediction list, and performing drug sensitivity prediction on the cancer cell tissues to be detected through the gene prediction list and the prediction model. Therefore, drug reactivity prediction on clinical patients can be quickly and accurately realized, the prediction cost and the time cost are reduced, the prediction efficiency is improved. and the efficacy prediction efficiency is improved.

The invention discloses a genotype predicting method based on deep learning. The genotype predicting method comprises the following steps of A, according to a collected gene fragment, constructing a preliminary training set; B, performing gene phase determining on the preliminary training set, and performing 0,1,0.5 coding on two haplotypes after gene phase determining, segmenting the coded data to a primary training set and a testing set; C, constructing a neural network model according to the acquired adjacent SNP sites, and training the model by means of the primary training set; D, processing the testing set in steps A and B, introducing the processed testing set into a trained neural network model, and calculating a predicted value and model credibility of the testing set; and E, processing an actual to-be-predicted gene sequence and introducing a model, intercepting a site with credibility which reaches a certain degree for effective predicting, and outputting a result. The genotype predicting method can settle problems of high calculating resource consumption and overlong time consumption in existing gene predicting technology.