31 results about "Gene subset" patented technology

The invention relates to a feature selection method and application based on feature identification degree and independence. The method comprises following steps: calculating the importance degree of each feature by measuring inter-class distinguished ability with feature identification degree and measuring correlational relationship between features with feature independence and sequencing in a descending order; and selecting top k features with the importance higher than those of others to form a feature subset with high class-discrimination performance. Differently-expressed gene subsets selected in application of oncogene expression profile data obtain fine time and class discrimination performance. The feature selection method and application based on feature identification degree and independence have following beneficial effects: easy calculations can be made; time complexity is reduced; selection efficiency runs high; and a good reference is provided for clinical diagnoses and judgments of tumors and other diseases.

The invention belongs to the technical field of biological information. The invention provides a method for integrating gene expression data by crossing a plurality of different chip platforms; the method comprises the following steps: the standard preprocessing is implemented for the gene expression profile of the plurality of chip platforms; the common gene expression data in the different chip platforms is merged; genes are divided into k subsets according to the expression similarity of the genes on the plurality of chip platforms; the expression linear relation exps1=as*exps2+bs of the different chip platforms in every gene subset can be calculated by the least square method; the gene expression values of the different chip platforms are standardized into the same change range by using the formula exp1=X*A.*exp2+X*B to obtain standard gene expression matrixes, wherein the implications of symbols are defined as the specification.

The invention relates to a heuristic breadth-first searching method for cancer-related genes. According to the method, appearance frequencies of genes in a selected gene subset are used for measuring the genes, and genes with higher appearance frequency are considered as the most important cancer-related genes, on the basis, a classifier is designed and a gene ordering method based on HBSA is established. As proved by study, information gene selection plays an important role in improving the classification performance, and the genes can be probably taken as important tumor clinical diagnosis signs, so discovery of the minimum gene subset with the highest classification performance is a very important research objective. As indicated by experimental results, the heuristic breadth-first searching method can not only obtain favorable generalization performance but also discover important tumor genes. And the relationship of the appearance frequencies of the selected genes and the gene number conforms to power-law distribution. The genes in the gene subset with extremely high classification accuracy are in close relationship with specific tumor subtypes, and even the genes are important genes directly related with the tumor.

The invention provides a redundancy removal feature selection method LLRFC (Locally Linear Representation Fisher Criterion) score+ based on LLRFC and correlation analysis. A DNA (Deoxyribonucleic Acid) microarray technology provides a new direction for clinic tumor diagnosis. Performance of gene expression data corresponding to different kinds of tumor is different; through the analysis on the tumor gene expression data, study personnel can realize the accurate recognition on the tumor and the tumor subtype in the molecular level; and important biological significance is realized on the diagnosis and the treatment of the tumor. The feature genes in LLRFC judging criterion descending sort gene expression data is used to be combined with the dynamic correlation analysis strategy for further eliminating redundant features; an LLRFC score+ algorithm is provided; and the optimum feature gene subset is selected. The feature selection method LLRFC score+ has the advantages that the classification precision of a classifier can be effectively improved; a sample data set does not need to meet the normal distribution; and the method is applicable to data in various distribution types. The feature selection method LLRFC score+ can help people to find the virulence gene of cancer, and the early-stage diagnosis, tumor staging and typing, prognosis treatment and the like of clinic tumor diseases are facilitated.

The invention discloses a tumor key gene identification method based on particle swarm optimization and a marking criterion. The method comprises the steps that one gene marking criterion is defined to acquire gene classification ability information so as to filter genes with a low correlation to a tumor category; and the Metropolis criterion is utilized to improve a particle swarm optimization (PSO) algorithm in combination with the gene classification ability information so as to realize identification of tumor key genes. The new method for gene classification information and PSO improvement overcomes the defect that a traditional method for identifying tumor key genes based on PSO is prone to fall into a locally optimal solution, gene subsets in a smaller number and with a high correlation to the tumor category can be selected, and therefore the method is beneficial for improving subsequent tumor identification.

The present invention provides algorithm-based molecular assays that involve measurement of expression levels of genes from a biological sample obtained from a kidney cancer patient. The present invention also provides methods of obtaining a quantitative score for a patient with kidney cancer based on measurement of expression levels of genes from a biological sample obtained from a kidney cancer patient. The genes may be grouped into functional gene subsets for calculating the quantitative score and the gene subsets may be weighted according to their contribution to cancer recurrence.

The invention relates to a gene expression profile feature selection method based on MFA score and redundancy exclusion. Feature selection and classification of oncogene expression profiles facilitate the early diagnosis of tumors, and the causes of the tumors are explained from the angle of gene expression. Firstly, a class inter neighbor matrix Wb and a class inter neighbor matrix Ww are structured through an MFA score algorithm, consequently a class inter Laplacian matrix Lb and a class inter Laplacian matrix Lw are obtained, and lastly genes are ranked. For the feature that gene expression data are high in redundancy, the correlation among the genes is judged through Pearson correlation coefficients, the high correlation genes, namely redundancy genes, are excluded, and finally a gene subset is obtained. The gene expression profile feature selection method based on the MFA score and redundancy exclusion is suitable for training samples distributed in any space, the number of dimensions of features is further reduced by excluding the redundancy genes, the complexity of the algorithm is small, and the high classification accuracy is obtained in experiments.

A PLS-based multi-disturbance integrated gene selection and tumor-specific gene subset recognition method features that different disturbance mechanisms are introduced to analyze gene selection of multi-disturbance integrate according to characteristics of tumor microarray data. Based on this framework, a new integrated gene selection method based on PLS is developed by using PLS polygenic metrics. On the one hand, the method of the invention is based on the whole effect of the subset, and can quickly identify the genes with differential expression, and also can identify the genes with weak differential expression signal; on the other hand, the method of the invention is based on a multiple disturbance mechanism, and can identify a series of different subsets of genes with small length andstrong discrimination ability. Therefore, the method of the invention can identify a series of different gene subsets and weakly differentially expressed genes, through which the specific expressionpattern of tumor genes can be more comprehensively recognized.

The method is characterized in that data of patients with malignant tumors are divided into clinical factors and pre-radiation gene expression profile data, ie, gene sets; a regression model of the clinical factors is constructed based on whether drugs are used or not for clinical factor data, and the clinical factors PS of each sample are calculated; t-test tests of two independent samples are performed based on radiotherapy sensitivity or tolerance groups, and a subset of differentially expressed genes with P less than 0.1 is screened out; the PS is included as a fixed independent variable,the expression amount of each gene of remaining genes included in the gene subset is taken as an independent variable, a regression model taking the radiotherapy sensitivity or tolerance as the outcome is constructed, the area AUC under a curve is calculated, and the gene expression amount with the largest AUC is selected and included to the regression model till loop termination is realized to form a multi-element regression model when the AUC of the regression model reaches the largest; the genes included in the multi-element regression model constitute radiosensitive sensitivity marker genes; based on the multi-element regression model, a dependent variable or its reciprocal is taken as the patient radiotherapy sensitivity score to predict whether a patient is sensitive to radiotherapywith a certain cutoff value.

The invention discloses a tumor key gene identification method based on a multi-objective particle swarm algorithm of a preference grid and Levi flight. The method comprises the steps that a classification information index is used to filter an original gene expression profile data set to acquire a primary gene pool; the GCS value of the gene category sensitivity information of each gene in the initial gene pool is calculated, and then particles are encoded by the GCS value; the classification accuracy of gene subsets on an extreme learning machine ELM and the size of the gene subsets are targeted to build a multi-objective optimization model; and the final gene subset is searched through the established multi-objective model, and then the key genes of a tumor are identified. In terms of the multi-objective optimization model, the method provided by the invention can quickly and efficiently identify a small number of key gene subsets with good classification performance in the primarygene pool through the multi-objective model.

The invention relates to a gene selection method and device based on fault tolerance, and belongs to the technical field of data processing, and the method comprises the steps: carrying out the reduction of a gene data set through employing a neighborhood rough set algorithm based on fault tolerance and a discrete particle swarm optimization algorithm, and obtaining an optimal gene subset. In thereduction process, the dependency degree based on the fault tolerance is introduced to evaluate the dependency of the decision attribute set on the condition attribute set, so that a fault tolerance-based dependency degree and neighborhood granularity mixed measurement method is provided, and a fitness function in a discrete particle swarm optimization algorithm, namely a particle fitness functionbased on the dependency degree based on the fault tolerance, is constructed. According to the gene selection method, the attribute set is evaluated from two different perspectives of dependency and neighborhood granularity, the problem of zero fault tolerance of a neighborhood rough set is solved, particles are guided to quickly search an optimal gene subset, and the classification precision of the obtained optimal gene subset is high.

The invention relates to a method for detecting a clinical result of a hepatocellular carcinoma patient by HBV (Hepatitis B Virus). Qualitative/quantitative evaluation or/and comparison is carried out on the basis of known functional annotation nodes on physiological metabolic pathways for diagnosing liver cancer types and obtained by transcriptome sequencing; a plurality of genes irrelevant to or redundant to the biological function of the diagnosed liver cancer type are excluded after function enrichment clustering to obtain a first group of differential gene subsets after first screening; the voucher used as the comparison opposite direction for excluding the gene or the gene subset in the first screening is the first voucher. The first credential can exist in a first gene library, and is characterized by having no contribution to the generation of a target disease or having weak correlation with physiological pathways involved in the generation of disease phenotypes.

In one embodiment, the present invention is a method and apparatus for classifying nucleic acid responses to infectious agents. In one embodiment, a method for selecting genes to be analyzed to determine exposure to a condition (from among a plurality of potential conditions) includes determining, for each gene in a set of test data that includes genes and corresponding expression patterns for exposure to given conditions, a distance between each pair of conditions. A subset of genes from within the set of test data is then identified for which the distance between each pair of conditions is maximized. In this way, the number of genes whose expression patterns must be analyzed in order to reliably diagnose a condition is minimized.