39 results about "Gene classification" patented technology

The invention relates to a gene classification method and system based on clustering and random forest algorithms and belongs to the technical field of biological information. The method comprises a step of acquiring gene sample data, clustering the acquired gene sample data by using the clustering algorithm to obtain a cluster center, and supplementing a training sample set with an obtained cluster center set, a step of adjusting the number of fixed decision tree random description attributes in a traditional random forest algorithm to a random value, wherein on one hand, strong decision trees in a decision tree set are kept, on the other hand, the number of average random description attributes of the decision tree set is reduced, thus the correlation between the decision trees is further reduced, and a step of predicting genetic data to be classified by using each decision tree in a random forest model. According to the method and the system, the cluster center obtained through theclustering algorithm is taken as artificial data to expand the training set of the random forest model, thus the random forest model is fully trained, the obtained classification model has high precision, and the accuracy of the classification of genetic data is improved.

Disclosed herein are methods of detecting an altered gene expression levels in a subject suspected of having psoriasis. Further described herein are methods of treating psoriasis in a subject having an exhibiting an altered gene expression level.

Disclosed herein, in certain embodiments, are methods of detecting the presence of a skin cancer based on molecular risk factors. In some instances, the skin cancer is cutaneous T cell lymphoma (CTCL). In some cases, the skin cancer is mycosis fungoides (MF) or Sézary syndrome (SS).

Disclosed herein are methods of detecting an altered gene expression levels in a subject suspected of having atopic dermatitis. Further described herein are methods of treating atopic dermatitis in a subject having an exhibiting an altered gene expression level.

The invention discloses a progressive ensemble classification method based on a kernel width learning system. The progressive ensemble classification method comprises the following steps: 1) inputtinga training sample and a test sample; 2) training a kernel width learning system as a base classifier by using the original training data; 3) calculating a prediction residual error according to the training result of the first base classifier, and taking the prediction residual error as a label trained by the next base classifier; 4) when the reduction rate of the trained loss function value reaches a threshold value, stopping the training, and not continuing to increase the base classifier any more; and 5) classifying the test samples to obtain a final prediction result. According to the method, the nonlinear fitting capability of the classifier is improved by introducing a kernel mapping technology while redundant back propagation is not needed by utilizing a width learning system, anda plurality of base classifiers are fused by using an integrated means, so that an obvious improvement effect is achieved on a biological information data set with noise, and the accuracy of biological gene classification is improved.

The invention discloses a prognosis analysis method based on primary liver cancer gene classification and liver cancer tissue energy metabolism. The prognosis analysis method comprises the following steps: acquiring clinical phenotype data, expression profile data and gene CNV and SNV mutation data of a liver cancer sample; calculating sample scores of four metabolic pathways of the tumor sample, and determining a plurality of optimal classifications; and analyzing differences of expression, gene mutation, clinical phenotypes and immune characteristics of a plurality of optimal classification metabolic pathways, and then comprehensively analyzing results to establish a primary liver cancer prognosis analysis model. The method has the advantages that the primary liver cancer gene classifier is constructed through a big data analysis technology, the molecular subtype of the primary liver cancer is determined, and the metabolic pathway expression difference, the gene mutation difference, the clinical manifestation difference and the immune difference of the molecular subtype of the primary liver cancer are analyzed, so that the primary liver cancer prognosis analysis model is established; the method is used for accurately predicting the prognosis of the primary liver cancer and provides a research basis for revealing an energy metabolism mode and a tumor microenvironment of the primary liver cancer.

The invention discloses a gene classification method and related equipment. The method comprises the steps of carrying out standardization processing on input gene data serving as training samples, wherein the gene data comprises a plurality of attributes; by difference values between intervals between the training samples and heterogeneous neighbor samples and intervals between the training samples and similar neighbor samples, and weight vectors of the corresponding attributes, building a logical regression optimization function which represents expected interval difference of all the training samples, building a minimized optimization model by taking the weight vectors of the corresponding attributes as norm constraint terms, and performing calculation through iterative operation to obtain the weight vectors of the corresponding attributes; and sorting attribute features according to values of the obtained weight vectors, carrying out classification training on the gene data servingas the training samples according to the sorted attribute features, and obtaining an optimal feature set as a classification basis, thereby classifying the to-be-classified gene data. According to the gene classification method and the related equipment provided by the invention, the relatively high classification precision can be obtained.

The invention relates to a gene classification method and device, which combines the LLE algorithm and the AP clustering algorithm, and uses the proposed mixed kernel function to improve the similarity measurement function. First, the LLE algorithm is used to map the original high-dimensional gene expression data set to a low-dimensional space to achieve the purpose of dimensionality reduction; secondly, a new global kernel function is proposed as the F-type kernel function, and it is linearly combined with the Gaussian kernel function to form a new The hybrid kernel function, and use the proposed hybrid kernel function to calculate the similarity measure, construct a new similarity matrix S; then cluster the data through the AP clustering algorithm and the similarity matrix, iteratively obtain the final clustering result; finally through Compared with other clustering methods, the validity and accuracy of the algorithm of the present invention are verified.

The invention discloses a human leukocyte HLA‑B*27 genotyping primer set, which includes detecting blood types A and A respectively. 205 , B and O (261G缺失) , O 1 , O 2 The allelic primer pair AR and AF; A 2 R and A 2 F;BR and BF;0 T R and O T F;O 1 R and O 1 F;O 2 R and O 2 F and internal reference primer pair; the allelic primer set designed by the present invention has high power and strong specificity, and the internal reference primer pair internal reference 1R and internal reference 1F, internal reference 2R and internal reference 2F are designed according to the conserved fragment of human albumin gene, and each detection The number of pairs of allelic primers in the well is 2 to 4 pairs, and at the same time, it contains 2 pairs of internal references to ensure the quality and correctness of PCR amplification, thereby ensuring the reliability of the test results.

The invention belongs to the technical field of in vitro detection of human nucleic acid, and particularly relates to a genotyping detection kit for human No. 5, No. 19, No. 21 and 23 gene loci of X / Y chromosomes. The present invention first designs a compound PCR amplification system for genotyping 23 gene loci distributed on human chromosomes 5, 19, 21 and X / Y at the same time, wherein the PCR amplification primer set is: SEQ ID No.1 to SEQ ID No.53; the genotyping detection kit of the present invention includes a primer composition container and a PCR reaction mother solution container; the primer composition container contains the primer composition of SEQ ID No.1 to SEQ ID No.53 stock solution. The invention realizes single-tube amplification of 23 gene loci, the gene loci in each fluorescence channel and in different fluorescence channels are amplified evenly, and the typing map is good; and the cost, manpower and time can be significantly saved, and work is improved. efficiency.

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 invention belongs to the field of gene expression spectrum classification, discloses a gene expression spectrum distance measurement method based on deep learning, and belongs to the mining and application of deep learning on biological big data. First, a convolutional neural network model suitable for gene feature metric learning is designed to extract the characteristics of the data, and then the distance between the data is calculated by using the improved cosine distance, and finally the classification effect of the classification algorithm is used to measure the performance of the method excellent. This method can quickly and efficiently measure the similarity between different gene expression profiles, and provide data for subsequent studies such as gene classification, clustering, differential expression analysis, and compound screening. Compared with the traditional gene enrichment method, this method significantly improves the distance measurement effect between data, and can effectively reduce the manual intervention in gene expression profile analysis, avoiding the over-fitting phenomenon that is easy to occur in conventional deep networks. This method has strong transferability.