88 results about "Gene Feature" patented technology

The invention provides a method for carrying out high-throughput sequencing on a TCR (T cell receptor) or a BCR (B cell receptor). The method is characterized by designing upstream primers according to gene features of a V region of the TCR or the BCR and designing downstream primers according to gene features of a C region or a J region of the TCR or the BCR and obtaining sequences of the of the TCR or the BCR in combination with the multiplex PCR (polymerase chain reaction) technology and high-throughput sequencing, thus analyzing the rearrangement information of the TCR or the BCR. Compared with 25-30 cycles of existing multiplex PCR, two cycles of the multiplex PCR technology provided by the invention can conduce to greatly reducing the sequencing errors caused by primer amplification preference. Besides, the invention also provides a method for correcting multiplex PCR (polymerase chain reaction) primer deviation by utilizing DNA (deoxyribonucleic acid) tag sequences, thus further reducing the sequencing errors caused by primer amplification preference and intrinsic sequencing errors of high-throughput sequencing.

The present invention pertains to specific gene signatures for cancer that are used to predict survival and novel processes for identifying such gene signatures. In one embodiment, gene signatures for human colorectal cancer are identified and outcomes are linked to the specific gene signatures using significance analysis of microarrays (SAM) and support vector machines (SVM) to provide a prognosis/survival classifier.

The invention discloses a gene expression data classification method and system. The gene expression data classification method comprises the following steps: after obtaining a gene characteristic data set, clustering the gene characteristic data set by adopting a clustering algorithm to obtain a first pre-set parameter clustering set; and processing the clustering set to obtain a second sample matrix, a second training set and a characteristic index set, and reducing dimensions of gene characteristic data so as to reduce the redundancy of the gene characteristic data, and reduce occupied computational resources and consumed computation time in a process of carrying out characteristic selection on the second training set to the very great extent. The occupied computational resources and the consumed computation time in a process of carrying out clustering operation on the gene characteristic data set by adopting the clustering algorithm are less, so that the occupied computational resources and the consumed computation time in a process of clustering gene characteristic data to be detected through adopting the gene characteristic data classification method are less.

The present invention provides one new gene MgKIN17 from Pyricularia gisea, and the gene features that it has the amino acid sequence from the site 1 to the site 3544 in the SEQ ID No. 1, the cDNA with the nucleotide sequence of SEQ ID No. 2, the promoter with the nucleotide sequence of SEQ ID No. 4, and coded protein with the amino acid sequence of SEQ ID No. 3. The insertion mutation and gene complementation of the present invention shows that the destruction of the gene leads the formation of Pyricularia gisea infecting organ and reduced lesion capacity of rice. Wheat bakanae fungus, corn stalk rot and other pathogenic fungus have homogenous protein with homogeneity over 40 % to MgKIN17 and maybe similar biological function. The gene of the present invention and its protein expression and modification may be used as the target site for designing and screening antifungal medicines.

A process to select signature gene by performing statistical analyses on gene datasets of various types of diseases for identifying signature genes for at least one of the diseases followed by categorizing and establishing gene expression table with the signature genes. The signature genes in the gene expression table are tested and verified by applying additional datasets to finalize and confirm the signature genes. The step of performing the statistical analyses on the gene datasets of various types of diseases further comprising a step of performing a total background normalization (TBN) of a relative gene expression (RGE) ratio then carried a two-tail T-test of the RGE ratios between the various diseases. The step of identifying the signature gene further comprising a step of carrying out a false positive elimination (FPE) by identifying differently expressed genes and removing overlapping genes among different diseases from a list of the signature genes

The invention discloses a drug sensitivity prediction method and device based on transfer learning and a graph neural network, and belongs to the technical field of drug sensitivity detection and evaluation. The method specifically comprises the steps: performing parameter optimization on a semi-inhibitory concentration prediction module through first sample data containing the semi-inhibitory concentration of a drug to a cell line; migrating the network parameters of a feature extraction unit of a semi-inhibitory concentration prediction module to a feature extraction unit of a drug sensitivity prediction module through migration learning, and on this basis, performing parameter optimization on the drug sensitivity prediction module through second sample data containing drug sensitivity category data; in this way, cross-dataset feature migration is effectively achieved, the defect that the sample size of the datasets is insufficient is overcome, the drug sensitivity prediction module is optimized by means of the datasets with large differences, the drug sensitivity prediction module can effectively extract gene features and drug features of individuals, and the drug sensitivity is predicted with high accuracy.

Methods for identifying and treating cancers that are homologous recombination (HR)-repair defective. In some aspects, HR defective cancers are treated with a PARP inhibitor therapy. Methods for sensitizing cancers to a PARP inhibitor therapy are also provided.

Biomarkers and methods using the biomarkers for molecular detection and classification of disease and, particularly, molecular markers for cancer diagnosis and prognosis and methods of use thereof are provided.

The invention provides for molecular classification of disease and, particularly, molecular markers for lung cancer prognosis and therapy selection and methods and systems of use thereof.

The invention provides a cancer tissue classification method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring gene data corresponding to a to-be-detected tissue set; the to-be-detected tissue comprises a plurality of to-be-detected tissue samples; determining a gene feature matrix and a gene adjacent matrix according to the gene data; inputting the gene feature matrix and the gene adjacent matrix into a graph convolutional neural network to obtain a plurality of graph convolutional network layers; aggregating the plurality of graph convolutional network layers through an enhanced graph convolutional neural network to obtain an aggregation result; and inputting an aggregation result into a classifier for classification to obtain a diagnosis result. The scheme is high in cancer tissue classification accuracy.

The invention provides a gene selection method which is used for gene characteristic selection. The method comprises the steps of obtaining a training set and a test set through a gene data microarraydata set, and determining an initialized population; carrying out binary coding on each individual of the current population by adopting a conversion function; calculating the fitness value of the current population, and updating related parameters in the dolio-sea squirt and moth fire suppression strategy; setting related parameters of a sine and cosine optimization algorithm, and updating the population by adopting a sine and cosine optimization algorithm iterative formula; updating the populations obtained through the sine and cosine optimization algorithm through a doliola scabra, moth fire suppression and reverse learning strategy in sequence so as to obtain three populations; selecting a next generation of population through greedy selection; and if the maximum number of iterationsis reached, ending the loop and outputting the optimal solution, otherwise, continuing the iteration until the iterative computation is ended. According to the invention, the gene characteristics which contribute most to categories can be screened out from the genes more accurately and more efficiently, and the detection cost is reduced.

The invention belongs to the field of gene expression profile classification, discloses a gene expression profile distance measurement method based on deep learning, and belongs to mining and application of deep learning on biological big data. Firstly, a convolutional neural network model suitable for gene characteristic metric learning is designed to extract data characteristics, then the distance between the data is calculated by applying an improved cosine distance, and finally, the good performance of the method is measured through the classification effect of a classification algorithm.According to the method, the similarity between different gene expression profiles can be quickly and efficiently measured, and data is provided for subsequent researches such as gene classification,clustering, differential expression analysis and compound screening. Compared with a traditional gene enrichment method, the method has the advantages that the distance measurement effect between thedata is obviously improved, the manual intervention during gene expression profile analysis can be effectively reduced, the overfitting phenomenon easily generated by a conventional deep network is avoided, and the method has relatively high mobility.

The invention relates to a biochip, in particular to the biochip for predicting the treatment effect of an antidepressant and an application. The biochip for predicting the treatment effect of the antidepressant consists of a carrier and a bioprobe and is characterized in that the bioprobe comprises any one kind or several kinds of materials with the sequence from Seq NO: 1 to 20, and the tail ends of the sequences are modified through fluorescence labels. Through the biochip technology, the treatment effect of the antidepressant on patients can be predicted in an early period according to genetic gene features (single nucleotide polymorphism) of the patients from aspects such as the medicine species, the sexes of the patients receiving the treatment, the putative effect taking time point of medicine, the possibly generated adverse effect and the like, so clinic doctors can be guided to make and implement individualized treatment schemes.

The present invention relates to novel iturin biosynthesis genes, and uses thereof. More specifically, the present invention provides novel iturin biosynthesis genes, wherein the iturin biosynthesis genes were cloned from Bacillus subtilis subsp. krictiensis ATCC 55079, the base sequence was determined after checking whether the cloned genes are iturin biosynthesis genes or not, and it was ascertained that the identified genes are novel genes different from the reported gene by comparing the base sequences with that of the reported gene, and uses thereof.

The invention relates to a wheat 4B chromosome grain weight QGW4B-CAPS molecular marker and an application thereof. A grain weight control genetic locus QGW4B-17 is positioned at 31.3-36.3cM of a short arm of a wheat 4B chromosome and is positioned between a wheat 4B chromosome molecular marker Ex-c101685-705 and a molecular marker RAC875-c27536-611. The invention also discloses a grain weight QGW4B-CAPS molecular marker developed according to the grain weight control genetic locus QGW4B-17. According to the molecular marker QGW4B-CAPS, large grain resources containing the gene feature base sequence can be selected in a purposeful mode and are used for high-yield wheat breeding or molecular designing convergent cross breeding, and molecular marker assisted selective breeding is performed by using the marker, so that breeding of high-yield wheat variety is rapidly and accurately performed.

The invention discloses a cancer driver gene prediction method. The method comprises the steps: constructing a first data set and a second data set, wherein the first data set represents the incidence relation between gene features and driving gene mutation types, and the second data set represents the incidence relation between the gene features and driving function types; training a first machine learning classification model by using the first data set, and predicting a new driver gene; confirming data corresponding to the new driver gene predicted by the first machine learning classification model as a second prediction data set; training a second machine learning classification model by using the second data set, and predicting the second prediction data set by using the trained second machine learning classification model to predict the driving function of the new driver gene. According to the invention, the prediction accuracy and the generalization ability of model application can be effectively improved.

The invention discloses a train bogie fault identification method based on biological information characteristics, which comprises the following steps: obtaining a historical vibration signal of a train bogie, and preprocessing and converting the historical vibration signal into an artificial DNA sequence; obtaining all window sequences through a sliding window method, and selecting a feature sequence meeting a preset requirement from the window sequences; taking the contents of four bases in the artificial DNA sequence, the sequence length and the number of the characteristic sequences as gene characteristic vectors of the artificial DNA sequence; constructing a training sample by using the gene feature vector of the artificial DNA sequence, and training a corresponding LPBoost binary classifier for each fault type; therefore, during fault detection, inputting the corresponding gene feature vector into each LPBoost binary classifier, and determining the fault type of the train bogie to be detected through a voting method. According to the invention, the feature sequence causing each fault type is mined, so that accurate identification and classification of various fault types arerealized.

Aiming at the Chinese document gene matching and orienting to document evasion checking scenarios, the present invention proposes a gene feature matching method of 28 hybrid documents. In particular, a multi-weight system is introduced for the first time to reflect the consideration of gene differentiation within and among systems and to form a unified similarity calculation formula. Based on the document gene matching method provided by the present invention, the weight can be finely configured, the process of algorithm condition jump can be reduced, and the achievability and practical applicability are strong.

The embodiment of the invention provides a gene detection method, a feature extraction method, a device, equipment and a system. The gene detection method comprises the following steps: acquiring a to-be-processed gene sequence, wherein the average number of gene segments corresponding to each position in the gene sequence is smaller than or equal to a preset threshold value; performing feature extraction operation on the gene sequence to obtain gene features; enhancing the gene features to obtain enhanced features corresponding to the gene features; and detecting the gene sequence based on the enhanced features to obtain a detection result. According to the technical scheme provided by the embodiment of the invention, the gene sequence is subjected to feature extraction operation to obtain the gene feature, then the gene feature is subjected to enhancement processing to obtain the enhanced feature, and then the gene sequence is detected based on the enhanced feature to obtain the detection result, so the accuracy of gene detection operation is ensured, and the data processing cost and the data processing amount are effectively reduced.

The present invention discloses a cDNA sequence of human repair gene DNA polymerase beta, which is a specific representation of DNA polymerase beta in esophagus cancer. The protein coded by it has fully lost the DNA repair activity of DNA polymerase beta. It can be used for early diagnosis and gene therapy of esophagus cancer.