34 results about "Functional prediction" patented technology

The invention belongs to the field of biological medicines, and relates to a method for screening HRDs disease-causing mutation and a gene chip hybridization probe designing method involved in the same. The method for screening the HRDs disease-causing mutation comprises the steps of (1) establishing an HRDs genetic resource repository; (2) designing and synthesizing a gene chip hybridization probe of an HRDs disease-causing gene, and integrating the gene chip hybridization probe onto a gene chip; (3) capturing a target area by utilizing the prepared gene chip and executing the depth sequencing; (4) analyzing the sequencing data on the aspect of bioinformatics, and screening the candidate disease-causing gene; (5) functionally predicting a newly-discovered splicing gene mutation site. By establishing the high-efficient HRDs target gene capturing technology, adopting the depth sequencing as a means and confirming the efficiency of the HRDs capturing chip, a high-efficient credible biological information analysis model is established.

The invention discloses a method for functional prediction of single nucleotide genomic variation in a non-coding region, which comprises the following steps: 1) identifying a chromatin open region; 2) identifying transcription factor bin sites; 3) assessing the role of single nucleotide variations: Based on the site-specific frequency matrix of transcription factors, the effect of single nucleotide variations in the transcription factor binding site region on transcription factor binding is calculated, and the single nucleotide variations that significantly change the binding capacity of transcription factors are identified; the role of single nucleotide variations is further evaluated by viewing the biological pathway of the target gene of the transcription factor. The method recognizesa variety of transcription factors and their binding sites at one time through chromatin open region information and gene expression information, and realizes the functional annotation of non-coding region genomic mutation.

The embodiment of the invention provides a model training, protein feature extraction and function prediction method and device.The model training method comprises the steps that based on a three-dimensional structure of initial protein, an initial topological graph G is constructed, the initial topological graph G adopts amino acid residues of the initial protein as nodes, and the initial topological graph G adopts the amino acid residues of the initial protein as the nodes; the initial topological graph G adopts adjacent amino acid residue pairs as edges; and inputting the initial topological graph G into a pre-training model, training the pre-training model so as to obtain the pre-training model for performing feature extraction on the protein, the pre-training model comprising a graph neural network with SE (3) and other degeneration. Therefore, the prediction precision of related prediction such as protein feature extraction can be improved, the working cost is reduced, and the prediction efficiency is improved.

The invention provides a screening method for tobacco antiviral regulatory genes and an application of the screening method. The screening method comprises the following steps: firstly constructing atobacco cDNA library by using a virus-induced gene silencing (VIGS) vector as a target vector, and performing homogenization treatment to obtain a VIGS-cDNA library capable of being directly used forgene silencing screening analysis; transforming VIGS-cDNA library plasmid into agrobacteria to obtain an agrobacterium library; performing spread plate culture on the agrobacterium library to obtain single colonies, performing VIGS silencing analysis on each single colony, and performing screening to obtain antiviral-related colonies; and performing sequencing analysis on genes corresponding to the screened antiviral-related colonies, performing homology analysis on the obtained sequences, and performing function prediction to obtain the antiviral regulatory genes. The method provided by the invention has the advantages of simple operation, no need to construct transgenic plants or mutants, short time consuming, comprehensive screening and high efficiency, is particularly suitable for screening of mutant lethal genes, and has broad application prospects.

The invention relates to an analysis method for succession of microbial communities during tobacco mellowing, and belongs to the technical field of environmental microbes. In order to define microbialpopulation structures and dynamic changes thereof and predict microbial gene functions during tobacco mellowing, the invention provides the analysis method for the succession of the microbial communities during tobacco mellowing, and the analysis method comprises the following steps of (1) performing sampling: taking naturally mellowed tobacco samples at the beginning of mellowing at intervals ofthe same time; (2) constructing gene libraries: extracting genomic DNA of the samples collected in each time period, and constructing a 16S ribosomal RNA (16S rRNA) gene library and an internal transcribed spacer region gene library; and (3) analyzing data of each gene library constructed in the step (2) to obtain the rule of the succession of the microbial communities during tobacco mellowing. The analysis method can be used for giving guidance on artificially mellowing tobacco and establishing the microbial communities.

In order to overcome the defects in the prior art, the invention aims to predict the function of the circRNA by using the provided cascade decision system in combination with the multi-classificationmodel of the LightGBM method. The technical scheme adopted by the invention mainly comprises the following steps of: (1) inputting the CircRNA of a big data sample in a (. bed) file form; (2) mappingthe CircRNA (. bed) file according to related information such as a starting site and the like to obtain a CircRNA sequence information (. fasta) file; (3) proposing a feature extraction and fusion method, and extracting a CircRNA feature; (4) proposing an A-type judgment system, and performing function prediction on the coded circRNA; (5) predicting other CircRNA by utilizing the LightGBM (LightGBM) algorithm; (6) according to a multi-classification model of a lightGBM algorithm, carrying out sampling and feature sampling of sample data by using core algorithms GOSS and EFB, mapping continuous features into discrete buckets by using a Histogram-based algorithm, and discretizing continuous variables; and (7) obtaining the optimal parameters of the model by adjusting the maximum depth of the tree, the minimum record number of the leaves, the data proportion used in each iteration and other parameters.

The invention relates to an object functionality prediction method and device, computer equipment and a storage medium. The method comprises the steps of acquiring a to-be-predicted object and a plurality of candidate scenes; inputting the to-be-predicted object and the current candidate scenes to a distance measurement model, performing calculation by the distance measurement model according to atrained scene feature sub-network to obtain eigenvectors corresponding to the current candidate scenes, and outputting distances from the to-be-predicted object to the current candidate scenes according to the to-be-predicted object and the eigenvectors corresponding to the current candidate scenes, wherein model parameters of the distance measurement model include parameters determined by a trained object feature sub-network; obtaining the distances from the to-be-predicted object to the candidate scenes according to the distance measurement model; determining a target scene corresponding tothe to-be-predicted object according to the distances from the to-be-predicted object to the candidate scenes; and obtaining a functionality prediction result corresponding to the to-be-predicted object according to the target scene. The object functionality prediction universality can be improved.

The invention belongs to the technical field of biological information, and provides a polypeptide anticancer function identification method, system, medium and equipment. The identification method comprises the following steps: acquiring a polypeptide sequence; inputting the polypeptide sequence into the trained anticancer function predictor of the polypeptide drug to obtain whether the polypeptide has an anticancer function or not; wherein the anticancer function predictor of the polypeptide drug comprises an embedding layer, a coding layer and a task specific layer, and the embedding layer is used for converting each residue of a received polypeptide sequence into a low-dimensional dense vector and outputting the low-dimensional dense vector in a matrix form; the coding layer being used for capturing contexts of each residual embedding vector at different positions from the matrix output by the embedding layer, learning identification characteristics of the anti-cancer peptide and outputting a characteristic matrix; and the task specific layer being used for judging the probability that the polypeptide sequence belongs to the anti-cancer peptide according to the characteristic matrix.

The invention provides bone remodeling regulating polypeptides and application. At the early stage, on the basis of first experiment findings, through sequence alignment, structural analysis, physicochemical properties and function prediction, a solid-phase polypeptide synthesis method is designed and utilized to newly synthesize the bone remodeling regulating polypeptides. The polypeptides have the characteristics of short length, simple synthesis, low cost, lower cytotoxicity, higher biological stability, moderate half-life period, good targeting ability and high bone absorption regulation capacity, differentiation and functions of osteoclasts and osteoblasts can be controlled by regulating the concentration of the synthesized bone remodeling regulating polypeptides to realize ordered regulation of bone absorption and bone formation, and the polypeptides have broad potential application prospects.

The invention provides a drug target prediction method for keeping consistency of chemical properties and functions of a drug and a system thereof, and belongs to the technical field of computer-aided drug research and development, and the method comprises the steps: obtaining a chemical fingerprint of a to-be-predicted drug; using the trained feature selection model to process the chemical fingerprint of the drug to obtain an interaction scoring matrix of the drug and the target; and taking the corresponding target with the highest score as the action target of the drug based on the interaction score matrix of the drug and the target. According to the invention, chemical properties and clinical functions of drugs are considered at the same time, and possible targets of the drugs are predicted; the feature vector of the drug is projected to a protein space and then projected to a disease space, a drug-target interaction prediction task is changed into a multi-label task from a traditional single-label classification task, and a complex repulsion relationship between the drug and protein is considered; by keeping the consistency of the chemical similarity and the functional similarity of the medicine, the consistency of the chemical property, the molecular mechanism and the clinical function of the medicine is kept.

The invention relates to a biological material function prediction and evaluation method, and solves the technical problems of intensive labor, long experimental period and high heterogeneity of a sample library in the existing evaluation method. The biological material function prediction and evaluation method comprises the following steps of (1) culturing human bone marrow mesenchymal stem cells in an environment of a material to be detected; (2) collecting the human bone marrow mesenchymal stem cells cultured in the step (1), extracting total RNA (Ribonucleic Acid), purifying and establishing a library, and sequencing a transcriptome to obtain transcriptome data of a to-be-detected sample; and (3) performing batch effect correction and feature extraction on the transcriptome data of the to-be-detected sample obtained in the step (2), inputting the transcriptome data into a function prediction evaluation model, and calculating the confidence of the to-be-detected sample for different cell types. The method can be used in the field of biological material function prediction and evaluation.

The invention discloses a function prediction and screening method of glioblastoma lncRNA coding micropeptides. The method comprises the following steps: screening a glucose transporter gene set; carrying out significant differential expression and survival analysis on the glucose transporter gene set in the pan cancer; verifying the SLC2A10 in the glioblastoma, and predicting ceRNA (Ribonucleic Acid); the method comprises the following steps: carrying out LINC02381 coding to predict the micro-peptide, positioning the predicted micro-peptide into a human chromosome, carrying out identification and function enrichment analysis on the predicted micro-peptide, and reserving the micro-peptide which has the same chromosome as the LINC02381 and is predicted to have potential functions. The invention provides a function prediction and screening method of glioblastoma lncRNA (long non-coding RNA) coded micropeptide, and provides a basis for researching the effect of the lncRNA coded micropeptide in glioblastoma in prognosis or diagnosis.

The invention relates to a cancer somatic mutation function influence prediction method. According to the method, a comprehensive mutation feature set is constructed, and mutation frequencies of different populations are integrated together; carrying out conservative estimation based on mutation sites of multiple species, and estimating the probability that the mutations are harmful mutations; mutation network feature construction based on gene product interaction is carried out, and mutation network feature construction is completed; and constructing a deep random forest prediction model based on multiple sampling and a hierarchical structure, and performing function prediction on cancer somatic mutation.

The invention discloses a computer-aided system and method for human health life cycle preventive maintenance, and relates to the technical field of artificial intelligence. Comprising a human body health function data analysis and evaluation system, a human body digital twin system, a deep neural network analysis system, a human nutrition food recommendation system, a data storage system, a cloud computing platform system, a user graphical interface system and a data collection system. Whether the human body has potential diseases or diseases can be predicted, the human body function is analyzed according to the data in the back-end data warehouse, whether the human body has potential diseases or diseases or not is predicted, warning and suggestions are provided for preventive measures, and the purpose of preventive maintenance of the human body health life cycle is achieved.

The invention discloses a forced expiration total amount prediction method, which comprises the following steps: S1, according to a forced lung function prediction standard, collecting forced lung function test data, and sorting and classifying the data to obtain a data set; and S2, constructing a forced expiration total amount prediction model, and outputting a forced expiration total amount prediction result by using the prediction model. The method has the beneficial effects that by providing the forced expiration total amount prediction method, a tester can still obtain an FVC value under the condition that the whole test is not completed, so that the problem that the diagnosis effect is influenced due to the fact that an FVC detection result does not meet the acceptability because it is difficult for the tester to insist in expiration time long enough is effectively solved.