37 results about "Functional annotation" patented technology

The invention discloses a pig SNP chip construction method based on gene regulatory network characteristics, and relates to the technical field of animal genetic breeding, and the pig SNP chip construction method comprises the following steps: constructing a pig tissue specificity multi-level gene regulatory network related to target traits and tissue types; performing function annotation and network comprehensive feature extraction on the whole genome SNP based on the gene regulation network; and carrying out score sorting and screening on the extracted network comprehensive characteristics, screening SNP variation sites with regulation function potential, constructing a pig SNP site set, and preparing the SNP chip. By introducing tissue / character related gene regulatory network information, functional priority ranking and screening are performed on SNP loci in a whole genome range, so that the character interpretation ability and breeding value estimation accuracy of SNP in a chip are remarkably improved.

The application relates to a cell infiltration inference method and system fusing GO function annotation and PPI network information, and the method comprises the following steps: collecting gene expression data, GO function annotation data and PPI network data; constructing a cell-cell function correlation network and a cell-cell physical interaction network respectively; performing weighted fusion processing on the two networks to obtain a comprehensive cell relationship network; calculating a final cell infiltration score through a restart walk algorithm, and inferring the infiltration degree in a tumor microenvironment according to the final cell infiltration score. The application innovatively fuses GO function annotation information and PPI network data, comprehensively considers the functional similarity and physical or signal interaction between cells, enables the model to understand cell synergy from the biological pathway level and analyze cell direct interaction from the protein interaction level, avoids one-sidedness of a single perspective, and provides a more stereoscopic cognitive framework for tumor microenvironment analysis.

The invention discloses a method for researching influence on hemolytic activity of marine microalgae based on a transcriptome technology, and relates to the field of hemolytic activity analys.The method comprises the steps that pretreatment is conducted on the marine microalgae based on culture requirements, and cystic morphological cell density and hemolytic activity of the marine microalgae are measured according to experimental design rules after pretreatment is completed; carrying out transcriptome sample collection operation by utilizing the marine microalgae subjected to pretreatment, constructing a library according to a transcriptome sample collection result, and obtaining a gene function annotation and a differential expression gene result; the growth conditions of the marine microalgae under different temperature conditions are analyzed according to cystic morphological cell density and hemolytic activity, and the regulatory gene influencing the hemolytic activity of the marine microalgae is obtained by combining gene function annotation and differential expression gene results. According to the method, the hemolytic activity of the marine microalgae cultured under different temperature conditions is extracted, so that the aim of researching related metabolic pathways possibly participating in toxin synthesis and hemolytic activity regulation is fulfilled.

The invention discloses a protein function prediction model generation method and system, and belongs to the technical field of bioinformatics, and the method specifically comprises the steps: firstly, extracting a natural disordered region of a target protein and experimental condition parameters thereof; retrieving a conformation database based on the regional features to obtain a reference protein set with multi-condition conformations and function annotations; thirdly, a condition dependent network fusing the target and the reference conformation is constructed, and the network edge weight is jointly determined by the conformation conversion difficulty and the experiment condition matching degree; if the target conformation cannot be effectively connected with the reference conformation, virtual folding simulation is started to generate supplementary conformation nodes; integrating all nodes to generate a conformation state relation graph, and training a prediction model according to the conformation state relation graph; and finally outputting a model which can receive a new protein sequence and condition parameters thereof and predict possible conformation states and corresponding functions thereof. According to the method, condition-dependent conformation and function association prediction can be realized aiming at natural disordered region protein.

This invention relates to the field of intelligent breeding technology, specifically disclosing a high-throughput intelligent screening method for multi-trait ginseng breeding materials based on deep learning. The method includes breeding data acquisition, high-throughput acquisition of hyperspectral phenotypes, construction of a multi-trait prediction model, model interpretability analysis, comprehensive screening of multiple traits, and verification of screening results. This scheme utilizes UAV hyperspectral remote sensing technology to achieve rapid and non-destructive determination of saponin content, significantly improving the throughput of phenotypic data acquisition. A multi-task learning architecture and deep neural networks are used to construct a multi-trait prediction model. By sharing representation layers, genetic associations between traits are captured, while retaining the specific information of each trait, achieving collaborative and accurate prediction of multiple traits. Through integrated gradient and attention weight analysis, key marker sites are accurately located, and their biological significance is revealed by functional annotation, enhancing the model's transparency and credibility.

The invention relates to the technical field of artificial intelligence and bioinformatics, and discloses a biological function feature fusion method based on a layered weight perception attention mechanism. The method comprises the following steps: acquiring gene sequence data and multi-source function annotations, and converting into vector representation by using a pre-training model; fusing the functional semantics in the library into a library-level summary vector by adopting a hierarchical fusion mechanism of weight perception; constructing a hierarchical fusion architecture, and realizing deep adaptive fusion of a gene sequence and multi-source knowledge through a shared projection layer, a cross attention mechanism and a gating network; and the model performance is improved through end-to-end multi-objective optimization training. According to the method, the problems of semantic gap, insufficient weight utilization and biological logic deficiency in multi-source functional data fusion are solved, the unified gene function feature vector with high biological characterization capability is generated, and the accuracy and interpretability of gene function annotation are improved.

The invention relates to the technical field of metagenomics, discloses an automatic analysis method and system for pit mud metagenomic data, and aims at solving the problem that an existing method is poor in efficiency and accuracy, and the scheme mainly comprises the steps that a sequencing data type, a file path and analysis parameters are received; performing quality control on the original offline data; sequence assembly is carried out, and a contigs file is generated; carrying out assembly quality evaluation on the contigs file; carrying out genome binning by using at least two binning tools; integrating output results of the binning tool, and performing optimization based on a preset integrity threshold value and a preset pollution degree threshold value to obtain an optimized binning genome data set; evaluating and optimizing the integrity, the pollution degree and the strain heterogeneity of the binning genome; calculating coverage and relative abundance; performing species classification annotation and function annotation; and integrating the result data of the previous steps to generate an analysis report. According to the method, automatic analysis of metagenome data is realized, and the analysis efficiency and accuracy are improved.

The application discloses a gene data processing method and device, computer equipment and a storage medium, and belongs to the technical field of computers. Through a gene function query request of a to-be-tested gene, the application can call a gene association model corresponding to a cell type to which the to-be-tested gene belongs, mine a nonlinear association degree between the to-be-tested gene and a known candidate gene, and use the candidate gene with a higher nonlinear association degree to label function annotation information of the to-be-tested gene. The way of calling the gene association model to extract the nonlinear relationship is completely different from the way of extracting the linear relationship in traditional statistics, can deeply mine the candidate gene with a higher similarity to the to-be-tested gene, and the similarity is not a linear similarity but an implicit nonlinear similarity, so that the accuracy of the gene data processing process is greatly improved.

The invention discloses a gene function prediction method based on semantic correspondence of a regulatory region. The method comprises the following steps: firstly, constructing an inter-species regulation semantic correspondence relationship data set, constructing an artificial intelligence model structure, then, constructing a cross-species semantic correspondence network, and finally, carrying out function annotation on a target gene or identifying a candidate gene with a specific function in a target species. The accuracy of the PhytoBabel model constructed by the method is obviously higher than that of other model structures. By utilizing the method disclosed by the invention, the genes ZmERF104 and ZmGRF16 for promoting the regeneration of the corn somatic embryos and the gene ZmNAC17 for inhibiting the regeneration of the somatic embryos, which cannot be found by the traditional method, are successfully identified.

The application provides a prediction method of pathogenic embryonic mutation, comprising the following steps: obtaining a variation site set of an embryonic mutation to be predicted, and performing population frequency screening on the variation site; filtering variation sites which are not annotated or are only annotated as clinically uncertain by using a clinical variation database; calculating a pathogenic posterior probability score of a candidate pathogenic variation by using a variation Bayesian inference (VBI) model with multiple types of function annotations; and cross- verifying the posterior probability score, external pathogenic prediction tool scores and variation types to determine a final pathogenicity discrimination result. Compared with an existing method based on single site frequency or single function score, the present application provides a posterior probability evaluation model with more biological interpretation in the field of rare variation judgment, effectively improves the prediction accuracy in a complex scene, significantly improves the risk classification accuracy based on multi-level evidence fusion discrimination, and effectively reduces the misdiagnosis and missed diagnosis rate in clinical stratification.

The application relates to a protein characterization learning method and device, computer equipment and a storage medium. The method comprises the following steps: collecting protein sequence, structure and function annotation information, and constructing a multi-modal feature data set; performing multi-modal feature extraction on the multi-modal feature data set by using a MASSA framework to obtain protein multi-modal representation; constructing a graph network by using the protein multi-modal representation, and storing the representation and a historical model of an existing protein task in the graph network; in the training process of a new protein task, a memory enhancement mechanism is used to retrieve a similar node of the new protein task from the graph network, a historical model of an existing protein task corresponding to the similar node is obtained, model parameters of the historical model are transferred by using a transfer learning framework, and model training is performed on the new protein task. The application effectively alleviates the data scarcity problem and improves the accuracy and generalization ability of the model in a small sample learning task.

This disclosure provides a method and related products for genome sequence generation and model training. During the training phase, pre-trained multimodal data, including sequence data, functional annotation data, omics data, and species evolution information, is acquired. A fused representation is obtained through heterogeneous coding and multimodal fusion, and input into the sequence generation model for feature calculation, outputting the predicted base probability distribution for each base position to be generated. The model is optimized by combining a multi-task training mode of autoregressive generation and intermediate padding, and a weighted loss function based on biological annotation. During the inference phase, sequences are generated progressively based on multimodal generation context information. Candidate bases are obtained through sampling and evaluated using biological constraints, omics validation, structural validation, and functional validation. Resampling is performed when conditions are not met until preset conditions are satisfied. This method can improve the biological rationality and application value of the generated sequences.

The application provides a single-cell RNA sequencing annotation method and device based on a dynamic hypergraph, relates to the technical field of bioinformatics, and comprises the following steps: obtaining a data set, extracting a low-dimensional embedding vector of each cell from a gene expression vector, and constructing a dynamic hypergraph with cells as nodes and gene pathways as hyperedges; extracting a pathway feature of each hyperedge from the dynamic hypergraph; calculating the importance weight of each cell in each hyperedge based on the low-dimensional embedding vector and the pathway feature of the hyperedge; inputting the dynamic hypergraph, the pathway feature and the importance weight into a preset hypergraph neural network for message aggregation and feature learning to generate a prediction label of a cell type; and training the hypergraph neural network through an optimization algorithm to obtain a trained cell annotation model. The application realizes more accurate and more biologically interpretable cell type and function annotation by introducing a hypergraph structure and a metabolic pathway activity dynamic modeling mechanism.

The invention relates to the technical field of new strains for degrading cellulose, in particular to a pseudoxanthomonas strain JC1303 and application thereof. Through whole genome sequencing and function annotation, it is systematically revealed for the first time that the strain carries a complete cellulose degrading enzyme system including incision beta-1, 4-glucanase, cellulase and beta-glucosidase, has a plurality of central metabolic pathways supporting efficient degradation and utilization of cellulose, and can be used for degrading cellulose. And specific gene resources are determined through generic genome analysis. The strain has the remarkable technical effects that the strain shows higher cellulase activity after being cultured for 5 days, and cellulose materials such as agricultural wastes and the like can be stably and efficiently degraded in a salt-containing environment by virtue of the unique genetic background and marine source characteristics of the strain.

The invention relates to the technical field of interactive prediction, in particular to a virus and disease associated prediction model, a construction method of the prediction model and a prediction method. Comprising the following steps: S1, collecting and processing virus and disease data; s2, performing feature extraction of the independent prediction model A; s3, performing feature extraction of the independent prediction model B; s4, based on five-fold cross validation and grid search, determining an optimal machine learning algorithm, and constructing an independent prediction model A and an independent prediction model B; and S5, based on a bagging integration strategy, integrating the independent prediction model A and the independent prediction model B, and generating a virus and disease associated prediction model. According to the invention, the VDP provides a new thought of multi-modal biological information integration; meanwhile, molecular sequence information of viruses, semantic structure information of diseases and GO function annotation information of the two parties are considered, more comprehensive feature representation is achieved, and the problems that an existing method is single in information source and insufficient in prediction accuracy are solved.

The invention relates to a base model training method and device based on a functional annotation abundance sequence. The method comprises the following steps: S1, carrying out function annotation on an open reading frame of a genome or metagenome sample; s2, counting the occurrence frequency of each annotation and constructing a sequence according to an abundance descending order; s3, after the sequence is subjected to token processing, inputting the sequence into a model based on Transform, and adopting joint training of language modeling, comparative learning and classification loss to obtain species-level and token-level fixed dimension embedding; s4, on the basis of the embedding, completing downstream tasks such as phylogenetic tree construction, species identification and phenotype prediction, BGC / MGC recognition and key gene positioning in three levels, namely a genome level, a gene cluster level and a gene / protein level. In the embodiment of the invention, good uniformity, expandability and interpretability are displayed, and the dependence on a reference database is reduced. The corresponding device comprises a data processing module, a model training module and an application module, and can be realized by program instructions in a computer readable storage medium.

The invention relates to the field of biological medicine, and discloses an integrated genome analysis method based on low-depth sequencing, and the method comprises the following steps: obtaining whole genome low-depth sequencing data; after quality control and comparison, SNV, Indel and CNV are calculated; performing multi-dimensional function annotation by combining genome position, coding influence, splicing disturbance, conservative property, regulatory element and three-dimensional chromatin interaction; database information such as ClinVar and HGMD is integrated, and according to a phenotype-driven rule engine, a clinical interpretable report is generated according to the ACMG / AMP standard. According to the method, a complete analysis chain covering sequence variation detection, multi-dimensional function annotation, three-dimensional genome association, public database integration and phenotype driven interpretation is constructed, so that the fundamental defect that only an original variation list is output and a clinical action basis cannot be provided in traditional low-depth sequencing is overcome.

The present application relates to a kind of functional information analysis method of marine microorganism in marine sample, based on liquid mass spectrometry obtains mass spectrum RAW file, utilize the peptide sequence obtained by macrogenomics sequencing, the database obtained by self-defined configuration or the database published in public is combined as macro proteome data search database.Combined with multiple sources of databases, such as databases published in public, databases obtained by self-defined configuration, and peptide sequences obtained by macrogenomics sequencing, as macro proteome data search database.The database is split according to the classification level of species, and the sub-database is reduced by iterative search method, and then the sub-database is combined, and the qualitative and quantitative analysis of macro proteome is carried out by using proteome search analysis software, and the function annotation software is used for function annotation based on public database.The proteome quantitative analysis software screens different environmental difference proteins, and deeply excavates the community composition and metabolic activity difference of different environmental microorganisms.

This invention provides a method for predicting protein methylation sites that integrates quantum and region-aware technologies, comprising the following steps: Step 1, obtaining protein sequences as data sources and constructing training and independent test sets respectively; Step 2, constructing multimodal features for each protein sequence using a three-way nested scattering network, fusing the multimodal features to obtain an optimized fused feature tensor; Step 3, inputting the optimized fused feature tensor into a RaQMeNet network model to perform methylation site prediction. This invention not only significantly outperforms existing technologies in terms of performance indicators but also possesses stronger adaptability, stability, and interpretability. It can be widely applied in multiple bioinformatics and biomedical fields such as protein functional annotation, disease mechanism research, and drug target discovery, demonstrating promising application prospects and commercial value.

The application discloses a method for eRNA transcription identification, regulation target prediction and function annotation based on high-throughput transcriptome sequencing data, and is characterized in that the method comprises the following steps: identifying part of non-coding RNA in which a transcription start site is located in an enhancer region as eRNA; obtaining eRNA-related protein coding genes which simultaneously exist in an eRNA-protein coding gene co-expression network and an eRNA-centered regulation network, constructing an eRNA-protein coding gene relationship network, and extracting protein coding genes which are directly connected or closely connected to the eRNA, so as to predict potential regulation targets of the eRNA; and finally, performing function enrichment analysis on the potential regulation targets of the eRNA, so as to obtain the results of eRNA function annotation, and the method has the advantages of wider application range, and can be applied to all eRNAs and more accurately obtain the action forms between the eRNA and the protein coding gene.

The invention relates to the technical field of drugs and the technical field of artificial intelligence, in particular to a protein-ligand binding affinity prediction method and system for drug research and development, and the method comprises the steps: obtaining a protein-ligand pair, and extracting structure-perceived protein characterization, functional characterization and ligand molecular characterization; wherein the protein characterization is determined by an amino acid sequence and structural information of the protein, and the function characterization is determined by the protein with function annotation information; performing token dimension alignment on the protein characterization and the functional characterization based on a multi-layer perceptron (MLP), performing multi-modal fusion on the aligned protein characterization and functional characterization, and obtaining a fused embedded representation by combining a token-by-token adaptive weight alpha; and splicing the fused embedded representation and ligand molecular representation to obtain a comprehensive feature vector for predicting binding affinity. Through deep interaction and fusion of multi-source information such as sequence, structure and function annotation, the accuracy of protein-ligand affinity prediction is improved.

The application provides a snowflake black cattle breeding method and system based on whole genome association analysis, relates to the technical field of black cattle breeding, and comprises the following steps: extracting PacBio long read HiFi sequencing data and second-generation whole genome resequencing data in a blood sample, and extracting Hi-C chromosome conformation capture sequencing data and multi-tissue full-length transcriptome sequencing data in a tissue sample; performing genome assembly to obtain a chromosome-level reference genome sequence; performing gene structure annotation on the reference genome sequence; detecting a whole genome SNP marker data set of a breeding population; screening whole genome SNP marker data meeting a preset significance threshold; performing functional annotation to obtain molecular markers for snowflake black cattle breeding. The application provides reliable and practically functional molecular marker support for the directional breeding of snowflake black cattle meat quality-related key economic traits.

The invention relates to a construction method of a database for discriminating proteolytic enzyme restriction enzyme cutting sites. Comprising the following steps: S1, acquiring family classification information and restriction enzyme cutting site data of proteolytic enzyme from an MEROPS database, acquiring sequence and function annotation data of substrate protein from a UniProt database, and acquiring three-dimensional structure data of the substrate protein from an AlphaFold database; s2, migrating and integrating the data in the S1 to the local; and S3, dividing the processed data into four correlative core data tables, and storing the four core data tables in a local database. According to the method disclosed by the invention, by combining MEROPS, UniProt and AlphaFold databases, the restriction enzyme cutting site of the proteolytic enzyme is accurately predicted by adopting an artificial intelligence algorithm. Compared with a traditional method, the method has the advantages that the restriction enzyme cutting sites can be recognized more efficiently and more accurately, and the protein function analysis speed and accuracy are remarkably improved.

The invention discloses a method for improving genome selection accuracy by integrating genome annotation information, and belongs to the technical field of molecular breeding. The method comprises the following steps: constructing a reference group and accurately determining target traits; acquiring high-density genotype data by using a whole genome re-sequencing technology; constructing an SNP function annotation matrix containing multi-dimensional information such as a gene structure, codon degeneracy in a coding region, nucleotide diversity and the like; estimating genetic variance weights of different functional regions by using a random Heismann-Elstarton regression (RHE) algorithm and a Monte Carlo REML algorithm; and constructing a weighted genome prediction model based on mixed prior distribution to estimate a breeding value. According to the method, differential modeling is carried out on functional sites and background noise markers through biological prior information, the genome selection accuracy of complex characters and the robustness of cross-population prediction are remarkably improved, and the method has a good application prospect.

The invention discloses a tree phenotype deep learning modeling method for multi-character collaborative prediction, and relates to the crossing field of tree breeding and artificial intelligence technologies. The method comprises the following components: S1, a multi-modal data acquisition step, S2, a multi-modal data preprocessing and fusion step, S3, a genotype-environment interaction algorithm development step, S4, a multi-character collaborative prediction model construction and optimization step and S5, a model verification and application step. According to the method, the contribution degree of key factors to phenotypes is quantified through an interpretability analysis method, core factors for regulating and controlling phenotype formation are mined in combination with gene function annotation, the process is beneficial to deep understanding of genetic and environmental bases of tree growth, a scientific basis is provided for rapid screening of good varieties, and particularly, the method has the advantages of being high in practicability and convenient to popularize and use. By analyzing a genotype-environment interaction effect, a genotype-environment combination having significant influence on phenotypes is identified, and then a core genotype-core environment factor-key phenotype regulation network is constructed.

This invention discloses an integrated method for identifying and functionally annotating metaprograms in tumor single-cell transcriptomes, belonging to the fields of bioinformatics, tumor biology, and single-cell transcriptome sequencing. This invention aims to address the problems of unstable metaprogram identification, significant technical artifact interference, and fragmented functional annotation in existing technologies. Based on multi-rank nonnegative matrix factorization, it systematically extracts co-expression modules at different scales from the tumor single-cell expression matrix. Robustness screening ensures the consistency and reliability of the obtained metaprograms under multiple factorizations and cross-sample conditions. Furthermore, it performs systematic functional analysis of the metaprograms to reveal the multi-dimensional functional states of tumor cells. This method improves the stability and biological interpretability of tumor metaprogram identification, providing a new technical means for tumor heterogeneity research and the discovery of precision therapeutic targets.

The application discloses a disease single cell AS detection marker panel construction method, device and system, and belongs to the field of database construction. Compared with a conventional database, the obtained marker panel is used for sequencing samples with different geographical sources on a plateau and a plain, so that dynamic changes of variable splicing driven by regional factors can be revealed, and defects of single data dimension and large deviation from a real scene of the conventional database can be made up. Secondly, cell type labels, barcodes and PSI matrices are integrated to construct a high-resolution variable splicing map, and cell heterogeneity and space-time expression patterns can be accurately captured. Finally, the AS marker panel obtained through differential screening and function annotation can provide more accurate, reliable and comprehensive research data for researchers.

This invention discloses a binary classification method for predicting immunotherapy response in colorectal cancer patients based on gut microbiome metagenomic data. The method includes the following steps: acquiring metagenomic sequencing data and immunotherapy response records from colorectal cancer patients; performing quality control, host removal, species and function annotation on the sequencing data to generate a microbial abundance matrix and a relative abundance spectrum of functional genes; integrating multi-source data to construct an initial feature dataset; constructing a microbial interaction network based on this dataset, and using a multi-stage feature selection strategy to select key features to form a final feature dataset; obtaining support vector machine (SVM) binary classification results for predicting immunotherapy response based on this dataset, and evaluating model performance using a cross-validation framework. This technical solution constructs a more stable feature dataset and ensures that the constructed classification model possesses both high accuracy in predicting immunotherapy response in colorectal cancer patients and good biological interpretability.

The invention discloses a method for identifying glycosyltransferase or glycosidase specific enzyme participating in DNA / RNA glycosylation, which is characterized in that oxidation labeling is carried out on glycosylation modification of DNA / RNA molecules, and solid phase coupling and enzyme digestion strategies are combined, so that enzyme or sugar binding protein specifically bound with glycosylation DNA / RNA can be efficiently and accurately captured, and the specific enzyme of glycosyltransferase or glycosidase can be identified. The interference caused by non-specific binding is obviously reduced. The method is not only suitable for various biological samples including tissue slices, blood and cell samples, but also compatible with subsequent mass spectrometric analysis, and high-throughput identification and function annotation of targeted proteins are realized. The technology provides a brand new tool for analyzing the action mechanism of DNA / RNA sugar modification in epigenetic regulation and control, and has important value for promoting the research of related disease mechanisms and the development of targeted therapy strategies.

This invention discloses a method for constructing a giant panda genetic map, belonging to the field of genetic map construction technology. The method includes the following steps: retrieving DNA samples, performing sequencing processing to obtain a sequencing BAM file; performing SNP+SV dual-type genetic marker targeted mining and marker hierarchical filtering; using an improved partial least squares regression algorithm to correct errors in the marker filtering genotype matrix and label pedigree relationships; using an improved minimum spanning tree-based genetic map construction algorithm to construct linkage groups and calculate preliminary genetic distances between markers; correcting the preliminary genetic distances between markers to construct the giant panda genetic map; and performing genome anchoring and functional annotation to obtain the final giant panda genetic map. This application improves the accuracy, coverage, and species suitability of the giant panda genetic map by combining SNP+SV dual-type genetic marker targeted mining, an improved error correction algorithm, and an improved genetic map construction algorithm.