6 results about "Gene ontology" patented technology

The application provides a gene ontology guided multi-expert gene expression prediction method, comprising the following steps: S1, using a feature extraction network to extract global morphological features with spatial context information from image patch sequences; S2, based on spatial transcriptome data, using gene ontology knowledge to generate and organize a spatial resolution functional atlas corresponding to a spatial structure; S3, inputting the global morphological features obtained in S1 and the spatial resolution functional atlas obtained in S2 into a hybrid expert model; generating function-aware collaborative features; S4, integrating features for a target image patch; inputting the integrated fusion features into a prediction network to regress a predicted gene expression profile of the target image patch. The application realizes the most advanced prediction performance on multiple public datasets, and significantly improves the biological interpretability of the model.

The present application belongs to the field of biotechnology, and specifically relates to a method for high-throughput screening of nucleic acid drug target genes, which comprises the following steps: treating cells with nucleic acid drug candidates or negative controls, and collecting measurement values for a plurality of cell characteristic parameters related to the treatment purpose of the nucleic acid drug; calculating the fold change of the characteristic parameter measurement values of the cells in each candidate hole relative to the negative control measurement values and normalizing them; for all measurement values, calculating the squared Mahalanobis distance of the plurality of cell characteristic parameters relative to the average value using the normalized values; screening out the candidates with squared Mahalanobis distance greater than a cutoff value, and unsupervised clustering the cells according to the plurality of cell characteristic parameters to divide the candidates into at least one cluster; obtaining the corresponding silenced genes of the candidates in each cluster, and performing gene ontology enrichment analysis on the genes in the cluster to obtain the biological processes associated with each cluster, and finally obtaining nucleic acid drug target genes for different biological processes.

The application provides serum biomarkers for diagnosing and evaluating the activity of aortitis and application, and relates to the field of disease activity evaluation. The serum biomarkers are serum proteins: HP and ORM1. HP and ORM1 are determined as two new serum biomarkers through comprehensive proteomics analysis; gene ontology and Kyoto Encyclopedia of Genes and Genomes pathway analysis are carried out using a DAVID database; a protein-protein interaction network is constructed using Metascape. A random forest model is trained using a caret package, and a nomogram is visualized using an rms package. Serum samples are obtained, and the serum levels of HP and ORM1 are determined using a commercial ELISA kit; they are significantly related to disease activity, and are involved in inflammation / immune processes in aortitis, so the markers have the potential to serve as an auxiliary tool for monitoring the activity of aortitis.

This invention proposes a method and apparatus for protein function prediction based on a topology-aware attention network. The method includes the following steps: S1: acquiring a publicly available protein function annotation dataset, a publicly available gene ontology description, and relational .obo files; S2: constructing a protein graph input and a gene ontology graph input; S3: building a topology-aware protein-gene ontology attention network, including a topology-aware attention module and a multi-head aggregator; S4: training the topology-aware protein-gene ontology attention network from step S3 using the data from step S1 to obtain a trained protein function prediction model; S5: for a protein whose function is to be predicted, using the trained model from step S5, generating the probability that it is annotated by each GO term. This method can improve the performance of protein function prediction.

The application discloses a kind of construction methods of glaucoma genetic information database, it is related to database technical field, and its technical solution key points include the following steps: through literature retrieval and database query, the genetic information of glaucoma related gene is collected;Through high-throughput gene sequencing, sequencing result obtained by genome sequencing of glaucoma patient;The sequencing result is analyzed by bioinformatics and the mutation variation data related to glaucoma is screened out;Mutation variation data and genetic information form preliminary gene dataset;Based on gene dataset, the rear end architecture of database is constructed using database management system, and the front-end website platform with data retrieval function is configured;Gene basic information query, gene ontology enrichment analysis and protein interaction network analysis on gene dataset are integrated in front-end website platform;Effect is to promote the fusion development of glaucoma genetic research and clinical practice.

The invention discloses an IncRNA function prediction method based on gene ontology structure semantic perception, and relates to an IncRNA function prediction method. In order to solve the problems that according to an existing lncRNA function prediction method, fusion of multi-source heterogeneous information is insufficient, a DAG structure of a GO body is difficult to use at the same time, and a prediction result violates a True Path Rule, firstly, a VAE-based method is used for effectively fusing multi-source heterogeneous features of lncRNA; the method comprises the following steps of: firstly, extracting semantic features of lncRNA by using a BioBERT method, finally, injecting lncRNA information into GO features through cross attention, adopting DAG-LSTM to bidirectionally spread the features, and finally, enabling GO to pay more attention to True Path Rule information by using a self-attention mechanism causal mask. According to the invention, the accuracy of lncRNA function prediction can be effectively improved.