4 results about "Tissue expression" patented technology

This invention relates to a method and system for predicting insect multi-tissue expression levels based on multimodal feature fusion. Using the target gene as the basic prediction unit, it simultaneously inputs the target gene's regulatory sequence information, RNA stability characteristics, and protein representation information. Joint modeling is performed through a multi-tower deep learning network, outputting predicted expression levels of the target gene in multiple tissues. Advantages: It overcomes the limitations of traditional methods that primarily rely on single-modality data. For the first time, it integrates insect gene regulatory sequences, RNA stability features, and pre-trained protein language models into a unified expression prediction framework. Utilizing the multimodal prediction model, it extracts, fuses, and predicts multimodal data features, providing accurate and comprehensive gene expression level prediction results. Furthermore, it introduces a gating backoff mechanism for missing protein annotations, avoiding the misinterpretation of missing values ​​as zero or noise, thus ensuring prediction stability.

The application discloses application of a SmCYP82D47 gene in improving resistance of eggplants to bacterial wilt, and belongs to the technical field of molecular biology. The nucleotide sequence is shown as SEQ ID NO. 2. On the basis of GWAS positioning of an eggplant bacterial wilt resistance linkage site, the application screens an eggplant bacterial wilt resistance candidate gene SmCYP82D47 through bioinformatics analysis such as gene sequence analysis and haplotype analysis; analyzes tissue expression specificity and hormone response expression characteristics of the candidate gene; and observes the disease resistance of a silencing plant and a wild type plant, and the disease resistance of a wild type plant and an overexpression plant by silencing the candidate gene in a resistant material S027 and overexpressing the candidate gene in a susceptible material S054, so as to not only verify the accuracy of the positioning result and determine the role of the candidate gene in regulating the bacterial wilt resistance of the eggplant, but also provide an important theoretical basis and technical means for eggplant disease resistance molecular breeding.

This invention relates to the fields of tumor biology and cell engineering, specifically disclosing the construction and application of a human prostate cancer cell line. The human prostate cancer cell line is derived from primary prostate cancer tissue, expresses prostate-specific antigen and α-methylacyl-CoA racemic enzyme, and has a 46,XY karyotype. The construction method employs an innovative strategy of co-culturing fully digested cell suspensions with incompletely digested tissue blocks, significantly improving the success rate of establishing the cell line from the primary lesion. This cell line can stably proliferate in conventional culture media supplemented with testosterone and has been successfully applied to subcutaneous tumorigenesis models in immunodeficient mice and in vivo migration models in zebrafish. The primary lesion-derived prostate cancer cell line provided by this invention offers a highly relevant, stable, and reliable new experimental tool for studying the biological characteristics of primary prostate cancer, drug screening, and personalized treatment.

The present application relates to a kind of based on multi-modal feature fusion insect multi-tissue expression quantity prediction method and system, with target gene as basic prediction unit, while inputting the regulatory sequence information, RNA stability characteristic information and protein representation information of target gene, carry out joint modeling by multi-tower deep learning network, output the expression quantity prediction value of the target gene in multiple tissues.Advantage: break through the limitation of traditional method mainly relying on single mode data, first embed uniform into an expression prediction framework for insect gene regulatory sequence, RNA stability characteristic and pre-training protein language model;Using multi-modal prediction model, the multi-modal data features are extracted, fused and predicted, so as to provide accurate and comprehensive gene expression prediction results, while introducing a gating back mechanism for missing protein annotation, avoiding missing values being treated as zero or noise, so as to ensure the stability of prediction.