Corn variable splicing isomer function prediction system based on tissue specificity

Abstract

The invention provides a corn variable splicing isomer function prediction system based on tissue specificity, which is characterized in that isoform co-expression networks of a plurality of tissues are constructed by processing expression data of isoform on each tissue, and the isoform co-expression networks of each tissue are integrated through self-adaptive weight, so that the function of the corn variable splicing isomer is predicted. A high-quality isoform organization specific association network can be obtained; according to the method, an isoform sequence similarity network is constructed by using isoform sequence data, and the isoform sequence similarity network is fused with an isoform organization specificity association network, so that a better isoform function association network can be obtained; multi-example learning is performed through non-negative matrix factorization, and meanwhile, the non-negative matrix factorization is guided by using an isoform function association network, so that more accurate and more comprehensive function prediction of isoform is realized.

Description

technical field [0001] The present invention relates to the technical field of function prediction of alternative splicing isoforms, in particular to a tissue specificity-based function prediction system of maize alternative splicing isoforms. Background technique [0002] The statements in this section merely provide background related to the present disclosure and do not necessarily constitute prior art. [0003] With the development of biology, gene-related research has played a role in promoting the improvement of maize breeding and improving the quality of maize varieties. Gene function prediction plays an important role in biology and has been widely studied. In recent years, the research on transcriptome has gradually attracted attention. Alternative splicing isoforms (isoforms) are an important part of the transcriptome. , and accurately predict the function of isoform, which is of great significance to maize breeding and protein variant function research. [0004]...

AI Technical Summary

Problems solved by technology

[0004] The inventors found that there are currently many programs using isoform tissue-specific data to predict isoform function through machine learning models; however, these existing isoform function prediction methods have certain limitations, and these prediction methods often simply use The RNA-seq data obtained the feature vector composed of the differential expression characteristics of isoform in different maize tissues, but did not make full use of tissue-specific data to improve the function prediction performance of isoform

Images