Intron retention prediction model establishing method and prediction method thereof

Abstract

The invention discloses an intron retention prediction model establishing method. The method comprises the following steps of: collecting analog data and real data related to intron retention; defining all the independent intron sets in a genome and using the intron sets as standard templates; acquiring an intron sequence reading distribution mode picture data set in the obtained analog data, andprocessing the intron sequence reading distribution mode picture data set to obtain a processed data set; dividing the processed data set into a training set and a test set according to a set proportion; and training a neural network model by adopting the training set to obtain a finally established neural network intron retention prediction model. The invention also discloses a prediction methodcomprising the intron retention prediction model establishing method. According to the invention, introns can be visualized and predicted based on an intron retention reading distribution mode, and high reliability and good accuracy are obtained.

Description

technical field [0001] The present invention specifically designs a method for establishing an intron retention prediction model and a prediction method thereof. Background technique [0002] Intron retention is a type of alternative splicing, which means that the introns in the pre-mRNA are not spliced ​​out but are retained in the mature mRNA. Intron retention, previously thought to be the result of missplicing, has received less attention. Many recent studies have shown that intron retention is related to gene expression regulation and complex diseases (such as Alzheimer's disease); and with the development of high-throughput sequencing technology, there are already many intron retention detection Methods proposed, iREAD and IRFinder are more prominent. Among them, iREAD detects intron retention by assuming that the reads of intron retention are evenly distributed, and calculates the entropy value, and the corresponding filtering index is stricter. IRFinder detects int...

AI Technical Summary

Problems solved by technology

[0003] Although the above methods have been successfully applied to real environments, the analysis based on sequence features is more or less limited by the bias caused by intron retention, which leads to insufficient robustness of the method, making the current The reliability of the method is not high, which restricts the development of related technologies

Images