Incidence relation prediction method of circular RNA

Abstract

The invention discloses an incidence relation prediction method of circular RNA. The method comprises the steps that step one, a circular RNA Gauss kernel similarity first matrix and a disease Gauss kernel similarity first matrix are constructed; step two, the relation initial values between new circular RNA and each disease, a new disease and each circular RNA are calculated based on a decreasingweight method; step three, a circular RNA Gauss kernel similarity second matrix and a disease Gauss kernel similarity second matrix are constructed; step four, a circular RNA similarity matrix and adisease similarity matrix are constructed; step five, a Kronecker product least square method is adopted to calculate a circular RNA and disease relation score matrix, and the relation scores of the new circular RNA and all diseases and the relation scores of the new disease and all circular RNA are obtained. By means of the method, prediction is conducted on incidence relation of circular RNA diseases through a computing prediction model, and the vacant of a computing model used for predicting the relation between circular RNA and disease is filled.

Description

technical field [0001] The invention belongs to the field of systems biology, and in particular relates to a method for predicting the association relationship of circular RNA diseases based on Gaussian kernel similarity and decreasing weight least squares method. Background technique [0002] Circular RNA is a type of non-coding RNA produced by reverse shearing. Unlike traditional linear RNA (linear RNA, including 5' and 3' ends), circRNA molecules have a closed circular structure and are not affected by RNA exonucleases. , the expression is more stable and not easy to degrade, but with the development of high-throughput deep sequencing technology, recent studies have shown that a variety of circRNAs have been identified in various tissues and cell lines of animals and plants. Usually, circRNAs regulate gene expression by regulating miRNA transcriptional or post-transcriptional levels, and then play an important regulatory role in diseases. In recent years, with the applic...

AI Technical Summary

Problems solved by technology

In addition, due to the inherent high cost and long cycle of traditional biological experiments to determine the relationship between circular RNA and disease, there is also an urgent need for a computational model for predicting the relationship between circular RNA and disease

But so far, there is no relevant computational model to predict t

Images