Non-coding RNA and disease relation prediction method based on Hessian regular non-negative matrix factorization

Abstract

The invention discloses a non-coding RNA and disease relationship prediction method based on Hessian regular non-negative matrix factorization, and belongs to the field of system biology. The method mainly comprises the following three steps: 1, respectively calculating Gaussian spectrum kernel similarity of non-coding RNA and Gaussian spectrum kernel similarity of diseases; 2, calculating a prediction score of the non-coding RNA-disease association pair by using an iterative solution algorithm; 3, sorting the scores according to the calculated non-coding RNA-disease association, and giving afinal prediction result. According to the method, the internal manifold structure of the data is described meticulously through Hessian regularization, so that the information of a negative sample iseffectively utilized; the l2, 1 norm constraint and the approximate orthogonal constraint ensure the group sparsity of the coding matrix, and the influence of noise data can be weakened. According tothe method, a relatively reliable prediction result can be obtained, and the problems of long consumed time and high cost of a biological experiment method are effectively solved.

Description

technical field [0001] The invention relates to the field of systems biology, and more specifically, the invention relates to a method for predicting the relationship between non-coding RNAs and diseases based on Hessian canonical non-negative matrix decomposition. Background technique [0002] Non-coding RNA (non-coding RNA, ncRNA) refers to RNA molecules that do not encode proteins in the transcriptome, and common ones include microRNA, lncRNA, and circRNA. [0003] MicroRNAs (miRNAs) are endogenous single-stranded RNAs approximately 22 nucleotides in length that are found in a variety of species, including plants, animals and some viruses. As an important post-transcriptional regulator, they inhibit gene expression and promote mRNA degradation by base-pairing with the 3'untranslated regions (UTR) of target RNAs. They play key roles in diverse biological processes such as cell division, differentiation, development, metabolism, infection, aging, apoptosis and signal trans...

AI Technical Summary

Problems solved by technology

However, since revealing associations by experimental methods is expensive and time-consuming, novel and efficient computational methods for association prediction are required

Common deficiencies of developed methods include failure to account for global similarity, high false positives involving transition components, or use of randomized unvalidated samples as negatives leading to imprecise approximation substitutions

Images