Disease-related miRNA prediction system

Abstract

The invention discloses a disease-related miRNA prediction system. The disease-related miRNA prediction system comprises a data acquisition module, a data processing module and a prediction module. The data acquisition module is used for acquiring disease sample data, disease-miRNA relationship data, disease-gene relationship data, gene interaction data and miRNA-gene interaction data; the data processing module is used for constructing a miRNA-gene-disease heterogeneous information network according to the data acquired by the data acquisition module, and decomposing and processing the miRNA-gene-disease heterogeneous information network through a multi-task matrix to obtain final representation characteristics of diseases, genes and miRNA; and the prediction module is used for predictingthe miRNA related to the disease according to the final representation characteristics of the disease and the final representation characteristics of the miRNA. According to the invention, predictioncan be carried out by effectively combining gene information and known disease-related miRNA, and the prediction performance of the disease-related miRNA is improved.

Description

technical field [0001] The present application relates to the technical field of systems biology, in particular to a disease-related miRNA prediction system. Background technique [0002] miRNA (microRNA, micro ribonucleic acid) is a small, endogenous, single-stranded, non-coding RNAs with a size of about 20-25 nucleotides. It mainly inhibits the expression of messenger ribonucleic acid mRNA carrying genetic information by binding to the 30-untraslated region of the target gene, resulting in cleavage or translational inhibition of mRNA. Accumulating evidence indicates that miRNAs play a positive regulatory role at the post-transcriptional level, which is a key point in disease development. Accumulating experimental evidence indicates that dysfunction of miRNA mutations and dysregulation of miRNA and target gene biosynthesis contribute to a wide variety of diseases. [0003] Therefore, identifying the relationship between miRNAs and disease is an important issue. There are...

AI Technical Summary

Problems solved by technology

However, these new computational methods still face many challenges

First of all, biological experiments can often only prove that one miRNA is related to a disease, but it is difficult to explain that a miRNA is completely irrelevant to a disease

Therefore, only positive samples can be obtained, and it is difficult to obtain negative samples

Second, when a new miRNA is discovered, other relevant information cannot be obtained, and it is difficult for existing computational methods to infer miRNA-related diseases

Images