Unlock instant, AI-driven research and patent intelligence for your innovation.

MiRNA-disease correlation prediction method based on cooperative smoothing

A collaborative filtering and prediction method technology, applied in the field of bioinformatics, can solve problems such as unpredictable connections, and achieve the effects of accurate CFMDA, reduced calculation, and fast and compact methods

Active Publication Date: 2017-12-29
HANGZHOU DIANZI UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main consideration of the present invention is that for previous prediction methods of potential relationship between miRNA and disease, negative samples need to be verified, and some methods cannot predict the connection between potential miRNA and disease without any known miRNA-disease relationship

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • MiRNA-disease correlation prediction method based on cooperative smoothing
  • MiRNA-disease correlation prediction method based on cooperative smoothing
  • MiRNA-disease correlation prediction method based on cooperative smoothing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in detail below in combination with specific embodiments.

[0035] The miRNA-disease association prediction method based on collaborative filtering proposed by the present invention is implemented according to the following steps:

[0036] Step 1: Calculate the adjacency matrix

[0037]The connection map is the input of the algorithm, so the connection map is obtained according to the verification between the disease and the miRNA, figure 1 The connectivity of 4 diseases and 5 miRNAs is given. figure 1 Some symbols are introduced in to represent the connection graph and the adjacency matrix, which is obtained from the connection graph. exist figure 1 Among them, d(i) is called the i-th disease, m(j) is called the j-th miRNA, and A(i,j) is called the adjacency matrix. If there is a relationship between the miRNA and the disease, the element at the corresponding position is number 1, otherwise the element is number 0. The adjac...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for predicting MiRNA-disease association based on collaborative filtering. The steps of the present invention are as follows: step 1, obtain the adjacency matrix that records the verified or unverified relationship between the disease and miRNA; step 2, obtain the importance matrix, specifically refer to the number of multiple miRNAs related to a certain disease in the following three factors , the similarities between diseases, the number of multiple diseases related to a certain miRNA; step 3, calculate the scoring matrix by multiplying the adjacency matrix and the importance matrix; step 4, predict according to the threshold setting; use the scoring matrix The calculation method obtains a threshold value, and compares the set threshold value with the threshold value obtained by the calculation of the scoring matrix, thereby proving whether miRNA-disease has a relationship. The present invention is fast and compact, with no recursive calls or complex linear algebraic transformations.

Description

technical field [0001] The invention belongs to the field of bioinformatics, and is especially aimed at the application of computer science and technology to the prediction of pathogenic genes, and in particular relates to a MiRNA-disease association prediction method based on collaborative filtering. Background technique [0002] MicroRNA (miRNA) is a small non-coding single-stranded RNA molecule of 20-22 nucleotides, usually a folded RNA precursor molecular structure of 60-110 nucleotides. In recent years, thousands of microRNA molecules have been identified in eukaryotes following the experimental research on microRNAs. A large amount of evidence shows that miRNA plays an important role in many biological processes, such as cell development, differentiation, proliferation, apoptosis, metabolism, aging, signal transmission and virus infection. At the same time, recent studies have shown that miRNA variation is closely related to many human diseases, such as cancer, metabo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F19/00
Inventor 李志胜颜成钢刘炳涛周旭俞灵慧陈靖文
Owner HANGZHOU DIANZI UNIV