Method for predicting miRNA [micro-RNA (ribonucleic acid)] target proteins of miRNA regulation protein interaction networks
A target protein and protein technology, applied in the field of bioinformatics and molecular biology, can solve the problems of lack of dynamic regulation relationship, expensive experiment interaction, high false positive, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0063] Example 1 miRNA target protein prediction method for miRNA-regulated protein interaction network
[0064] A miRNA target protein prediction method for miRNA regulation protein interaction network, comprising the steps of:
[0065] 1. Construct the following three sub-networks respectively:
[0066] (1) Construction of HIPPIE-based human protein-protein interaction network (PPIN)
[0067] Download the entire human protein-protein interaction data from the HIPPIE database, remove self-interactions, repeated interactions, and interactions with an interaction score of 0; obtain protein sequence information (sequence information) from the UniprotKB / Swiss-Prot database according to the protein access number That is, primary structure data), calculate amino acid composition (20 dimensions), dipeptide composition (400 dimensions), autocorrelation descriptors and composition (1221 dimensions), transformation (21 dimensions) and distribution (105 dimensions) in total 1767 dimens...
Embodiment 2
[0097] Example 2 Taking the miRNA network related to cardiovascular and cerebrovascular diseases as an example to verify the miRNA target protein prediction method of the present invention
[0098] 1. Collect data sets and build a node- and edge-weighted miRNA-protein interaction network
[0099] Human protein-protein interaction data were collected from the HIPPIE database, removing self-interactions, repeated interactions, and interactions with an interaction score of 0. According to the protein acquisition number, the protein primary structure data was obtained from the UniprotKB / Swiss-Prot database, and the amino acid composition, dipeptide composition, autocorrelation descriptors and protein primary structure descriptors such as composition, transformation and distribution were calculated. The node weight in the protein network is the primary structure feature of 1767-dimensional protein, and the edge weight is the interaction trust score.
[0100] The data on the intera...
Embodiment 3
[0126] Embodiment 3 compares with other methods
[0127] Currently, four target prediction methods commonly used in the prior art are PITA, miRanda, rna22, and targetspy. These methods are only based on sequence information for prediction, such as matching analysis, secondary structure prediction, and genetic conservation analysis. Data such as gene expression and information on mutual regulation between genes (such as action pathways, protein networks) have not been used reasonably.
[0128] For this purpose, use Mark Menor (Mark Menor, Travers Ching, Xun Zhu, et al. mirMark: asite-level and UTR-level classifier for miRNA target prediction [J]. GenomeBiology, 2014, 15:500) et al. In the data set, 253 positive samples and 362 negative samples are taken as an independent test set.
[0129] The method of the present invention, PITA, miRanda, rna22 and targetspy are analyzed to this data set respectively, and the result is shown in Table 3, and ROC curve and PRC curve are as fol...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com