Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Nucleosome classification forecasting method based on convolutional neural network

A technology of convolutional neural network and classification prediction, which is applied in the field of classification prediction of genetics and can solve problems such as the limitation of positioning accuracy

Active Publication Date: 2018-01-05
GUILIN UNIV OF ELECTRONIC TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Based on a method called "iNuc-PseKNC" (Guo S H, Deng E Z, Xu L Q, et al. iNuc-PseKNC: a sequence-based predictor for predicting nucleosome positioning in genomes with pseudok-tuple nucleotide composition. [J]. Bioinformatics ,2014,30(11):1522) is the core algorithm for predicting nucleosome position, but most of the existing prediction algorithms are only based on the statistical characteristics of nucleosomes, and the positioning accuracy is very limited.

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
  • Nucleosome classification forecasting method based on convolutional neural network
  • Nucleosome classification forecasting method based on convolutional neural network
  • Nucleosome classification forecasting method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The content of the present invention will be further described below in conjunction with the accompanying drawings and embodiments, but the present invention is not limited.

[0047] Example:

[0048] refer to figure 1 , a method for predicting nucleosome classification based on a convolutional neural network, comprising the following steps:

[0049] 1) Feature extraction: select the DNA sequences of the nucleosomes or linkers of Homo sapiens, nematodes and Drosophila melanogaster in the UCSC genome database. Refers to the base pair, which converts the 16 combinations of the dinucleotide ATCG in the DNA sequence of each nucleosome or linker into a 16-dimensional vector through one-hot encoding. The feature vector is expressed as formula (1) :

[0050] x i =(P i,1 ,P i,2 ,...,P i,16 ) T (1)

[0051] x i Indicates the eigenvector of the i-th nucleosome or link body at this time, P i,1 ,P i,2 ,...,P i,16 Represents one-hot encoding of 16 combinations of dinuc...

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 nucleosome classification forecasting method based on a convolutional neural network. The nucleosome classification forecasting method is characterized by comprising the following steps that firstly, feature extraction is conducted; secondly, the physical and chemical properties of nucleotides in nucleosomes or in the DNA sequence of a linking body are extracted; thirdly,biological characteristics are added; fourthly, the twenty-fourth dimension vector is obtained; fifthly, the chemical properties of the nucleotides are added; sixthly, a matrix containing biologicalinformation is obtained; seventhly, the structure of the convolutional neural network is built; eighthly, the nucleosomes are classified. By means of the method, the classification of the nucleosomescan be precisely forecasted.

Description

technical field [0001] The invention relates to classification prediction of genetics, in particular to a method for prediction of nucleosome classification based on convolutional neural network. Background technique [0002] Nucleosome prediction is an important part of current genetic research. The special structure of nucleosomes limits the contact between proteins responsible for basic life processes and DNA surrounding histones, so its formation and precise positioning on chromatin are important in genes. It plays an irreplaceable role in the expression process, directly or indirectly affecting basic biological processes such as transcription. Nucleosome positioning is an important way to regulate gene transcription in eukaryotes. To thoroughly understand the regulatory information of gene expression, it is necessary to consider the regulatory role of nucleosome positioning. The relationship between nucleosome position information and gene expression regulation is curre...

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): G06F19/24G06N3/04
CPCY04S10/50
Inventor 樊永显龚浩蔡国永张向文张龙
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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