Caffe based extraction method of stack denoising self-encoding gene information characteristics

A gene feature and feature extraction technology, applied in the field of bioinformatics

Active Publication Date: 2017-01-04
MELUX TECH CO LTD
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, BLAST is more of a query comparison tool, and cannot automatically extract features and identify genetic traits through deep learning algorithms

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
  • Caffe based extraction method of stack denoising self-encoding gene information characteristics
  • Caffe based extraction method of stack denoising self-encoding gene information characteristics
  • Caffe based extraction method of stack denoising self-encoding gene information characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0023] Data preparation in step S1: first prepare the gene information data used for training the model, where the gene information data uses genes with the same name from different individuals, assuming that there are n gene sample data from different individuals. Visualize the base sequence of the gene of the n people, and the visualization result is genetic data in n image formats;

[0024] Suppose the image pixel size is p 0 ×q 0 , and then set the n image pixels to a fixed size p×q. Use the convert_imageset tool provided by Caffe to convert the n image samples into a database file suitable for Caffe. The database file format is leveldb or lmdb, preferably lmdb.

[0025] Step S2 is to build a stack noise reduction self-encoding gene feature extraction model based on Caffe. The basic unit of the model is a noise-reduction self-encoding model, and a gene feature extraction model is composed of several basic units of the noise-reduction self-encoding model stacked together...

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 Caffe based extraction method of stack denoising self-encoding gene information characteristics. The Caffe based extraction method of the stack denoising self-encoding gene information characteristics comprises specific steps as follows: S1, data is prepared; S2, a Caffe based stack denoising self-encoding gene characteristic extraction model is built; S3, the stack denoising self-encoding gene characteristic extraction model is trained layer by layer; S4, the stack denoising self-encoding gene characteristic extraction model is subjected to fine adjustment according to labeled gene data; S5, a gene trait identification system is built by utilizing the well trained gene characteristic extraction model. According to the technical scheme, a deep learning algorithm framework is adopted, and on the basis of image characteristic extraction, to-be-detected genes can be subjected to characteristic extraction and further classification and recognition through training of a classification and identification model.

Description

technical field [0001] The invention relates to the technical field of biological information, in particular to a method for extracting features of self-encoded gene information based on Caffe-based stack noise reduction. Background technique [0002] The Human Genome Project has laid the foundation for the study of complex diseases from genes, and people hope to find the relationship between human disease and genes. Genome-wide association study (Genome-wide association study) refers to finding out the sequence variations existing in the whole human genome, that is, single nucleotide polymorphisms (SNPs), and screening SNPs associated with diseases. The introduction of this research method makes the prediction of the onset of genetic epidemics no longer stay in the traditional analysis of "environmental" factors such as age and family history, but through the analysis of the whole genome of the human body, find out the factors that may lead to future onset of diseases. gen...

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): G06F19/18G06K9/62
CPCG16B20/00G06F18/2155
Inventor 余孟春何庆瑜特伦斯·古力谢清禄闫磊
Owner MELUX TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap