Gene Feature Extraction Method Based on Manifold Learning and Closed-loop Deep Convolutional Dual Network Model

A deep convolution and genetic feature technology, applied in biological neural network models, informatics, biostatistics, etc., can solve problems such as inability to preserve to the greatest extent, slow dimensionality reduction, etc., and achieve the goal of retaining genetic features and quickly reducing dimensionality Effect

Active Publication Date: 2020-08-25
ZHEJIANG UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to overcome the shortcomings of the existing gene feature extraction methods, which are slow in dimensionality reduction and unable to preserve gene features to the greatest extent, the present invention provides a dual-layer method based on manifold learning and closed-loop deep convolution that preserves gene features to the greatest extent and realizes rapid dimensionality reduction. Gene Feature Extraction Method Based on Network Model

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
  • Gene Feature Extraction Method Based on Manifold Learning and Closed-loop Deep Convolutional Dual Network Model
  • Gene Feature Extraction Method Based on Manifold Learning and Closed-loop Deep Convolutional Dual Network Model
  • Gene Feature Extraction Method Based on Manifold Learning and Closed-loop Deep Convolutional Dual Network Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] refer to figure 1 and figure 2 , a gene feature extraction method based on manifold learning and closed-loop deep convolution dual network model, including rough extraction of cancer-associated gene features based on manifold learning, and fine capture of gene feature vectors based on closed-loop deep convolution dual network structure. Rapid dimensionality reduction can be achieved on the premise of retaining the characteristics of cancer-associated genes to the greatest extent.

[0048] The rough extraction of gene features adopts the feature extraction method based on manifold learning. The genetic data feature is the assumption of a low-dimensional sub-manifold sampled in a high-dimensional peripheral Euclidean space, and the manifold has a certain low-dimensional internal structure. However, ordinary dimensionality reduction methods have deficiencies su...

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

A genetic feature extraction method based on flowing learning and closed -loop deep convolution dual network models, including the following steps: the first step, a rough extraction of cancer -based cancer -based cancer -based genes.The genetic characteristics of the network structure are finely extracted.In the end, the key features are projected; the reverse convolutional neural network realizes the reverse projection of key features.The present invention provides a genetic feature extraction method for the maximum extent to retain gene characteristics and achieve rapid dimension -based learning and closed -loop deep convolution dual network models.

Description

technical field [0001] The invention relates to the technical field of gene feature extraction, in particular to a gene feature extraction method. Background technique [0002] The era of precision medicine has gradually arrived, and the accurate diagnosis and precise treatment of cancer bear the brunt. In China, 6 people are diagnosed with malignant tumors every minute, and the lifetime probability of Chinese residents suffering from cancer is 22%. Cancer has become the leading cause of death for Chinese residents. Cancer prevention and treatment are the focus of scientists in various disciplines. With the reduction of the cost of gene sequencing, by sequencing and comparing the gene expression data of normal people and cancer patients, a cancer risk assessment report can be obtained, which is also a relatively advanced means of early detection of cancer. At the same time, it also analyzes the progress and effect of treatment by tracking and detecting gene expression data ...

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 Patents(China)
IPC IPC(8): G16B40/30G16B40/00G06K9/62G06N3/04
CPCG16B40/00G06N3/044G06N3/045G06F18/23211G06F18/2134
Inventor 陈晋音郑海斌熊晖吴洋洋李南应时彦
Owner ZHEJIANG UNIV OF TECH
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