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

Improved GA-SVM based tumor feature gene extraction method

A tumor characteristic gene, GA-SVM technology, applied in gene models, genetic laws, instruments, etc., can solve problems such as lack of persuasion

Inactive Publication Date: 2018-10-16
ZHEJIANG UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the above literature, only internal verification was carried out, and no external test was carried out, so the results obtained are not convincing.
[0004] Therefore, the existing GA-SVM method has defects in feature gene extraction and needs to be improved

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
  • Improved GA-SVM based tumor feature gene extraction method
  • Improved GA-SVM based tumor feature gene extraction method
  • Improved GA-SVM based tumor feature gene extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with the accompanying drawings.

[0042] In order to make the purpose, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, and are not intended to limit the present invention.

[0043] refer to figure 1 , a method for extracting tumor characteristic genes based on improved GA-SVM, comprising the following steps:

[0044] Step S1, the gene expression profile data set is subjected to support vector machine SVM for sample selection, and the samples are divided into: training set, verification set and test set;

[0045] Step S2, input the test set and verification set obtained above into the improved GA-SVM to perform data dimensionality reduction processing to obtain a subs...

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 an improved GA-SVM based tumor feature gene extraction method, comprising the steps: tumor gene expression profile data is subjected to support vector machine to classify samples which are divided into three parts: a training set, a verification set and a test set; then the test set and the verification set are input into an improved GA-SVM to reduce the dimension of the data to obtain a gene feature subset; and finally, the obtained gene feature subset is input to the support vector machine for classification and identification. The result shows that the invention hasa better classification effect on tumor expression profile data and good stability. The invention provides the improved GA-SVM based tumor feature gene extraction method, which has a good classification effect and high classification stability.

Description

technical field [0001] The invention relates to a method for extracting tumor characteristic genes based on improved GA-SVM, which belongs to the technical field of machine learning. Background technique [0002] Through microarray chip experiments, people can obtain gene expression profile data, and through the analysis of these data, people can dig out information and knowledge with biological significance. How to select characteristic genes containing sample classification information from gene expression profile data, establish a classifier, and realize tumor typing diagnosis is an important field of current bioinformatics research. In view of the importance of tumor subtype identification and classification feature gene selection, a large number of research literatures on this issue have appeared. At present, the main methods for classifying and analyzing gene expression data include artificial neural network, genetic algorithm, support vector machine and Bayesian, etc...

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
IPC IPC(8): G06K9/62G06N3/12G06N99/00
CPCG06N3/126G06F18/23213G06F18/2411G06F18/214
Inventor 陈伟锋郭明应时彦张贵军
Owner ZHEJIANG UNIV OF 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