Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A distance measurement method for gene expression profiles based on deep learning

A gene expression profile and distance measurement technology, which is applied in the field of gene expression profile distance measurement based on deep learning, can solve the problems of high time cost, poor performance of calculating gene expression profile distance, etc., and achieve the effect of low accuracy

Active Publication Date: 2022-05-03
HUNAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved in the present invention is to give full play to the advantages of deep metric learning that can accurately obtain the characteristics of data and can quickly and effectively calculate the distance between data, so as to solve the problem of poor performance and time overhead in calculating gene expression spectrum distance in traditional methods. big problem

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
  • A distance measurement method for gene expression profiles based on deep learning
  • A distance measurement method for gene expression profiles based on deep learning
  • A distance measurement method for gene expression profiles based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] according to figure 1 The flow shown in the implementation mode includes the following four steps:

[0029] Step 1: data conversion processing, including the following steps,

[0030] 1.1. Convert the gene expression profile data into a square data matrix, and the length of the square matrix is ​​calculated according to the dimension of the expression profile data. The specific calculation method is: convert the sample whose data dimension is N into a square matrix of x*x, where x is passed through the formula Obtained, the extra pixel position is filled to 0.

[0031] 1.2. Perform normalization and mean subtraction data preprocessing operations on the square matrix.

[0032] 1.3. Assign different category labels to the expression spectrum matrices of different categories, and divide the training, verification and test sample sets.

[0033] Step 2: extracting high-level features of training sample data, including the following steps,

[0034] 2.1. Pass the trainin...

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 belongs to the field of gene expression spectrum classification, discloses a gene expression spectrum distance measurement method based on deep learning, and belongs to the mining and application of deep learning on biological big data. First, a convolutional neural network model suitable for gene feature metric learning is designed to extract the characteristics of the data, and then the distance between the data is calculated by using the improved cosine distance, and finally the classification effect of the classification algorithm is used to measure the performance of the method excellent. This method can quickly and efficiently measure the similarity between different gene expression profiles, and provide data for subsequent studies such as gene classification, clustering, differential expression analysis, and compound screening. Compared with the traditional gene enrichment method, this method significantly improves the distance measurement effect between data, and can effectively reduce the manual intervention in gene expression profile analysis, avoiding the over-fitting phenomenon that is easy to occur in conventional deep networks. This method has strong transferability.

Description

Technical field: [0001] The present invention belongs to the field of gene expression spectrum classification, and more specifically relates to the mining and application of deep learning on gene expression spectrum data, and in particular to a method for measuring the distance of gene expression spectrum based on deep learning. Background technique: [0002] At present, with the rapid development of biotechnology, the experimental methods and research methods in the field of biomedicine have undergone tremendous changes, showing the trend of "big data". Among them, the similarity comparison of expression profile data can be applied to compare the expression levels of genes in normal and abnormal cells, help identify disease-related genes and drug targets, and analyze the pathogenic mechanism of complex diseases. Therefore, the similarity of gene expression profiles Research has gradually become a research hotspot. At present, the calculation method of gene expression profil...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/213G06F18/22
Inventor 彭绍亮刘伟李非杨亚宁李肯立卢新国张磊毕夏安
Owner HUNAN UNIV
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
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