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

Method for screening tumor protein markers on basis of multilayer complex network

A complex network and protein technology, applied in the field of screening tumor protein markers based on multi-layer complex networks, can solve problems such as failure to learn, difficult to interpret output results, and long learning time for artificial neural network algorithms, and the method is simple and accurate. high degree of effect

Active Publication Date: 2017-02-15
赵毅
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the learning process in the middle cannot be observed, the output results are difficult to explain, which will affect the credibility and acceptability of the results, and the artificial neural network algorithm takes a long time to learn, and sometimes it may not even achieve the purpose of learning

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
  • Method for screening tumor protein markers on basis of multilayer complex network
  • Method for screening tumor protein markers on basis of multilayer complex network
  • Method for screening tumor protein markers on basis of multilayer complex network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] The source of the research data is The Cancer Genome Atlas / TCGA (https: / / tcga-data.nci.nih.gov / tcga / dataAccessMatrix.htm). Select the data of invasive breast cancer patients whose protein Experssion-Protein data level is 3 to download. Among them, there are 285 protein data from 937 patients. Among the protein expression data, 45 are normal tissue protein data of breast cancer patients, and the rest are tumor tissue protein data of breast cancer patients. In the protein data of normal tissues and tumor tissues, there are many proteins that are not expressed or have a low expression rate. After removing individuals with no protein expression, the protein data of normal tissues and breast tumor tissues with a size of 137×45 are obtained, that is, 137 out of 45 patients There are three different types of normal tissue protein data and 137 same types of tumor tissue protein data in normal tissues.

[0068] The random forest model is used to encapsulate and filter the protein...

Embodiment 2

[0077] The method of Example 1 was used to download the protein data of lung cancer patients. Among them, there were 276 protein data from 166 patients. After the censored data is also deleted, 137×166 lung cancer tumor tissue protein data is obtained. Since lung cancer patients lack normal tissue data, here we select the normal tissue data of breast cancer patients as the control, that is, select 131 tumor tissue proteins of the same type from 166 patients Data and protein data of 131 normal tissues in 45 patients.

[0078] The random forest model is used to encapsulate and filter the protein data of normal tissues of lung cancer patients and the protein data of tumor tissues to select the best subset. In order to select the protein subset with the smallest number of genes and maintain the highest classification accuracy, ten-fold cross-validation was used to evaluate the classifier model, and the protein classification results are shown in Table 4. For the breast cancer data s...

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 provides a method for screening tumor protein markers on the basis of a multilayer complex network. According to the method, node betweennesses of a random forest mode and of a complex network are combined to provide a new visual angle to discover the tumor pathogenic factors and diagnosis markers. Through bioinformatics and mathematic statistical analysis, the correlation of multilayer protein network data is established and a screening method which is more convenient and higher in correctness is disclosed, so that more valuable reference is provided or the cancer diagnosis and drug discovery.

Description

Technical field [0001] The invention relates to the technical field of tumor markers, in particular to a method for screening tumor protein markers based on a multi-layer complex network. Background technique [0002] Cancer is one of the major diseases and serious public health problems that seriously threaten human survival and social development. Cancer control has become the focus of health strategies of governments around the world. In recent years, there have been more and more studies on protein. The expression level of protein is related to the type and stage of cancer and other clinical data of patients. It plays a role in almost all aspects of cancer biology, such as proliferation, apoptosis, invasion, Metastasis and angiogenesis. [0003] When selecting tumor markers, choosing only one serum protein as a tumor marker is often less specific. If multiple protein combinations or protein expression profiles are measured, the accuracy of diagnosis can be improved. But the c...

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): G06F19/18G06F19/24
CPCG16B20/00G16B40/00
Inventor 赵毅张阳
Owner 赵毅
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