Distance metastasis identification method based on gene interaction mode optimization graph representation

An identification method, a technology of distant transfer, applied in the field of biological information, can solve problems such as incompatibility, and achieve the effect of accurately predicting performance

Active Publication Date: 2022-03-04
TIANJIN UNIV
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These graphs may not be suitable for GCN architecture

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
  • Distance metastasis identification method based on gene interaction mode optimization graph representation
  • Distance metastasis identification method based on gene interaction mode optimization graph representation
  • Distance metastasis identification method based on gene interaction mode optimization graph representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0123] For the CESC sample data set, follow the method of step 5 above to input the training set CESC_Xtrian of each fold described in step 3-1 into the glmGCN model based on the optimization graph representation of the gene interaction mode described in step 4, by minimizing step 4 The loss function described in -4 is optimized to obtain the network weight W_CESC. And use step 5-2, step 5-3 and step 5-4 to obtain the average value of the ten-fold cross-validation results of three repeated experiments as the final result.

[0124] For the STAD sample data set, according to the method of step 5 above, the training set STAD_Xtrian of each fold described in step 3-2 is input into the glmGCN model based on the optimization graph representation of the gene interaction mode described in step 4, and by minimizing step 4 The loss function described in -4 is optimized to obtain the network weight W_STAD. And use step 5-2, step 5-3 and step 5-4 to obtain the average value of the ten-fo...

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 remote metastasis identification method based on gene interaction mode optimization graph representation. The method comprises the following steps: preprocessing data; constructing and processing a protein-protein interaction network (PPI); dividing a training test set; constructing a glmGCN model expressed on the basis of a gene interaction mode optimization graph; using a ten-fold cross validation network model; and applying the model to a test set test. Compared with the prior art, the method has the advantages that the tumor metastasis is predicted under the GCN framework, more attention is paid to the gene-gene relation of the given initial graph in the field in the graph learning layer, and therefore more accurate prediction performance is obtained.

Description

technical field [0001] The invention belongs to the technical field of biological information, and in particular relates to a distant metastasis recognition method based on gene interaction pattern optimization graph representation. Background technique [0002] Tumor metastasis refers to the process in which tumor cells spread from the primary site and continue to grow and form tumors at sites other than the primary site by invading lymphatic vessels and blood vessels. Metastasis can be divided into regional metastasis and distant metastasis. In order to improve the cure rate of cancer and reduce the pain of patients, it is necessary to predict whether there is metastasis in cancer patients, and then choose an appropriate treatment strategy. [0003] In recent years, transcriptome data generated by microarray and RNA-sequencing technologies have been widely used to explore the molecular nature of metastasis. For example, the paper "Integrative clinical genomics of metasta...

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): G16B20/00G06Q10/04G06N3/04G06N3/06G06N3/08
CPCG16B20/00G06N3/08G06Q10/04G06N3/061G06N3/045Y02A90/10
Inventor 苏苒朱莹莹
Owner TIANJIN 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
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