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

Method for identifying cancer molecular subtype based on spectral clustering algorithm of sparse similar matrix

A spectral clustering algorithm and molecular subtyping technology, which is applied in the field of identifying cancer molecular subtypes based on sparse similarity matrix spectral clustering algorithm, can solve the problems of different prognosis, poor prognosis and unpredictability of patients. Achieve the effects of avoiding singularity problems, improving prediction accuracy, and reducing computational complexity

Inactive Publication Date: 2017-03-22
HEFEI UNIV OF TECH
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The basis for the treatment of cancer patients is TNM staging, but the prognosis is not good; in actual treatment, doctors rely on their own experience to determine the treatment plan for cancer patients, which is highly subjective and difficult to replicate, and is unpredictable, and the prognosis of patients is not good. different

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 identifying cancer molecular subtype based on spectral clustering algorithm of sparse similar matrix
  • Method for identifying cancer molecular subtype based on spectral clustering algorithm of sparse similar matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In this embodiment, a spectral clustering algorithm based on a sparse similarity matrix uses cancer gene expression profile data as a training set sample to construct a cancer molecular subtype prediction model; the prediction model is used to predict the cancer molecular subtype of an independent test set sample, Thus, the independent test set samples are divided into multiple classes of molecular subtypes.

[0028] Specifically, proceed as follows:

[0029] Step 1. Calculate the similarity matrix SL(n×n) between any two cancer samples in the cancer gene expression profile data as the training set samples.

[0030] A cancer sample refers to a vector whose columns are gene expression profile data; the similarity value s between two cancer samples is calculated according to a Gaussian function ij , with similarity value s ij Construct similarity matrix SL(n×n); where x i and x j is a cancer sample, 1≤i≤n, 1≤j≤n, n is the number of samples in the cancer gene express...

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 method for identifying a cancer molecular subtype based on a spectral clustering algorithm of a sparse similar matrix. The method is characterized in that based on the spectral clustering algorithm of the sparse similar matrix, a cancer molecular subtype prediction model is built by utilizing cancer gene expression profile data as a training set sample; and the prediction model is used for predicting a cancer modular subtype of an independent test set sample, and a cancer sample set is divided into multiple types of molecular subtypes. According to the method, various patients with different prognosis effects are effectively distinguished for high heterogeneity of cancer molecular expression level, and different individual treatment schemes can be made for various cancer patients respectively.

Description

technical field [0001] The invention belongs to the field of bioinformatics, and more specifically relates to a method for identifying cancer molecular subtypes based on a sparse similarity matrix spectral clustering algorithm, using the classification results of the algorithm to formulate corresponding cancer treatment plans, and improving cancer patients' life expectancy. survival rate. Background technique [0002] The expression level of cancer molecules is highly heterogeneous. Heterogeneity, that is, the existence of multiple mutation types in cancer tissues, is one of the basic characteristics of cancer, and it is also the biggest problem in the development of precision medicine. Cancer patients with the same clinical stage or pathological features have significant differences in prognosis when treated with the same treatment regimen. The classification of molecular subtypes of cancer based on gene expression studies provides an important basis for analyzing the high...

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): G06F19/00G06F19/20G06F19/24
CPCG16B25/00G16B40/00G16H50/20G16H50/70
Inventor 史明光王俊文
Owner HEFEI 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