Biomarker identification method based on multiple networks

A technology of biomarkers and identification methods, applied in the fields of biological systems, bioinformatics, neural learning methods, etc., can solve problems such as the inability to reflect the characteristics and topology structure well, and the mutual interference of data.
CN110797083AActive Publication Date: 2020-02-14CENT SOUTH UNIV
3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CENT SOUTH UNIV
Publication Date
2020-02-14

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a biomarker identification method based on multiple networks. Considering the influence of sample heterogeneity, the method disclosed by the invention comprises the following steps of: firstly, standardizing gene expression profile data, carrying out principal component analysis on samples, and clustering the samples through a Gaussian mixture model by utilizing the first two principal components, constructing a network propagation model based on multiple networks to sort all genes in the networks as for each type of samples for preliminarily screening important genes,and in order to obtain the biomarker with the maximum distinguishing capability and the minimum redundancy, further grading and sequencing the genes in the important characteristics obtained in the previous step through an area under curve (AUC) optimization model of a receiver operation characteristic curve to obtain the biomarker. According to the method, the multi-source biological network information is fully utilized, and the biomarker with the maximum distinguishing capacity, the minimum redundancy and the biointerpretability can be effectively recognized and used for heterogeneous complex disease analysis.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of bioinformatics, in particular to a multi-network-based biomarker identification method. Background technique

[0002] Complex diseases have strong heterogeneity and are easily affected by environmental factors, which brings difficulties to the diagnosis and treatment of complex diseases. Therefore, the analysis of heterogeneous and complex diseases has become one of the focuses of modern medical research. Biomarkers are indicators for objectively measuring and evaluating normal biological processes, pathological processes, or drug intervention responses, and are also important early warning indicators when the body is damaged. Mining effective biomarkers from diverse biological data is the key to solving complex diseases.

[0003] With the in-depth study of systems biology and the rapid development of high-throughput technologies, a large number of biological interaction networks have been obtained, such as prote...

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