A co-expression network-based method for mapping cancer target markers

Abstract

A cancer target marker mapping method based on a co-expression network, comprising the following steps: 1) constructing a co-expression basic network, and calculating an adjacency matrix and a topology matrix according to gene expression data of characteristic genes; 2) extracting the characteristics of the co-expression basic network , that is to convert each gene node of the topological network into an eigenvector as the eigenvalue of the network; 3) train the neural network model, and train the parameters of the neural network model according to the walk sequence; 4) conduct cancer target marker mapping, according to the An adaptive algorithm for cluster centers of density peaks for automatic discovery of targeted gene communities. The invention provides a method with good universality and precision, which adopts co-expression basic network construction, node feature vector extraction and gene community automatic discovery to realize target gene mapping.

Description

technical field [0001] The invention belongs to the technical field of biological information, and in particular relates to a cancer targeting target gene mapping method. Background technique [0002] With the continuous improvement of science and technology and medical level in recent years, people's ability and confidence in fighting diseases have been continuously enhanced, but there are still many defects and technical obstacles. According to the cancer report of the World Health Organization, in the past five years, the number of cancer cases in China accounted for about one-fifth of the total number of global cases, and the number of deaths due to cancer has exceeded one-quarter of the total number of global cancer deaths. An important reason for the high mortality rate of cancer is that most cancers in my country are found in the middle and late stages. Therefore, while people continue to study new cancer treatment methods, more scientific research efforts need to be...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the complexity of the co-expression network, the present invention constructs the basic network by calculating the correlation coefficient of the expression level between genes, uses second-order random walk and neural network model training to obtain the eigenvectors of the network nodes, and designs an adaptive algorithm for the clustering center Perform automated discovery of targeted gene communities

Images