Heuristic breadth-first searching method for cancer-related genes

Abstract

The invention relates to a heuristic breadth-first searching method for cancer-related genes. According to the method, appearance frequencies of genes in a selected gene subset are used for measuring the genes, and genes with higher appearance frequency are considered as the most important cancer-related genes, on the basis, a classifier is designed and a gene ordering method based on HBSA is established. As proved by study, information gene selection plays an important role in improving the classification performance, and the genes can be probably taken as important tumor clinical diagnosis signs, so discovery of the minimum gene subset with the highest classification performance is a very important research objective. As indicated by experimental results, the heuristic breadth-first searching method can not only obtain favorable generalization performance but also discover important tumor genes. And the relationship of the appearance frequencies of the selected genes and the gene number conforms to power-law distribution. The genes in the gene subset with extremely high classification accuracy are in close relationship with specific tumor subtypes, and even the genes are important genes directly related with the tumor.

Description

[0001] Field [0002] The present invention relates to technologies and theories such as tumor gene expression profile data collection, tumor-related gene importance selection, and machine learning, especially the system uses a heuristic breadth-first search method aimed at the characteristics of tumor gene expression profile sample sets to discover important tumor-related genes And classify tumor subtypes according to these important tumor-related genes, so the system belongs to the application field of pattern recognition in biomedicine. Background technique [0003] From the perspective of molecular biology, tumors are a type of complex genetic disease caused by abnormal expression of genes in cells due to DNA damage on certain chromosomes, resulting in uncontrolled cell growth, lack of differentiation and abnormal proliferation. Therefore, tumors are also a systemic biological Diseases, so far human beings still do not fully understand the mechanism of tumor development. ...

AI Technical Summary

Problems solved by technology

However, due to the curse of dimensionality problem brought by the gene expression profile data set, selecting the smallest gene subset from thousands of genes implies two problems: overfitting phenomenon and selection bias

Although their method can obtain highly unbiased results, when the initial selection of genes is very large (for example, more than 300 genes), the computational cost of this method is too large to be feasible for the algorithm

Images