Multi-granularity breast cancer gene classification method based on dual adaptive neighborhood radius

Abstract

The invention provides a multi-granularity breast cancer gene classification method based on dual adaptive neighborhood radiuses, and the method comprises the following steps: reading large-scale gene locus data, carrying out normalization processing, and carrying out data analysis on large-scale gene loci; combining a contour coefficient and PCA dimension reduction visualization, selecting an optimal K value, and adjusting an information granulation model; realizing the multi-granularity attribute reduction based on cluster center distance adaptive neighborhood radius and multi-granularity attribute reduction based on neighborhood radius of attribute inclusion degree by using a heuristic reduction algorithm, and classifying and predicting breast cancer gene big data are classified and predicted by adopting an SVM machine learning classification algorithm. The invention has the beneficial effects that the penalty term is adjusted, so that the model has higher accuracy and recall rate in breast cancer gene classification, redundant attributes in large-scale data are removed, the calculation efficiency is improved, and the efficiency and precision of breast cancer data classification are improved by utilizing support information between samples.

Description

technical field [0001] The invention relates to the technical field of medical information intelligent processing, in particular to a multi-granularity breast cancer gene classification method based on double adaptive neighborhood radius. Background technique [0002] Cancer is one of the most common genetic diseases. Relevant medical studies have shown that lung cancer, skin cancer and breast cancer are closely related to genes. The appearance of cancer can often be explained by gene mutations. If the genetic material is damaged and not repaired, cancer cells will absorb it. The infinite division of nutrients of normal cells leads to the decline of human body functions. The cure rate of early cancer is high, and the cure rate of cancer cells after metastasis is low. Early detection and early treatment are the best treatment methods at present. Genetic testing is a non-destructive testing method. Simultaneous detection of thousands of gene loci through next-generation sequen...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a multi-granularity breast cancer gene classification method based on double adaptive neighborhood radius, which solves the problem that the existing effective way to judge the status of breast cancer is that the dimension of breast cancer-related gene data is too high to be observed. The influence of gene mutation on the early discrimination of breast cancer, through the connection between breast cancer gene data and double adaptive neighborhood radius, solves the problem of difficult selection of neighborhood radius in neighborhood rough set, and then uses multi-granularity neighborhood rough set attribute Jane can effectively remove noise and redundant data

Images