Cancer disease gene characteristic selection method based on historical data

Abstract

The invention discloses a cancer disease gene characteristic selection method based on historical data. The cancer disease gene characteristic selection method based on historical data includes the following steps: A, dividing cancer disease gene data into a training set and a test set; b, calculating a total average error rate after all characteristics on the training set are selected; C, generating an initial population, and constructing a fitness function; D, recording all characteristic selection schemes into a characteristic tree, adjusting the distribution of the characteristic selectionschemes, taking the characteristic selection scheme with the minimum fitness value as the optimal characteristic selection scheme, and returning a result to a genetic operator and a guide search operator; E, guiding the evolutionary direction of the characteristic population; and F, judging a termination condition, if the termination condition is not met, repeating the steps D-F, and if the termination condition is met, outputting an optimal solution. The cancer disease gene characteristic selection method based on historical data has the advantages that the data dimension can be effectivelyreduced; the prediction accuracy is improved; the related genes of diseases such as cancer are screened through the characteristic tree in combination with the genetic algorithm; and assistance is provided for diagnosis and treatment.

Description

technical field [0001] The invention relates to the technical field of disease-causing gene screening, in particular to a method for selecting gene features of cancer diseases based on historical data. Background technique [0002] As the most common malignant tumor in human beings, cancer seriously affects people's physical and mental health, and has attracted great attention from experts and scholars in different fields. Because cancer patients will generate a large amount of clinical data in the process of examination, treatment and medication. These data are of great significance for predicting the occurrence of malignant tumors and the development of diseases. However, these data often have the characteristics of high dimensionality, diversity, data chaos and small samples. [0003] With the rapid development of computer technology, people think of using computers to process these complex data. Through the establishment of relevant machine learning prediction models,...

AI Technical Summary

Problems solved by technology

However, the existing methods often have problems such as ineffective dimension reduction, too many redundant features, high time complexity, and poor practicability.

Images