Classification query method for global human mtDNA development tree based on ensemble learning

Abstract

The invention discloses a global human mtDNA developmental tree classification and query method based on integrated learning, using manually measured mtDNA data to train a neural network classifier, using mtDNA developmental tree data to calculate the parameters of the Naive Bayesian classifier, and classifying The queried mtDNA variation site sequence is input into the neural network classifier to obtain the first Q possible classifications, and the mtDNA variation site sequence to be classified and the corresponding variation site sequences of the first Q possible classifications are combined to obtain the simple shell The input variable site sequence of the Yassian classifier, and calculate the weight of each variable site in the input variable site sequence, obtain the first Q possible classifications through the Naive Bayesian classifier, and then classify the two groups of Q possible classifications The probability is weighted, and the top Q possible classifications are obtained as the final classification results. The invention comprehensively utilizes the advantages of the neural network classifier and the naive Bayesian classifier, and improves the accuracy rate of the global human mtDNA development tree classification query.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and more specifically relates to a global human mtDNA development tree classification query method based on integrated learning. Background technique [0002] my country is a country with a large population. Based on such a large country base, and the continuous exchanges and integration of various regions in the long river of history, as well as the isolation and migration based on geographical relations, my country's multi-ethnic population characteristics have gradually formed, providing researchers with A rich and diverse genetic treasure trove. But how to use such a treasure trove of genes to study human origin, migration, development and genetic structure is a problem we face. The research on the origin, migration and evolution of various ethnic groups is not only a major scientific issue, but also involves the self-identification of each ethnic group, which has important humanisti...

AI Technical Summary

Problems solved by technology

[0005] As far as the current global human mtDNA development tree classification query method is concerned, due to the problem of algorithm design, its correct rate is low, it is difficult to meet the actual needs, and the data cannot be updated, so the practicability is not enough

Images