Method and device for classifying chromosome sequences and plasmid sequences

Abstract

The invention is applicable to the technical field of data mining and provides a method and a device for classifying chromosome sequences and plasmid sequences. The method comprises steps: chromosome sequences and plasmid sequences are acquired, and a first training sample and a second training sample are obtained; frequency characteristics of all k character short strings and reverse complementary sequence pairs thereof are extracted and a first frequency characteristic table and a second frequency characteristic table are generated, wherein k is no less than 2 but no more than 5; a training set and a test set are extracted from the first frequency characteristic table and the second frequency characteristic table, and a chi-square test algorithm is adopted to calculate weight values of all characteristic data in the training set; a random forests algorithm is adopted and according to the characteristic data whose weight values meet preset conditions, a classification model is trained; and according to the classification model, the chromosome sequences and the plasmid sequences are classified. Thus, the training efficiency and the training effects of the classification model are improved, and accuracy on classification on the chromosome sequences and the plasmid sequences is improved.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a method and a device for classifying chromosome sequences and plasmid sequences. Background technique [0002] Metagenomics is a biological omics technology that mixes multiple microbial cells in the environment into one sample, and uses genome sequencing technology to obtain all DNA (Deoxyribonucleic acid, deoxyribonucleic acid) data of the sample. Metagenomic data provide information on all microbial populations active in the environment, and play a key role in the study of major issues including human diseases, biomass energy and the evolution of life in nature. [0003] After the DNA is extracted, since the existing sequencing technology can only sequence sequences with a certain length limit, it is necessary to break the very long DNA chain into fragments for sequencing. After sequencing all the fragments, it is necessary to assemble the fragments and resto...

AI Technical Summary

Problems solved by technology

[0006] In view of this, an embodiment of the present invention provides a method and device for classifying chromosomal sequences and plasmid sequences to solve the problems of low accuracy in classifying chromosomal sequences and plasmid sequences, low efficiency of training models, and less effective problem

Images