A hybrid supervised approach to human population identification using genomics data

Sahar Araghi, Thanh Nguyen

Research output: Contribution to journalArticleResearchpeer-review

4 Citations (Scopus)

Abstract

Single nucleotide polymorphisms (SNPs) are one type of genetic variations and each SNP represents a difference in a single DNA building block, namely a nucleotide. Previous research demonstrated that SNPs can be used to identify the correct source population of an individual. In addition, variations in the DNA sequences have an influence on human diseases. In this regard, SNPs studies are helpful for personalized medicine and treatment. In the literature, unsupervised clustering methods especially principal component analysis (PCA) have been popular for studying population structure. In this study, we investigate supervised approaches, particularly the LASSO multinomial regression classification method, for recognizing individuals' origin genetic population. Then, we introduce PCA-LASSO as an extension of LASSO method that benefits from advantageous characteristics of both PCA and LASSO regression. The experimental results obtained on the 1,000 genome project dataset show PCA-LASSO's significantly high accuracy in prediction of individual's origin population.

Original languageEnglish
Article number8723537
Pages (from-to)443-454
Number of pages12
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume18
Issue number2
DOIs
Publication statusPublished - Mar 2021
Externally publishedYes

Keywords

  • LASSO
  • multinomial classification
  • PCA
  • personalised treatment
  • Population structure

Cite this