Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest

BMC Bioinformatics

Research

Michael Cho¹  Tanya Novak²  Adrienne G. Randolph³  Georg Hahn⁴  Sanghun Lee⁵  Christoph Lange⁶  Jonathan Abraham⁷  Lindsey R. Baden⁸  Surender Khurana⁹  Dmitry Prokopenko^1,10  Scott T. Weiss^1,11  Julian Hecker^1,11 

[1] Channing Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, 02115, Boston, MA, USA;Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children’s Hospital, 02115, Boston, MA, USA;Department of Anesthesiology, Critical Care and Pain Medicine, Boston Children’s Hospital, 02115, Boston, MA, USA;Harvard Medical School, Harvard University, 02115, Boston, MA, USA;Department of Biostatistics, T.H. Chan School of Public Health, Harvard University, 02115, Boston, MA, USA;Department of Biostatistics, T.H. Chan School of Public Health, Harvard University, 02115, Boston, MA, USA;Department of Medical Consilience, Graduate School, Dankook University, Yongin, South Korea;Department of Biostatistics, T.H. Chan School of Public Health, Harvard University, 02115, Boston, MA, USA;Harvard Medical School, Harvard University, 02115, Boston, MA, USA;Channing Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, 02115, Boston, MA, USA;Department of Microbiology, Harvard Medical School, Blavatnik Institute, 77 Avenue Louis Pasteur, 02115, Boston, MA, USA;Division of Infectious Diseases, Harvard Medical School, Brigham and Women’s Hospital, 02115, Boston, MA, USA;Food and Drug Administration, 20993, Silver Spring, MD, USA;Genetics and Aging Research Unit, Department of Neurology, McCance Center for Brain Health, Massachusetts General Hospital, 02114, Boston, MA, USA;Harvard Medical School, Harvard University, 02115, Boston, MA, USA;Channing Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital, 02115, Boston, MA, USA;

关键词: SARS-CoV-2;    Nucleotide sequences;    Outlier detection;    Variants of interest;    Machine learning;   

DOI  :  10.1186/s12859-022-05105-y

 received in 2022-06-26, accepted in 2022-12-07,  发布年份 2022

来源: Springer

【 摘 要 】

As of June 2022, the GISAID database contains more than 11 million SARS-CoV-2 genomes, including several thousand nucleotide sequences for the most common variants such as delta or omicron. These SARS-CoV-2 strains have been collected from patients around the world since the beginning of the pandemic. We start by assessing the similarity of all pairs of nucleotide sequences using the Jaccard index and principal component analysis. As shown previously in the literature, an unsupervised cluster analysis applied to the SARS-CoV-2 genomes results in clusters of sequences according to certain characteristics such as their strain or their clade. Importantly, we observe that nucleotide sequences of common variants are often outliers in clusters of sequences stemming from variants identified earlier on during the pandemic. Motivated by this finding, we are interested in applying outlier detection to nucleotide sequences. We demonstrate that nucleotide sequences of common variants (such as alpha, delta, or omicron) can be identified solely based on a statistical outlier criterion. We argue that outlier detection might be a useful surveillance tool to identify emerging variants in real time as the pandemic progresses.

【 授权许可】

CC BY   
© The Author(s) 2022

【 图 表 】

Fig. 4

40517_2022_243_Article_IEq3.gif

Fig. 2

Fig. 2

Fig. 1

Fig. 3

Fig. 2

Fig. 3

Fig. 1

Fig. 6