Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest
Abstract 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 th...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-12-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-022-05105-y |
| _version_ | 1797977189127290880 |
|---|---|
| author | Georg Hahn Sanghun Lee Dmitry Prokopenko Jonathan Abraham Tanya Novak Julian Hecker Michael Cho Surender Khurana Lindsey R. Baden Adrienne G. Randolph Scott T. Weiss Christoph Lange |
| author_facet | Georg Hahn Sanghun Lee Dmitry Prokopenko Jonathan Abraham Tanya Novak Julian Hecker Michael Cho Surender Khurana Lindsey R. Baden Adrienne G. Randolph Scott T. Weiss Christoph Lange |
| author_sort | Georg Hahn |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-04-11T05:02:58Z |
| format | Article |
| id | doaj.art-428c807d66334f48a8d811a6960611da |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-11T05:02:58Z |
| publishDate | 2022-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-428c807d66334f48a8d811a6960611da2022-12-25T12:32:06ZengBMCBMC Bioinformatics1471-21052022-12-0123111810.1186/s12859-022-05105-yUnsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interestGeorg Hahn0Sanghun Lee1Dmitry Prokopenko2Jonathan Abraham3Tanya Novak4Julian Hecker5Michael Cho6Surender Khurana7Lindsey R. Baden8Adrienne G. Randolph9Scott T. Weiss10Christoph Lange11Department of Biostatistics, T.H. Chan School of Public Health, Harvard UniversityDepartment of Biostatistics, T.H. Chan School of Public Health, Harvard UniversityGenetics and Aging Research Unit, Department of Neurology, McCance Center for Brain Health, Massachusetts General HospitalDepartment of Microbiology, Harvard Medical School, Blavatnik InstituteDepartment of Anesthesiology, Critical Care and Pain Medicine, Boston Children’s HospitalHarvard Medical School, Harvard UniversityChanning Division of Network Medicine, Department of Medicine, Brigham and Women’s HospitalFood and Drug AdministrationDivision of Infectious Diseases, Harvard Medical School, Brigham and Women’s HospitalDepartment of Anesthesiology, Critical Care and Pain Medicine, Boston Children’s HospitalHarvard Medical School, Harvard UniversityDepartment of Biostatistics, T.H. Chan School of Public Health, Harvard UniversityAbstract 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.https://doi.org/10.1186/s12859-022-05105-ySARS-CoV-2Nucleotide sequencesOutlier detectionVariants of interestMachine learning |
| spellingShingle | Georg Hahn Sanghun Lee Dmitry Prokopenko Jonathan Abraham Tanya Novak Julian Hecker Michael Cho Surender Khurana Lindsey R. Baden Adrienne G. Randolph Scott T. Weiss Christoph Lange Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest BMC Bioinformatics SARS-CoV-2 Nucleotide sequences Outlier detection Variants of interest Machine learning |
| title | Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest |
| title_full | Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest |
| title_fullStr | Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest |
| title_full_unstemmed | Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest |
| title_short | Unsupervised outlier detection applied to SARS-CoV-2 nucleotide sequences can identify sequences of common variants and other variants of interest |
| title_sort | unsupervised outlier detection applied to sars cov 2 nucleotide sequences can identify sequences of common variants and other variants of interest |
| topic | SARS-CoV-2 Nucleotide sequences Outlier detection Variants of interest Machine learning |
| url | https://doi.org/10.1186/s12859-022-05105-y |
| work_keys_str_mv | AT georghahn unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT sanghunlee unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT dmitryprokopenko unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT jonathanabraham unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT tanyanovak unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT julianhecker unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT michaelcho unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT surenderkhurana unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT lindseyrbaden unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT adriennegrandolph unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT scotttweiss unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest AT christophlange unsupervisedoutlierdetectionappliedtosarscov2nucleotidesequencescanidentifysequencesofcommonvariantsandothervariantsofinterest |