Conference
View in EDS

Predicting Variant Fitness of SARS-COV-2 from Full Viral Genome Sequences

Bibliographic Details
Title: Predicting Variant Fitness of SARS-COV-2 from Full Viral Genome Sequences
Authors: Annan, Richard, Nkonu, Ursula, Hatami, Parisa, Pantho, Md Jubair, Qingge, Letu, Qin, Hong
Source: Computer Science Faculty Publications
Publisher Information: ODU Digital Commons
Publication Year: 2025
Collection: Old Dominion University: ODU Digital Commons
Subject Terms: COVID-19 (Disease)—Variation, Deep learning (Machine learning), Epidemiology—Mathematical models, Genomes—Data processing, Neural networks (Computer science)—Statistical methods, Phylogenetics—Data processing, SARS-CoV-2—Genetics, Viral populations—Growth, Virus mutation—Mathematical models, Artificial Intelligence and Robotics, Epidemiology, Genetics and Genomics
Description: Accurate prediction of the transmission fitness of emerging SARS-CoV-2 variants is vital for timely public health responses. In this study, we present a deep learning framework that predicts variant fitness from raw genomic sequences using a convolutional neural network (CNN) trained to regress Differential Population Growth Rate (DPGR) values. Our approach achieves high predictive accuracy R-square value of 0.92 on genomic sequences sampled from the USA and Europe. To interpret the model’s predictions, we apply SHapley Additive exPlanations (SHAP) to identify nucleotide-level contributions to predicted fitness. Our analysis highlights key mutations in ORF9 (nucleocapsid), ORF2 (spike), ORF5 (membrane), and ORF8 that either enhance or reduce predicted DPGR. Notably, we identify amino acid–altering mutations such as D3L, E484K, N501Y, and V97I as strong positive contributors to fitness, while synonymous or non-coding mutations had more subtle or regulatory effects. These findings validate the potential of sequence-based modeling and interpretable AI to support early detection and prioritization of high-risk variants.
Document Type: conference object
Language: unknown
Relation: https://digitalcommons.odu.edu/computerscience_fac_pubs/420; https://doi.org/10.1609/aaaiss.v7i1.36915
DOI: 10.1609/aaaiss.v7i1.36915
Availability: https://digitalcommons.odu.edu/computerscience_fac_pubs/420
https://doi.org/10.1609/aaaiss.v7i1.36915
Rights: © 2023, Association for the Advancement of Artificial Intelligence. All rights reserved. "In the Returned Rights section of the AAAI copyright form, authors are specifically granted back the right to use their own papers for noncommercial uses, such as inclusion in their dissertations or the right to deposit their own papers in their institutional repositories, provided there is proper attribution. The published version is not available for posting outside the AAAI Digital Library."
Accession Number: edsbas.A0EBAF97
Database: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://digitalcommons.odu.edu/computerscience_fac_pubs/420#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.A0EBAF97
RelevancyScore: 985
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 984.935607910156
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Predicting Variant Fitness of SARS-COV-2 from Full Viral Genome Sequences
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Annan%2C+Richard%22">Annan, Richard</searchLink><br /><searchLink fieldCode="AR" term="%22Nkonu%2C+Ursula%22">Nkonu, Ursula</searchLink><br /><searchLink fieldCode="AR" term="%22Hatami%2C+Parisa%22">Hatami, Parisa</searchLink><br /><searchLink fieldCode="AR" term="%22Pantho%2C+Md+Jubair%22">Pantho, Md Jubair</searchLink><br /><searchLink fieldCode="AR" term="%22Qingge%2C+Letu%22">Qingge, Letu</searchLink><br /><searchLink fieldCode="AR" term="%22Qin%2C+Hong%22">Qin, Hong</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Computer Science Faculty Publications
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: ODU Digital Commons
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Old Dominion University: ODU Digital Commons
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22COVID-19+%28Disease%29—Variation%22">COVID-19 (Disease)—Variation</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning+%28Machine+learning%29%22">Deep learning (Machine learning)</searchLink><br /><searchLink fieldCode="DE" term="%22Epidemiology—Mathematical+models%22">Epidemiology—Mathematical models</searchLink><br /><searchLink fieldCode="DE" term="%22Genomes—Data+processing%22">Genomes—Data processing</searchLink><br /><searchLink fieldCode="DE" term="%22Neural+networks+%28Computer+science%29—Statistical+methods%22">Neural networks (Computer science)—Statistical methods</searchLink><br /><searchLink fieldCode="DE" term="%22Phylogenetics—Data+processing%22">Phylogenetics—Data processing</searchLink><br /><searchLink fieldCode="DE" term="%22SARS-CoV-2—Genetics%22">SARS-CoV-2—Genetics</searchLink><br /><searchLink fieldCode="DE" term="%22Viral+populations—Growth%22">Viral populations—Growth</searchLink><br /><searchLink fieldCode="DE" term="%22Virus+mutation—Mathematical+models%22">Virus mutation—Mathematical models</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence+and+Robotics%22">Artificial Intelligence and Robotics</searchLink><br /><searchLink fieldCode="DE" term="%22Epidemiology%22">Epidemiology</searchLink><br /><searchLink fieldCode="DE" term="%22Genetics+and+Genomics%22">Genetics and Genomics</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Accurate prediction of the transmission fitness of emerging SARS-CoV-2 variants is vital for timely public health responses. In this study, we present a deep learning framework that predicts variant fitness from raw genomic sequences using a convolutional neural network (CNN) trained to regress Differential Population Growth Rate (DPGR) values. Our approach achieves high predictive accuracy R-square value of 0.92 on genomic sequences sampled from the USA and Europe. To interpret the model’s predictions, we apply SHapley Additive exPlanations (SHAP) to identify nucleotide-level contributions to predicted fitness. Our analysis highlights key mutations in ORF9 (nucleocapsid), ORF2 (spike), ORF5 (membrane), and ORF8 that either enhance or reduce predicted DPGR. Notably, we identify amino acid–altering mutations such as D3L, E484K, N501Y, and V97I as strong positive contributors to fitness, while synonymous or non-coding mutations had more subtle or regulatory effects. These findings validate the potential of sequence-based modeling and interpretable AI to support early detection and prioritization of high-risk variants.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: conference object
– Name: Language
  Label: Language
  Group: Lang
  Data: unknown
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://digitalcommons.odu.edu/computerscience_fac_pubs/420; https://doi.org/10.1609/aaaiss.v7i1.36915
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1609/aaaiss.v7i1.36915
– Name: URL
  Label: Availability
  Group: URL
  Data: https://digitalcommons.odu.edu/computerscience_fac_pubs/420<br />https://doi.org/10.1609/aaaiss.v7i1.36915
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: © 2023, Association for the Advancement of Artificial Intelligence. All rights reserved. "In the Returned Rights section of the AAAI copyright form, authors are specifically granted back the right to use their own papers for noncommercial uses, such as inclusion in their dissertations or the right to deposit their own papers in their institutional repositories, provided there is proper attribution. The published version is not available for posting outside the AAAI Digital Library."
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.A0EBAF97
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.A0EBAF97
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1609/aaaiss.v7i1.36915
    Languages:
      – Text: unknown
    Subjects:
      – SubjectFull: COVID-19 (Disease)—Variation
        Type: general
      – SubjectFull: Deep learning (Machine learning)
        Type: general
      – SubjectFull: Epidemiology—Mathematical models
        Type: general
      – SubjectFull: Genomes—Data processing
        Type: general
      – SubjectFull: Neural networks (Computer science)—Statistical methods
        Type: general
      – SubjectFull: Phylogenetics—Data processing
        Type: general
      – SubjectFull: SARS-CoV-2—Genetics
        Type: general
      – SubjectFull: Viral populations—Growth
        Type: general
      – SubjectFull: Virus mutation—Mathematical models
        Type: general
      – SubjectFull: Artificial Intelligence and Robotics
        Type: general
      – SubjectFull: Epidemiology
        Type: general
      – SubjectFull: Genetics and Genomics
        Type: general
    Titles:
      – TitleFull: Predicting Variant Fitness of SARS-COV-2 from Full Viral Genome Sequences
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Annan, Richard
      – PersonEntity:
          Name:
            NameFull: Nkonu, Ursula
      – PersonEntity:
          Name:
            NameFull: Hatami, Parisa
      – PersonEntity:
          Name:
            NameFull: Pantho, Md Jubair
      – PersonEntity:
          Name:
            NameFull: Qingge, Letu
      – PersonEntity:
          Name:
            NameFull: Qin, Hong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
          Titles:
            – TitleFull: Computer Science Faculty Publications
              Type: main
ResultId 1