A deep learning approach predicting the activity of COVID-19 therapeutics and vaccines against emerging variants
Understanding which viral variants evade neutralization is crucial for improving antibody-based treatments, especially with rapidly evolving viruses like SARS-CoV-2. Yet, conventional assays are labor intensive and cannot capture the full spectrum of variants. We present a deep learning approach to predict changes in neutralizing antibody activity of COVID-19 therapeutics and vaccine-elicited sera/plasma against emerging viral variants. Our approach leverages data of 67,885 unique SARS-CoV-2 Spike sequences and 7,069 in vitro assays. The resulting model accurately predicted fold changes in neutralizing activity (R<sup>2</sup> = 0.77) for a test set (N = 980) of data collected up to eight months after the training data. Next, the model was used to predict changes in activity of current therapeutic and vaccine-induced antibodies against emerging SARS-CoV-2 lineages. Consistent with other work, we found significantly reduced activity against newer XBB descendants, notably EG.5, FL.1.5.1, and XBB.1.16; primarily attributed to the F456L spike mutation.
Authors
- Kanny K. Wan (ORCID: https://orcid.org/0000-0002-7246-343X)
- Michiel J.M. Niesen (ORCID: https://orcid.org/0000-0002-9255-6203)
- Brittany J. Poelaert
- Işın Y. Comba (ORCID: https://orcid.org/0000-0002-0955-6270)
- Eli Silvert (ORCID: https://orcid.org/0000-0003-0445-4395)
- Robert P. Matson (ORCID: https://orcid.org/0000-0003-4241-0641)
- Kyle R. Brimacombe (ORCID: https://orcid.org/0000-0002-9629-1417)
- Dhruti Patwardhan
- Karthik Murugadoss (ORCID: https://orcid.org/0000-0002-4247-6168)
- AJ Venkatakrishnan (ORCID: https://orcid.org/0000-0003-2819-3214)
- Rohit Suratekar (ORCID: https://orcid.org/0000-0002-6281-5526)
- Venky Soundararajan (ORCID: https://orcid.org/0000-0001-7434-9211)
- Elizabeth-Grace Goel
Institutions
- National Institutes of Health (US)
- Mayo Clinic (US)
- Nference (India) (IN)
- Mayo Clinic in Florida (US)
- National Center for Advancing Translational Sciences (US)
- Nference (United States) (US)
Publication Details
- Journal
- npj Systems Biology and Applications
- Published
- 2024-11-27
- DOI
- https://doi.org/10.1038/s41540-024-00471-0
- Citations
- 3
- Primary Topic
- SARS-CoV-2 and COVID-19 Research
- Type
- article
- Field-Weighted Citation Impact
- 1.17
Funders
- Foundation for the National Institutes of Health
- National Institutes of Health
- National Center for Advancing Translational Sciences