Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in context
Summary: Background: SARS-CoV-2-neutralizing antibodies (nABs) showed great promise in the early phases of the COVID-19 pandemic. The emergence of resistant strains, however, quickly rendered the majority of clinically approved nABs ineffective. This underscored the imperative to develop nAB cockta...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | EBioMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352396423005261 |
| _version_ | 1797353631051153408 |
|---|---|
| author | Delphine Diana Acar Wojciech Witkowski Magdalena Wejda Ruifang Wei Tim Desmet Bert Schepens Sieglinde De Cae Koen Sedeyn Hannah Eeckhaut Daria Fijalkowska Kenny Roose Sandrine Vanmarcke Anne Poupon Dirk Jochmans Xin Zhang Rana Abdelnabi Caroline S. Foo Birgit Weynand Dirk Reiter Nico Callewaert Han Remaut Johan Neyts Xavier Saelens Sarah Gerlo Linos Vandekerckhove |
| author_facet | Delphine Diana Acar Wojciech Witkowski Magdalena Wejda Ruifang Wei Tim Desmet Bert Schepens Sieglinde De Cae Koen Sedeyn Hannah Eeckhaut Daria Fijalkowska Kenny Roose Sandrine Vanmarcke Anne Poupon Dirk Jochmans Xin Zhang Rana Abdelnabi Caroline S. Foo Birgit Weynand Dirk Reiter Nico Callewaert Han Remaut Johan Neyts Xavier Saelens Sarah Gerlo Linos Vandekerckhove |
| author_sort | Delphine Diana Acar |
| collection | DOAJ |
| description | Summary: Background: SARS-CoV-2-neutralizing antibodies (nABs) showed great promise in the early phases of the COVID-19 pandemic. The emergence of resistant strains, however, quickly rendered the majority of clinically approved nABs ineffective. This underscored the imperative to develop nAB cocktails targeting non-overlapping epitopes. Methods: Undertaking a nAB discovery program, we employed a classical workflow, while integrating artificial intelligence (AI)-based prediction to select non-competing nABs very early in the pipeline. We identified and in vivo validated (in female Syrian hamsters) two highly potent nABs. Findings: Despite the promising results, in depth cryo-EM structural analysis demonstrated that the AI-based prediction employed with the intention to ensure non-overlapping epitopes was inaccurate. The two nABs in fact bound to the same receptor-binding epitope in a remarkably similar manner. Interpretation: Our findings indicate that, even in the Alphafold era, AI-based predictions of paratope-epitope interactions are rough and experimental validation of epitopes remains an essential cornerstone of a successful nAB lead selection. Funding: Full list of funders is provided at the end of the manuscript. |
| first_indexed | 2024-03-08T13:33:49Z |
| format | Article |
| id | doaj.art-d61b439c0eca42cfae0b6e3405d320a1 |
| institution | Directory Open Access Journal |
| issn | 2352-3964 |
| language | English |
| last_indexed | 2024-03-08T13:33:49Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EBioMedicine |
| spelling | doaj.art-d61b439c0eca42cfae0b6e3405d320a12024-01-17T04:17:00ZengElsevierEBioMedicine2352-39642024-02-01100104960Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in contextDelphine Diana Acar0Wojciech Witkowski1Magdalena Wejda2Ruifang Wei3Tim Desmet4Bert Schepens5Sieglinde De Cae6Koen Sedeyn7Hannah Eeckhaut8Daria Fijalkowska9Kenny Roose10Sandrine Vanmarcke11Anne Poupon12Dirk Jochmans13Xin Zhang14Rana Abdelnabi15Caroline S. Foo16Birgit Weynand17Dirk Reiter18Nico Callewaert19Han Remaut20Johan Neyts21Xavier Saelens22Sarah Gerlo23Linos Vandekerckhove24HIV Cure Research Center, Department of Internal Medicine and Pediatrics, Ghent University Hospital, Ghent University, Ghent 9000, BelgiumHIV Cure Research Center, Department of Internal Medicine and Pediatrics, Ghent University Hospital, Ghent University, Ghent 9000, BelgiumHIV Cure Research Center, Department of Internal Medicine and Pediatrics, Ghent University Hospital, Ghent University, Ghent 9000, BelgiumHIV Cure Research Center, Department of Internal Medicine and Pediatrics, Ghent University Hospital, Ghent University, Ghent 9000, BelgiumDepartment of Basic and Applied Medical Sciences, Ghent University, Ghent 9000, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumMAbSilico, Tours 37000, FranceLaboratory of Virology and Chemotherapy, Department of Microbiology, Immunology and Transplantation, Rega Institute for Medical Research, KU Leuven, Leuven 3000, BelgiumLaboratory of Virology and Chemotherapy, Department of Microbiology, Immunology and Transplantation, Rega Institute for Medical Research, KU Leuven, Leuven 3000, BelgiumLaboratory of Virology and Chemotherapy, Department of Microbiology, Immunology and Transplantation, Rega Institute for Medical Research, KU Leuven, Leuven 3000, BelgiumLaboratory of Virology and Chemotherapy, Department of Microbiology, Immunology and Transplantation, Rega Institute for Medical Research, KU Leuven, Leuven 3000, BelgiumDepartment of Imaging and Pathology, Translational Cell and Tissue Research, KU Leuven, Leuven 3000, BelgiumDepartment of Bioengineering Sciences, Vrije Universiteit Brussel, Brussels 1050, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumDepartment of Bioengineering Sciences, Vrije Universiteit Brussel, Brussels 1050, Belgium; VIB-VUB Center for Structural Biology, VIB, Brussels 1050, BelgiumLaboratory of Virology and Chemotherapy, Department of Microbiology, Immunology and Transplantation, Rega Institute for Medical Research, KU Leuven, Leuven 3000, BelgiumVIB-UGent Center for Medical Biotechnology, VIB, Ghent 9052, Belgium; Department of Biochemistry and Microbiology, Ghent University, Ghent 9052, BelgiumHIV Cure Research Center, Department of Internal Medicine and Pediatrics, Ghent University Hospital, Ghent University, Ghent 9000, Belgium; Department of Biomolecular Medicine, Ghent University, Ghent 9000, BelgiumHIV Cure Research Center, Department of Internal Medicine and Pediatrics, Ghent University Hospital, Ghent University, Ghent 9000, Belgium; Corresponding author.Summary: Background: SARS-CoV-2-neutralizing antibodies (nABs) showed great promise in the early phases of the COVID-19 pandemic. The emergence of resistant strains, however, quickly rendered the majority of clinically approved nABs ineffective. This underscored the imperative to develop nAB cocktails targeting non-overlapping epitopes. Methods: Undertaking a nAB discovery program, we employed a classical workflow, while integrating artificial intelligence (AI)-based prediction to select non-competing nABs very early in the pipeline. We identified and in vivo validated (in female Syrian hamsters) two highly potent nABs. Findings: Despite the promising results, in depth cryo-EM structural analysis demonstrated that the AI-based prediction employed with the intention to ensure non-overlapping epitopes was inaccurate. The two nABs in fact bound to the same receptor-binding epitope in a remarkably similar manner. Interpretation: Our findings indicate that, even in the Alphafold era, AI-based predictions of paratope-epitope interactions are rough and experimental validation of epitopes remains an essential cornerstone of a successful nAB lead selection. Funding: Full list of funders is provided at the end of the manuscript.http://www.sciencedirect.com/science/article/pii/S2352396423005261SARS-CoV-2Neutralizing antibodyIn silico predictionEpitope mappingCovid-19 |
| spellingShingle | Delphine Diana Acar Wojciech Witkowski Magdalena Wejda Ruifang Wei Tim Desmet Bert Schepens Sieglinde De Cae Koen Sedeyn Hannah Eeckhaut Daria Fijalkowska Kenny Roose Sandrine Vanmarcke Anne Poupon Dirk Jochmans Xin Zhang Rana Abdelnabi Caroline S. Foo Birgit Weynand Dirk Reiter Nico Callewaert Han Remaut Johan Neyts Xavier Saelens Sarah Gerlo Linos Vandekerckhove Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in context EBioMedicine SARS-CoV-2 Neutralizing antibody In silico prediction Epitope mapping Covid-19 |
| title | Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in context |
| title_full | Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in context |
| title_fullStr | Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in context |
| title_full_unstemmed | Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in context |
| title_short | Integrating artificial intelligence-based epitope prediction in a SARS-CoV-2 antibody discovery pipeline: caution is warrantedResearch in context |
| title_sort | integrating artificial intelligence based epitope prediction in a sars cov 2 antibody discovery pipeline caution is warrantedresearch in context |
| topic | SARS-CoV-2 Neutralizing antibody In silico prediction Epitope mapping Covid-19 |
| url | http://www.sciencedirect.com/science/article/pii/S2352396423005261 |
| work_keys_str_mv | AT delphinedianaacar integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT wojciechwitkowski integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT magdalenawejda integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT ruifangwei integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT timdesmet integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT bertschepens integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT sieglindedecae integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT koensedeyn integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT hannaheeckhaut integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT dariafijalkowska integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT kennyroose integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT sandrinevanmarcke integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT annepoupon integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT dirkjochmans integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT xinzhang integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT ranaabdelnabi integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT carolinesfoo integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT birgitweynand integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT dirkreiter integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT nicocallewaert integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT hanremaut integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT johanneyts integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT xaviersaelens integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT sarahgerlo integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext AT linosvandekerckhove integratingartificialintelligencebasedepitopepredictioninasarscov2antibodydiscoverypipelinecautioniswarrantedresearchincontext |