Unconstrained generation of synthetic antibody–antigen structures to guide machine learning methodology for antibody specificity prediction
dc.contributor.author | Robert, Philippe A. | |
dc.contributor.author | Akbar, Rahmad | |
dc.contributor.author | Frank, Robert | |
dc.contributor.author | Pavlović, Milena | |
dc.contributor.author | Widrich, Michael | |
dc.contributor.author | Snapkov, Igor | |
dc.contributor.author | Slabodkin, Andrei | |
dc.contributor.author | Chernigovskaya, Maria | |
dc.contributor.author | Scheffer, Lonneke | |
dc.contributor.author | Smorodina, Eva | |
dc.contributor.author | Rawat, Puneet | |
dc.contributor.author | Mehta, Brij Bhushan | |
dc.contributor.author | Vu, Mai Ha | |
dc.contributor.author | Mathisen, Ingvild Frøberg | |
dc.contributor.author | Prósz, Aurél | |
dc.contributor.author | Abram, Krzysztof | |
dc.contributor.author | Olar, Alex | |
dc.contributor.author | Miho, Enkelejda | |
dc.contributor.author | Haug, Dag Trygve Tryslew | |
dc.contributor.author | Lund-Johansen, Fridtjof | |
dc.contributor.author | Hochreiter, Sepp | |
dc.contributor.author | Haff, Ingrid Hobæk | |
dc.contributor.author | Klambauer, Günter | |
dc.contributor.author | Sandve, Geir Kjetil | |
dc.contributor.author | Greiff, Victor | |
dc.date.accessioned | 2024-08-13T07:33:48Z | |
dc.date.available | 2024-08-13T07:33:48Z | |
dc.date.issued | 2022-12-19 | |
dc.description.abstract | Machine learning (ML) is a key technology for accurate prediction of antibody–antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: the lack of a unified ML formalization of immunological antibody-specificity prediction problems and the unavailability of large-scale synthetic datasets to benchmark real-world relevant ML methods and dataset design. Here we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based three-dimensional antibody–antigen-binding structures with ground-truth access to conformational paratope, epitope and affinity. We formalized common immunological antibody-specificity prediction problems as ML tasks and confirmed that for both sequence- and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework has the potential to enable real-world relevant development and benchmarking of ML strategies for biotherapeutics design. | |
dc.identifier.doi | 10.1038/s43588-022-00372-4 | |
dc.identifier.issn | 2662-8457 | |
dc.identifier.uri | https://irf.fhnw.ch/handle/11654/46938 | |
dc.language.iso | en | |
dc.publisher | Nature | |
dc.relation.ispartof | Nature Computational Science | |
dc.subject | Machine learning | |
dc.subject | Deep learning | |
dc.subject | Antibody | |
dc.subject | Antigen | |
dc.subject | Specificity | |
dc.subject | Epitope | |
dc.subject | Paratope | |
dc.subject | Structure | |
dc.subject | Real-world | |
dc.subject.ddc | 600 - Technik, Medizin, angewandte Wissenschaften | |
dc.title | Unconstrained generation of synthetic antibody–antigen structures to guide machine learning methodology for antibody specificity prediction | |
dc.type | 01A - Beitrag in wissenschaftlicher Zeitschrift | |
dc.volume | 2 | |
dspace.entity.type | Publication | |
fhnw.InventedHere | Yes | |
fhnw.ReviewType | Anonymous ex ante peer review of a complete publication | |
fhnw.affiliation.hochschule | Hochschule für Life Sciences | de_CH |
fhnw.affiliation.institut | Institut für Medizintechnik und Medizininformatik | de_CH |
fhnw.openAccessCategory | Closed | |
fhnw.pagination | 845-865 | |
fhnw.publicationState | Published | |
relation.isAuthorOfPublication | 30aa6b4f-8d02-4f33-8551-6261e7383b23 | |
relation.isAuthorOfPublication | 3d39049f-ff63-4e50-949b-ee67f7dcb763 | |
relation.isAuthorOfPublication.latestForDiscovery | 30aa6b4f-8d02-4f33-8551-6261e7383b23 |
Dateien
Lizenzbündel
1 - 1 von 1
Lade...
- Name:
- license.txt
- Größe:
- 2.66 KB
- Format:
- Item-specific license agreed upon to submission
- Beschreibung: