In silico proof of principle of machine learning-based antibody design at unconstrained scale
Lade...
Autor:in (Körperschaft)
Publikationsdatum
04.04.2022
Typ der Arbeit
Studiengang
Typ
01A - Beitrag in wissenschaftlicher Zeitschrift
Herausgeber:innen
Herausgeber:in (Körperschaft)
Betreuer:in
Übergeordnetes Werk
mAbs
Themenheft
DOI der Originalpublikation
Link
Reihe / Serie
Reihennummer
Jahrgang / Band
14
Ausgabe / Nummer
1
Seiten / Dauer
Patentnummer
Verlag / Herausgebende Institution
Taylor & Francis
Verlagsort / Veranstaltungsort
Auflage
Version
Programmiersprache
Abtretungsempfänger:in
Praxispartner:in/Auftraggeber:in
Zusammenfassung
Generative machine learning (ML) has been postulated to become a major driver in the computational design of antigen-specific monoclonal antibodies (mAb). However, efforts to confirm this hypothesis have been hindered by the infeasibility of testing arbitrarily large numbers of antibody sequences for their most critical design parameters: paratope, epitope, affinity, and developability. To address this challenge, we leveraged a lattice-based antibody-antigen binding simulation framework, which incorporates a wide range of physiological antibody-binding parameters. The simulation framework enables the computation of synthetic antibody-antigen 3D-structures, and it functions as an oracle for unrestricted prospective evaluation and benchmarking of antibody design parameters of ML-generated antibody sequences. We found that a deep generative model, trained exclusively on antibody sequence (one dimensional: 1D) data can be used to design conformational (three dimensional: 3D) epitope-specific antibodies, matching, or exceeding the training dataset in affinity and developability parameter value variety. Furthermore, we established a lower threshold of sequence diversity necessary for high-accuracy generative antibody ML and demonstrated that this lower threshold also holds on experimental real-world data. Finally, we show that transfer learning enables the generation of high-affinity antibody sequences from low-N training data. Our work establishes a priori feasibility and the theoretical foundation of high-throughput ML-based mAb design.
Schlagwörter
Generative machine learning, Antibody design, Paratope, Epitope
Fachgebiet (DDC)
600 - Technik, Medizin, angewandte Wissenschaften
Veranstaltung
Startdatum der Ausstellung
Enddatum der Ausstellung
Startdatum der Konferenz
Enddatum der Konferenz
Datum der letzten Prüfung
ISBN
ISSN
1942-0862
1942-0870
1942-0870
Sprache
Englisch
Während FHNW Zugehörigkeit erstellt
Ja
Publikationsstatus
Veröffentlicht
Begutachtung
Peer-Review der ganzen Publikation
Open Access-Status
Gold
Zitation
AKBAR, Rahmad, Philippe A. ROBERT, Cédric R. WEBER, Michael WIDRICH, Robert FRANK, Milena PAVLOVIĆ, Lonneke SCHEFFER, Maria CHERNIGOVSKAYA, Igor SNAPKOV, Andrei SLABODKIN, Brij Bhushan MEHTA, Enkelejda MIHO, Fridtjof LUND-JOHANSEN, Jan Terje ANDERSEN, Sepp HOCHREITER, Ingrid HOBÆK HAFF, Günter KLAMBAUER, Geir Kjetil SANDVE und Victor GREIFF, 2022. In silico proof of principle of machine learning-based antibody design at unconstrained scale. mAbs. 4 April 2022. Bd. 14, Nr. 1. DOI 10.1080/19420862.2022.2031482. Verfügbar unter: https://doi.org/10.26041/fhnw-9953