Počet záznamů: 1  

Learning to design protein-protein interactions with enhanced generalization

  1. 1.
    0585897 - ÚOCHB 2025 RIV AT eng C - Konferenční příspěvek (zahraniční konf.)
    Bushuiev, A. - Bushuiev, Roman - Kouba, P. - Filkin, A. - Gabrielová, M. - Gabriel, M. - Sedlář, J. - Pluskal, Tomáš - Damborský, J. - Mazurenko, S. - Šivic, J.
    Learning to design protein-protein interactions with enhanced generalization.
    ICLR 2024. The Twelfth International Conference on Learning Representations. Vienna: ICLR, 2024.
    [ICLR 2024. International Conference on Learning Representations /12./. Vienna (AT), 07.05.2024-11.05.2024]
    Grant CEP: GA MŠMT(CZ) LM2023055; GA ČR(CZ) GM21-11563M
    GRANT EU: European Commission(XE) 891397 - KavaTarget
    Výzkumná infrastruktura: e-INFRA CZ II - 90254; RECETOX RI II - 90269
    Institucionální podpora: RVO:61388963
    Klíčová slova: protein-protein interactions * protein design * generalization * self-supervised learning * equivariant 3D representations
    Obor OECD: Other biological topics
    https://openreview.net/forum?id=xcMmebCT7s

    Discovering mutations enhancing protein-protein interactions (PPIs) is critical for advancing biomedical research and developing improved therapeutics. While machine learning approaches have substantially advanced the field, they often struggle to generalize beyond training data in practical scenarios. The contributions of this work are three-fold. First, we construct PPIRef, the largest and non-redundant dataset of 3D protein-protein interactions, enabling effective large-scale learning. Second, we leverage the PPIRef dataset to pre-train PPIformer, a new SE(3)-equivariant model generalizing across diverse protein-binder variants. We fine-tune PPIformer to predict effects of mutations on protein-protein interactions via a thermodynamically motivated adjustment of the pre-training loss function. Finally, we demonstrate the enhanced generalization of our new PPIformer approach by outperforming other state-of-the-art methods on new, non-leaking splits of standard labeled PPI mutational data and independent case studies optimizing a human antibody against SARS-CoV-2 and increasing the thrombolytic activity of staphylokinase.
    Trvalý link: https://hdl.handle.net/11104/0353542

     
    Název souboruStaženoVelikostKomentářVerzePřístup
    0585897.pdf09.5 MBVydavatelský postprintpovolen
     
Počet záznamů: 1  

  Tyto stránky využívají soubory cookies, které usnadňují jejich prohlížení. Další informace o tom jak používáme cookies.