We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
AI-guided pipeline for protein–protein interaction drug discovery identifies a SARS-CoV-2 inhibitor.
- Authors
Trepte, Philipp; Secker, Christopher; Olivet, Julien; Blavier, Jeremy; Kostova, Simona; Maseko, Sibusiso B; Minia, Igor; Silva Ramos, Eduardo; Cassonnet, Patricia; Golusik, Sabrina; Zenkner, Martina; Beetz, Stephanie; Liebich, Mara J; Scharek, Nadine; Schütz, Anja; Sperling, Marcel; Lisurek, Michael; Wang, Yang; Spirohn, Kerstin; Hao, Tong
- Abstract
Protein–protein interactions (PPIs) offer great opportunities to expand the druggable proteome and therapeutically tackle various diseases, but remain challenging targets for drug discovery. Here, we provide a comprehensive pipeline that combines experimental and computational tools to identify and validate PPI targets and perform early-stage drug discovery. We have developed a machine learning approach that prioritizes interactions by analyzing quantitative data from binary PPI assays or AlphaFold-Multimer predictions. Using the quantitative assay LuTHy together with our machine learning algorithm, we identified high-confidence interactions among SARS-CoV-2 proteins for which we predicted three-dimensional structures using AlphaFold-Multimer. We employed VirtualFlow to target the contact interface of the NSP10-NSP16 SARS-CoV-2 methyltransferase complex by ultra-large virtual drug screening. Thereby, we identified a compound that binds to NSP10 and inhibits its interaction with NSP16, while also disrupting the methyltransferase activity of the complex, and SARS-CoV-2 replication. Overall, this pipeline will help to prioritize PPI targets to accelerate the discovery of early-stage drug candidates targeting protein complexes and pathways. Synopsis: A new pipeline for prioritizing protein-protein interactions (PPIs) for drug discovery, combines machine learning-based scoring of quantitative PPI data, protein complex structure prediction and virtual drug screening. A multi-adaptive support vector machine (maSVM) classifier is used for scoring PPIs from quantitative interaction and structure prediction data. The machine learning-based classifier is applicable to PPI datasets from various assays and AlphaFold-Multimer predictions improving comparability between different methods. Interaction mapping with LuTHy and maSVM-based scoring identified high-confidence SARS-CoV-2 PPIs. Subsequent AlphaFold-Multimer predictions revealed key interaction residues within the NSP10-NSP16 methyltransferase complex. Targeting the complex with virtual compound screening identified an early-stage small molecule inhibitor that disrupts the NSP10-NSP16 interaction and SARS-CoV-2 replication. A new pipeline for prioritizing protein-protein interactions (PPIs) for drug discovery, combines machine learning-based scoring of quantitative PPI data, protein complex structure prediction and virtual drug screening.
- Subjects
DRUG discovery; DRUG interactions; PROTEIN structure prediction; SARS-CoV-2; MACHINE learning; PROTEIN-protein interactions
- Publication
Molecular Systems Biology, 2024, Vol 20, Issue 4, p428
- ISSN
1744-4292
- Publication type
Article
- DOI
10.1038/s44320-024-00019-8