Back
Full-text
Journal article

A machine learning-based chemoproteomic approach to identify drug targets and binding sites in complex proteomes.

  • Piazza I ETH Zürich, Institute of Molecular Systems Biology, Department of Biology, Otto-Stern-Weg 3, 8093, Zürich, Switzerland.
  • Beaton N Biognosys AG, Wagistrasse 21, 8952, Schlieren, Switzerland.
  • Bruderer R Biognosys AG, Wagistrasse 21, 8952, Schlieren, Switzerland.
  • Knobloch T Bayer SAS, Crop Science Division, Lyon, France.
  • Barbisan C Bayer SAS, Crop Science Division, Lyon, France.
  • Chandat L Bayer SAS, Crop Science Division, Lyon, France.
  • Sudau A Bayer SAS, Crop Science Division, Lyon, France.
  • Siepe I BASF SE, Ludwigshafen, Germany.
  • Rinner O Biognosys AG, Wagistrasse 21, 8952, Schlieren, Switzerland.
  • de Souza N ETH Zürich, Institute of Molecular Systems Biology, Department of Biology, Otto-Stern-Weg 3, 8093, Zürich, Switzerland.
  • Picotti P ETH Zürich, Institute of Molecular Systems Biology, Department of Biology, Otto-Stern-Weg 3, 8093, Zürich, Switzerland. picotti@imsb.biol.ethz.ch.
  • Reiter L Biognosys AG, Wagistrasse 21, 8952, Schlieren, Switzerland. lukas.reiter@biognosys.com.
Show more…
  • 2020-08-23
Published in:
  • Nature communications. - 2020
Binding Sites
Botrytis
Cell Survival
Computational Biology
Drug Delivery Systems
Drug Discovery
HeLa Cells
Humans
Ligands
Machine Learning
Mass Spectrometry
Phosphotransferases
Protein Binding
Proteolysis
Proteome
Proteomics
Saccharomyces cerevisiae
English Chemoproteomics is a key technology to characterize the mode of action of drugs, as it directly identifies the protein targets of bioactive compounds and aids in the development of optimized small-molecule compounds. Current approaches cannot identify the protein targets of a compound and also detect the interaction surfaces between ligands and protein targets without prior labeling or modification. To address this limitation, we here develop LiP-Quant, a drug target deconvolution pipeline based on limited proteolysis coupled with mass spectrometry that works across species, including in human cells. We use machine learning to discern features indicative of drug binding and integrate them into a single score to identify protein targets of small molecules and approximate their binding sites. We demonstrate drug target identification across compound classes, including drugs targeting kinases, phosphatases and membrane proteins. LiP-Quant estimates the half maximal effective concentration of compound binding sites in whole cell lysates, correctly discriminating drug binding to homologous proteins and identifying the so far unknown targets of a fungicide research compound.
Language
  • English
Open access status
gold
Identifiers
Persistent URL
https://folia.unifr.ch/global/documents/175217
Statistics
Document views: 41 File downloads:
  • Full-text: 0