Modelling protein complexes with crosslinking mass spectrometry and deep learning.
Kolja StahlRobert WarnekeLorenz DemannRica BremenkampBjörn HormesOliver BrockOliver BrockJuri RappsilberPublished in: Nature communications (2024)
Scarcity of structural and evolutionary information on protein complexes poses a challenge to deep learning-based structure modelling. We integrate experimental distance restraints obtained by crosslinking mass spectrometry (MS) into AlphaFold-Multimer, by extending AlphaLink to protein complexes. Integrating crosslinking MS data substantially improves modelling performance on challenging targets, by helping to identify interfaces, focusing sampling, and improving model selection. This extends to single crosslinks from whole-cell crosslinking MS, opening the possibility of whole-cell structural investigations driven by experimental data. We demonstrate this by revealing the molecular basis of iron homoeostasis in Bacillus subtilis.
Keyphrases
- mass spectrometry
- deep learning
- liquid chromatography
- bacillus subtilis
- gas chromatography
- multiple sclerosis
- high performance liquid chromatography
- ms ms
- capillary electrophoresis
- single cell
- protein protein
- electronic health record
- high resolution
- amino acid
- artificial intelligence
- cell therapy
- binding protein
- big data
- machine learning
- convolutional neural network
- mesenchymal stem cells
- data analysis
- tandem mass spectrometry
- social media