Deep learning the collisional cross sections of the peptide universe from a million experimental values

Florian Meier,Niklas D Köhler,Andreas-David Brunner,Eugenia Voytik,Matthias Mann,Jean-Marc H Wanka,Fabian J Theis,Maximilian T Strauss

doi:10.1038/s41467-021-21352-8

Abstract

The size and shape of peptide ions in the gas phase are an under-explored dimension for mass spectrometry-based proteomics. To investigate the nature and utility of the peptide collisional cross section (CCS) space, we measure more than a million data points from whole-proteome digests of five organisms with trapped ion mobility spectrometry (TIMS) and parallel accumulation-serial fragmentation (PASEF). The scale and precision (CV < 1%) of our data is sufficient to train a deep recurrent neural network that accurately predicts CCS values solely based on the peptide sequence. Cross section predictions for the synthetic ProteomeTools peptides validate the model within a 1.4% median relative error (R > 0.99). Hydrophobicity, proportion of prolines and position of histidines are main determinants of the cross sections in addition to sequence-specific interactions. CCS values can now be predicted for any peptide and organism, forming a basis for advanced proteomics workflows that make full use of the additional information.

Highlights

The size and shape of peptide ions in the gas phase are an under-explored dimension for mass spectrometry-based proteomics
Technological advances have rekindled the interest in ion mobility spectrometry (IMS), which is about to become mainstream in proteomic laboratories
To investigate the benefit of this additional information in proteomics and making use of the speed and sensitivity of parallel accumulation-serial fragmentation (PASEF), we measured over two million collisional cross section (CCS) values of about 500,000 unique peptide sequences from five biological species

Summary

Introduction

The size and shape of peptide ions in the gas phase are an under-explored dimension for mass spectrometry-based proteomics. An intriguing feature of the combination of TIMS and PASEF is that it should allow the acquisition of ion mobility values on a very large scale Such data have previously been measured on a case by case basis by classical drift tube IMS, in which a weak electric field drags ions through an inert buffer gas[16,17,18]. In TIMS the physical process is the same, except that the setup is reversed with the electric field holding ions stationary against an incoming gas flow, prior to their controlled release from the device by lowering the electric field[19,20] In both cases, the measured ion mobility (reported as the reduced ion mobility coefficient K0) can be used to derive a collisional cross section (CCS), which is the rotational average of an ion’s gas-phase conformation[21,22]. Conformations vary within a compound class - to the extent that isobaric peptide sequences can be distinguishable by their different CCS24,25

Methods

Results

Conclusion