Deep Learning Predicts Non-Normal Transmission Distributions in High-Field Asymmetric Waveform Ion Mobility (FAIMS) Directly from Peptide Sequence.

Journal: Analytical chemistry
PMID:

Abstract

Peptide ion mobility adds an extra dimension of separation to mass spectrometry-based proteomics. The ability to accurately predict peptide ion mobility would be useful to expedite assay development and to discriminate true answers in a database search. There are methods to accurately predict peptide ion mobility through drift tube devices, but methods to predict mobility through high-field asymmetric waveform ion mobility (FAIMS) are underexplored. Here, we successfully model peptide ions' FAIMS mobility using a multi-label classification scheme to account for non-normal transmission distributions. We trained two models from over 100,000 human peptide precursors: a random forest and a long-term short-term memory (LSTM) neural network. Both models had different strengths, and the ensemble average of model predictions produced a higher F2 score than either model alone. Finally, we explored cases where the models make mistakes and demonstrate the predictive performance of F2 = 0.66 (AUROC = 0.928) on a new test data set of nearly 40,000 peptide ions. The deep learning model is easily accessible via https://faims.xods.org.

Authors

  • Justin McKetney
    Department of Biomolecular Chemistry, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States.
  • Ian J Miller
    National Center for Quantitative Biology of Complex Systems, Madison, WI 53562, USA; Department of Biomolecular Chemistry, University of Wisconsin, Madison, WI 53562, USA.
  • Alexandre Hutton
    Department of Computational Biomedicine, Cedars Sinai Medical Center, Los Angeles, California 90048, United States.
  • Pavel Sinitcyn
    Morgridge Institute for Research, Madison, Wisconsin 53715, United States.
  • Lia R Serrano
    National Center for Quantitative Biology of Complex Systems, Madison, WI 53562, USA; Department of Chemistry, University of Wisconsin, Madison, WI 53562, USA.
  • Joshua J Coon
    National Center for Quantitative Biology of Complex Systems, Madison, WI 53562, USA; Morgridge Institute for Research, Madison, WI 53562, USA; Department of Biomolecular Chemistry, University of Wisconsin, Madison, WI 53562, USA; Department of Chemistry, University of Wisconsin, Madison, WI 53562, USA. Electronic address: jcoon@chem.wisc.edu.
  • Jesse G Meyer
    Department of Biochemistry, Medical College of Wisconsin, Milwaukee, WI 53226, USA.