scholarly journals A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry

Biomolecules ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1904
Author(s):  
Yulia V. Samukhina ◽  
Dmitriy D. Matyushin ◽  
Oksana I. Grinevich ◽  
Aleksey K. Buryak

Most frequently, the identification of peptides in mass spectrometry-based proteomics is carried out using high-resolution tandem mass spectrometry. In order to increase the accuracy of analysis, additional information on the peptides such as chromatographic retention time and collision cross section in ion mobility spectrometry can be used. An accurate prediction of the collision cross section values allows erroneous candidates to be rejected using a comparison of the observed values and the predictions based on the amino acids sequence. Recently, a massive high-quality data set of peptide collision cross sections was released. This opens up an opportunity to apply the most sophisticated deep learning techniques for this task. Previously, it was shown that a recurrent neural network allows for predicting these values accurately. In this work, we present a deep convolutional neural network that enables us to predict these values more accurately compared with previous studies. We use a neural network with complex architecture that contains both convolutional and fully connected layers and comprehensive methods of converting a peptide to multi-channel 1D spatial data and vector. The source code and pre-trained model are available online.

The Analyst ◽  
2015 ◽  
Vol 140 (20) ◽  
pp. 6814-6823 ◽  
Author(s):  
Cris Lapthorn ◽  
Frank S. Pullen ◽  
Babur Z. Chowdhry ◽  
Patricia Wright ◽  
George L. Perkins ◽  
...  

Evaluation of N2(g) and He(g) MOBCAL collision cross section values from 20 compounds ∼ m/z 122 to 609.


2012 ◽  
Vol 65 (5) ◽  
pp. 504 ◽  
Author(s):  
Antonio N. Calabrese ◽  
Lauren A. Speechley ◽  
Tara L. Pukala

This study demonstrates the ability of travelling wave ion mobility-mass spectrometry to measure collision cross-sections of ions in the negative mode, using a calibration based approach. Here, negative mode ion mobility-mass spectrometry was utilised to understand structural transitions of calmodulin upon Ca2+ binding and complexation with model peptides melittin and the plasma membrane Ca2+ pump C20W peptide. Coexisting calmodulin conformers were distinguished on the basis of their mass and cross-section, and identified as relatively folded and unfolded populations, with good agreement in collision cross-section to known calmodulin geometries. Titration of calcium tartrate to physiologically relevant Ca2+ levels provided evidence for intermediately metalated species during the transition from apo- to holo-calmodulin, with collision cross-section measurements indicating that higher Ca2+ occupancy is correlated with more compact structures. The binding of two representative peptides which exemplify canonical compact (melittin) and extended (C20W) peptide-calmodulin binding models has also been interrogated by ion mobility mass spectrometry. Peptide binding to calmodulin involves intermediates with metalation states from 1–4 Ca2+, which demonstrate relatively collapsed structures, suggesting neither the existence of holo-calmodulin or a pre-folded calmodulin conformation is a prerequisite for binding target peptides or proteins. The biological importance of the different metal unsaturated calmodulin complexes, if any, is yet to be understood.


The Analyst ◽  
2016 ◽  
Vol 141 (13) ◽  
pp. 4084-4099 ◽  
Author(s):  
Jennifer L. Lippens ◽  
Srivathsan V. Ranganathan ◽  
Rebecca J. D'Esposito ◽  
Daniele Fabris

This study explored the use of modular nucleic acid (NA) standards to generate calibration curves capable of translating primary ion mobility readouts into corresponding collision cross section (CCS) data.


The Analyst ◽  
2017 ◽  
Vol 142 (22) ◽  
pp. 4289-4298 ◽  
Author(s):  
Jong Wha Lee ◽  
Kimberly L. Davidson ◽  
Matthew F. Bush ◽  
Hugh I. Kim

Theoretical collision cross section calculations revisited for reliable ion structural studies.


2019 ◽  
Vol 10 (4) ◽  
pp. 983-993 ◽  
Author(s):  
Jaqueline A. Picache ◽  
Bailey S. Rose ◽  
Andrzej Balinski ◽  
Katrina L. Leaptrot ◽  
Stacy D. Sherrod ◽  
...  

The Unified Compendium is an online interactive tool that utilizes ion mobility collision cross sections to annotate biochemical molecules.


2018 ◽  
Vol 25 (3) ◽  
pp. 291-299 ◽  
Author(s):  
Virginie Domalain ◽  
Marie Hubert-Roux ◽  
Laurence Quéguiner ◽  
Dany JD Fouque ◽  
Eric Arnoult ◽  
...  

Mycobacterium tuberculosis infection results in more than two million deaths per year and is the leading cause of mortality in people infected with HIV. A new structural class of antimycobacterials, the diarylquinolines, has been synthesized and is being highly effective against both M. tuberculosis and multidrug-resistant tuberculosis. As diarylquinolines are biologically active only under their ( R,S) stereoisomeric form, it is essential to differentiate the stereoisomers ( R,S) and ( R,R). To achieve this, tandem mass spectrometry and ion mobility spectrometry-mass spectrometry have been performed with 10 diarylquinoline diastereomers couples. In this study, we investigated cationization with alkali metal cations and several ion mobility drift gases in order to obtain diastereomer differentiations. We have shown that diastereomers of the diarylquinolines family can be differentiated separately by tandem mass spectrometry and in mixture by ion mobility spectrometry-mass spectrometry. However, although the structure of each diastereomer is close, several behaviors could be observed concerning the cationization and the ion mobility spectrometry separation. The ion mobility spectrometry isomer separation efficiency is not easily predictable; it was however observed for all diastereomeric couples with a significant improvement of separation using alkali adducts compared to protonated molecules. With the use of drift gas with higher polarizability only an improvement of separation was obtained in a few cases. Finally, a good correlation of the experimental collision cross section (relative to three-dimensional structure of ions) and the theoretical collision cross section has been shown.


2017 ◽  
Vol 19 (23) ◽  
pp. 14937-14946 ◽  
Author(s):  
S. Vangaveti ◽  
R. J. D'Esposito ◽  
J. L. Lippens ◽  
D. Fabris ◽  
S. V. Ranganathan

We developed a five bead model that facilitates calculation of collision cross sections of coarse grained structures of nucleic acids, enabling their structural elucidation using Ion Mobility Spectrometry–Mass Spectrometry (IMS-MS).


Sign in / Sign up

Export Citation Format

Share Document