Ionmob: a Python package for prediction of peptide collisional cross-section values

Publication type:
Journal article
Metadata:
Autoren
  • David Teschner
  • David Gomez-Zepeda
  • Arthur Declercq
  • Mateusz K Lacki
  • Seymen Avci
  • Konstantin Bob
  • Ute Distler
  • Thomas Michna
  • Lennart Martens
  • Stefan Tenzer
  • Andreas Hildebrandt
  • Jonathan Wren
Autoren-URL
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:001070600700001&DestLinkType=FullRecord&DestApp=WOS_CPL
DOI
10.1093/bioinformatics/btad486
eISSN
1367-4811
Externe Identifier
  • Clarivate Analytics Document Solution ID: S4AB7
  • PubMed Identifier: 37540201
ISSN
1367-4803
Ausgabe der Veröffentlichung
9
Zeitschrift
BIOINFORMATICS
Artikelnummer
ARTN btad486
Datum der Veröffentlichung
2023
Status
Published
Titel
Ionmob: a Python package for prediction of peptide collisional cross-section values
Sub types
  • Article
Ausgabe der Zeitschrift
39

Data source: Web of Science (Lite)

Other metadata sources:
Abstract
<jats:title>Abstract</jats:title> <jats:sec> <jats:title>Motivation</jats:title> <jats:p>Including ion mobility separation (IMS) into mass spectrometry proteomics experiments is useful to improve coverage and throughput. Many IMS devices enable linking experimentally derived mobility of an ion to its collisional cross-section (CCS), a highly reproducible physicochemical property dependent on the ion’s mass, charge and conformation in the gas phase. Thus, known peptide ion mobilities can be used to tailor acquisition methods or to refine database search results. The large space of potential peptide sequences, driven also by posttranslational modifications of amino acids, motivates an in silico predictor for peptide CCS. Recent studies explored the general performance of varying machine-learning techniques, however, the workflow engineering part was of secondary importance. For the sake of applicability, such a tool should be generic, data driven, and offer the possibility to be easily adapted to individual workflows for experimental design and data processing.</jats:p> </jats:sec> <jats:sec> <jats:title>Results</jats:title> <jats:p>We created ionmob, a Python-based framework for data preparation, training, and prediction of collisional cross-section values of peptides. It is easily customizable and includes a set of pretrained, ready-to-use models and preprocessing routines for training and inference. Using a set of ≈21 000 unique phosphorylated peptides and ≈17 000 MHC ligand sequences and charge state pairs, we expand upon the space of peptides that can be integrated into CCS prediction. Lastly, we investigate the applicability of in silico predicted CCS to increase confidence in identified peptides by applying methods of re-scoring and demonstrate that predicted CCS values complement existing predictors for that task.</jats:p> </jats:sec> <jats:sec> <jats:title>Availability and implementation</jats:title> <jats:p>The Python package is available at github: https://github.com/theGreatHerrLebert/ionmob.</jats:p> </jats:sec>
Autoren
  • David Teschner
  • David Gomez-Zepeda
  • Arthur Declercq
  • Mateusz K Łącki
  • Seymen Avci
  • Konstantin Bob
  • Ute Distler
  • Thomas Michna
  • Lennart Martens
  • Stefan Tenzer
  • Andreas Hildebrandt
DOI
10.1093/bioinformatics/btad486
Editoren
  • Jonathan Wren
eISSN
1367-4811
Ausgabe der Veröffentlichung
9
Zeitschrift
Bioinformatics
Sprache
en
Online publication date
2023
Datum der Veröffentlichung
2023
Status
Published
Herausgeber
Oxford University Press (OUP)
Herausgeber URL
http://dx.doi.org/10.1093/bioinformatics/btad486
Datum der Datenerfassung
2023
Titel
Ionmob: a Python package for prediction of peptide collisional cross-section values
Ausgabe der Zeitschrift
39

Data source: Crossref

Abstract
<h4>Motivation</h4>Including ion mobility separation (IMS) into mass spectrometry proteomics experiments is useful to improve coverage and throughput. Many IMS devices enable linking experimentally derived mobility of an ion to its collisional cross-section (CCS), a highly reproducible physicochemical property dependent on the ion's mass, charge and conformation in the gas phase. Thus, known peptide ion mobilities can be used to tailor acquisition methods or to refine database search results. The large space of potential peptide sequences, driven also by posttranslational modifications of amino acids, motivates an in silico predictor for peptide CCS. Recent studies explored the general performance of varying machine-learning techniques, however, the workflow engineering part was of secondary importance. For the sake of applicability, such a tool should be generic, data driven, and offer the possibility to be easily adapted to individual workflows for experimental design and data processing.<h4>Results</h4>We created ionmob, a Python-based framework for data preparation, training, and prediction of collisional cross-section values of peptides. It is easily customizable and includes a set of pretrained, ready-to-use models and preprocessing routines for training and inference. Using a set of ≈21 000 unique phosphorylated peptides and ≈17 000 MHC ligand sequences and charge state pairs, we expand upon the space of peptides that can be integrated into CCS prediction. Lastly, we investigate the applicability of in silico predicted CCS to increase confidence in identified peptides by applying methods of re-scoring and demonstrate that predicted CCS values complement existing predictors for that task.<h4>Availability and implementation</h4>The Python package is available at github: https://github.com/theGreatHerrLebert/ionmob.
Addresses
  • Institute of Computer Science, Johannes Gutenberg University, 55128 Mainz, Germany.
Autoren
  • David Teschner
  • David Gomez-Zepeda
  • Arthur Declercq
  • Mateusz K Łącki
  • Seymen Avci
  • Konstantin Bob
  • Ute Distler
  • Thomas Michna
  • Lennart Martens
  • Stefan Tenzer
  • Andreas Hildebrandt
DOI
10.1093/bioinformatics/btad486
eISSN
1367-4811
Externe Identifier
  • PubMed Identifier: 37540201
  • PubMed Central ID: PMC10521631
Funding acknowledgements
  • Bundesministerium für Bildung und Forschung:
  • Research Foundation Flanders:
Open access
true
ISSN
1367-4803
Ausgabe der Veröffentlichung
9
Zeitschrift
Bioinformatics (Oxford, England)
Schlüsselwörter
  • Ions
  • Peptides
  • Proteomics
  • Amino Acid Sequence
  • Mass Spectrometry
  • Machine Learning
Sprache
eng
Medium
Print
Open access status
Open Access
Paginierung
btad486
Datum der Veröffentlichung
2023
Status
Published
Publisher licence
CC BY
Datum der Datenerfassung
2023
Titel
Ionmob: a Python package for prediction of peptide collisional cross-section values.
Sub types
  • Research Support, Non-U.S. Gov't
  • research-article
  • Journal Article
Ausgabe der Zeitschrift
39

Files

https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btad486/51038853/btad486.pdf https://europepmc.org/articles/PMC10521631?pdf=render

Data source: Europe PubMed Central

Abstract
MOTIVATION: Including ion mobility separation (IMS) into mass spectrometry proteomics experiments is useful to improve coverage and throughput. Many IMS devices enable linking experimentally derived mobility of an ion to its collisional cross-section (CCS), a highly reproducible physicochemical property dependent on the ion's mass, charge and conformation in the gas phase. Thus, known peptide ion mobilities can be used to tailor acquisition methods or to refine database search results. The large space of potential peptide sequences, driven also by posttranslational modifications of amino acids, motivates an in silico predictor for peptide CCS. Recent studies explored the general performance of varying machine-learning techniques, however, the workflow engineering part was of secondary importance. For the sake of applicability, such a tool should be generic, data driven, and offer the possibility to be easily adapted to individual workflows for experimental design and data processing. RESULTS: We created ionmob, a Python-based framework for data preparation, training, and prediction of collisional cross-section values of peptides. It is easily customizable and includes a set of pretrained, ready-to-use models and preprocessing routines for training and inference. Using a set of ≈21 000 unique phosphorylated peptides and ≈17 000 MHC ligand sequences and charge state pairs, we expand upon the space of peptides that can be integrated into CCS prediction. Lastly, we investigate the applicability of in silico predicted CCS to increase confidence in identified peptides by applying methods of re-scoring and demonstrate that predicted CCS values complement existing predictors for that task. AVAILABILITY AND IMPLEMENTATION: The Python package is available at github: https://github.com/theGreatHerrLebert/ionmob.
Date of acceptance
2023
Autoren
  • David Teschner
  • David Gomez-Zepeda
  • Arthur Declercq
  • Mateusz K Łącki
  • Seymen Avci
  • Konstantin Bob
  • Ute Distler
  • Thomas Michna
  • Lennart Martens
  • Stefan Tenzer
  • Andreas Hildebrandt
Autoren-URL
https://www.ncbi.nlm.nih.gov/pubmed/37540201
DOI
10.1093/bioinformatics/btad486
eISSN
1367-4811
Externe Identifier
  • PubMed Central ID: PMC10521631
Ausgabe der Veröffentlichung
9
Zeitschrift
Bioinformatics
Schlüsselwörter
  • Peptides
  • Mass Spectrometry
  • Machine Learning
  • Amino Acid Sequence
  • Proteomics
  • Ions
Sprache
eng
Country
England
PII
7237255
Datum der Veröffentlichung
2023
Status
Published
Datum, an dem der Datensatz öffentlich gemacht wurde
2023
Titel
Ionmob: a Python package for prediction of peptide collisional cross-section values.
Sub types
  • Journal Article
  • Research Support, Non-U.S. Gov't
Ausgabe der Zeitschrift
39

Data source: PubMed

Beziehungen:
Property of

Tools