Prediction of liquid chromatographic retention times of peptides generated by protease digestion of the Escherichia coli proteome usina artificial neural networks

Kosaku Shinoda, Masahiro Sugimoto, Nozomu Yachie, Naoyuki Sugiyama, Takeshi Masuda, Martin Robert, Tomoyoshi Soga, Masaru Tomita

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

We developed a computational method to predict the retention times of peptides in HPLC using artificial neural networks (ANN). We performed stepwise multiple linear regressions and selected for ANN input amino acids that significantly affected the LC retention time. Unlike conventional linear models, the trained ANN accurately predicted the retention time of peptides containing up to 50 amino acid residues. In 834 peptides, there was a strong correlation (R2= 0.928) between measured and predicted retention times. We demonstrated the utility of our method by the prediction of the retention time of 121 273 peptides resulting from LysC-digestion of the Escherichia coli proteome. Our approach is useful for the proteome-wide characterization of peptides and the identification of unknown peptide peaks obtained in proteome analysis.

Original languageEnglish (US)
Pages (from-to)3312-3317
Number of pages6
JournalJournal of Proteome Research
Volume5
Issue number12
DOIs
StatePublished - Dec 1 2006
Externally publishedYes

Fingerprint

Proteome
Escherichia coli
Digestion
Peptide Hydrolases
Neural networks
Peptides
Liquids
Linear Models
Amino Acids
Computational methods
Linear regression
High Pressure Liquid Chromatography

Keywords

  • Artificial neural networks
  • Liquid chromatography
  • Peptide identification
  • Retention time prediction
  • Stepwise multiple linear regression

ASJC Scopus subject areas

  • Biochemistry
  • Chemistry(all)

Cite this

Prediction of liquid chromatographic retention times of peptides generated by protease digestion of the Escherichia coli proteome usina artificial neural networks. / Shinoda, Kosaku; Sugimoto, Masahiro; Yachie, Nozomu; Sugiyama, Naoyuki; Masuda, Takeshi; Robert, Martin; Soga, Tomoyoshi; Tomita, Masaru.

In: Journal of Proteome Research, Vol. 5, No. 12, 01.12.2006, p. 3312-3317.

Research output: Contribution to journalArticle

Shinoda, Kosaku ; Sugimoto, Masahiro ; Yachie, Nozomu ; Sugiyama, Naoyuki ; Masuda, Takeshi ; Robert, Martin ; Soga, Tomoyoshi ; Tomita, Masaru. / Prediction of liquid chromatographic retention times of peptides generated by protease digestion of the Escherichia coli proteome usina artificial neural networks. In: Journal of Proteome Research. 2006 ; Vol. 5, No. 12. pp. 3312-3317.
@article{9873e2eaad3b46b8985e1c465a67a4f0,
title = "Prediction of liquid chromatographic retention times of peptides generated by protease digestion of the Escherichia coli proteome usina artificial neural networks",
abstract = "We developed a computational method to predict the retention times of peptides in HPLC using artificial neural networks (ANN). We performed stepwise multiple linear regressions and selected for ANN input amino acids that significantly affected the LC retention time. Unlike conventional linear models, the trained ANN accurately predicted the retention time of peptides containing up to 50 amino acid residues. In 834 peptides, there was a strong correlation (R2= 0.928) between measured and predicted retention times. We demonstrated the utility of our method by the prediction of the retention time of 121 273 peptides resulting from LysC-digestion of the Escherichia coli proteome. Our approach is useful for the proteome-wide characterization of peptides and the identification of unknown peptide peaks obtained in proteome analysis.",
keywords = "Artificial neural networks, Liquid chromatography, Peptide identification, Retention time prediction, Stepwise multiple linear regression",
author = "Kosaku Shinoda and Masahiro Sugimoto and Nozomu Yachie and Naoyuki Sugiyama and Takeshi Masuda and Martin Robert and Tomoyoshi Soga and Masaru Tomita",
year = "2006",
month = "12",
day = "1",
doi = "10.1021/pr0602038",
language = "English (US)",
volume = "5",
pages = "3312--3317",
journal = "Journal of Proteome Research",
issn = "1535-3893",
publisher = "American Chemical Society",
number = "12",

}

TY - JOUR

T1 - Prediction of liquid chromatographic retention times of peptides generated by protease digestion of the Escherichia coli proteome usina artificial neural networks

AU - Shinoda, Kosaku

AU - Sugimoto, Masahiro

AU - Yachie, Nozomu

AU - Sugiyama, Naoyuki

AU - Masuda, Takeshi

AU - Robert, Martin

AU - Soga, Tomoyoshi

AU - Tomita, Masaru

PY - 2006/12/1

Y1 - 2006/12/1

N2 - We developed a computational method to predict the retention times of peptides in HPLC using artificial neural networks (ANN). We performed stepwise multiple linear regressions and selected for ANN input amino acids that significantly affected the LC retention time. Unlike conventional linear models, the trained ANN accurately predicted the retention time of peptides containing up to 50 amino acid residues. In 834 peptides, there was a strong correlation (R2= 0.928) between measured and predicted retention times. We demonstrated the utility of our method by the prediction of the retention time of 121 273 peptides resulting from LysC-digestion of the Escherichia coli proteome. Our approach is useful for the proteome-wide characterization of peptides and the identification of unknown peptide peaks obtained in proteome analysis.

AB - We developed a computational method to predict the retention times of peptides in HPLC using artificial neural networks (ANN). We performed stepwise multiple linear regressions and selected for ANN input amino acids that significantly affected the LC retention time. Unlike conventional linear models, the trained ANN accurately predicted the retention time of peptides containing up to 50 amino acid residues. In 834 peptides, there was a strong correlation (R2= 0.928) between measured and predicted retention times. We demonstrated the utility of our method by the prediction of the retention time of 121 273 peptides resulting from LysC-digestion of the Escherichia coli proteome. Our approach is useful for the proteome-wide characterization of peptides and the identification of unknown peptide peaks obtained in proteome analysis.

KW - Artificial neural networks

KW - Liquid chromatography

KW - Peptide identification

KW - Retention time prediction

KW - Stepwise multiple linear regression

UR - http://www.scopus.com/inward/record.url?scp=33845436279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845436279&partnerID=8YFLogxK

U2 - 10.1021/pr0602038

DO - 10.1021/pr0602038

M3 - Article

VL - 5

SP - 3312

EP - 3317

JO - Journal of Proteome Research

JF - Journal of Proteome Research

SN - 1535-3893

IS - 12

ER -