PSORT-B

Improving protein subcellular localization prediction for Gram-negative bacteria

Jennifer L. Gardy, Cory Spencer, Ke Wang, Martin Ester, Gábor E. Tusnády, István Simon, Sujun Hua, Katalin deFays, Christophe Lambert, Kenta Nakai, Fiona S L Brinkman

Research output: Contribution to journalArticle

322 Citations (Scopus)

Abstract

Automated prediction of bacterial protein subcellular localization is an important tool for genome annotation and drug discovery. PSORT has been one of the most widely used computational methods for such bacterial protein analysis; however, it has not been updated since it was introduced in 1991. In addition, neither PSORT nor any of the other computational methods available make predictions for all five of the localization sites characteristic of Gram-negative bacteria. Here we present PSORT-B, an updated version of PSORT for Gram-negative bacteria, which is available as a web-based application at http://www.psort.org. PSORT-B examines a given protein sequence for amino acid composition, similarity to proteins of known localization, presence of a signal peptide, transmembrane alpha-helices and motifs corresponding to specific localizations. A probabilistic method integrates these analyses, returning a list of five possible localization sites with associated probability scores. PSORT-B, designed to favor high precision (specificity) over high recall (sensitivity), attained an overall precision of 97% and recall of 75% in 5-fold cross-validation tests, using a dataset we developed of 1443 proteins of experimentally known localization. This dataset, the largest of its kind, is freely available, along with the PSORT-B source code (under GNU General Public License).

Original languageEnglish
Pages (from-to)3613-3617
Number of pages5
JournalNucleic Acids Research
Volume31
Issue number13
DOIs
Publication statusPublished - Jul 1 2003

Fingerprint

Gram-Negative Bacteria
Bacterial Proteins
Proteins
Drug Discovery
Licensure
Protein Sorting Signals
Amino Acid Sequence
Genome
IgA receptor
Datasets

ASJC Scopus subject areas

  • Genetics

Cite this

PSORT-B : Improving protein subcellular localization prediction for Gram-negative bacteria. / Gardy, Jennifer L.; Spencer, Cory; Wang, Ke; Ester, Martin; Tusnády, Gábor E.; Simon, István; Hua, Sujun; deFays, Katalin; Lambert, Christophe; Nakai, Kenta; Brinkman, Fiona S L.

In: Nucleic Acids Research, Vol. 31, No. 13, 01.07.2003, p. 3613-3617.

Research output: Contribution to journalArticle

Gardy, JL, Spencer, C, Wang, K, Ester, M, Tusnády, GE, Simon, I, Hua, S, deFays, K, Lambert, C, Nakai, K & Brinkman, FSL 2003, 'PSORT-B: Improving protein subcellular localization prediction for Gram-negative bacteria', Nucleic Acids Research, vol. 31, no. 13, pp. 3613-3617. https://doi.org/10.1093/nar/gkg602
Gardy, Jennifer L. ; Spencer, Cory ; Wang, Ke ; Ester, Martin ; Tusnády, Gábor E. ; Simon, István ; Hua, Sujun ; deFays, Katalin ; Lambert, Christophe ; Nakai, Kenta ; Brinkman, Fiona S L. / PSORT-B : Improving protein subcellular localization prediction for Gram-negative bacteria. In: Nucleic Acids Research. 2003 ; Vol. 31, No. 13. pp. 3613-3617.
@article{97082ccb9556408b821106d8027e48e4,
title = "PSORT-B: Improving protein subcellular localization prediction for Gram-negative bacteria",
abstract = "Automated prediction of bacterial protein subcellular localization is an important tool for genome annotation and drug discovery. PSORT has been one of the most widely used computational methods for such bacterial protein analysis; however, it has not been updated since it was introduced in 1991. In addition, neither PSORT nor any of the other computational methods available make predictions for all five of the localization sites characteristic of Gram-negative bacteria. Here we present PSORT-B, an updated version of PSORT for Gram-negative bacteria, which is available as a web-based application at http://www.psort.org. PSORT-B examines a given protein sequence for amino acid composition, similarity to proteins of known localization, presence of a signal peptide, transmembrane alpha-helices and motifs corresponding to specific localizations. A probabilistic method integrates these analyses, returning a list of five possible localization sites with associated probability scores. PSORT-B, designed to favor high precision (specificity) over high recall (sensitivity), attained an overall precision of 97{\%} and recall of 75{\%} in 5-fold cross-validation tests, using a dataset we developed of 1443 proteins of experimentally known localization. This dataset, the largest of its kind, is freely available, along with the PSORT-B source code (under GNU General Public License).",
author = "Gardy, {Jennifer L.} and Cory Spencer and Ke Wang and Martin Ester and Tusn{\'a}dy, {G{\'a}bor E.} and Istv{\'a}n Simon and Sujun Hua and Katalin deFays and Christophe Lambert and Kenta Nakai and Brinkman, {Fiona S L}",
year = "2003",
month = "7",
day = "1",
doi = "10.1093/nar/gkg602",
language = "English",
volume = "31",
pages = "3613--3617",
journal = "Nucleic Acids Research",
issn = "0305-1048",
publisher = "Oxford University Press",
number = "13",

}

TY - JOUR

T1 - PSORT-B

T2 - Improving protein subcellular localization prediction for Gram-negative bacteria

AU - Gardy, Jennifer L.

AU - Spencer, Cory

AU - Wang, Ke

AU - Ester, Martin

AU - Tusnády, Gábor E.

AU - Simon, István

AU - Hua, Sujun

AU - deFays, Katalin

AU - Lambert, Christophe

AU - Nakai, Kenta

AU - Brinkman, Fiona S L

PY - 2003/7/1

Y1 - 2003/7/1

N2 - Automated prediction of bacterial protein subcellular localization is an important tool for genome annotation and drug discovery. PSORT has been one of the most widely used computational methods for such bacterial protein analysis; however, it has not been updated since it was introduced in 1991. In addition, neither PSORT nor any of the other computational methods available make predictions for all five of the localization sites characteristic of Gram-negative bacteria. Here we present PSORT-B, an updated version of PSORT for Gram-negative bacteria, which is available as a web-based application at http://www.psort.org. PSORT-B examines a given protein sequence for amino acid composition, similarity to proteins of known localization, presence of a signal peptide, transmembrane alpha-helices and motifs corresponding to specific localizations. A probabilistic method integrates these analyses, returning a list of five possible localization sites with associated probability scores. PSORT-B, designed to favor high precision (specificity) over high recall (sensitivity), attained an overall precision of 97% and recall of 75% in 5-fold cross-validation tests, using a dataset we developed of 1443 proteins of experimentally known localization. This dataset, the largest of its kind, is freely available, along with the PSORT-B source code (under GNU General Public License).

AB - Automated prediction of bacterial protein subcellular localization is an important tool for genome annotation and drug discovery. PSORT has been one of the most widely used computational methods for such bacterial protein analysis; however, it has not been updated since it was introduced in 1991. In addition, neither PSORT nor any of the other computational methods available make predictions for all five of the localization sites characteristic of Gram-negative bacteria. Here we present PSORT-B, an updated version of PSORT for Gram-negative bacteria, which is available as a web-based application at http://www.psort.org. PSORT-B examines a given protein sequence for amino acid composition, similarity to proteins of known localization, presence of a signal peptide, transmembrane alpha-helices and motifs corresponding to specific localizations. A probabilistic method integrates these analyses, returning a list of five possible localization sites with associated probability scores. PSORT-B, designed to favor high precision (specificity) over high recall (sensitivity), attained an overall precision of 97% and recall of 75% in 5-fold cross-validation tests, using a dataset we developed of 1443 proteins of experimentally known localization. This dataset, the largest of its kind, is freely available, along with the PSORT-B source code (under GNU General Public License).

UR - http://www.scopus.com/inward/record.url?scp=0042622254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0042622254&partnerID=8YFLogxK

U2 - 10.1093/nar/gkg602

DO - 10.1093/nar/gkg602

M3 - Article

VL - 31

SP - 3613

EP - 3617

JO - Nucleic Acids Research

JF - Nucleic Acids Research

SN - 0305-1048

IS - 13

ER -