Improving signal peptide prediction accuracy by simulated neural network

I. Ladunga, F. Czakó, I. Csabai, T. Geszti

Research output: Contribution to journalComment/debate

32 Citations (Scopus)

Abstract

The accuracy of distinguishing amino-terminal signal peptides from cytosolic proteins has been improved to 95% by combining a neural network classifier with von Heijne's statistical prediction, the latter is itself 85-90% reliable. The network processed not the cleavage site, but amino-terminal 20-residue segments by the 'tiling' algorithm. Concordant positive predictions of both methods led to the safe identification of 496 novel signal peptides from the Protein Identification Resources.

Original languageEnglish (US)
Pages (from-to)485-487
Number of pages3
JournalBioinformatics
Volume7
Issue number4
DOIs
StatePublished - Oct 1 1991

Fingerprint

Protein Sorting Signals
Peptides
Neural Networks
Neural networks
Proteins
Protein
Prediction
Tiling
Classifiers
Classifier
Resources

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Improving signal peptide prediction accuracy by simulated neural network. / Ladunga, I.; Czakó, F.; Csabai, I.; Geszti, T.

In: Bioinformatics, Vol. 7, No. 4, 01.10.1991, p. 485-487.

Research output: Contribution to journalComment/debate

Ladunga, I. ; Czakó, F. ; Csabai, I. ; Geszti, T. / Improving signal peptide prediction accuracy by simulated neural network. In: Bioinformatics. 1991 ; Vol. 7, No. 4. pp. 485-487.
@article{1535e28093fd4b8abc5639cdf7d9213f,
title = "Improving signal peptide prediction accuracy by simulated neural network",
abstract = "The accuracy of distinguishing amino-terminal signal peptides from cytosolic proteins has been improved to 95{\%} by combining a neural network classifier with von Heijne's statistical prediction, the latter is itself 85-90{\%} reliable. The network processed not the cleavage site, but amino-terminal 20-residue segments by the 'tiling' algorithm. Concordant positive predictions of both methods led to the safe identification of 496 novel signal peptides from the Protein Identification Resources.",
author = "I. Ladunga and F. Czak{\'o} and I. Csabai and T. Geszti",
year = "1991",
month = "10",
day = "1",
doi = "10.1093/bioinformatics/7.4.485",
language = "English (US)",
volume = "7",
pages = "485--487",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - Improving signal peptide prediction accuracy by simulated neural network

AU - Ladunga, I.

AU - Czakó, F.

AU - Csabai, I.

AU - Geszti, T.

PY - 1991/10/1

Y1 - 1991/10/1

N2 - The accuracy of distinguishing amino-terminal signal peptides from cytosolic proteins has been improved to 95% by combining a neural network classifier with von Heijne's statistical prediction, the latter is itself 85-90% reliable. The network processed not the cleavage site, but amino-terminal 20-residue segments by the 'tiling' algorithm. Concordant positive predictions of both methods led to the safe identification of 496 novel signal peptides from the Protein Identification Resources.

AB - The accuracy of distinguishing amino-terminal signal peptides from cytosolic proteins has been improved to 95% by combining a neural network classifier with von Heijne's statistical prediction, the latter is itself 85-90% reliable. The network processed not the cleavage site, but amino-terminal 20-residue segments by the 'tiling' algorithm. Concordant positive predictions of both methods led to the safe identification of 496 novel signal peptides from the Protein Identification Resources.

UR - http://www.scopus.com/inward/record.url?scp=0025945726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025945726&partnerID=8YFLogxK

U2 - 10.1093/bioinformatics/7.4.485

DO - 10.1093/bioinformatics/7.4.485

M3 - Comment/debate

C2 - 1747780

AN - SCOPUS:0025945726

VL - 7

SP - 485

EP - 487

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 4

ER -