Cited by 6,350Machine Learning in BioinformaticsProtein Structure and DynamicsGenomics and Phylogenetic Studies

Improved Prediction of Signal Peptides: SignalP 3.0

Dyrløv Bendtsen, Jannick, Nielsen, Henrik, von Heijne, Gunnar, Brunak, Søren·2004·Journal of Molecular Biology

Abstract

We describe improvements of the currently most popular method for prediction of classically secreted proteins, SignalP. SignalP consists of two different predictors based on neural network and hidden Markov model algorithms, where both components have been updated. Motivated by the idea that the cleavage site position and the amino acid composition of the signal peptide are correlated, new features have been included as input to the neural network. This addition, combined with a thorough error-correction of a new data set, have improved the performance of the predictor significantly over SignalP version 2. In version 3, correctness of the cleavage site predictions has increased notably for all three organism groups, eukaryotes, Gram-negative and Gram-positive bacteria. The accuracy of cleavage site prediction has increased in the range 6-17% over the previous version, whereas the signal peptide discrimination improvement is mainly due to the elimination of false-positive predictions, as well as the introduction of a new discrimination score for the neural network. The new method has been benchmarked against other available methods. Predictions can be made at the publicly available web server

Integrity signals

Registry

Crossref · 10.1016/j.jmb.2004.05.028

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Cleavage by signal peptidase is predicted to occur following serine-17, resulting in a 328 amino acid mature protein with a calculated molecular mass of 36 kDa.

    “Cleavage by signal peptidase is predicted to occur following serine-17 (Bendtsen et al., 2004), resulting in a 328 amino acid mature protein with a calculated molecular mass of 36 kDa, excluding any contribution of carbohydrates.”

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Dyrløv Bendtsen, J., Nielsen, H., von Heijne, G., & Brunak, S.
Affiliations
Technical University of Denmark (DK)
Corresponding author
Brunak, Søren
Venue
Journal of Molecular Biology
Publisher
Elsevier BV
Published
2004-07
Volume
340
Issue
4
Pages
783-795
ISSN
0022-2836 (ISSN-L)
OpenAlex
W2161746138
Cited by
6,350
References
2
Citations by year
2026: 31 · 2025: 42 · 2024: 73 · 2023: 72 · 2022: 83 · 2021: 110 · 2020: 129 · 2019: 135 · 2018: 162 · 2017: 169 · 2016: 199 · 2015: 245 · 2014: 287 · 2013: 387 · 2012: 546
FWCI
153.48
Type
journal article
Language
en
Open access
closed
Locations
  • Journal of Molecular Biology (publishedVersion)
  • PubMed (publishedVersion)
  • Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU) (submittedVersion)
Funders
Danmarks Grundforskningsfond
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
Keywords
signal peptide prediction, SignalP, secreted proteins, cleavage site prediction, artificial neural networks, hidden Markov models, amino acid composition, false positive reduction, protein secretion
MeSH terms
Algorithms, Amino Acid Sequence, Amino Acids, Chemistry, Physical, Computer Systems, Eukaryotic Cells, False Positive Reactions, Gram-Negative Bacteria, Gram-Positive Bacteria, Isoelectric Point, Markov Chains, Peptide Hydrolases, Protein Precursors, Proteins, Sensitivity and Specificity, Databases, Factual, Neural Networks, Computer, Internet, Protein Sorting Signals, Chemical Phenomena

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review