Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Evaluating eukaryotic secreted protein prediction.

Eric W Klee1, Lynda B M Ellis

  • 1Department of Laboratory Medicine and Pathology, University of Minnesota, Mayo Mail Code 609, Minneapolis, MN 55455, USA. klee0025@tc.umn.edu

BMC Bioinformatics
|October 18, 2005
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Association of a Polygenic Risk Score with Diagnosis and Outcomes in Idiopathic Pulmonary Fibrosis.

American journal of respiratory and critical care medicine·2026
Same author

A Second Report of a Missense Variant in AMMECR1 Causing Midface Hypoplasia, Hearing Impairment, Elliptocytosis, and Nephrocalcinosis: Case Report and Literature Review.

Clinical genetics·2026
Same author

Clinical and genetic characterization of constitutional MLH1 promoter hypermethylation: Implications for Lynch syndrome diagnosis.

Genetics in medicine : official journal of the American College of Medical Genetics·2026
Same author

Unmasking Compound Heterozygosity in GYG1 Myopathy: Diagnostic Insights From RNA-Seq and Long-Read Genomics.

Clinical genetics·2026
Same author

Identification of a Novel Missense Homozygous Variant in LINS1 in Two Distinct Iranian Families With Consanguineous Marriage.

Molecular genetics & genomic medicine·2026
Same author

Genomic profiling reveals molecular heterogeneity in patients with Richter transformation (RT) and chronic lymphocytic leukemia (CLL).

Leukemia research·2025
Same journal

Covariance decomposition for distance based species tree estimation.

BMC bioinformatics·2026
Same journal

SNPio: a Python interface for population genomic data processing.

BMC bioinformatics·2026
Same journal

SpaHNR: a spatial domain identification method via sparse attention-based hierarchical node representation and multi-view contrastive learning.

BMC bioinformatics·2026
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
See all related articles

Accurately predicting secreted proteins is crucial. Combining multiple prediction tools, like SignalP and TargetP, significantly improves accuracy over single methods for robust protein annotation.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Proteomics

Background:

  • Advancements in protein sequence annotation and databases have spurred the development of numerous tools for predicting secreted proteins.
  • High-throughput prediction of secreted proteins is essential for understanding cellular functions and protein localization.

Purpose of the Study:

  • To evaluate the accuracy of six prominent software tools for predicting secreted proteins: SignalP 3.0, SignalP 2.0, TargetP 1.01, PrediSi, Phobius, and ProtComp 6.0.
  • To determine if combining prediction methods enhances accuracy compared to individual tool performance.

Main Methods:

  • Evaluation of six secreted protein prediction software programs using a diverse set of 372 unbiased, eukaryotic SwissProt protein sequences.
  • Assessment of prediction accuracies for individual scores and combined scores from multiple prediction algorithms.

Related Experiment Videos

Main Results:

  • TargetP, SignalP 3.0 (S-score), and SignalP 3.0 (D-score) demonstrated the highest single-score prediction accuracies, ranging from 90-91%.
  • Combining predictions from TargetP, SignalP 2.0 (Y-score), and SignalP 3.0 (S-score) resulted in a six percent increase in prediction accuracy.

Conclusions:

  • Individual predictive scores can achieve high accuracy, though often slightly lower than reported by software developers.
  • Integrating scores from multiple prediction methods into a composite prediction substantially improves overall accuracy for secreted protein identification.