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

Improved benchmarks for computational motif discovery.

Geir Kjetil Sandve1, Osman Abul, Vegard Walseng

  • 1Department of Computer and Information Science, Norwegian University of Science and Technology (NTNU), Trondheim, Norway. sandve@ntnu.no

BMC Bioinformatics
|June 15, 2007
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

A robust machine learning approach for breast cancer subtype classification using relative gene expression order representations.

Computer methods and programs in biomedicine·2026
Same author

PEPE: scalable extraction of multi-modal protein language model representations.

Bioinformatics (Oxford, England)·2026
Same author

Identification of a type 1 diabetes-associated T cell receptor repertoire signature from the human peripheral blood.

Science advances·2026
Same author

Correction: B cell tolerance and antibody production to the celiac disease autoantigen transglutaminase 2.

The Journal of experimental medicine·2026
Same author

inMOTIFin: a lightweight end-to-end simulation software for regulatory sequences.

Bioinformatics (Oxford, England)·2026
Same author

Meta simulation approach for evaluating machine learning method selection in data limited settings.

Scientific reports·2025
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
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

Robust assessment of computational methods for identifying transcription factor binding sites is crucial. New benchmark datasets are introduced to better evaluate motif discovery algorithms and models, distinguishing tool performance from problem complexity.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Accurate identification of transcription factor binding sites is essential for genome annotation.
  • Numerous computational methods exist, making tool selection challenging.
  • Robust assessment is vital for validating existing tools and guiding future research.

Purpose of the Study:

  • To develop improved benchmark datasets for evaluating motif discovery algorithms.
  • To differentiate the performance of motif discovery algorithms from the limitations of motif models.
  • To provide a framework for assessing computational methods in transcription factor binding site identification.

Main Methods:

  • Utilized a machine learning perspective to analyze transcription factor binding sites.

Related Experiment Videos

  • Developed algorithms for discovering position weight matrices (PWMs), IUPAC-type motifs, and mismatch motifs.
  • Proposed a novel approach for constructing benchmark datasets based on ranked binding site fragments.

    • Main Results:

    • Identified limitations in common motif models for discriminating binding sites in existing benchmark datasets.
    • Demonstrated potential bias in synthetic datasets towards presupposed motif models.
    • Created benchmark suites enabling discrimination between algorithm performance and motif model power.

    Conclusions:

    • New benchmark suites effectively distinguish motif discovery algorithm performance from motif model capabilities.
    • The developed benchmarks aid in evaluating the true potential of motif discovery tools.
    • A web server is available for accessing benchmark datasets and submitting predictions.