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

Context-specific independence mixture modeling for positional weight matrices.

Benjamin Georgi1, Alexander Schliep

  • 1Max Planck Institute for Molecular Genetics, Department of Computational Molecular Biology, Ihnestrasse 73, 14195 Berlin, Germany. georgi@molgen.mpg.de

Bioinformatics (Oxford, England)
|July 29, 2006
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

FRONTIER-3: a randomised phase 2a study to investigate tozorakimab, an anti-interleukin-33 monoclonal antibody, in early-onset asthma.

ERJ open research·2026
Same author

Evolution shapes and conserves genomic signatures in viruses.

Communications biology·2024
Same author

Compressed computations using wavelets for hidden Markov models with continuous observations.

PloS one·2023
Same author

Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction.

Molecular informatics·2022
Same author

Blood Glucose Prediction with Variance Estimation Using Recurrent Neural Networks.

Journal of healthcare informatics research·2022
Same author

Fast parallel construction of variable-length Markov chains.

BMC bioinformatics·2021
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
See all related articles

We introduce a new context-specific independence (CSI) mixture model for transcription factor binding sites. This model offers a more parsimonious and robust approach compared to conventional mixture models, improving parameter estimation and prediction accuracy.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Systems Biology

Background:

  • Transcription factors (TFs) bind DNA at specific sites.
  • Positional weight matrices (PWMs) model TF binding patterns.
  • Mixtures of PWMs improve modeling for TFs with divergent binding sites, but conventional mixtures risk overfitting.

Purpose of the Study:

  • To develop a novel mixture model for TF binding sites that avoids overfitting.
  • To create a more parsimonious and robust model for TF binding patterns.
  • To improve the accuracy of predicting TF binding sites.

Main Methods:

  • Proposed a context-specific independence (CSI) mixture model.
  • Developed a Bayesian learning algorithm for the CSI model.
  • Evaluated the CSI model on simulated data and real TF binding data (JASPAR database).

Related Experiment Videos

Main Results:

  • The CSI model automatically adapts its complexity to observed sequence variation, improving parsimony and robustness.
  • Favorable results were observed compared to conventional mixture models on simulated data.
  • The CSI model required 30% fewer parameters than a conventional mixture for the transcription factor Leu3.
  • CSI performed as well or better than conventional mixtures for 89% of 64 JASPAR TFs and better than single PWMs for 70%.

Conclusions:

  • The CSI mixture model provides a more parsimonious and robust representation of TF binding patterns.
  • This approach improves parameter estimation and prediction accuracy for TF binding sites.
  • The CSI model offers a superior alternative to conventional mixture models and single PWMs for many TFs.