BoCaTFBS: a boosted cascade learner to refine the binding sites suggested by ChIP-chip experiments

Genome Biol. 2006;7(11):R102. doi: 10.1186/gb-2006-7-11-r102.

Abstract

Comprehensive mapping of transcription factor binding sites is essential in postgenomic biology. For this, we propose a mining approach combining noisy data from ChIP (chromatin immunoprecipitation)-chip experiments with known binding site patterns. Our method (BoCaTFBS) uses boosted cascades of classifiers for optimum efficiency, in which components are alternating decision trees; it exploits interpositional correlations; and it explicitly integrates massive negative information from ChIP-chip experiments. We applied BoCaTFBS within the ENCODE project and showed that it outperforms many traditional binding site identification methods (for instance, profiles).

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Algorithms
  • Base Sequence
  • Binding Sites
  • Chromatin Immunoprecipitation*
  • Computational Biology / methods*
  • DNA / genetics
  • DNA / metabolism
  • Genome, Human / genetics
  • Humans
  • Molecular Sequence Data
  • ROC Curve
  • Reproducibility of Results
  • Response Elements / genetics*
  • Software
  • Transcription Factors / metabolism*

Substances

  • Transcription Factors
  • DNA