Skip to main content

Table 2 Full model ChIP evaluation bootstrap results

From: Identifying targets of multiple co-regulating transcription factors from expression time-series by Bayesian model comparison

Validating both positive and negative predictions
Top 200 Top 400 Top 800
  MAP ML Reg Inf   MAP ML Reg Inf   MAP ML Reg Inf
MAP   *** ** - MAP   *** *** - MAP   *** *** -
ML     - ML     - ML     -
Reg   +   - Reg     - Reg     -
Inf - - - - Inf - - - - Inf - - - -
Top 1600 Top 3200 Top 6003
  MAP ML Reg Inf   MAP ML Reg Inf   MAP ML Reg Inf
MAP   *** *** - MAP   ***   - MAP   ***   ***
ML     - ML     - ML     
Reg   *   - Reg *** ***   - Reg *** ***   ***
Inf - - - - Inf - - - - Inf   *   
Validating only positive predictions
Top 200 Top 400 Top 800
  MAP ML Reg Inf   MAP ML Reg Inf   MAP ML Reg Inf
MAP   . *** - MAP   ** *** - MAP   *** *** -
ML    ** - ML    *** - ML    *** -
Reg     - Reg     - Reg     -
Inf - - - - Inf - - - - Inf - - - -
Top 1600 Top 3200 Top 6003
  MAP ML Reg Inf   MAP ML Reg Inf   MAP ML Reg Inf
MAP   *** *** - MAP   *** *** - MAP   *** * ***
ML    *** - ML    *** - ML     ***
Reg     - Reg     - Reg   ***   ***
Inf - - - - Inf - - - - Inf     
  1. The results of 100,000-fold bootstrap resampling of the data set of observed genes to assess significance of differences in ranking method performance. The methods studied are: MAP = MAP GP method, ML = ML Baseline method, Reg = regression baseline method, Inf = Inferelator. For each pair of methods, the marks in the tables show how often the method on the corresponding row dominated the one on the corresponding column. The marks are interpreted as follows: ‘.’: >80% dominance, ‘+’: >90% dominance, ‘*’: >95% dominance, ‘**’: >99% dominance, ‘***’: >99.9% dominance, ‘-’: comparison not applicable.