Table 1

Input features to train CoreBoost

Feature list


Core promoter elements

Score of each core element

Weighted score of pairs between TATA, Inr, and CCAAT- and GC-box


Weighted maximal scores for weight matrices from TRANSFAC and density of TFBS

Mechanical properties

Weighted energy/flexibility scores around position -25 and +1

Average energy/flexibility scores

Correlation with the empirical average energy/flexibility profile

Markovian score

Likelihood ratios from homogeneous third order Markov models

k-mer frequency

Frequency of 1- or 2-mers related to nucleotide G or C

TFBS, transcription factor binding site.

Zhao et al. Genome Biology 2007 8:R17   doi:10.1186/gb-2007-8-2-r17

Open Data