Extracting Sequence Features to Predict Protein-DNA Interactions: A Comparative Study

Qing Zhou and Jun S. Liu (2008), Nucleic Acids Research, 36: 4137-4148. [Link to the paper]

Supplemental materials: Supplemental text, Supplemental Table 1, Supplemental Table 2.

Sequence sets: human Oct4 bound regions and Sox2 bound regions.

ChIP-enrichment and Feature matrices: Oct4 data set and Sox2 data set.
Data matrix format with columns corresponding to SeqID, ChIP-fold change, and the 269 extracted features. Note that log(ChIP-fold change) was used in the paper.