Figure 1

CFBI Overview. Diagram illustrating the structure of the framework for the computational prediction of transcription factor binding sites. The diagram shows the multiple sources of input data, including ensembl, compara, TRANSFAC (or alternatively, novel motifs obtained by a motif-finding algorithm, such as MDScan), the optional data preprocessing RepeatMasker step, and the post-processing steps including data integration from multiple species and logistic regression of gene expression defined classes of genes. Dotted lines indicate optional or alternative steps.