PromoterPlot: a graphical display of promoter similarities by pattern recognition

Abstract

PromoterPlot (http://promoterplot.fmi.ch) is a web-based tool for simplifying the display and processing of transcription factor searches using either the commercial or free TransFac distributions. The input sequence is a TransFac search (public version) or FASTA/Affymetrix IDs (local install). It uses an intuitive pattern recognition algorithm for finding similarities between groups of promoters by dividing transcription factor predictions into conserved triplet models. To minimize the number of false-positive models, it can optionally exclude factors that are known to be unexpressed or inactive in the cells being studied based on microarray or proteomic expression data. The program will also estimate the likelihood of finding a pattern by chance based on the frequency observed in a control set of mammalian promoters we obtained from Genomatix. The results are stored as an interactive SVG web page on our server.

Figure 1

Pattern finding with PromoterPlot. 1: Transcription factor binding sites are predicted using the balance FP/FN option in TransFac. 2: Any factor for which there is evidence that it is not actually expressed or active in the tissue under investigation may be selectively removed from the analysis. 3: Patterns of three factors with conserved internal spacings and consistent binding strands which are found in two or more promoters are retained all others are discarded. 4: The frequency of the predicted patterns is compared with a database of mammalian promoters to estimate the probability of finding the observed results by chance. 5: The results are displayed as an interactive web page with matching genes from the database returned as Affymetrix IDs.

Figure 2

The start(s) of transcription are represented by circles colored gold, silver or bronze. Each factor is colored according to its name with the fill color based on the name stem and the border color based on the name ending. The factors and promoters are clickable and clicking provides information about pattern groups, binding sites and other genes which share the same patterns.