SCOPE: a web server for practical de novo motif discovery

Abstract

SCOPE is a novel parameter-free method for the de novo identification of potential regulatory motifs in sets of coordinately regulated genes. The SCOPE algorithm combines the output of three component algorithms, each designed to identify a particular class of motifs. Using an ensemble learning approach, SCOPE identifies the best candidate motifs from its component algorithms. In tests on experimentally determined datasets, SCOPE identified motifs with a significantly higher level of accuracy than a number of other web-based motif finders run with their default parameters. Because SCOPE has no adjustable parameters, the web server has an intuitive interface, requiring only a set of gene names or FASTA sequences and a choice of species. The most significant motifs found by SCOPE are displayed graphically on the main results page with a table containing summary statistics for each motif. Detailed motif information, including the sequence logo, PWM, consensus sequence and specific matching sites can be viewed through a single click on a motif. SCOPE's efficient, parameter-free search strategy has enabled the development of a web server that is readily accessible to the practising biologist while providing results that compare favorably with those of other motif finders. The SCOPE web server is at <http://genie.dartmouth.edu/scope>.

Figure 1.

SCOPE home page. The drop-down menu for “Species” has been used to select S. cerevisiae and the user has chosen to examine the 800 bp upstream of the transcription start site for the set of genes typed into the gene list box.

Figure 2.

Top-level results of a typical run of SCOPE. The results are shown for the gal4 regulon as entered in Figure 1. Note the motif map, which indicates that the top scoring motif (in this case, the true binding motif) is clustered in the −175 to −525 region (red).

Figure 3.

Motif-level output from SCOPE. This is the page that results when the first motif in Figure 2 is clicked. The sequence logo displays additional information from what is displayed in the consensus sequence. The PWM provides the details of occurrence of each nucleotide for each position of the motif. The table at the bottom lists all of the occurrences of this motif in the upstream sequences of the set of genes submitted. This bipartite motif was identified by the SPACER algorithm, which has also helped specify some preferences for nucleotides in the internal “spacer” sequence.