DREME: motif discovery in transcription factor ChIP-seq data

Abstract

Motivation: Transcription factor (TF) ChIP-seq datasets have particular characteristics that provide unique challenges and opportunities for motif discovery. Most existing motif discovery algorithms do not scale well to such large datasets, or fail to report many motifs associated with cofactors of the ChIP-ed TF.

Results: We present DREME, a motif discovery algorithm specifically designed to find the short, core DNA-binding motifs of eukaryotic TFs, and optimized to analyze very large ChIP-seq datasets in minutes. Using DREME, we discover the binding motifs of the the ChIP-ed TF and many cofactors in mouse ES cell (mESC), mouse erythrocyte and human cell line ChIP-seq datasets. For example, in mESC ChIP-seq data for the TF Esrrb, we discover the binding motifs for eight cofactor TFs important in the maintenance of pluripotency. Several other commonly used algorithms find at most two cofactor motifs in this same dataset. DREME can also perform discriminative motif discovery, and we use this feature to provide evidence that Sox2 and Oct4 do not bind in mES cells as an obligate heterodimer. DREME is much faster than many commonly used algorithms, scales linearly in dataset size, finds multiple, non-redundant motifs and reports a reliable measure of statistical significance for each motif found. DREME is available as part of the MEME Suite of motif-based sequence analysis tools (http://meme.nbcr.net).

Fig. 1.

Comparison of DREME mESC TF ChIP-seq motifs with in vitro motifs. Each panel shows the logo of the in vivo binding motif discovered by DREME in the designated TF ChIP-seq dataset (lower logo) aligned with the logo of the best available in vitro motif (upper logo). Since no in vitro motifs are available for Sox2, Oct4 and E2f1, UniProbe motifs for closely related TF family members Sox11, Pou2f3 and E2f3 are used. The in vitro motif for Nanog is taken from Jauch et al. (2008).

Fig. 2.

Discriminative motif discovery in mESC ChIP-seq datasets. Panels (a) and (b) show the logo of the binding motif discovered by DREME in the two designated TF ChIP-seq datasets (lower logo) aligned with the logo of a known motif for the ChIP-ed TF (upper logo). (a) Upper logo is known Oct4 motif (Pou-family member Pou3f3, UniProbe Pou3f3_3235.2). (b) Upper logo is known Sox2 motif (TRANSFAC M01272). (c) Shows the most significant motif found by DREME in the Nanog dataset using (top to bottom) the shuffled Nanog dataset, the Oct4 dataset or the Sox2 dataset as the negative set.

Fig. 3.

Comparison of motif discovery algorithms. (a) The table shows the average number of motifs discovered (N), number of datasets in which the ChIP-ed motif was found (S), the average number of identifiable co-factor motifs found (C), and the average running time in seconds of the algorithm on the mESC ChIP-seq datasets. Bold font indicates best performance. Note: Times for nestedMICA and MEME are for the reduced size datasets (0.5 megabase-pairs). (b) The plot shows the running times for DREME, Amadeus, Trawler and WEEDER on the full-size mESC ChIP-seq datasets. Inset plot is the same data plotted with log scales on both axes.