Dicer's helicase domain is required for accumulation of some, but not all, C. elegans endogenous siRNAs

Abstract

Years after the discovery that Dicer is a key enzyme in gene silencing, the role of its helicase domain remains enigmatic. Here we show that this domain is critical for accumulation of certain endogenous small interfering RNAs (endo-siRNAs) in Caenorhabditis elegans. The domain is required for the production of the direct products of Dicer, or primary endo-siRNAs, and consequently affects levels of downstream intermediates, the secondary endo-siRNAs. Consistent with the role of endo-siRNAs in silencing, their loss correlates with an increase in cognate mRNA levels. We find that the helicase domain of Dicer is not necessary for microRNA (miRNA) processing, or RNA interference following exposure to exogenous double-stranded RNA. Comparisons of wild-type and helicase-defective strains using deep-sequencing analyses show that the helicase domain is required by a subset of annotated endo-siRNAs, in particular, those associated with the slightly longer 26-nucleotide small RNA species containing a 5' guanosine.

FIGURE 1.

Germline defects of dcr-1(−/−) animals are rescued by transgenes encoding wild-type Dicer and Dicer with point mutations in the helicase domain. (A) The DCR-1 open-reading-frame is depicted as a line with domains as rectangles. Relative positions of domains and point mutations are to scale; sequence surrounding mutations is shown for species indicated. Gray rectangle at N terminus, histidine-FLAG tag; DUF 283, domain of unknown function 283; PAZ, Piwi Argonaute Zwille domain; III, RNase III domains; dsR, dsRNA binding motif. (B) Differential interference contrast micrographs show distal (d) and proximal (p) regions of gonad for dcr-1(−/−) and transgenic rescue strains.

FIGURE 2.

C. elegans with mutations in Dicer's helicase domain are defective for production of endo-siRNAs, but not exo-siRNAs or other small RNAs. (A) Total RNA from mixed stage animals of indicated genotypes was subjected to Northern analysis using probes to a piRNA (21U-1), a miRNA (let-7), or endo-siRNAs (E01G4.5, X-cluster). 5S RNA stained with SYBR Gold, or a second hybridization with U6 snRNA probes, provided loading controls. (B) cDNA from total RNA of indicated strains (colors) was subjected to qRT-PCR to assess mRNA levels for indicated genes (x-axis). mRNA levels were normalized to eft-3 mRNA [N2, dcr-1(mg375); n = 6] or act-1 (transgenic rescue lines; n = 3) and plotted as average ratio of mRNA in mutant animals relative to wild type. Error bars, standard deviation; single asterisks, P < 0.05, and double asterisks, P < 0.01. Identical results were obtained using strand-specific primers/probes for reverse transcription or Northern analysis (data not shown), confirming measured mRNA levels derive from sense rather than antisense transcripts. (C) Embryo extracts of indicated strains were analyzed by Western analysis using α-Flag antibody (top panel) or α-HSP90 antibody (bottom panel) to assess levels of transgenic DCR-1. (D) Embryo extracts of indicated genotype (LOAD) were immunoprecipitated (IP) with an α-DCR-1 antibody. Co-precipitating proteins were analyzed by Western blot using the indicated antibodies. eri-1 encodes two isoforms, and the longer (ERI-1b) interacts with DCR-1 (Duchaine et al. 2006). eri-1(mg366) encodes a premature stop codon, so ERI-1 is not detected in extracts from these animals. Bottom panel, tubulin loading control. (E) Small RNAs were isolated from indicated strains (after feeding E. coli expressing dsRNA to the sel-1 gene), and Northern analyses performed with a probe to detect antisense sel-1. Upper bands are unprocessed sel-1 exo-dsRNA that served as an internal loading control; position of exo-siRNAs is indicated. (F) Small RNAs of mixed stage N2 and rde-4(ne299) C. elegans were subjected to Northern analysis using probes as indicated. Re-probing for U6 served as loading control. (G) N2 and rde-4(ne299) worms (n = 7) were grown at 25°C, and progeny counted to obtain average brood size. Asterisks, P < 0.01.

FIGURE 3.

endo-siRNAs are a smaller fraction of reads for dcr-1(−/−)K39A animals compared to dcr-1(−/−)WT animals. (A) Pie charts show percentage of reads in classes defined by previous annotations (see Materials and Methods). Binomial P-value for differences in piRNA, miRNA, and endo-siRNA fractions, <4.9e−324. (B) The plot shows percentage of reads corresponding to sense or antisense annotated endo-siRNAs (see Materials and Methods).

FIGURE 4.

Screen shots of representative loci show endo-siRNAs mostly in exons. (A,B) Sense and antisense reads are shown for dcr-1(−/−)WT (red) and dcr-1(−/−)K39A (blue) with gene structures for plus strand loci above coordinates and those for minus below. Each bar is one read (size to scale, except F28D1.10 [gex-3]), and here data were not normalized to account for the ∼2.5-fold more reads of dcr-1(−/−)K39A samples. In A reads map almost exclusively to exons (black rectangles), while those in B map to introns (lines, reads in shaded boxes) and exons. (C) Bar height is number of reads at each genomic position of X-cluster for dcr-1(−/−)WT (red) and dcr-1(−/−)K39A (blue) samples.

FIGURE 5.

Features of dcr-1(−/−)K39A small RNAs compared to those of dcr-1(−/−)WT. Bar height is number of reads of a particular length and 5′ nt (colors as indicated) for: (A) all 2179 annotated endo-siRNA-producing genes for which we obtained reads (1936 genes); (B) annotated miRNAs; (C) sense and antisense reads mapping to rncs-1. (D) Spearman's rank correlation analysis (ρ, rho) indicates a positive correlation between number of 26 nt reads of a particular gene and the degree to which reads are reduced in dcr-1(−/−)K39A at that loci (fold change = (normalized reads in dcr-1(−/−)WT + 1)/(reads in dcr-1(−/−)K39A + 1). The P-value was estimated based on randomizing ranked lists and computationally determining ρ 1e5 times; under no circumstances was ρ > 0.656.