Genetic and functional diversification of small RNA pathways in plants

Abstract

Multicellular eukaryotes produce small RNA molecules (approximately 21-24 nucleotides) of two general types, microRNA (miRNA) and short interfering RNA (siRNA). They collectively function as sequence-specific guides to silence or regulate genes, transposons, and viruses and to modify chromatin and genome structure. Formation or activity of small RNAs requires factors belonging to gene families that encode DICER (or DICER-LIKE [DCL]) and ARGONAUTE proteins and, in the case of some siRNAs, RNA-dependent RNA polymerase (RDR) proteins. Unlike many animals, plants encode multiple DCL and RDR proteins. Using a series of insertion mutants of Arabidopsis thaliana, unique functions for three DCL proteins in miRNA (DCL1), endogenous siRNA (DCL3), and viral siRNA (DCL2) biogenesis were identified. One RDR protein (RDR2) was required for all endogenous siRNAs analyzed. The loss of endogenous siRNA in dcl3 and rdr2 mutants was associated with loss of heterochromatic marks and increased transcript accumulation at some loci. Defects in siRNA-generation activity in response to turnip crinkle virus in dcl2 mutant plants correlated with increased virus susceptibility. We conclude that proliferation and diversification of DCL and RDR genes during evolution of plants contributed to specialization of small RNA-directed pathways for development, chromatin structure, and defense.

Figure 1. Genetic Requirements for miRNA and Endogenous siRNA Generation

(A) miRNA genes and selected loci corresponding to three siRNAs or siRNA populations. Cloned small RNA sequenc-es are shown as green (sense orientation relative to the genome) or red (antisense orientation) bars. Protein-coding and miRNA genes are indicated by blue arrowheads. From top to bottom: miR-171 and miR-159a loci; siRNA02 loci, with each siRNA02 sequence indicated by an asterisk and the inverted duplication shown by the gray arrows; cluster2 siRNA locus; a segment of chromosome III showing 10 5S rDNA repeats (blue indicates 5S rRNA, gray indicates spacer) containing the siRNA1003 sequence. (B) Small RNA blot assays for miR-171, miR-159, and endogenous siRNAs. Ethid-ium bromide-stained gels (prior to transfer) in the zone corresponding to tRNA and 5S RNA are shown at the bottom. Each mutant is presented in a panel with the corresponding wild-type control (Col-0 or La-er).

Figure 2. Endogenous siRNAs in Arabidopsis

(A) Size distribution of endogenous siRNAs. (B) Distribution of distinct siRNAs in different sequence categories. (C) Density of siRNAs from highly repeated (mainly transposons and retroelements; the asterisk shows repeat sequences identified using RepeatMasker), 5S rDNA, and unique genomic sequence.

Figure 3. Effects of Mutations on AtSN1 and 5S rDNA Chromatin Structure and Gene Expression

(A) Analysis of CpG (left), CpNpG (center), and CpHpH (right) methylation in AtSN1 by bisulfite sequencing of genomic DNA. (B) Blot analysis of 5S rDNA digested with methylation-sensitive restriction enzymes HpaII (left) and MspI (right). HpaII is sensitive to CpG and CpNpG methylation, whereas MspI is sensitive to only CpNpG methylation. Methylation is indicated by the ascending ladder, which corresponds to 5S rDNA multimers (monomer = approximately 0.5 kb). Duplicate samples from each plant were analyzed. (C) ChIP assays using antibodies against dimethyl-histone H3K9 and dimethyl-histone H3K4. Genomic DNA associated with immunoprecipitated chromatin was analyzed by semiquantitative PCR with primer pairs specific for AtSN1, retrotransposon reverse transcriptase (At4g03800) (internal control for H3K9 methylation), and PFK (At4g04040) (internal control for H3K4 methylation). The PCR products were quantitated and compared against the respective internal controls, and the relative H3K4 and H3K9 methylation levels were expressed relative to that in Col-0 (arbitrarily set to 1.00). (D) Detection of AtSN1-specific transcripts by semiquantitative RT-PCR. Primers specific for PFK transcripts were used as the internal control. A parallel set of reactions without addition of reverse transcriptase (RT) was run as a quality control for genomic DNA contamination. The PCR products were normalized relative to PFK, and the expression levels were calculated relative to that in Col-0 (arbitrarily set to 1.00).

Figure 4. Subcellular Localization of GFP Fusion Proteins

Pairwise presentation of confocal microscopic images showing GFP fluorescence (top) and DAPI fluorescence (bottom) in N. benthamiana expressing the indicated GFP fusion proteins. Arrowheads indicate the location of nuclei. Note that the GUS–GFP control protein accumulates in cytoplasm at the cell periphery and immediately surrounding nuclei, while the NIa–GFP control protein accumulates in nuclei. Scale bar = 25μm.

Figure 5. Genetic Requirements for DCLs in Viral siRNA Generation

Blot analysis of viral siRNA. Systemic tissue samples were analyzed at the indicated time points from parental and mutant lines that were infected with TuMV–GFP (A), CMV-Y (B), and TCV (C). RNA blots were analyzed using virus-specific probes to detect siRNAs. Ethidium bromide-stained gels in the zone corresponding to tRNA and 5S RNA are shown. Relative accumulation (RA) of siRNAs is indicated at the bottom of each panel, with the level measured in infected control plants (Col-0 or La-er, depending on the mutant) at 7 dpi arbitrarily set to 1.0.

Figure 6. Altered Susceptibility to TCV Infection in dcl2-1 Mutant Plants

(A) Noninfected control (left) and TCV-infected (right) Col-0, dcl2-1, and dcl3-1 plants at 14 dpi. (B) TCV accumulation, as measured by ELISA, in the systemic tissues of infected wild-type and mutant plants at 7 dpi (open bars) and 14 dpi (filled bars). (C) Plant height (left), number of flowers/plant (center), and fresh weight of bolt tissue (right) were measured at 14 dpi in noninfected (open bars) and infected (filled bars) plants (n = 9).