Characterization of endogenous human Argonautes and their miRNA partners in RNA silencing

Abstract

Small RNAs triggering RNA silencing are loaded onto Argonautes and then sequence-specifically guide them to target transcripts. Epitope-tagged human Argonautes (hAgo1, hAgo2, hAgo3, and hAgo4) are associated with siRNAs and miRNAs, but only epitope-tagged hAgo2 has been shown to have Slicer activity. Contrarily, how endogenous hAgos behave with respect to small RNA association and target RNA destruction has remained unclear. Here, we produced monoclonal antibodies for individual hAgos. High-throughput pyrosequencing revealed that immunopurified endogenous hAgo2 and hAgo3 associated mostly with miRNAs. Endogenous hAgo3 did not show Slicer function but localized in P-bodies, suggesting that hAgo3 endogenously expressed is, like hAgo2, involved in the miRNA pathway but antagonizes the RNAi activity of hAgo2. Sequence variations of miRNAs were found at both 5' and 3' ends, suggesting that multiple mature miRNAs containing different "seed" sequences can arise from one miRNA precursor. The hAgo antibodies we raised are valuable tools for ascertaining the functional behavior of endogenous Argonautes and miRNAs in RNA silencing.

Fig. 1.

Characterization of immunoprecipitates with anti-hAgo2, -hAgo3, and -hAgo4 antibodies from Jurkat cells. (A) Jurkat cell lysates prepared with a cell lysis buffer containing Empigen, and immunoprecipitation performed by using anti-hAgo2, -hAgo3, and -hAgo4 antibodies. Protein components in the immunoprecipitates were stained with silver. Protein bands indicated with arrowheads in green, red, and blue are hAgo2, hAgo3, and hAgo4, respectively. Immunoprecipitates of anti-hAgo4 contain proteins other than hAgo4 (shown with single and double asterisks), demonstrating undesired cross-reactivity of the antibody. The protein indicated with double asterisks was identified by mass spectrometric analysis as E1B-55kDa-associated protein. h.c., heavy chains of the antibodies used for immunoprecipitation. (B) Immunoprecipitates of anti-hAgo2 analyzed by Western blot analysis with anti-hAgo2. (C) Immunoprecipitates of anti-hAgo3 analyzed by Western blot analysis with anti-hAgo3.

Fig. 2.

Immunofluorescence on HeLa cells with anti-hAgo2 and anti-hAgo3. (A) HeLa cells immunostained with anti-hAgo2 and anti-DCP1a antibodies. It is shown that hAgo2 localizes in P-bodies (green), the cytoplasmic foci where miRNA targets are accumulated as a consequence of translational repression mediated by Argonaute–miRNA complexes (15, 16). The staining patters of hAgo2 were quite similar to those of epitope-tagged hAgo2 exogenously expressed in HEK 293 or U2-OS cells (10, 11, 13). Almost all of the P-bodies, where DCP1a, a factor functioning in mRNA decay in the bodies (17), resides (red), are costained with anti-hAgo2 (yellow arrowheads in merged image). Part of the merged image is enlarged (enlarged), where a P-body costained with anti-hAgo2 and anti-DCP1a is indicated by a yellow arrowhead. We occasionally found foci only stained with anti-hAgo2 and anti-DCP1a, which are indicated by green and red arrowheads, respectively. (B) HeLa cells stained with anti-hAgo3 (green) and anti-DCP1a (red). Almost all of the P-bodies are stained with both of the antibodies (yellow arrowheads). The cytoplasmic foci containing only hAgo3 or DCP1a are indicated by green and red arrowheads, respectively (in the enlarged image).

Fig. 3.

Identification of small RNAs associated with hAgo2 and hAgo3 in Jurkat cells. (A) Small RNAs associated with hAgo2 and hAgo3 in Jurkat cells visualized by ³²P-labeling. Both hAgos are associated with small RNAs ranging from 21 to 23 nt in length. (B) Compositions of small RNAs in the hAgo2 and hAgo3 libraries. The most abundant class of small RNAs in both libraries was miRNAs. Small RNAs corresponding to sequences of piRNA (piwi-interacting RNA) (0.03%), rRNA (ribosomal RNA) (0.08%), tRNA (transfer RNA) (0.004%), snRNA (small nuclear RNA) (0.002%), snoRNA (small nucleolar RNA) (0.01%), and scRNA (small cytoplasmic RNA) (0.004%) appear in the hAgo2 library. The hAgo3 library had piRNA (0.13%), tRNA (0.001%), snRNA (0.01%), snoRNA (0.005%), and scRNA (0.007%). Their appearance was negligible; thus, they apparently did not show up in the graphs. (C) Top 30 miRNAs appearing in each library.

Fig. 4.

Occurrence of variations at the 5′ and 3′ ends of miRNA with hAgo2 and hAgo3. (A) Occurrence of nontemplated extensions at the 5′ and 3′ ends of miRNA compared for hAgo2 and hAgo3. The Wilcoxon matched-pair signed-rank test was used to test for any significant difference between nontemplated extensions occurring at 5′ and 3′ ends. There is a significant difference between the occurrence of nontemplated extensions at 5′ and 3′ in both hAgo2 (P ≤ 2.9 × 10⁻⁵) and hAgo3 (P ≤ 1.6 × 10⁻⁶). The blank square represents the interquartile range (IQR) of the first quartile (Q1) and third quartile (Q3) where 50% of the observed points are included. The thick horizontal line drawn in the square represents the median of the distribution. The lower whisker represents Q1 − 1.5 × IQR, whereas the upper whisker represents Q3 + 1.5 × IQR. Observations outside of the whiskers are “outliers,” represented as white circles. (B) Occurrences of alternative ends at 5′ and 3′ ends compared for hAgo2 and hAgo3. There are significant differences between the occurrence of alternative ends at 5′ and 3′ in both hAgo2 (P ≤ 3.9 × 10⁻²) and hAgo3 (P ≤ 5.5 × 10⁻³).

Fig. 5.

Endogenous hAgo2 and hAgo3 Slicer activities. (A) Immunopurified hAgo2 from HeLa cells, which contained miR-21 (shown in B), subjected to in vitro target RNA cleavage assays. Even hAgo2 immunopurified from HeLa cells in an Empigen buffer shows Slicer activity. (B) miR-21 associated with hAgo2 in HeLa cell lysates prepared in a buffer containing Nonidet P-40 or Empigen visualized by Northern blot analysis. Total RNAs from HeLa cells and DNA oligos with sequences of miR-21 (sense) and miR-21* (antisense) were used as controls. (C) Immunopurified hAgo2 and hAgo3 from Jurkat cells in an Empigen buffer were subjected to in vitro target RNA cleavage assays. hAgo3 does not cleave a target RNA (miR-150 target), whereas hAgo2 does. Association of hAgo3 with miR-150 is confirmed by Northern blot analysis (Fig. S7B). (D) hAgo2 and hAgo3 associated with luc guide siRNA subjected to in vitro target RNA cleavage assays. hAgo2 but not hAgo3 cleaves the luc target RNA. (E) Northern blot analysis showing that hAgo2 and hAgo3 are able to be loaded with luc guide siRNA under the same circumstances.