Identification of mRNAs bound and regulated by human LIN28 proteins and molecular requirements for RNA recognition

Abstract

Human LIN28A and LIN28B are RNA-binding proteins (RBPs) conserved in animals with important roles during development and stem cell reprogramming. We used Photoactivatable-Ribonucleoside-Enhanced Crosslinking and Immunoprecipitation (PAR-CLIP) in HEK293 cells and identified a largely overlapping set of ∼3000 mRNAs at ∼9500 sites located in the 3' UTR and CDS. In vitro and in vivo, LIN28 preferentially bound single-stranded RNA containing a uridine-rich element and one or more flanking guanosines and appeared to be able to disrupt base-pairing to access these elements when embedded in predicted secondary structure. In HEK293 cells, LIN28 protein binding mildly stabilized target mRNAs and increased protein abundance. The top targets were its own mRNAs and those of other RBPs and cell cycle regulators. Alteration of LIN28 protein levels also negatively regulated the abundance of some but not all let-7 miRNA family members, indicating sequence-specific binding of let-7 precursors to LIN28 proteins and competition with cytoplasmic miRNA biogenesis factors.

FIGURE 1.

LIN28A and LIN28B are cytoplasmic mRNA-binding proteins. (A) Western blot analysis of nucleocytoplasmic fractions prepared from indicated cell lines. Total cell lysate (T), cytoplasmic extract (C), and nuclear extract (N) corresponding to the indicated number of cells were resolved on a 4%–12% SDS gel and then probed by Western blotting using antibodies targeting LIN28A and LIN28B. Antibodies for TUBB and LAMC were used to control for the purity of the cytoplasmic and nuclear fractions, respectively. (B) Immunofluorescence staining of FLAG epitope in stable HEK293 cells expressing FLAG/HA-LIN28A (top) and FLAG/HA-LIN28B (bottom). (C) Phosphorimage of an SDS-PAGE fractionating PAR–CLIP immunoprecipitate from stable HEK293 cells inducibly overexpressing FLAG/HA-tagged LIN28A and LIN28B. The crosslinked RNA–LIN28A and LIN28B complexes are indicated. Anti-HA Western blotting control for expression and loading is shown at the bottom. (D) Distribution of PAR–CLIP binding sites on mRNAs as identified by PARalyzer. (E) Overlap of binding sites for LIN28A and LIN28B at the nucleotide level (top) and at the transcript level (bottom). (F) Representative mRNA target sites identified by PAR–CLIP and shared by LIN28A and LIN28B. Nucleotides colored in green are predicted by RNAfold to be paired, uridines colored in red showed the T-to-C mutation characteristic of crosslinking. Underlined sequence stretches contained the AYYHY polypyrimidine stretch identified by motif analysis. The number of crosslinked sequence reads per region displayed the total number of crosslinked sequence reads across the entire mRNA, and the total number of LIN28B PAR–CLIP groups are listed. (*) Sequences that were selected for in vitro assays.

FIGURE 2.

LIN28 proteins binds PAR–CLIP targets and single-stranded RNA in electrophoretic mobility shift assays (EMSA). (A) Synthetic RNAs representing the stem–loop and the loop of LIN28 mRNA targets were radiolabeled, incubated with 0, 10, 100, and 1000 nM recombinant LIN28A, and separated on a 5% native polyacrylamide gel. The RNA sequences are shown to the left, with nucleotides predicted to pair marked in green. The estimated K_D value of the interaction is indicated. (B) Same as in A, with sequences representing single-stranded RNA. (C) Same as in A, with sequences from B that were hybridized to each other to yield double-stranded RNA. (D) Same as in A using the nonbinding 18-nt sequence (AC)₉ and substituting a number of cytidines for guanosines (panels 2–4) or uridines (panel 5). LIN28A dilution series was 0, 1, 10, 100, and 1000 nM. (E) Same as in A, with sequences derived from human pre-let-7a-1.

FIGURE 3.

LIN28 does not require the stem of stem–loop structure for binding. EMSAs for synthetic RNAs derived from a LIN28 target site on the 3′ UTR of CBX5 were performed as in Figure 2. The RNA sequences are shown to the left, with nucleotides predicted to pair marked in green. The estimated K_D value of the interaction is indicated.

FIGURE 4.

LIN28 binding increases target mRNA and protein abundance. (A) Western blot using antibodies against endogenous LIN28B after knockdown, mock transfection, and induced expression of FLAG/HA-tagged LIN28B. Sample loading was controlled using an anti-TUBB antibody. Signals for LIN28B and TUBB were quantified, and relative LIN28B protein levels are indicated. LIN28B mRNA levels were determined using Affymetrix HGU133 whole-genome microarrays. (B) Increase in LIN28 target mRNA abundance. Changes in transcript stability from LIN28B overexpression relative to LIN28B knockdown were inferred from microarray analysis. Shown are the distributions of changes upon four transcripts that were divided into the indicated bins based on the presence of PAR–CLIP binding sites, detection of protein in mass spectrometric assays, and the number of crosslinked sequence reads. (*) P < 0.05, (**) P < 0.01, (***) P < 0.001 in Student’s t-test, two-tailed. (C) Changes in protein levels after LIN28B overexpression and knockdown were determined by SILAC approaches. (*) P < 0.05. Proteins were grouped according to the same criteria as in B. (D) Changes in miRNA profiles of HEK293 cells after LIN28B knockdown (left) and overexpression (middle) were recorded by small RNA cDNA library sequencing. miRNAs were sorted according to expression in uninduced HEK293 cells. Top eight mature miRNAs are indicated and members of the let-7 miRNA family are shown as red squares and miRNAs coexpressed with let-7 miRNAs in transcriptional units or cistrons are shown as orange triangles. (Right) The comparison of miRNA levels after knockdown and overexpression of LIN28B.

FIGURE 5.

Sequence alignment of let-7 miRNA family members. ClustalW alignment of pre-let-7 miRNA family members. The mature miRNA and the miRNA* sequences are indicated in red and blue font, respectively. Guanosines interacting with the ZK-domains of LIN28 proteins in structural studies are highlighted in yellow, and uridines possibly contributing to LIN28 binding in the unpaired loop region of pre-let-7 miRNAs are highlighted in red. The number of sequence reads from a small RNA-sequencing experiment for HEK293 cells (see Supplemental Table 8, data set uninduced, replicate A) are indicated for each let-7 member. (#) Sequence reads that were split between the three indistinguishable mature miRNAs let-7a-1, let-7a-2, and let-7a-3 and between let-7f-1 and let-7f-2, respectively. Also indicated is the LIN28B-dependent regulation, expressed as the ratio of miRNA expression in HEK293 cells depleted of LIN28B compared with cells after induction of FLAG/HA-LIN28B (Fig. 4D; Supplemental Table 8).