High-throughput identification of RNA localization elements in neuronal cells

Abstract

Hundreds of RNAs are enriched in the projections of neuronal cells. For the vast majority of them, though, the sequence elements that regulate their localization are unknown. To identify RNA elements capable of directing transcripts to neurites, we deployed a massively parallel reporter assay that tested the localization regulatory ability of thousands of sequence fragments drawn from endogenous mouse 3' UTRs. We identified peaks of regulatory activity within several 3' UTRs and found that sequences derived from these peaks were both necessary and sufficient for RNA localization to neurites in mouse and human neuronal cells. The localization elements were enriched in adenosine and guanosine residues. They were at least tens to hundreds of nucleotides long as shortening of two identified elements led to significantly reduced activity. Using RNA affinity purification and mass spectrometry, we found that the RNA-binding protein Unk was associated with the localization elements. Depletion of Unk in cells reduced the ability of the elements to drive RNAs to neurites, indicating a functional requirement for Unk in their trafficking. These results provide a framework for the unbiased, high-throughput identification of RNA elements and mechanisms that govern transcript localization in neurons.

Figure 1.

Identification of 3′ UTRs sufficient to drive RNA localization in neuronal cells. (A) Diagram of mechanical fractionation of neuron cells and analysis of subcellular transcriptomes. (B) Neurite-localized genes were identified through high-throughput RNA sequencing of compartment-specific transcriptomes from 32 mouse primary neuron and cell line-derived samples. Z-normalized neurite enrichments for the RNAs from selected genes are shown. Genes in purple were defined as repeatedly neurite-enriched. Genes in blue were defined as repeatedly soma-enriched, and the gene in black showed neither soma nor neurite enrichment. Wilcoxon P values represent the differences in neurite localization distributions between the indicated genes and all genes (gray). (C) PhastCons conservation scores for the 3′ UTRs of all genes (gray) and the chosen neurite-enriched genes (purple). (D) Diagram of RT-qPCR experiment. Reporter plasmids expressing the firefly and renilla luciferase transcripts are integrated into the genome through Cre-mediated recombination and are expressed from a bidirectional promoter. Sequences whose RNA localization activity will be tested are fused onto the 3′ UTR of Firefly luciferase. The ratio of firefly to renilla luciferase transcripts in soma and neurite samples is measured using Taqman qPCR. Comparing these ratios in soma and neurite samples quantifies localization of the firefly luciferase transcript. (E) 3′ UTRs of the indicated genes were fused to firefly luciferase and the neurite localization of the resulting transcript was quantified using RT-qPCR. The neurite localization of the firefly luciferase with no added 3′ UTR was used as a control.

Figure 2.

Design of MPRA and QC of synthesized oligonucleotide pool. (A) Oligonucleotides of length 260 nt were designed against the 3′ UTRs of chosen genes. Neighboring oligonucleotides were spaced 4 nt from each other, giving an average coverage of 65X per nucleotide. These oligonucleotides were then integrated into the 3′ UTR of reporter transcripts, generating a library of reporters. (B) Distribution of oligonucleotide abundances in the synthesized pool. (C) Distribution of oligonucleotide abundances in the integrated GFP reporter transcript in CAD neuronal cells.

Figure 3.

Overview and QC of MPRA results. (A) Hierarchical clustering of oligonucleotide abundances from the GFP reporter in CAD cells. (B) Concordance of results across cell lines. Neurite enrichment in N2A GFP samples of oligonucleotides defined as soma- (blue), neurite- (purple) or non-localized (gray) in CAD GFP samples. (C) Concordance of results across reporter scaffolds. Neurite enrichment in CAD firefly luciferase samples of oligonucleotides defined as soma-, neurite- or non-localized in CAD GFP samples. (D) Distribution of absolute differences in neurite enrichment values for neighboring oligonucleotides. As a control, the positional relationship between all oligonucleotides was randomly shuffled, and the difference in neurite enrichment for neighboring oligonucleotides were recalculated. (E) Number of significantly neurite- and soma-enriched oligonucleotides among those drawn from UTRs from neurite- and soma-enriched genes. All significance tests were performed using a Wilcoxon rank-sum test. P value notation: * < 0.05, ** < 0.01, *** < 0.001, **** < 0.0001.

Figure 4.

Identification of UTR regions with RNA localization activity and their properties. (A–F) Neurite enrichments of oligonucleotides as a function of their location within the gene's UTR. These plots are using GFP reporter data from CAD (pink) and N2A (green) cells. Lines represent a sliding average of eight oligonucleotides, and the ribbon represents the standard deviation of neurite enrichment for the oligonucleotides in the sliding window. Dots below the lines represent the locations of significantly neurite-localized oligonucleotides (FDR < 0.05). Blue boxes represent the locations of ‘active windows’ defined using the CAD data. Note that the 3′ UTR of Afap1l1 was not expected to contain active oligonucleotides. (G) Definition of oligonucleotide unions. (H) Resolution of active sequences afforded by high density oligo design. Neighboring oligos show vast differences in activity even though they lie only 4 nt apart. (I) Nucleotide content of oligos defined as significantly soma-, neurite, and non-localized using CAD GFP data. (J) A/G content of active windows and inactive sequences in the indicated UTRs. (K) Conservation scores of soma-, neurite- and non-localized oligonucleotide sequences. (L) Maximum A/G content of 100 nt windows for the 3′ UTRs of the human orthologs of the genes that contain active peaks in the MPRA. (M) Maximum A/G content in all 3′ UTR 100 nt windows for nonlocalized (gray) and neurite-localized (purple) RNAs. Localized RNAs were defined as having a median Z-normalized neurite enrichment across 32 RNA localization experiments of at least 2. Nonlocalized RNAs were defined as those with Z-normalized neurite enrichments of less than 2. (N) Median Z-normalized neurite enrichment across 32 RNA localization experiments for genes whose 3′ UTR either does (purple) or does not (gray) contain a 100 nt window with at least 75% A/G content. All significance tests were performed using a Wilcoxon rank-sum test. P value notation: * < 0.05, ** < 0.01, *** < 0.001, **** < 0.0001.

Figure 5.

Experimental validation of regulatory sequences. (A) Oligonucleotide unions (blue) were defined as the sequences present within any oligonucleotide contained within a stretch of neurite-localized oligonucleotides. Oligonucleotide intersections (red) were defined as those present within all oligonucleotides of a stretch of neurite-localized oligonucleotides. Peak oligonucleotides were those with high localization activity, often found at the center of an oligonucleotide union. (B) smFISH of reporter constructs containing peak oligonucleotide sequences. (C) RNA localization activity, as assayed by RT-qPCR, of peak oligonucleotide sequences and the full UTRs from which they were drawn. Observed neurite enrichments for each construct were compared to the enrichment of a control reporter construct lacking an active 3′ UTR. (D) As in C, RNA localization activity of reporter constructs containing peak oligonucleotide or full UTRs lacking the sequences of the peak oligonucleotides. (E) RNA localization activity of reporter constructs containing peak oligonucleotides or oligonucleotide intersections as defined in (A). (F) Schematic of differentiation of human iPS cells into motor neurons. (G) RNA localization activity, as assayed in human motor neurons, of a reporter construct containing the peak oligonucleotide from the mouse Net1 gene. (H) Fraction of UTR alleles that remain wildtype for the sequence in between designed gRNA cut sites. Wildtype cells and CRISPR-generated clones in which approximately 360 bp was deleted from Net1 and Trak2 3′ UTRs were interrogated. This fraction was calculated using a qPCR strategy that quantified the relative amount of wildtype and total alleles. (I) Neurite enrichment of endogenous Net1 and Trak2 RNA in wildtype and CRISPR-generated peak oligonucleotide deletion clones. All significance tests were performed using a t-test. P value notation: * < 0.05, ** < 0.01, *** < 0.001, **** < 0.0001.

Figure 6.

Identification and functional validation of RBPs required for peak oligonucleotide localization. (A) Scheme of mass-spectrometry-based experiment to identify RBPs bound to peak oligonucleotide sequences. (B) RBPs derived from CAD extract that were significantly different in abundance(FDR < 0.05) in the Net1 peak oligonucleotide RNA pulldown than the control RNA pulldown. (C) Western blot of RNA pulldowns from N2A cell lysate using RNA baits composed of peak oligonucleotides (Net1 and Trak2) or a portion of the coding sequence of firefly luciferase (control). (D) Neurite-enrichments, as determined by cell fractionation and RT-qPCR, of Net1 and Trak2 peak oligonucleotide reporter transcripts following the siRNA-mediated knockdown of Unk. (E) Neurite enrichment of endogenous Net1 and Trak2 following siRNA-mediated knockdown of Unk. All significance tests were performed using a Wilcoxon rank-sum test. P value notation: * < 0.05, ** < 0.01, *** < 0.001, **** < 0.0001.