Genome-wide antisense transcription drives mRNA processing in bacteria

Abstract

RNA deep sequencing technologies are revealing unexpected levels of complexity in bacterial transcriptomes with the discovery of abundant noncoding RNAs, antisense RNAs, long 5' and 3' untranslated regions, and alternative operon structures. Here, by applying deep RNA sequencing to both the long and short RNA fractions (<50 nucleotides) obtained from the major human pathogen Staphylococcus aureus, we have detected a collection of short RNAs that is generated genome-wide through the digestion of overlapping sense/antisense transcripts by RNase III endoribonuclease. At least 75% of sense RNAs from annotated genes are subject to this mechanism of antisense processing. Removal of RNase III activity reduces the amount of short RNAs and is accompanied by the accumulation of discrete antisense transcripts. These results suggest the production of pervasive but hidden antisense transcription used to process sense transcripts by means of creating double-stranded substrates. This process of RNase III-mediated digestion of overlapping transcripts can be observed in several evolutionarily diverse Gram-positive bacteria and is capable of providing a unique genome-wide posttranscriptional mechanism to adjust mRNA levels.

Fig. 1.

Genome-wide analysis of mapped reads from long and short RNA-seq libraries. (A) Percentage of the genome of S. aureus NCTC 8325 covered by uniquely mapped reads on both strands, reads on one of the strands, and showed no coverage, respectively. The long RNA-seq libraries were prepared from S. aureus 15981 wild-type strain (WT) and its corresponding RNase III mutant (Δrnc). (B and C) Comparison of the cumulative distribution of ORF coverage by long (B) and short (C) RNA reads. The plot represents the number of ORFs (x axis) found above the ORF coverage value (y axis). The coverage was computed from the collapsed reads uniquely mapped in the sense and antisense orientation to the ORFs. The dashed line represents 50% coverage.

Fig. 2.

Long and short mapped reads distribution in S. aureus genome. The drawing is an IGB software image showing the uniquely mapped long and short RNAs in a 30-kb region (1%) of the genome of S. aureus NCTC 8325. Transcripts are represented as dashed red arrows. Genomic coordinates denote the position in kilobases of the S. aureus NCTC 8325 genome. Annotated ORFs are shown as blue lines. The number on the ORF indicates the gene identification. Long and short RNAs show the distribution of uniquely mapped reads of long and short RNA libraries. S. aureus 15981 (black) and S. aureus 15981 Δrnc (RNase III mutant) (green). The scale (log₂) indicates the number of mapped reads per nucleotide position.

Fig. 3.

Examples of mapped reads distribution in regions with overlapping transcription of S. aureus. Drawings are images from IGB software showing different regions of the genome of S. aureus NCTC 8325. Examples of overlapping 5′ UTRs (A), overlapping 3′ UTRs (B), overlapping operons (C), and antisense RNA (D) are shown. Transcripts are represented as dashed red arrows. Genomic coordinates denote the position in kilobases of the S. aureus NCTC 8325 genome. Annotated ORFs are shown as blue lines. The number on the ORF indicates the gene identification. Long and short RNAs show the distribution of uniquely mapped reads of long and short RNA libraries in S. aureus 15981. The scale (log₂) indicates the number of mapped reads per nucleotide position. Dashed rectangles highlight increased accumulation of short mapped reads in regions with overlapping transcription, according to long RNA reads.

Fig. 4.

Expression levels of sense/antisense transcripts. (A and C) The plots show the dependence of the antisense vs. sense ORF-averaged signal in long RNA reads. Each dot corresponds to one ORF annotated in the S. aureus NCTC 8325 genome. S. aureus 15981 wild-type (A) and S. aureus 15981 Δrnc (RNase III mutant) (C). (B and D) The plots show the dependence of the number of uniquely mapped reads per ORF for the antisense strand vs. sense strand in the short RNA reads. S. aureus 15981 wild-type (B) and S. aureus 15981 Δrnc (RNase III mutant) (D). (E) Genome-wide analysis distribution of mapped reads from short RNA-seq libraries in different bacterial species. The plot shows the dependence of the number of uniquely mapped reads per ORF for the antisense strand vs. sense strand in the short RNA-seq libraries of E. faecalis, L. monocytogenes, B. subtilis, and Salmonella Enteritidis. The color scale represents the number of points within a ±20% window of each point. The number in the bottom right corner is the Spearman correlation coefficient R².

Fig. 5.

Expression levels of sense/antisense transcripts. Northern blot analysis of RNA harvested from S. aureus 15981 wild-type and its corresponding S. aureus 15981 Δrnc. The blot was probed with a riboprobe specific for sense and antisense transcripts. The positions of RNA standards in kilobases are indicated. The time of exposure of the autoradiographies are indicated in hours (h) or days (d).