A case for a negative-strand coding sequence in a group of positive-sense RNA viruses

Abstract

Positive-sense single-stranded RNA viruses form the largest and most diverse group of eukaryote-infecting viruses. Their genomes comprise one or more segments of coding-sense RNA that function directly as messenger RNAs upon release into the cytoplasm of infected cells. Positive-sense RNA viruses are generally accepted to encode proteins solely on the positive strand. However, we previously identified a surprisingly long (∼1,000-codon) open reading frame (ORF) on the negative strand of some members of the family Narnaviridae which, together with RNA bacteriophages of the family Leviviridae, form a sister group to all other positive-sense RNA viruses. Here, we completed the genomes of three mosquito-associated narnaviruses, all of which have the long reverse-frame ORF. We systematically identified narnaviral sequences in public data sets from a wide range of sources, including arthropod, fungal, and plant transcriptomic data sets. Long reverse-frame ORFs are widespread in one clade of narnaviruses, where they frequently occupy >95 per cent of the genome. The reverse-frame ORFs correspond to a specific avoidance of CUA, UUA, and UCA codons (i.e. stop codon reverse complements) in the forward-frame RNA-dependent RNA polymerase ORF. However, absence of these codons cannot be explained by other factors such as inability to decode these codons or GC3 bias. Together with other analyses, we provide the strongest evidence yet of coding capacity on the negative strand of a positive-sense RNA virus. As these ORFs comprise some of the longest known overlapping genes, their study may be of broad relevance to understanding overlapping gene evolution and de novo origin of genes.

Keywords: RNA virus; overlapping genes.

Figure 1.

Narnavirus genome structure and taxonomy. (A) Updated narnaviral genome sequences: genome structures of ONLV1 and ONLV2. (B) Bayesian phylogeny of narnaviruses and selected outgroup sequences. Alphanarnaviruses and betanarnaviruses form clades with posterior probabilities of 0.95. The tree is rooted with the mitoviral clade as an outgroup. Accession numbers are for the nucleotide sequences from which the corresponding protein sequences were derived.

Figure 2.

Midpoint-rooted Bayesian phylogenetic tree of alphanarnaviruses. The longest 5′-proximal ORF in the negative-strand R0 frame is shown in the bars to the right. Sequences with R0-frame ORFs occupying over 90 per cent of the sequence are indicated with red bars. Nine highly similar sequences for Zhejiang mosquito virus 3 (indicated with an asterisk) are collapsed to a single taxon. Accession numbers are for the nucleotide sequences from which the corresponding protein sequences were derived.

Figure 3.

Midpoint-rooted Bayesian phylogenetic tree of betanarnaviruses. As in Fig. 2, the longest 5′-proximal ORF in the negative-strand R0 frame is shown in the bars to the right. Five highly similar TSA sequences for Pyropia haitanensis and six highly similar sequences for Phytophthora infestans RNA virus 4 (both indicated with asterisks) are collapsed to single nodes. Accession numbers are for the nucleotide sequences from which the corresponding protein sequences were derived.

Figure 4.

The longest 5′-proximal stop codon-free regions in each of the three possible positive-strand and negative-strand reading frames, for alphanarnaviruses (red) and betanarnaviruses (blue), as a percentage of the sequence length. Wenling narna-like virus 7 (WNLV7) has an intermediate-length R0-frame ORF, as indicated. Mean values are plotted for nodes with high levels of representation in the underlying data set (i.e. Zhejiang mosquito virus 3, Phytophthora infestans RNA virus 4, and TSA sequences from Pyropia haitanensis).

Figure 5.

Box plots of codon usage (proportion of total codons) in RdRp ORFs. The upper and lower hinges are located at the first and third quartiles, respectively; the median values are indicated as horizontal lines; and the whiskers extend from the hinges to the furthest data points within 1.5 times the interquartile range (IQR) of the hinges. Data more than 1.5 times the IQR from the hinges are drawn as individual points (outliers). Codons are ordered according to their median frequency in alphanarnaviruses that contain the rORF. Alphanarnaviruses that contain the rORF show a specific avoidance of the three codons marked with red asterisks (CUA, UUA and UCA), which correspond to the reverse complements of stop codons.

Figure 6.

Specific selection against CUA, UUA and UCA codons in rORF-containing alphanarnaviruses. (A) Box plots of codon usage bias (proportion of codons encoding the amino acid) for leucine and serine. Box plots are drawn as in Fig. 5. (B) Comparison of mean usage of CUA, UUA and UCA (per associated amino acid) with the third-position GC (GC3) content of codons. Prokaryotic and eukaryotic taxa in NCBI RefSeq are shown as grey points. The RdRp ORFs of non-rORF alphanarnaviruses, rORF alphanarnaviruses and betanarnaviruses are indicated with orange, green and blue points, respectively. The Wenling narna-like virus 7 (WNLV7) and Hubei narna-like virus 16 (HNLV16) sequences are indicated.

Figure 7.

Amino acid conservation and synonymous site conservation in rORF-containing alphanarnaviruses. (A) RdRp amino acid conservation, and the corresponding synonymous site conservation analysis. In the latter, the grey dashed line indicates an approximate 5 per cent false positive threshold after correcting for multiple tests (i.e. ∼69 non-overlapping/independent 15-codon windows in the 1027-codon ORF). (B) The equivalent plots for the rORF. In each case, conservation was assessed in a 15 codon/amino acid window. Motifs A–G in the RdRp amino acid sequence are indicated with letters. Additional consensus motifs indicated with asterisks are as follows: * = R&UP, ** = Pxx[L/V]GGx[G/N]xP and *** = QvxExExxPREREAH; U = I, L, V, or M, & = I, L, V, M, A, P, G, F, W, or Y.