Cooperating H3N2 Influenza Virus Variants Are Not Detectable in Primary Clinical Samples

Abstract

The high mutation rates of RNA viruses lead to rapid genetic diversification, which can enable cooperative interactions between variants in a viral population. We previously described two distinct variants of H3N2 influenza virus that cooperate in cell culture. These variants differ by a single mutation, D151G, in the neuraminidase protein. The D151G mutation reaches a stable frequency of about 50% when virus is passaged in cell culture. However, it is unclear whether selection for the cooperative benefits of D151G is a cell culture phenomenon or whether the mutation is also sometimes present at appreciable frequency in virus populations sampled directly from infected humans. Prior work has not detected D151G in unpassaged clinical samples, but those studies have used methods like Sanger sequencing and pyrosequencing, which are relatively insensitive to low-frequency variation. We identified nine samples of human H3N2 influenza virus collected between 2013 and 2015 in which Sanger sequencing had detected a high frequency of the D151G mutation following one to three passages in cell culture. We deep sequenced the unpassaged clinical samples to identify low-frequency viral variants. The frequency of D151G did not exceed the frequency of library preparation and sequencing errors in any of the sequenced samples. We conclude that passage in cell culture is primarily responsible for the frequent observations of D151G in recent H3N2 influenza virus strains. IMPORTANCE Viruses mutate rapidly, and recent studies of RNA viruses have shown that related viral variants can sometimes cooperate to improve each other's growth. We previously described two variants of H3N2 influenza virus that cooperate in cell culture. The mutation responsible for cooperation is often observed when human samples of influenza virus are grown in the lab before sequencing, but it is unclear whether the mutation also exists in human infections or is exclusively the result of lab passage. We identified nine human isolates of influenza virus that had developed the cooperating mutation after being grown in the lab and performed highly sensitive deep sequencing of the unpassaged clinical samples to determine whether the mutation existed in the original human infections. We found no evidence of the cooperating mutation in the unpassaged samples, suggesting that the cooperation arises primarily under laboratory conditions.

Keywords: D151G; cooperation; deep sequencing; influenza virus; neuraminidase; quasispecies.

FIG 1

Sequencing coverage along the influenza virus genome. Average sequencing coverage is plotted for 50-bp bins across the genome, with library replicates shown as solid and dashed lines.

FIG 2

D151G does not exceed the frequency of library preparation and sequencing errors in unpassaged clinical samples. Shown is the distribution of frequencies of A-to-G mutations across the genome for each clinical sample. Typically, the D151 viral variant is encoded by the nucleotides GAT, and the G151 variant is encoded by GGT, meaning that D151G arises as the result of an A-to-G mutation. The red vertical line shows the proportion of A-to-G mutations at codon position 2 of amino acid site 151 of NA, which corresponds to the frequency of D151G. In cases where no A-to-G mutations were identified at this site, this red line is not shown. At each nucleotide site in the genome with consensus identity A, we calculated the total proportion of reads reporting an identity of G at that site and averaged this proportion between the two replicate libraries. As expected, A-to-G mutations make up <0.1% of the total sequencing reads at most sites in the genome and are probably errors introduced through library preparation and sequencing.