Previously, we have shown that the N-terminal 25 aa of FluA PB1 (PB1_1–25A) are sufficient to bind FluA-PA and inhibit the polymerase activity of FluA [32]. However, this sequence was not able to block the polymerase activity of FluB. Since the first 25 aa of FluA-PA and FluB-PA differ at 8 positions (Fig. 1A), the failure to block FluB polymerase activity might be due to impaired binding of PB1_1–25A to FluB PA. Alternatively, the PA-binding domain of FluB PB1 might extend beyond the extreme 25 amino acids. To test this, we generated FluA/B PB1 chimeras by substituting N-terminal regions of varying length from FluA-PB1 into FluB-PB1 (Fig. 1B). After transient co-expression in human 293T cells, we then used immunoprecipitation assays to test which of these chimeras could bind to FluA-PA. All PB1 chimeras tested, including a chimera containing only the first 25 aa of FluA-PB1, could bind FluA-PA equally, whereas wild-type FluB-PB1 could not (Fig. 1C). This implied that the few aa differences in this small domain are the major determinant in PB1 for the type-specific binding of PB1 to PA.

To further characterize which amino acid positions are important for the type-specific binding of PB1_1–25 to PA, we developed an ELISA-based binding assay to quantify this interaction. For this purpose, we immobilized biotinylated peptides corresponding to PB1_1–25 on streptavidin-coated plates and subsequently added cell lysates containing HA-tagged PA. Bound PA was detected using HA-specific primary and peroxidase-coupled secondary antibodies. To determine the binding efficiency of variant peptides we performed the ELISA in a competitive manner. In this case, non-biotinylated competitor peptides were added simultaneously with HA-tagged PA to wells containing immobilized PB1_1–25 peptide.

The core-binding site of the PA-binding domain of FluA-PB1 was recently determined by co-crystalization with the C-terminus of PA and is comprised of a 3₁₀-helix ranging from aa 5–11 [25]. We therefore first evaluated our FluA-binding assay by using a soluble wild-type PB1_1–25A peptide, which resulted in a 50% inhibitory concentration (IC₅₀) of 1.8 nM (Fig. 2A). A “scrambled peptide” harboring the same amino acid composition as PB1_1–25A but with the order randomized, did not block PA-HA binding at highest concentrations (3000 nM, data not shown). Next, the minimal binding domain was determined by deleting aa from the N- and/or C-terminus of PB11-25A. Determination of the IC₅₀ using the truncated competitor peptides demonstrated that the 3-10 helix is absolutely essential for binding to PA, since any truncation of this sequence resulted in no competition (Fig. 2B). This is congruent with the results obtained by mutational analysis of the PA-binding domain [28]. Residual competition from partially C- or N-truncated peptides was observed, implying that some of the aa positions flanking the 3–10 helix may be dispensable for binding. Specifically, truncating the C-terminal 10 aa of FluA PB1_1–25A resulted in an IC₅₀ of 43.3 nM compared to 1.8 nM for the full-length peptide (Fig. 2B). Since this truncated peptide can efficiently bind to PA, yet still contains many of the differing aa positions between FluA and FluB, we chose this sequence as a basis to test variant peptides for their binding to both FluA- and FluB-PA.

As the PB1_1–15 sequence differs by 8 aa between FluA and FluB (Fig. 1A), we decided to create chimeras containing combinations of FluA- and FluB-specific residues and test these 15mer peptides in the competitive ELISA using both FluA-PA and FluB-PA. For this assay, biotinylated PB1_1–25A was used in combination with FluA-PA-HA, biotinylated PB1_1–25B was combined with FluB-PA-HA, and the competitor peptides were tested with both combinations. Competitor peptides PB1_1–15A and PB1_1–15B, derived from the wild-type sequences, competed only for FluA PA or FluB PA, respectively, with no cross-type competition detectable (Fig. 3). We then tested competitor peptides containing combinations of FluB-specific aa in the PB1_1–15A background. While most of these combinations showed no affinity for FluB, substituting positions 6 and 7 led to a significantly reduced IC₅₀ for FluB-PA as well as a slight decrease in the IC₅₀ for FluA-PA, suggesting that this peptide could bind to both proteins. By substituting only the FluB-specific tyrosine at position 6, efficient binding to PA of both types resulted. In contrast, changing only position 7 of a FluA- to a FluB-specific sequence ablated binding to PA of both types. Introduction of a phenylalanine or tryptophan at position 6 demonstrated that related residues can significantly increase the binding affinity to FluA PA, but only partially increase the affinity to FluB PA. A histidine or cysteine at position 6 led to peptides failing to bind to FluB PA, while binding to FluA PA was still possible, indicating that not all amino acid substitutions confer the dual-binding activity observed with tyrosine at this position.

To further confirm that tyrosine at position 6 of FluA PB1 can bind directly to both FluA- and FluB-PA, we used a biotinylated 25mer peptide PB1_1–25A_T6Y as well as wild-type peptides and cell lysates containing overexpressed PA-HA derived from several different FluA and FluB strains in the ELISA. As shown in Fig. 4A–C, PA-HA from several FluA strains of various subtypes, including a human H5N1 isolate, bound to both PB1_1–25A and PB1_1–25 A_T6Y, but not to PB1_1–25B or a scrambled biotinylated peptide. Conversely, PA-HA derived from several different FluB strains bound to both the PB1_1–25B and PB1_1–25A_T6Y (Fig. 4D). Thus, a FluA-PB1-derived sequence containing a single substitution at position 6 can directly bind to PA from different FluA and FluB viruses. Molecular modeling suggests that the FluB-derived tyrosine at position 6 of PB1_1–25A_T6Y fits into a hydrophobic pocket of FluA PA and displaces a water molecule (Fig. 3F). Both the increased hydrophobic interaction as well as the entropic effect of the water displacement might explain the enhanced binding of PB1-T6Y to PA of FluA and possibly of FluB.

To demonstrate that PB1_1–25A_T6Y can bind to both FluA- and FluB-PA in a cellular context, we performed immunoprecipitation experiments using overexpressed PA and PB1_1–25 peptides fused to GFP (Fig. 5B). This confirmed that PB1_1–25 derived from FluA or FluB can only bind to FluA-PA or FluB-PA, respectively. However, PB1_1–25A_T6Y could be immunoprecipitated with either FluA-PA or FluB-PA.

Next, we tested the ability of these fusion proteins to inhibit the polymerase activity of both FluA and FluB using a reconstituted viral ribonucleoprotein complex and a reporter gene. As previously shown [32], PB1_1–25A-GFP inhibits the activity of FluA, but not FluB, while the converse is true of PB1_1–25B-GFP (Fig. 5C). However, PB1_1–25A_T6Y-GFP inhibited both FluA and FluB polymerase activity to comparable levels as the wild-type-derived sequences (Fig. 5C), indicating that this variant peptide is also biologically active.

Finally, we tested the ability of these peptides to inhibit viral spread in cell culture. MDCK cells were infected with either A/WSN/33 (H1N1), A/Thailand/1/2004 (H5N1), B/Yamagata/73, or vesicular stomatitis virus (VSV) as a specificity control from a different virus family. A plaque reduction assay was then performed in the presence of PB1_1–25A, PB1_1–25A_T6Y, or a negative-control peptide fused to an HIV-Tat derived sequence [33] (Table 1) to allow the peptides to cross the plasma membrane. Similar experiments with a FluB-derived peptide were not possible due to its insolubility. The peptide containing the T6Y substitution inhibited the growth of all influenza strains tested, while PB1_1–25A-Tat only inhibited FluA (Fig 6). Thus, a single mutation in the PB1_1–25A sequence results in a peptide which is active against both FluA and FluB strains.

Infection experiments were carried out using A/WSN/33 (H1N1) [32] and A/Thailand/1(Kan-1)/2004 [47], B/Yamagata/73 [48] and VSV (serotype Indiana) [49].

Plasmids pCA-Flag-GFP and pCA-PB1_1–25A-GFP [32], pCA-PB1-HA [32], the FluA minireplicon plasmids [50] and the expression plasmids for the FluB minireplicon [32] were described elsewhere. The FluB minigenome expression plasmid, pPolI-lucRT_B, was obtained by cloning the firefly luciferase ORF (inverse orientation) flanked by the non-coding region of the segment 8 of the B/Yamagata/73 into the SapI-digested plasmid pPolI-SapI-Rib [50]. For the construction of pCA-PB1_1–25B-GFP, a linker containing the first 25 codons of PB1 (B/Yamagata/73) was cloned into the EcoRI/NotI sites of pCA-Flag-GFP plasmid, replacing the Flag-coding sequence with PB1_1–25B. Site directed mutagenesis was carried out with pCA-PB1_1–25A-GFP to create the plasmid pCA-PB1_1–25A_T6Y-GFP. The ORFs of PB1 (B/Yamagata/73) and PA (A/SC35M, A/Thailand/1(KAN-1)/04, A/Vietnam/1203/04, B/Yamagata/73, B/Lee/40; accession numbers: Influenza A virus (A/WSN/1933(H1N1)) segment 2 (CY034138), segment 3 (CY034137), A/SC35M (H7N7) segment 2 (DQ266098), segment 3 (DQ266099), A/Thailand/1(KAN-1)/2004(H5N1) segment 3 (AY555150), B/Lee/40 segment 3 (NC_002206)) were PCR amplified with sense primers containing a NotI site (FluA strains) or a EcoRI site (FluB strains) upstream of the initiation codon and antisense primers with a deleted stop codon followed by an XmaI site, a coding sequence for an HA-tag and a XhoI site. The PCR products were cloned into a modified pCAGGs-vector [51] digested either with EcoRI/XhoI or NotI/XhoI, resulting in pCA-PB1-HA or pCA-PA-HA plasmids, coding for C-terminal tagged versions of the polymerase subunits. To obtain the pCA-PA_A/SC35M-His plasmid, pCA-PA_A/SC35M-HA was digested with XmaI/XhoI and the HA coding sequence was replaced by a 6xHis-linker. The A/B-chimeric expression plasmids were obtained by assembly PCR using the pCA-PB1-HA plasmids of SC35M and B/Yamagata/73 and by cloning the resulting PCR product in pCA-PB1_{B/Yamagata/73}-HA digested with EcoRI/EcoRV.

293T cells were transiently transfected with a plasmid mixture containing either FluA- or FluB-derived PB1-, PB2-, PA- and NP-expression plasmids, polymerase I (Pol I)-driven plasmid transcribing an influenza A or influenza B virus-like RNA coding for the reporter protein firefly luciferase to monitor viral polymerase activity and with expression plasmids coding for the indicated GFP fusion proteins. Both minigenome RNAs were flanked by non-coding sequences of segment 8 of FluA and FluB, respectively. The transfection mixture also contained a plasmid constitutively expressing Renilla luciferase, which served to normalize variation in transfection efficiency. The reporter activity was determined 24 h post transfection and normalized using the Dual-Glu® Lufierase Assay System (Promega). The activity observed with transfection reactions containing Flag-GFP were set to 100%.

The solid-phase synthesis of the peptides, including the peptides for the plaque reduction assay (Table 1), was carried out on a Pioneer automatic peptide synthesizer (Applied Biosystems, Foster City, USA) employing Fmoc chemistry with TBTU/diisopropylethyl amine activation. Side chain protections were as follows: Asp, Glu, Ser, Thr and Tyr: t-Bu; Asn, Gln and His: Trt; Arg: Pbf; Lys and Trp: Boc. Coupling time was 1 h. Double couplings were carried out if a difficult coupling was expected according to the program Peptide Companion (CoshiSoft/PeptiSearch, Tucson, USA). All peptides were generated as carboxyl amides by synthesis on Rapp S RAM resin (Rapp Polymere, Tübingen, Germany). Biotin was incorporated at the C-terminus of indicated peptides with Fmoc-Lys(Biotin)-OH (NovaBiochem/Merck, Nottingham, UK) and TBTU/diisopropylethyl amine activation for 18 h, followed by coupling of Fmoc-β-Ala-OH for 1 h. Peptides were cleaved from the resin and deprotected by a 3 h treatment with TFA containing 3% triisobutylsilane and 2% water (10 ml/g resin). After precipitation with t-butylmethyl ether, the resulting crude peptides were purified by preparative HPLC (RP-18) with water/acetonitrile gradients containing 0.1% TFA and characterized by analytical HPLC and MALDI-MS. Some peptides were synthesized by peptides&elephants (Nuthetal, Germany) and subsequently purified and characterized as described above.

293T cells were transfected with the indicated plasmids in 6-well plates using Metafectene (Biontex, Martinsried, Germany). Cells were incubated 24 h post transfection with lysis buffer (20 mM Tris pH 7.5, 100 mM NaCl, 0.5 mM EDTA, 0.5% NP-40, 1% Protease inhibitor Mix G, (Serva, Heidelberg, Germany), 1 mM DTT) for 15 min on ice. After centrifugation by 13.000 rpm at 4°C supernatant was incubated with anti HA-specific antibodies coupled to agarose beads (Sigma) for 1 h at 4°C. After three washes with 1 ml of washing buffer (lysis buffer without protease inhibitor mix), bound material was eluted under denaturing conditions and separated on SDS-PAGE gels and transferred to PVDF membranes. Viral polymerase subunits and GFP fusion proteins were detected with antibodies directed against the HA- (Covance, Berkeley, California) or His-(Qiagen) or GFP-tag (Santa Cruz Biotechnology).

Streptavidin-coated microwell plates were incubated with saturating concentrations of biotinylated peptides, washed and subsequently incubated at room temperature with HA-tagged PA. To obtain PA-HA, 293T cells were seeded into 94 mm-dishes, transfected with the respective plasmid and treated with lysis buffer 24 h post transfection as previously described [32]. After washing the microwell plates, the wells were incubated with an HA-specific primary antibody (Covance, MMS-101R), followed by three washes and an incubation with a peroxidase-coupled secondary antibody (Jackson Immuno Research, Newmarket, UK). After the final wash step, ABTS-substrate (Sigma, ready-to-use solution) was added and the optical density was determined at 405 nm.

The competition ELISA was carried out as described above with the exception that the competitor peptides were added to wells of the plate with bound peptides simultaneously with the addition of the cell extract containing HA-tagged PA subunits.