Bordetella pertussis strains with increased toxin production associated with pertussis resurgence

Abstract

Before childhood vaccination was introduced in the 1940s, pertussis was a major cause of infant death worldwide. Widespread vaccination of children succeeded in reducing illness and death. In the 1990s, a resurgence of pertussis was observed in a number of countries with highly vaccinated populations, and pertussis has become the most prevalent vaccine-preventable disease in industrialized countries. We present evidence that in the Netherlands the dramatic increase in pertussis is temporally associated with the emergence of Bordetella pertussis strains carrying a novel allele for the pertussis toxin promoter, which confers increased pertussis toxin (Ptx) production. Epidemiologic data suggest that these strains are more virulent in humans. We discuss changes in the ecology of B. pertussis that may have driven this adaptation. Our results underline the importance of Ptx in transmission, suggest that vaccination may select for increased virulence, and indicate ways to control pertussis more effectively.

Figure 1

Alleles of pertussis toxin promoter (ptxP) observed worldwide. Bases are numbered –173 to +27 relative to the start of transcription (+1). The region to which 6 dimers of BvgA, the global regulator of B. pertussis virulence genes, bind is shaded. The –10 sequence motif and initiation codon are underlined. The DNA region –370 to –174, not shown here, was devoid of polymorphism. Locations of transcriptional signals and BvgA bindings sites are based on Bartoloni et al. (16).

Figure 2

Relationship between the emergence of pertussis toxin promoter 3 (ptxP3) strains and the epidemiology of pertussis in the Netherlands, 1989–2004. A) Temporal trends in the frequencies of ptxP3 strains and notifications. In this period 99% of the strains harbored either ptxP1 or ptxP3. B) Shift in age-specific distribution of notifications.

Figure 3

Production of pertussis toxin (Ptx) and pertactin (Prn) by pertussis toxin promoter 1 (ptxP1) and ptxP3 strains. Strains were incubated for the 48, 54, and 60 h, after which the amount of Ptx and Prn was determined by ELISA. The production ratio was calculated as follows: ptxP3 strain values/ptxP1 strain values; 8 strains, 4 ptxP1 strains and 4 ptxP3 strains, were used. The experiment was performed 3 times. Error bars indicate 95% confidence intervals. The Ptx and Prn ratios were significantly different from 1 (p<0.0001 and 0.03, respectively).