Phylogroup stability contrasts with high within sequence type complex dynamics of Escherichia coli bloodstream infection isolates over a 12-year period

Abstract

Background: Escherichia coli is the leading cause of bloodstream infections, associated with a significant mortality. Recent genomic analyses revealed that few clonal lineages are involved in bloodstream infections and captured the emergence of some of them. However, data on within sequence type (ST) population genetic structure evolution are rare.

Methods: We compared whole genome sequences of 912 E. coli isolates responsible for bloodstream infections from two multicenter clinical trials that were conducted in the Paris area, France, 12 years apart, in teaching hospitals belonging to the same institution ("Assistance Publique-Hôpitaux de Paris"). We analyzed the strains at different levels of granularity, i.e., the phylogroup, the ST complex (STc), and the within STc clone taking into consideration the evolutionary history, the resistance, and virulence gene content as well as the antigenic diversity of the strains.

Results: We found a mix of stability and changes overtime, depending on the level of comparison. Overall, we observed an increase in antibiotic resistance associated to a restricted number of genetic determinants and in strain plasmidic content, whereas phylogroup distribution and virulence gene content remained constant. Focusing on STcs highlighted the pauci-clonality of the populations, with only 11 STcs responsible for more than 73% of the cases, dominated by five STcs (STc73, STc131, STc95, STc69, STc10). However, some STcs underwent dramatic variations, such as the global pandemic STc131, which replaced the previously predominant STc95. Moreover, within STc131, 95 and 69 genomic diversity analysis revealed a highly dynamic pattern, with reshuffling of the population linked to clonal replacement sometimes coupled with independent acquisitions of virulence factors such as the pap gene cluster bearing a papGII allele located on various pathogenicity islands. Additionally, STc10 exhibited huge antigenic diversity evidenced by numerous O:H serotype/fimH allele combinations, whichever the year of isolation.

Conclusions: Altogether, these data suggest that the bloodstream niche is occupied by a wide but specific phylogenetic diversity and that highly specialized extra-intestinal clones undergo frequent turnover at the within ST level. Additional worldwide epidemiological studies overtime are needed in different geographical and ecological contexts to assess how generalizable these data are.

Trial registration: ClinicalTrials.gov NCT02890901.

Keywords: Antibiotic resistance; Bloodstream infection; Clonal replacement; Escherichia coli; Extra-intestinal infection; Pandemic clones.

Fig. 1

Global comparison of the 2005 and 2016-7 collections. a Phylogroup distribution of the strains. b Distribution of the number of virulence factors per strain among the six main functional classes of virulence. c Bar chart of predicted phenotypes of the strains. The results are presented as percentage of resistant strains for nine antibiotics of clinical importance. d Distribution of the number of replicons per strain and the plasmid sequence length predicted by PlaScope [36]. e Bar chart of the number of strains carrying complete integron, CALIN (clusters of attC sites lacking integron-integrases), and In0 (integron integrase only). Significant differences are highlighted by asterisks. AMP, ampicillin; TZP, piperacillin/tazobactam; CTX/CAZ, cefotaxime/ceftazidime; FEP, cefepime; CARB, carbapenems; FQ, fluoroquinolones; GEN, gentamicin; AMK, amikacin; SXT, cotrimoxazole

Fig. 2

a Distribution of the patristic distances between all strains of a given STc in a given collection. b Distribution of the genome fluidity between all strains of a given STc in a given collection. Significant differences are highlighted by asterisks (Benjamini-Hochberg corrected p value < 0.05)

Fig. 3

Distribution of the combinations O:H/fimH among the big four STcs and the STc10. a STc131. b STc95. c STc73. d STc69. e STc10. To have a rapid overview, the combinations O:H/fimH are also schematically represented by colored squares at the top of each bar graph

Fig. 4

Comparison of STc131 strains in the 2005 and 2016-7 collections. a Distribution of strains in the three clades of STc131 described by Ben Zakour et al. [50]. b Distribution of the number of virulence factors per strain among the six main functional classes of virulence. c Distribution of the adhesins in both collections. Only adhesins with a significant difference between 2005 and 2016-7 are presented (Benjamini-Hochberg corrected p value < 0.05). d Predicted phenotypes of the strains. The results are presented as percentage of resistant strains for eight antibiotics of clinical importance (no carbapenem-resistant strain has been found). Significant differences are highlighted by asterisks. AMP, ampicillin; TZP, piperacillin/tazobactam; CTX/CAZ, cefotaxime/ceftazidime; FEP, cefepime; FQ, fluoroquinolones; GEN, gentamicin; AMK, amikacin; SXT, cotrimoxazole

Fig. 5

Comparison of STc95 strains in the 2005 and 2016-7 collections. a Bar chart of the distribution of strains in the five subgroups of STc95 described by Gordon et al. [51]. b Distribution of the number of virulence factors per strain among the six main functional classes of virulence. c Distribution of the iron acquisition related genes in both collections. Only virulence factors with a significant difference between 2005 and 2016-7 are presented. d Predicted phenotypes of the strains. The results are presented as percentage of resistant strains for seven antibiotics of clinical importance (no strain resistant to carbapenems and amikacin has been found). Significant differences are highlighted by asterisks. AMP, ampicillin; TZP, piperacillin/tazobactam; CTX/CAZ, cefotaxime/ceftazidime; FEP, cefepime; FQ, fluoroquinolones; GEN, gentamicin; SXT, cotrimoxazole

Fig. 6

Comparison of STc69 strains in 2005 and 2016-7 collections. a Bar chart of the distribution of strains in the four subgroups of STc69 defined by fastbaps [52]. b Distribution of the number of virulence factors per strain among the six main functional classes of virulence. c Distribution of the adhesins in both collections. Only virulence factors with the most significant differences (i.e., significant before multiple test correction) between 2005 and 2016-7 are presented. d Predicted phenotypes of the strains. The results are presented as percentage of resistant strains for seven antibiotics of clinical importance (no strain resistant to carbapenems and amikacin has been found). Significant differences are highlighted by asterisks. AMP, ampicillin; TZP, piperacillin/tazobactam; CTX/CAZ, cefotaxime/ceftazidime; FEP, cefepime; FQ, fluoroquinolones; CARB, carbapenems; GEN, gentamicin; SXT, cotrimoxazole

Fig. 7

Schematic representation of the different scenarios leading to within STc dynamic. a Example of clonal replacement as observed in STc95. The represented plasmid corresponds to pS88 whereas the red terminal branches correspond to the emerging O1:H7 fimH41 subgroup A clone. The emerging O25b:H4 clone in the subgroup D is indicated by colored squares as in Fig. 3 and the branches are highlighted in green. b Multiple acquisitions of related PAIs associated to clonal expansion as observed in STc69 and STc131. The pap gene cluster with the papGII allele is represented in red on genetic maps. Red arrows indicate the acquisition of PAIs. c High antigenic diversity at a given time and overtime, as observed in STc10. This pattern corresponds probably to multiple recombination events at the main chromosomal hot spots (rfb, fimH)