Clinical outcome and genetic differences within a monophyletic Dengue virus type 2 population

Abstract

The exact mechanisms of interplay between host and viral factors leading to severe dengue are yet to be fully understood. Even though previous studies have implicated specific genetic differences of Dengue virus (DENV) in clinical severity and virus attenuation, similar studies with large-scale, whole genome screening of monophyletic virus populations are limited. Therefore, in the present study, we compared 89 whole genomes of DENV-2 cosmopolitan clade III isolates obtained from patients diagnosed with dengue fever (DF, n = 58), dengue hemorrhagic fever (DHF, n = 30) and dengue shock syndrome (DSS, n = 1) in Singapore between July 2010 and January 2013, in order to determine the correlation of observed viral genetic differences with clinical outcomes. Our findings showed no significant difference between the number of primary and secondary infections that progressed to DHF and DSS (p>0.05) in our study cohort. Despite being highly homogenous, study isolates possessed 39 amino acid substitutions of which 10 substitutions were fixed in three main groups of virus isolates. None of those substitutions were specifically associated with DHF and DSS. Notably, two evolutionarily unique virus groups possessing C-P43T+NS1-S103T+NS2A-V83I+NS3-R337K+ NS3-I600T+ NS5-P136S and NS2A-T119N mutations were exclusively found in patients with DF, the benign form of DENV infections. Those mutants were significantly associated with mild disease outcome. These observations indicated that disease progression into DHF and DSS within our patient population was more likely to be due to host than virus factors. We hypothesize that selection for potentially less virulent groups of DENV-2 in our study cohort may be an evolutionary adaptation of viral strains to extend their survival in the human-mosquito transmission cycle.

Fig 1. Phylogenetic analysis of DENV-2 study sequences.

The maximum-likelihood tree was constructed based on the complete coding sequences generated during this study and those retrieved from GenBank. Sequences of only 37 isolates, mainly comprising of three groups of isolates (NS2A-V83I, n = 15; NS2A-T119N, n = 6; E-V164I+NS2A-L153S, n = 9), are shown in the tree. Viral sequences obtained from patients with DF (mild) and DHF/DSS (severe) manifestations are highlighted in green and red respectively. An enlarged view has been inserted to illustrate the two mutant groups (NS2A-V83I and NS2A-T119N) that were exclusively observed in patients with mild disease (DF) (highlighted in green boxes). Figures on branches are bootstrap values. Only bootstrap values more than 90% are shown on the major nodes.

Fig 2. Median joining network analysis and amino acid substitution map of study sequences.

The median joining network was drawn in Network version 4.6.1.2 [28] using complete coding sequences (10173 nucleotides) of DENV-2 cosmopolitan clade III sequences (n = 89). Circles represent either individual isolates or clusters. The diameter of each circle is proportional to the number of isolates within each circle. The length of lines linking circles is not proportional to the mutational distance between them. The empty nodes represent hypothetical ancestral strains or strains present in the population but not sampled. Different colors indicate clinical categories as shown in the figure legend. As the analysis only included clade III sequences, mutations were stated as compared to wild-type clade III sequences (Table 2). Only amino acid substitutions associated with groups of isolates (n>6) are mapped. DF = dengue fever; DHF = dengue hemorrhagic fever; DSS = dengue shock syndrome

Fig 3. Comparison of RNA secondary structures of the variable region of 3’UTR between wild type (NS2A-V83) and mutant (NS2A-V83I) variants.

The first (5’ end) 120 nucleotides of 3’UTR was used to draw the secondary structure as predicted by the MFOLD web server [31]. Position 1 indicates the first nucleotide of 3’UTR. (A). Wild type (NS2A-V83) DENV-2 cosmopolitan clade III (B). Mutant (NS2A-V83I) DENV-2 cosmopolitan clade III. The mutated position (19T) in Stem Loop-I (SL-I) is indicated with an asterisk. Stem Loop structures (I-III) were named as illustrated elsewhere [68].

Fig 4. Comparison of RNA secondary structures of the 5’UTR between wild type (NS2A-V83) and mutant (NS2A-V83I) variants.

The complete sequence (96 nucleotides) of 5’UTR was used to draw the secondary structure as predicted by the MFOLD web server [31]. Position 1 indicates the first nucleotide of 5’UTR. (A). Wild type (NS2A-V83) DENV-2 cosmopolitan clade III (B). Mutant (NS2A-V83I) DENV-2 cosmopolitan clade III. The mutated position (34C) in the top loop of Stem Loop A (SLA) is indicated with an asterisk. Stem Loop structures were named as illustrated elsewhere [64].