Aedes aegypti is globally distributed throughout the tropics and subtropics and highly adapted to humans and urban environments. It acts as a primary vector for various arboviral infections including yellow fever virus, dengue virus (DENV) and chikungunya virus (CHIKV) [1]–[5]. Dengue has recently become a major health problem around the world with more than 120 countries endemic for dengue [6] and has been ranked as the most important mosquito borne viral disease [7]. Recent estimates by the World Health Organization (WHO) suggests that 50–100 million dengue infections occur worldwide every year and over 40% of the world's population is now at risk of the disease [8]. A study based on a cartographic approach estimated 90 million apparent dengue infections globally in year 2010 with India accounting for 34% (32 million) infections [9]. Chikungunya is another important arboviral infection spread by Ae. aegypti, prevalent in Africa, Southeast Asia and India [10]. In India it re-emerged in 2006 after a gap of 32 years [10].

Since there is no specific vaccine or drug available for the treatment of dengue and chikungunya, vector control and personal protection are the only options to reduce the spread of these arboviral infections. Vector control strategies employed for Aedes control in India are mainly anti-larval measures, source reduction and use of adulticides (pyrethrum space spray and malathion-fogging) during a disease outbreak. Pyrethroids are widely used for personal protection in the form of repellents and insecticide treated materials [11], which provides effective protection against day biting Aedes. It has also been shown that window curtains and domestic water container covers treated with insecticide may reduce densities of dengue vectors to low levels and potentially affect dengue transmission [12]. In addition pyrethroids have been recommended by WHO for space spraying for Aedes control [13] due to rapid knockdown effect and less mammalian toxicity. However, the use of pyrethroids is being challenged by the rapid emergence of resistance, which needs to be monitored periodically to manage effective programmes to avoid or delay resistance in vector species. Key to this is, understanding of the mechanisms of resistance so that informed decisions can be made to select appropriate insecticides for effective control of target vector species.

One of the mechanisms of resistance in insects against DDT and pyrethroids is knockdown resistance (kdr) which is conferred by mutation(s) in the target site, the voltage gated sodium channel (VGSC). Several kdr mutations have been reported in many insects of agricultural and medical importance including Ae. aegypti. In Ae. Aegypti, eleven non-synonymous mutations at nine different loci have been reported [14]–[17], amongst which mutations at three loci, i.e., Iso1011 (I→M/V) and Val1016 (V→G/I) in domain II and F1534 (F→C) in domain III are most commonly reported as contributing to pyrethroid resistance [14]–[22]. The most common kdr-mutations L1014F/S reported in many insects of agricultural and medical importance is not yet found in Ae. aegypti possibly due to codon constraint [23]. Although widespread in Southeast Asia and Latin America, the presence of kdr mutations has yet to be established in India. Here we report the presence of two kdr mutations, F1534C and a novel mutation T1520I, in an Indian Ae. aegypti population.

Vector control is the only option for suppression of Ae. aegypti-borne dengue and chikungunya infections in the absence of vaccine or drugs. Several pyrethroids have been recommended by WHO for use in space spray against Aedes [13]. Though in India pyrethroids are being extensively used in malaria control programme, their use in urban areas is limited to space spraying of pyrethrum and fogging with malathion. However, pyrethroid-based household anti-mosquito gadgets (liquid vaporizer, mats, coils) are extensively used as personal protectants against mosquito nuisance. Use of these devices may be contributing to resistance in Ae. aegypti in Delhi. Insecticide susceptibility tests carried out in India by several authors prior to the year 2014 did not reveal pyrethroid resistance, though they were found to be resistant to DDT [30]–[33]. Only in one case, 2% survival was recorded in Aedes aegypti on exposure to diagnostic concentration of deltamethrin in a strain from Jharkhand, India [30]. Very recently, for the first time in India, resistance to pyrethroids has been reported from Assam state [34].

In the absence of baseline insecticide susceptibility data for Indian Ae. aegypti or universally acceptable discriminating dose for Ae. aegypti, we used 4% DDT, 0.05% deltamethrin and 0.75% permethrin papers for bioassays, the most frequently cited doses in recent publications [30]–[31], [34]–[40] to facilitate easy comparison. Previous published data from Delhi showed that Ae. aegypti was 100% susceptible to even lower doses of insecticides, i.e., 0.025% deltamethrin and 0.25% permethrin [31]. Less than 80% mortalities of mosquitoes at higher doses (which are 2-fold and 3-fold respectively) confirm resistance against these insecticides.

The extensive use of insecticides for vector control has raised concern over the development of insecticide resistance and adverse effects on the environment and human health [41]. Genes conferring insecticide resistance have been spreading in vector populations, particularly in vectors of pathogens causing malaria and dengue [42]. The fact that dispersal of Aedes may be more rapid than other mosquitoes due to transportability of dried, but viable eggs through containers, a single resistance mechanism can spread rapidly. Knockdown resistance (kdr) is one of the mechanisms of DDT and pyrethroid resistance in insects. It is conferred by amino acid substitution(s) in the target site (VGSC) resulting in reduced sensitivity of the target site. A number of mutations have been reported in the VGSC of Ae. aegypti across Latin America and Southeast Asia amongst which V1016G/I, I1011M/V and F1534C [14], [18], [21], [22], [15], [43] are known to confer resistance. F1534C has been reported from Latin America [44], [22], [45] and Southeast Asia [15], [43], [46], and shown to confer resistance against DDT and pyrethroids. In our study we provide evidence that this mutation confers a high level of protection against DDT and relatively low protection against deltamethrin. However, we failed to show significant protection against permethrin. Our failure to establish association of F1534C with permethrin resistance is contrary to findings by Harris et al. (2010) [22] and Yanola et al., (2011) [15]. Our result is also contradictory to the findings of Du et al., (2013) [47] who were able to demonstrate that F1534C reduced the channel sensitivity to permethrin but not against deltamethrin when expressed in Xenopus oocyte. Failure to establish association of F1534C with permethrin resistance is surprising and needs to be further investigated. It may be possible that the dose of permethrin (0.75%) used for discrimination of kdr-resistant mosquito in the Indian population is too high that might have killed kdr-resistant mosquitoes. Another possible reason for such discrepancy may be due to the presence of some other linked mutations. For example, F1534C has shown to be strongly associated with permethrin in Grand Cayman [22] where another mutation V1016I co-existed. It is possible that protection against permethrin in Grand Cayman may be due to the combined effect of F1534C and V1016I. It is interesting to explore such association because such linkage has been shown in Brazil, where V1016I was always associated with F1534C [44]. To know the exact role of any particular kdr mutation, one should perform such association studies using laboratory lines of mosquitoes characterized for complete VGSC sequence.

In this study we explored a novel mutation T1520I in an Indian Ae. aegypti population. Its potential role in resistance to insecticides is yet to be ascertained. However, since this mutation has always been found in association with F1534C mutation (D′ = 1), it may be a compensatory mutation to reduce the fitness cost from possible deleterious effects of F1534C mutation, though it has been shown through laboratory experiments that Ae. aegypti homozygous for F1534C does not have reduced fitness [48]. However, its additive effect on protection against DDT and pyrethroids cannot be ruled out. We also observed that 1520I is associated with 1534C, but not vice versa explaining the low r² (0. 039), which reflects a very low frequency of T1520I as compared to F1534C. Whether haplotype 1534C/1520I is under positive selection remains to be established. Interestingly a similar linkage association is found in the Brazilian population where 1016I is associated with 1534C, but not vice versa [44]. These different associations in different geographical locations indicate that the most likely association of T1520I in India and V1016I in Brazil with F1534C are under positive selection. Linss et al. 2014 [44], noted a progressive increase of the Na_V^R2 haplotype (double mutant, F1534C with V1016I) from year 2002 through 2012 and concluded that it is likely to be the most favourably selected allele. Linkage of kdr mutations is very common in Ae. aegypti. Co-segregation has been shown between 1016G with D1794Y [17], 1016G with 989P [49] and 1016G with 1534C [22], [46]. Whether positive selection of such linkage associations is due to additive role in protection against insecticides or due to compensatory advantage, is worth investigating. Since novel mutation T1520I is tightly linked to F1534C and homozygotes are found in very low frequency, the exact role of this novel mutation could not be established.

Our result shows that F1534 genotypes show significant deviation from Hardy-Weinberg equilibrium in all populations (p<0.0001) except in South Delhi-II. Initially we thought that this might be due to discrepancy in allele specific PCR genotyping, which often fails to prevent non-specific annealing during PCR extension. However, when we carried out genotyping using highly specific PCR-RFLP method, there was no change in HWE parameter for F1534 alleles. Surprisingly, T1520 genotypes in the same group of mosquitoes were in perfect HWE (p = 0.99). The possible explanation for such a deviation may be the presence of heterogeneous populations or gene duplication. Further studies are required to resolve this issue.

Knockdown resistance, which is known to confer cross-resistance to DDT and pyrethroids cannot be monitored through routine insecticide susceptibility tests and requires a sensitive and reliable molecular method of detection. PCR-based methods, allele specific PCR in particular, are most widely used method for this purpose. The specificity of allele specific PCRs which are based on single nucleotide polymorphism is often compromised due to the fact that single base mismatch often does not prevent extension [50] and leads to non-specific amplification [26], [51]. Yanola et al., (2011) reported an overestimation of 1534C frequency by 1.8% while using allele specific PCR [26]. In the present study, non-specific amplification was evident in the allele specific PCRs we employed for identification of various kdr alleles located at different loci. We therefore opted to develop a PCR-RFLP method for the identification of F1534 and T1520 alleles, which is presumed to be specific owing to the fact that restriction enzymes are highly specific. The sequencing of representative samples of PCR-RFLP genotyped samples (n = 20) showed 100% specificity of the assay. An additional advantage of the PCR-RFLP over allele specific PCR was that a single PCR amplicon could be used for detection of four alleles present at two loci since two mutations T1520I and F1534C are in proximity, whereas for allele specific PCR assays normally two PCR reactions are required to be performed for detecting four alleles at two loci.

The emergence of pyrethroid resistance in Indian Ae. Aegypti associated with the presence of the F1534C-kdr mutation is a threat to the success of pyrethroid-based Aedes control and necessitates countrywide monitoring of insecticide resistance and mapping the distribution of F1534C and T1520I mutations. Though F1534C mutation is shown to be associated with DDT and pyrethroids, the role of novel mutation T1520I still remains to be investigated.