Recording the geographic distribution and identifying the possible routes of expansion of both arthropod-borne diseases and their associated vectors is essential information for surveillance as well as the execution and elaboration of control strategies [1].

In Brazil, the expansion of the geographic range of Lutzomyia longipalpis (Lutz & Neiva), the principal vector of Leishmania (Leishmania) infantum chagasi (Cunha & Chagas), and its adaptation to domiciliary habitats in the urban areas throughout Brazil has resulted in an increase in the incidence of both canine and human visceral leishmaniasis (VL) in the last 25 years [2–6]. According to the Brazilian Ministry of Health, in the period from 2009 to 2011, there were 251 municipalities classified as having moderate (mean number of human cases > = 2.4 and < 4.4) or intense (mean number of human cases > = 4.4) VL transmission in the country [7].

Before 1998, São Paulo State was considered free of autochthonous cases of this zoonotic disease and records of the vector’s presence were restricted to some rural areas of municipalities in the Northeast region of the state [8]. Two human cases had been reported in Greater São Paulo, but possible reservoirs and vectors were not described [9]. The first record of L. longipalpis in an urban area in São Paulo State was in 1997 from Araçatuba in the West of São Paulo State [8]. Canine and autochthonous human cases occurred in the same municipality in 1998 and 1999 respectively [10]. Since then, the appearance of L. longipalpis in urban areas of other municipalities has been linked to an increase in both canine and human visceral leishmaniasis within the State [11, 12]. From 1999 to April 2013, São Paulo State recorded 2204 autochthonous human cases of disease, with 192 deaths [13]. In São Paulo State, 18 municipalities were classified as having moderate or intense transmission in the period from 2010 to 2012 [11].

Based on genetic and behavioural studies it is generally accepted that L. longipalpis is a species complex, but it is unclear how many members there are and how they are related [14, 15]. Chemical, behavioural and ecological analysis of male produced sex pheromones suggests that L. longipalpis is a complex of at least four different, reproductively isolated members [16–19]. In Brazil two of these are represented by members where the males produce either 3-methyl-α-himachalene [20], a novel bicyclic methylsesquiterpene (C16; mw 218) found in Jacobina, Bahia State, or (S)-9-methylgermacrene-B [21], a novel monocyclic methylsesquiterpene (C16; mw 218) that is widely distributed throughout Brazil but typically represented by L. longipalpis from Lapinha Cave, Minas Gerais State. The other two members of the complex produce novel diterpenes, cembrene-1 and cembrene-2 (C20; mw 272) and are represented by the Sobral-2S population from Ceará State and the Jaíbas-1S population from Minas Gerais State [22]. Two of these chemotype populations, (S)-9-methylgermacrene-B and cembrene-1, have been identified in São Paulo State [23].

Considering the remarkable epidemiological differences between the two municipalities of Araçatuba and Espírito Santo do Pinhal (mainly the number of human cases notified as well as the abundance, and chemotype of the L. longipalpis population present in each urban area), Casanova et al (2006) [23] suggested that the (S)-9-methylgermacrene-B and cembrene-1—chemotype populations had different vectorial capacities. If this is true then it is important to have more detailed information on the distribution of the chemotypes to produce more accurate risk maps and to direct more effective control programs. With this in mind, the present study is aimed at determining the chemotypes of a greater number of L. longipalpis populations from different regions of São Paulo State.

Before 1997, L. longipalpis had been found only in the rural areas of six municipalities of São Paulo State, all of which are in the East and Northeast regions of the state. The first report of the vector in an urban area was in 1997 in the municipality of Araçatuba, in the Western region near the border with Mato Grosso do Sul State (Fig. 2). From 1998 to June 2014, L. longipalpis has been reported in another 164 municipalities (Fig. 2, S1 Database). During this period, between 2 and 21 new municipalities per year reported the presence of L. longipalpis, with more than 45 reporting the presence of the vector in the last 3 years (Fig. 3). The biggest expansion in the distribution of L. longipalpis happened in the western part of Sao Paulo where 146 municipalities have recorded their presence in urban areas during this 17.5 year period.

The spatial and temporal distribution of L. longipalpis and human and canine cases in general shows that the presence of the vector preceded the canine cases, and these in turn preceded the human cases (Figs. 2, 4, 5, S1 Database). Up until 2014, there have been 105 municipalities with canine and/or human VL transmission. The majority of these municipalities (93.3%), are placed in the Western part of São Paulo State, and the cases show an expansion route in a Southeasterly direction, towards the Central region, and from there, an expansion both to the North and the South (Figs. 4 and 5). In 71 of these municipalities, there has been both human and canine cases, in 23 only canine transmission and in five only human cases (Figs. 4 and 5). It is interesting to note that in the East region, L. longipalpis has been found in 25 municipalities only, with canine cases reported in seven, and no known human cases.

The chemical analysis of all samples of L. longipalpis males from 11 municipalities in the West region (Araçatuba, Promissão, Bauru, Dracena, Adamantina, Oswaldo Cruz, Jales, Presidente Prudente, Marília, Lourdes and Salmourão) have been shown to contain (S)-9-methylgermacrene-B (Fig. 6). On the other hand, all samples of male L. longipalpis collected in eight municipalities of the Eastern region (Espírito Santo do Pinhal, Socorro, Salto, Indaiatuba, Campinas, Águas da Prata, Sorocaba and Votorantim) contained cembrene-1 (C-20) (Fig. 6). In the municipality of São Pedro, situated in Central region of the State, it was found a (S)-9-methylgermacrene-B producing population and in addition, two flies that produced both (S)-9-methylgermancrene-B, and cembrene-1.

The argument in favour of the hypothesis of the recent introduction of L. longipalpis into the Western region of São Paulo State can be supported by its absence, for decades, from various sporadic rural collections of sand flies [28–30]. These collections were done in areas where autochthonous cases of cutaneous leishmaniasis, caused by Leishmania (Viannia) braziliensis, had been reported. The contrary hypothesis, that L. longipalpis has always been there, hidden in the primitive natural vegetation habitat, could be supported because of the existence of several areas where collections have never been done [28–30] Therefore, there are gaps in our knowledge of its distribution and in future, it would be interesting to collect samples from the few natural vegetation areas of São Paulo State.

It is very difficult to pinpoint the year when L. longipalpis first reached the urban areas of the municipalities in the Western region, however it is likely that, when detected for the first time in the municipality of Araçatuba, in 1997 [8], L. longipalpis was already present in the urban areas of surrounding municipalities, as the species was found there in the first collections of the following year. From that point on, the spatial and temporal distribution leaves no doubt as to the west-east progression (as far as the central region of the state). This progression can be inferred from the annual urban entomological collection results, which showed that in various municipalities the vector detection only occurred after successive annual negative collections. It is possible that factors related to the economic development of the country, such as the increase in transportation of goods and people by road and railway, could have been responsible for the dispersion of the vector and, consequently, the expansion in the vector’s range in the West.

The higher number of municipalities from the West of the state which reported the presence of L. longipalpis for the first time since 1997 indicates a rapid inter-municipality dispersion rate. The greatest number of municipalities reported in 2012 and 2013 (21 and 14, respectively) is a further indication of this ongoing, fast expansion. The fact that the expansion of canine and human cases through the Western São Paulo has followed the same dispersion route as that of the vector with a temporal delay cannot be considered to be merely coincidental because it has long been observed that in VL epidemiology the vector precedes canine and subsequently human cases [31]. The lower number of municipalities notifying the presence of the vector in the East region of the state, in contrast to the West, does not show a recognisable dispersion route. Spread of the disease is more likely therefore to be due to the expansion of urban areas into rural or wild areas. This hypothesis is further supported by the observation that L. longipalpis was only found exclusively in rural habitats in nine of the 25 studied municipalities. In the other 16 municipalities, L. longipalpis was found in both rural and urban areas in four, and in periurban areas (i.e. those that have the characteristics of rural areas) in 12 municipalities.

It is clear that there are two distinct epidemiological patterns of VL in these two regions of São Paulo State. In the western region it is defined by the occurrence of human cases [12], frequent high prevalence of canine cases [32, 33], and a greater number of municipalities where L. longipalpis is present. Generally, a great number of flies is frequently found in both manual and CDC light trap collections carried out in peridomiciliary environments associated with food sources, such as chickens and dogs [33, 34]. In this area, all the males analysed have been shown to be the (S)-9-methylgermacrene-B chemotype population, including those collected in the 6 of the 18 municipalities currently classified as having moderate or intense transmission in the period from 2010 to 2012. In contrast, the eastern region, can be characterized by the absence of notified human cases—even where the presence of L. longipalpis and canine cases have been reported for at least 12 years—low prevalence in dogs and a smaller number of municipalities where the vector is present. The populations of sand flies are generally low in abundance in manual and CDC light trap collections carried out in peridomiciliary and rural environments associated with the feeding sources, such as chickens and dogs [35]. All samples of males analysed were the cembrene-1 chemotype.

These observations support the hypothesis of Casanova et al [2006] [23] which proposes that the (S)-9-methylgermacrene-B chemotype population has a greater vectorial capacity than the cembrene-1 chemotype in São Paulo State. Differences in ecological parameters of the vector capacity (e.g. vector abundance, survival, host feeding pattern and blood feeding rate) could vary between the two chemotype populations. Furthermore, susceptibility and coevolutionary interactions with Leishmania genotypes, which can influence Leishmania transmission, are parameters involved in vectorial competence and can vary between different species of L. longipalpis complex [15, 36, 37]. It is interesting to note that the two main genetic clusters of L. i. chagasi, identified by multilocus microsatellite typing, isolated from dogs from Northwest and Southeast regions of the São Paulo State [38] show distribution coinciding with the two L. longipalpis chemotype populations distribution presented here. The present study indicates that the chemotype of L. longipalpis populations as well as the effect of spatial and temporal environmental heterogeneity (reviewed in Belo et al 2013 [39]), should also be considered when explaining the variety of eco-epidemiological transmission scenarios in São Paulo State. However, it is also important to mention that the available data for pheromone types populations from municipalities of other states of Brazil and classified by the Brazilian Ministry of Health as having moderate and intense transmission of VL in the period from 2009 to 2011, shows that in three of these municipalities (Marajó-PA, Natal-RN, Pancas-ES) the chemotype population is cembrene-1, in two (Terezina-PI, Campo Grande-MS) it is (S)-9-methylgermacrene-B chemotype, and in one (Sobral-CE) both occur [7, 15]. Further studies are required to access the parameters of vectorial capacity of the longipalpis species complex.

The (S)-9-methylgermacrene-B, distributed throughout São Paulo State’s western region has previously been found and characterized in males from Lapinha Cave-MG [21] and later in populations from Sobral-CE, Terezina-PI, Campo Grande-MS, Barra de Guaratiba-RJ, Montes Claros-MG and Araçatuba-SP [15, 19, 23, 40]. The diterpene (C-20) found in populations from municipalities of the East region of the state was previously found and characterized as cembrene-1 in L. longipalpis from Sobral-CE, and later also found in populations from Marajó-PA, Natal-RN, Estrela-AL, Jaíba-MG, Pancas-ES and Espírito Santo do Pinhal-SP [15, 19, 23]. The presence of a cembrene-1 population in São Paulo State is the southernmost extension of this chemotype.

Based on the results of our present study we suggest that the L. longipalpis cembrene-1 populations are of rural origin and native of the Eastern region of the São Paulo State, while (S)-9-methylgermacrene-B is an introduced chemotype population. Although L. longipalpis has been found in urban areas of several municipalities of Mato Grosso do Sul State [41], we are not aware of any publications on L. longipalpis distribution through time in this State. However, although human cases are not a good space-time indicator of parasite circulation, the occurrence of the first human autochthonous case in a municipality usually indicates that the vector and the canine transmission were already established in the area. The West-to-East expansion of human VL in Mato Grosso do Sul was properly demonstrated by Correa-Antonialli et al (2007) [42] who pointed to the construction of the Bolivia-Brazil gas pipeline as a possible cause for the VL time and space expansion. This same hypothesis was considered to explain the spread of the canine and human disease in the west region of São Paulo [12, 38]. Finding the same pheromone type in males in the same temporal expansion route from West to East in São Paulo State may also support the hypothesis that the (S)-9-methylgermacrene-B L. longipalpis chemotype has been introduced from Mato Grosso do Sul.

More samples of males from São Pedro, in the Central region of São Paulo State, should be analysed to allow a better understanding of the possible presence and distribution of sympatric populations of the two pheromone chemotypes. Molecular and behavioural analyses such as those done by Araki et al (2009, 2013) [15, 43] may also help to clarify this question.

Information on the dispersion route and distribution of L. longipalpis chemotype populations is essential to understand the epidemiological patterns observed in São Paulo State. It may be used to identify areas at risk and consequently define priorities for control measures. In addition, identifying the distribution of the different chemotype populations is helpful in the application of appropriate synthetic male sex pheromone, in pheromone-baited traps or other appropriate “attract-and-kill” approaches [40, 44–49].