The role of bats as reservoirs for viral pathogens—including several responsible for severe human disease—has received increasing attention in recent years [1]. The extent to which this pattern is mirrored by bats’ abilities to host and transmit other zoonotic agents, including bacteria, is less widely acknowledged. Bats have been confirmed as asymptomatic reservoirs for several species of gram-negative Bartonella bacteria in localities as wide-ranging as the United Kingdom [2], Kenya [3], Guatemala [4], Peru [5], Taiwan [6], Nigeria [7], and Puerto Rico [8]. Bartonella spp. infect erythrocytes and epithelial cells of predominantly mammalian hosts, and some are known to cause zoonotic disease (bartonellosis) in humans. Most recently, bats in the Northern Hemisphere have been implicated as hosts for the human pathogen, Bartonella mayotimonensis, although the mechanism of transmission between bats and humans remains unclear [9]. Bartonella spp. are frequently transmitted via arthropod vectors [10] and have been identified in several bat ectoparasites, including 19 bat fly species (Diptera: Hippoboscoidea: Nycteribiidae and Streblidae) [11,12]. However, the presence of Bartonella spp. within these arthropods may simply reflect their ingestion of host blood, and vector transmission of Bartonella between bats has yet to be confirmed via experimental trial or controlled field study. Nonetheless, phylogenetic analyses of global bat fly-Bartonella-bat associations demonstrate Bartonella spp. similarities across bat hosts and ectoparasites [12], suggesting that bat flies might play a vector role in transmission. To elucidate this relationship, we examined Bartonella prevalence in two sympatric Madagascar fruit bat species—one containing bat flies and fleas and one in which ectoparasites were conspicuously absent. Here we report the presence of closely related Bartonella genotypes in Madagascan fruit bats (Eidolon dupreanum) and their associated bat flies (Nycteribiidae) in Madagascar. We simultaneously report the absence of Bartonella spp. in bat fleas (Thaumapsylla sp.) of E. dupreanum, in addition to the concomitant absence of both ectoparasites and Bartonella in sympatric Madagascan flying foxes (Pteropus rufus).

Seven of 24 (29.2%) Eidolon dupreanum sampled from Angavobe cave and 20 of 23 (87%) E. dupreanum sampled from Angavokely cave were found to host Cyclopodia dubia (Nycteribiidae) bat flies. Ten of those 23 (43.5.1%) Angavokely E. dupreanum also hosted Thaumapsylla sp. fleas (Table 1). Both frequency of bat fly and flea hosting varied significantly by roosting site, via analysis by chi-squared tests of independence (bat fly: X² = 13.768, df = 1, p = 0.0002; flea: X² = 10.7863, df = 1, p = 0.001) and Fisher’s exact tests (bat fly: p = 8.828e-05; flea: p = 0.0002). Two of 2 (100%) bat flies processed from Angavobe and 15 of 17 (88.2%) bat flies processed from Angavokely were considered positive for Bartonella DNA by sequence, although all bat flies processed were Bartonella spp. positive by PCR alone. None of the six Thaumapsylla fleas processed were positive for any Bartonella target gene. The presence of Thaumapsylla sp. at the Angavokely site represents the first geographic record for Madagascar; this genus is known from Eidolon spp. elsewhere [16].

Blood samples from eight of 24 (33.3%) Angavobe E. dupreanum and thirteen of 23 Angavokely (56.5%) E. dupreanum were positive for Bartonella DNA by PCR confirmed with sequence for one or more genes (Table 1). Bartonella spp. prevalence did not vary significantly between Angavobe and Angavokely roosting sites as indicated by a chi-squared test for independence (X² = 1.7029, df = 1, p-value = 0.1919) and Fisher’s exact test (p-value = 0.1468). In Angavobe, bats demonstrated both singular infections with Bartonella spp. and with bat flies, as well as simultaneous co-infection with bat flies and Bartonella spp. (Fig. 2). In Angavokely, E. dupreanum individuals hosted every possible combination of bat fly/flea/Bartonella spp. infection and co-infection save for singular flea infestations in the absence of other pathogens (Fig. 2). It should be noted that, prior to processing, bats were housed together with others from the same sample site in wooden transport cages, and ectoparasite sharing among individuals was easily facilitated.

No ectoparasites were recovered from either the 12 Pteropus rufus examined at the Marovitsika site or the 17 P. rufus sampled at the Ambakoana site (Table 1). As with ectoparasites, none of the 29 P. rufus samples (12 from Marovitisika, 17 from Ambakoana) were positive for Bartonella spp. by either molecular target (Table 1).

All Bartonella spp. sequences from E. dupreanum bats and associated C. dubia bat flies nested within or close to known major Bartonella lineages (Fig. 3) [17]. Although sequence data retrieved are insufficient to reach final Bartonella species identification, novel genotypes are present. Sequences (gltA) from sampled bats group with those retrieved from Cyclopodia bat flies.

The recent identification of bats as reservoirs for human pathogenic Bartonella mayotimonensis [9] validates further investigation of the zoonotic potential of Bartonella spp. in Chiropteran reservoirs. In Madagascar, insectivorous bats are known to roost in human residences, and both P. rufus and E. dupreanum are widely consumed as bushmeat, highlighting the extent of human-wildlife interface in the region [13].

In keeping with trends of persistent bacterial infection exhibited by bat-borne Bartonella elsewhere [3–5], we report high Bartonella spp. prevalence (57.4%) in a long-lived, cave-roosting E. dupreanum host (lifespan 10–20 years [13]). We correspondingly report no Bartonella infections in sympatric P. rufus, though our current sample size is too small to determine whether this absence is universal across the Madagascar population. Additionally, further study is needed to address whether these Bartonella spp. prevalence patterns are an artifact of phylogeny or ecology. The ability of Eidolon bats to serve as hosts for Bartonella spp. has now been documented in both tree-roosting [3] and cave-roosting environments—consistently in association with bat flies. P. rufus does not seem to host bat flies in Madagascar [18], although sampling has not been exhaustive enough to consider this absence a certainty. Tree-roosting Pteropus spp. are known to host bat flies throughout southeast Asia [19] and Australia [20], and investigation of Bartonella spp. infections in these populations will help address the relative influence of host genetic predisposition for Bartonella infection versus vector ecology.

In addition to pathogen prevalence in the host, we report Bartonella spp. infection in bat flies (Cyclopodia dubia) of E. dupreanum, simultaneous with Bartonella DNA absence in flea ectoparasites (Thaumapsylla sp.) of those same bats. Fleas are the confirmed vector for Bartonella henselae, the causative agent in cat scratch fever [21], and fleas of bats have been previously reported in association with Bartonella DNA [9,22]. In our study, both bat flies and fleas were host-specific and likely consumed host blood, although only flies tested positive for Bartonella spp., suggesting that the mechanisms by which arthropods host and transmit pathogens vary and impact their functionality as vectors. Sampling of flea ectoparasites was not extensive enough to assess the true extent of their ability, or lack of ability, to transmit Bartonella spp., and further experimental studies of the vector potential of both bat flies and fleas for Bartonella is warranted.

Finally, observed differences in the frequency of ectoparasite burden between sample sites for E. dupreanum indicated significantly higher rates of ectoparasite infection with both flies and fleas in Angavokely vs. Angavobe. These differences could result from ecological variation in both host density and/or climate between the two cave roosts. More extensive spatial sampling, in conjunction with climactic monitoring, in other E. dupreanum roost sites of varying size, temperature, and humidity across Madagascar will help elucidate habitat thresholds for ectoparasite invasion. In particular, sampling of E. dupreanum in reported tree roosts in central Madagascar will shed light on the extent to which roosting behavior limits bats’ abilities to support ectoparasites in this system [13]. If Bartonella spp. are, indeed, transmitted by bat fly vectors, such findings will have important implications for our understanding of the distribution, prevalence, and transmission dynamics of a potentially zoonotic pathogen.