Seasonal pulses of Marburg virus circulation in juvenile Rousettus aegyptiacus bats coincide with periods of increased risk of human infection

Abstract

Marburg virus (family Filoviridae) causes sporadic outbreaks of severe hemorrhagic disease in sub-Saharan Africa. Bats have been implicated as likely natural reservoir hosts based most recently on an investigation of cases among miners infected in 2007 at the Kitaka mine, Uganda, which contained a large population of Marburg virus-infected Rousettus aegyptiacus fruit bats. Described here is an ecologic investigation of Python Cave, Uganda, where an American and a Dutch tourist acquired Marburg virus infection in December 2007 and July 2008. More than 40,000 R. aegyptiacus were found in the cave and were the sole bat species present. Between August 2008 and November 2009, 1,622 bats were captured and tested for Marburg virus. Q-RT-PCR analysis of bat liver/spleen tissues indicated ~2.5% of the bats were actively infected, seven of which yielded Marburg virus isolates. Moreover, Q-RT-PCR-positive lung, kidney, colon and reproductive tissues were found, consistent with potential for oral, urine, fecal or sexual transmission. The combined data for R. aegyptiacus tested from Python Cave and Kitaka mine indicate low level horizontal transmission throughout the year. However, Q-RT-PCR data show distinct pulses of virus infection in older juvenile bats (~six months of age) that temporarily coincide with the peak twice-yearly birthing seasons. Retrospective analysis of historical human infections suspected to have been the result of discrete spillover events directly from nature found 83% (54/65) events occurred during these seasonal pulses in virus circulation, perhaps demonstrating periods of increased risk of human infection. The discovery of two tags at Python Cave from bats marked at Kitaka mine, together with the close genetic linkages evident between viruses detected in geographically distant locations, are consistent with R. aegyptiacus bats existing as a large meta-population with associated virus circulation over broad geographic ranges. These findings provide a basis for developing Marburg hemorrhagic fever risk reduction strategies.

Figure 1. Bayesian phylogeny of full length Marburg genome.

Phylogenetic results from a Bayesian analysis on full-length Marburg virus genome sequences from 12 Marburg bat isolates, 3 recent Ugandan human isolates from the two Kitaka miners (01Uga 2007, 02Uga 2007), and the Dutch tourist (01Uga/Net 2008), as well as 45 historical isolates (Table S2 for GenBank accession numbers). Posterior probabilities above .50 are shown above the appropriate nodes. Marburg virus sequences from human cases from Kitaka mine (Uganda 2007) in are in orange, sequences from human cases from Python Cave (2008 Uganda) are in blue, sequences from Kitaka Mine bats are in red, and sequences from Python Cave bats are in green.

Figure 2. Bayesian phylogeny of Marburg NP and VP35 genes.

Phylogenetic results from a Bayesian analysis on concatenated NP and VP35 sequence fragments obtained from bat specimens, historical isolates (45), and the recent Ugandan human samples (01Uga 2007, 02Uga 2007, 01Uga/Net 2008) as well as the American tourist (01Uga/USA 2007), for which there was no isolate, only partial Marburg virus sequence (Table S2 for GenBank accession numbers). Sequences 846QBat_Uga_2009, 849QBat_Uga_2009, 1079QBat_Uga_2009, 1261QBat_Uga_2009, 1328QBat_Uga_2009, and 1511QBat_Uga_2009 represent NP only. Posterior probabilities above .50 are shown above the appropriate nodes. Marburg virus sequences from human cases from Kitaka mine (Uganda 2007) in are in orange, sequences from human cases from Python Cave (2008 Uganda) are in blue, sequences from Kitaka Mine bats are in red, and sequences from Python Cave bats are in green.

Figure 3. Percent active infection among older and younger juvenile bats and adults.

(A) Histogram showing the percent of juvenile bats from Kitaka Mine and Python Cave actively infected (Q-RT-PCR+) with Marburg virus during breeding and birthing seasons. (B) Histogram of the percent of adult bats from Kitaka Mine and Python Cave actively infected (Q-RT-PCR+) with Marburg virus during breeding and birthing seasons.

Figure 4. Increases in seasonal risk to human health.

Historical spillover events (colored circles on X axis) compared to predicted seasonal levels of PCR+ juveniles (sinusoidal curve). The amplitude of the curve is based on average PCR+ juveniles experimentally determined during birthing (12.4%) and breeding (2.7%) seasons. Large light green vertical rectangles represent the proposed approximate three month seasons of increased risk based on the average level of juvenile infected bats at peak times of encompassing birthing (February and August) and breeding (May and November). Large gray arrows depict the twice yearly influx of newly autonomous juvenile bats born in the prior birthing season. The influx begins at the approximate time of the juvenile's independence from their mothers.