Whole blood transcriptomics analysis of Indonesians reveals translocated and pathogenic microbiota in blood

Abstract

Pathogens found within local environments are a major cause of morbidity and mortality. This is particularly true in Indonesia, where infectious diseases such as malaria or dengue are a significant part of the disease burden. Unequal investment in medical funding throughout Indonesia, particularly in rural areas, has resulted in under-reporting of cases, making surveillance challenging. Here, we use transcriptome data from 117 healthy individuals living on the islands of Mentawai, Sumba, and the Indonesian side of New Guinea Island to explore which pathogens are present within whole blood. We identified diverse microbial taxa in RNA-sequencing data from whole blood but found no evidence of a consistent core microbiome across the Indonesian cohort. Yet, Flaviviridae and Plasmodium stood out as the most predominantly abundant taxa, particularly in samples from the easternmost island within our Indonesian dataset. The high prevalence of Plasmodium, the pathogen responsible for malaria, aligns with epidemiological data showing that the Indonesian part of New Guinea has the country's highest malaria rates. We also compare the Indonesian data to two other cohorts from Mali and UK and find a distinct microbiome profile for each group. Higher levels of dissimilarity were found between UK cohort (urban) compared to Indonesian and Malian cohorts (rural), where the former also have significantly lower within-population dissimilarity. This study provides a framework for RNA-seq as a possible retrospective surveillance tool and an insight to what makes up the transient human blood microbiome.

Fig 1. The blood metatranscriptome of the Indonesian populations.

A) Circular barplot showing relative abundance (as percentage of reads) of the detected taxa within each individual in the Indonesian dataset, resolved at the family level. Bacteria are shown in blue, eukaryotes in orange, and viruses in green. KOR = Korowai; MTW = Mentawai; SMB = Sumba. Taxon labels include both phylum and family information. Empty bars represent individuals with no detected non-human RNA reads. B) Principal component analysis of the CLR-normalised taxa abundance data at the phylum level. Plotting shapes indicate population while ${\log }_{10}$ Plasmodiidae abundance is indicated in orange and C) green for Flaviviridae.

Fig 2. Blood microbiomes are not statistically different between island populations.

A) Volcano plot of BH-adjusted p-values from Welch’s t-test and the effect size for each taxa at the phylum level, in Mentawai versus Korowai B) Sumba versus Korowai and C) Sumba versus Mentawai. D) Estimates of Shannon and E) inverse Simpson diversity within each population (median in blue text). KOR = Korowai; MTW = Mentawai; SMB = Sumba.

Fig 3. Relative abundance of the top 20 taxa within the Indonesian, Malian, and UK dataset at the superkingdom, phylum, and family level.

Bacteria are shown in blue, eukaryotes in orange, and viruses in green.

Fig 4. Taxa differences between Indonesian individuals and other global populations.

A) Volcano plot of BH adjusted p-values from Welch’s t-test for each phyla in Malian versus Indonesian individuals and B) UK versus Indonesian individuals. Taxa with an FDR-corrected p-value below 0.05 (above red threshold line) are coloured by superkingdom (blue: bacteria; green: viruses). C) Principal components (PCs) 1 and 2 of the CLR-normalised taxa abundance data at the phylum level, colored by population. D) PCs 3 and 4 of the same data colored by Plasmodiidae and E) Flaviviridae loads. F) Bray-Curtis distance estimates for Indonesian, Malian, and UK population comparisons at the phylum level (mean in red text).