Interconnected microbiomes and resistomes in low-income human habitats

Abstract

Antibiotic-resistant infections annually claim hundreds of thousands of lives worldwide. This problem is exacerbated by exchange of resistance genes between pathogens and benign microbes from diverse habitats. Mapping resistance gene dissemination between humans and their environment is a public health priority. Here we characterized the bacterial community structure and resistance exchange networks of hundreds of interconnected human faecal and environmental samples from two low-income Latin American communities. We found that resistomes across habitats are generally structured by bacterial phylogeny along ecological gradients, but identified key resistance genes that cross habitat boundaries and determined their association with mobile genetic elements. We also assessed the effectiveness of widely used excreta management strategies in reducing faecal bacteria and resistance genes in these settings representative of low- and middle-income countries. Our results lay the foundation for quantitative risk assessment and surveillance of resistance gene dissemination across interconnected habitats in settings representing over two-thirds of the world's population.

Extended Data Figure 1

Overview of study and methods. a, Location and overview of study sites in El Salvador and Peru. RES photographs by Giordano Sosa-Soto and Melissa Mejía-Bautista, PST photographs by Pablo Tsukayama. b, AR markers and OTUs detected vs. number of samples interrogated by whole metagenome and 16S sequencing by habitat in RES and PST. c, Proportion of metagenomic libraries (n=67), all AR proteins identified from functional metagenomic selections (n=1100), and novel AR proteins identified from functional metagenomic selections (n=121) originating from each microbial habitat. The percent of total libraries/proteins in that category originating from each microbial habitat is listed above the bar. For all AR proteins and novel AR proteins, the total sums to >100% due to proteins identified in more than one habitat. The number of novel AR proteins vs. libraries screened was significantly different than expected compared to the total for human and latrines (Chi-squared test, p< 0.005).

Extended Data Figure 2

Human fecal and environmental microbiota from RES and PST. Microbiota are colored by habitat. a, PCoA of Bray-Curtis distances between resistomes. (n = 86/10/16/30/4/27/7 for human/animal/latrine/soil/water/pre-treatment sewage/post-treatment sewage) Adonis R²=22.4%, p< 0.001. b, PCoA of weighted UniFrac distances between microbiota. (n = 105/14/36/84/22/30/13 for human/animal/latrine/soil/water/pre-treatment sewage/post-treatment sewage) Adonis R² = 41.9%, p<0.001. c, Procrustes transformation of taxonomic composition vs. resistome. Only samples interrogated with both methods were included (n=172). M²=0.360, p<0.001 (172 dimensions, 999 permutations).

Extended Data Figure 3

Phylogenetic composition of RES and PST human fecal microbiota and published microbiota from previous studies ^,,. a, b, e, f, RES vs. PST. (RES n = 60, PST n = 45) c, d, g, h, RES and PST vs. published human microbiota. (RES n = 60, PST n = 46, other n = 446; see Supplementary Table 14) a, PCoA of weighted UniFrac distances between RES and PST human fecal microbiota, colored by cohort. Adonis R² = 29.7%, p < 0.001. b, Taxa discriminating between RES and PST human fecal microbiota as determined by LEfSe. The phylogenetic tree includes all kingdom- to family-level taxa present in any sample. Colored taxa are discriminative between cohorts and have an LDA effect size of ≥ 4.0; they are colored by the cohort in which they have the highest abundance. Circle size is relative to the highest abundance in either cohort. c, PCoA of weighted UniFrac distances between RES and PST human fecal microbiota and published human fecal microbiota, colored by cohort. Cohorts are labeled by lifestyle and study (*, ^**, ^***). Adonis R² = 37.6%, p < 0.001. d, Taxa discriminating between host lifestyles for RES and PST and published human fecal microbiota as determined by LEfSe, effect size threshold 3.0. Discriminative taxa are colored by the host lifestyle in which they are most abundant. e-f, Relative abundances of microbial e, phyla and f, families in human fecal microbiota from RES and PST. * p<0.05, Wilcox test with Bonferroni correction. g-h, Relative abundances of microbial g, phyla and h, families in human fecal microbiota from RES and PST and published human fecal microbiota, by lifestyle. * p<0.05, Kruskal-Wallis test with Bonferroni correction. e-h, Only taxa with a mean relative abundance of ≥1% in one cohort/lifestyle are shown. Taxa are in order of increasing overall mean relative abundance. Error bars = s.d., center bars = median.

Extended Data Figure 4

RES and PST human fecal resistomes and comparison to the published datasets from . a-e, RES and PST resistomes, colored by cohort. (RES n = 42, PST n = 44) f-g, RES and PST vs. published human datasets, colored by cohort. (RES n = 42, PST n = 44, other n = 53; see Supplementary Table 15) a-c, Absolute abundances of AR a, categories, b, antibiotic targets, and c, mechanisms of action in human fecal resistomes from RES and PST. Only categories with a mean RPKM of >10 in one cohort are shown. Categories are in increasing order of overall mean absolute abundance. Abundances are plotted in log10 scale. *p<0.05, Wilcox test with Bonferroni correction. d, Number of AR proteins per RES and PST human fecal resistome. *p<0.05, non-parametric Student’s t-tests. e, PCoA of Bray-Curtis distances between RES and PST resistomes, with abundance-weighted coordinates of the top five most discriminative AR categories enriched in each cohort (squares, size proportional to overall abundance). Adonis R²=25.0%, p<0.001. f, PCoA of Bray-Curtis distances between human fecal resistomes from RES and PST and . Adonis R²=19.7%, p<0.001. g, Total reads mapping to AR markers per person (normalized by marker length) normalized by the total reads in that sample in RES and PST and published human fecal microbiota, by cohort. Includes both paired and unpaired reads. The overall distribution of normalized AR read depth was significantly different than expected (Kruskal-Wallis, p < 1 x 10⁻¹⁵). n.s., not significant. All other comparisons are p<0.05, Wilcox test with Bonferroni correction. a-d, f, Error bars = s.d., center bars = median.

Extended Data Figure 5

RES human fecal and environmental microbiota and resistomes. a-b, Relative abundances of microbial a, phyla and b, families in RES microbiota, by habitat. (n = 60/6/36/84/22 for human/animal/latrine/soil/water) Only taxa with a mean relative abundance of ≥1% in one habitat are shown. Taxa are in increasing order of overall mean relative abundance. * p<0.05, Kruskal-Wallis test with Bonferroni correction. c-d, Absolute abundances of AR c, categories and d, antibiotic targets in RES resistomes, by habitat. (n = 42/4/16/30/4 for human/animal/latrine/soil/water) Only categories with a mean RPKM of >10 in one habitat are shown. Categories are in increasing order of overall mean absolute abundance. Abundances are plotted in log10 scale. *p < 0.05, Kruskal-Wallis test with Bonferroni correction. a-d, Error bars = s.d., center bars = median.

Extended Data Figure 6

PST human fecal and environmental microbiota and resistomes. a-b, Relative abundances of microbial a, phyla and b, families in human fecal and sewage microbiota from PST, by stage. (n = 45/16/14/13 for human/street-access/influent/effluent) Only taxa with a mean relative abundance of ≥1% in one stage are shown. Taxa are in increasing order of overall mean relative abundance. * p<0.05, Kruskal-Wallis test with Bonferroni correction. c-d, Absolute abundances of AR c, categories and d, antibiotic targets in PST resistomes, by stage. (n = 44/14/13/7 for human/street-access/influent/effluent) Only categories with a mean RPKM of >10 in one stage are shown. Categories are in increasing order of overall mean absolute abundance. Abundances are plotted in log10 scale. * p<0.05, Kruskal-Wallis test with Bonferroni correction. a-d, Error bars = s.d., center bars = median.

Extended Data Figure 7

AR gene sharing across habitats. a, Highly cosmopolitan AR proteins. The prevalence of each AR protein in metagenomes from each microbial habitat is depicted for all proteins detected in six of the seven habitats (n=21). Detection was based on ShortBRED quantification of the protein in each metagenome. Prevalences for an AR protein are linked by lines of the same color. The shape of each point reflects the number of habitats in which it was found, as well as the minimum prevalence within each habitat. The legend lists the annotation for each protein. b, Protein sequences of AR genes isolated from functional metagenomic selections were clustered at 100% amino acid identity, and the number of metagenomic libraries, microbial habitats (e.g., human fecal, soil), and cohorts in which each unique protein (n=1100) was encoded were calculated across all members of the cluster. AR contigs (n = 1955) were clustered at 90% local identity to identify different genetic contexts, and the number of genetic contexts in which each unique protein was encoded was calculated across all contigs encoding a protein in that cluster. Spearman’s rho = 0.59, p < 2.2 x 10⁻¹⁶, number of genetic contexts vs. libraries; rho = 0.47, p < 2.2 x 10⁻¹⁶, number of genetic contexts vs. habitats; Wilcox test, p < 2.2 x 10⁻¹⁶, number of genetic contexts vs. cohorts (one or both).

Extended Data Figure 8

Mobilome analyses. a, PCoA of Bray-Curtis distances between RES and PST human and environmental resistomes, colored by habitat. (n = 86/10/16/30/4/27/7 for human/animal/latrine/soil/water/pre-treatment sewage/post-treatment sewage) Adonis R²=24.1%, p < 0.001. b, Procrustes transformation of taxonomic composition vs. resistome. Only samples interrogated with both methods were included (n=172). M²=0.493, p<0.001 (172 dimensions, 999 permutations). c, PCoA of Bray-Curtis distances between RES (n = 42) and PST (n = 44) resistomes, colored by cohort. Adonis R²=31.0%, p<0.001. d-f, RES human fecal and environmental microbiota and resistomes, colored by habitat. (n = 42/4/16/30/4 for human/animal/latrine/soil/water). d, PCoA of Bray-Curtis distances between resistomes. Adonis R²=32.0%, p<0.001. e, Observed AR proteins. * p<0.05, non-parametric Student’s t-tests, Bonferroni correction. f, Percentage of latrine, soil, and water resistomes attributable to human feces, as determined by SourceTracker. * p<0.05, pairwise Wilcox tests, Bonferroni correction. g-i, PST human fecal and sewage microbiota and resistomes, colored by stage. (n = 44/14/13/7 for human/street-access/influent/effluent). g, PCoA of Bray-Curtis distances between resistomes. Adonis R²=34.8%, p<0.001. h, Observed AR proteins. * p<0.05, non-parametric Student’s t-tests, Bonferroni correction. i, Percentage of sewage resistomes attributable to human feces at each sewage treatment stage, as determined by SourceTracker. * p<0.05, pairwise Wilcox tests, Bonferroni correction. Error bars = s.d., center bars = median.

Figure 1. RES and PST human fecal microbiota and resistomes versus global populations

a, PCoA of weighted UniFrac distances between RES (n=60) and PST (n=46) microbiota and published human fecal microbiota from^,, (n=446; see Supplementary Table 14), colored by host lifestyle. Adonis R²=15.4%, p<0.001. b, Number of AR proteins per person in RES (n=42) and PST (n=44) and (n=53; see Supplementary Table 15). Error bars = s.d., center bars = median. *p<0.05, non-parametric Student’s t-tests, Bonferroni correction.

Figure 2. Salvadoran rural agriculturalist (RES) human fecal and environmental microbiota and resistomes

a,c,e, Phylogenetic composition (n = 60/6/36/84/22 for human/animal/latrine/soil/water). b,d,f, Resistome (n = 42/4/16/30/4 for human/animal/latrine/soil/water). a, PCoA of weighted UniFrac distances between microbiota. Adonis R²=43.2%, p<0.001. b, PCoA of Bray-Curtis distances between resistomes with abundance-weighted coordinates of the top five most discriminative AR categories enriched in human or non-human habitats (squares, size proportional to overall abundance). Adonis R²=26.6%, p<0.001. c-d, *p<0.05, non-parametric Student’s t-tests, Bonferroni correction. c, Faith’s phylogenetic diversity. d, Observed AR proteins. e-f, Percentage of latrine, soil, and water e, microbiota and f, resistomes attributable to human feces, as determined by SourceTracker. *p<0.05, pairwise Wilcox tests, Bonferroni correction. Error bars = s.d., center bars = median.

Figure 3. Peruvian peri-urban slum (PST) human fecal and sewage microbiota and resistomes

a,c,e, Phylogenetic composition (n = 45/16/14/13 for human/street-access/influent/effluent). b,d,f, Resistome (n = 44/14/13/7 for human/street-access/influent/effluent). a, PCoA of weighted UniFrac distances between microbiota. Adonis R²=58.0%, p<0.001. b, PCoA of Bray-Curtis distances between resistomes with abundance-weighted coordinates of the top five most discriminative AR categories enriched in human or sewage habitats (squares, size proportional to overall abundance). Adonis R²=32.3%, p<0.001. c-d, *p<0.05, non-parametric Student’s t-tests, Bonferroni correction. c, Faith’s phylogenetic diversity. d, Observed AR proteins. e-f, Percentage of sewage e, microbiota and f, resistomes attributable to human feces at each sewage treatment stage, as determined by SourceTracker. *p<0.05, pairwise Wilcox tests, Bonferroni correction. Error bars = s.d., center bars = median.

Figure 4. AR proteins found in multiple habitats and genetic contexts in RES and PST

a, Representative alignment of 5 of 25 contigs encoding a TEM-type β-lactamase at 99.9% nucleotide identity (full list of contigs in Methods). Contigs were annotated with Resfams v1.2. Source metagenomic libraries are indicated on the left. b, AR networks between human and environmental metagenomes in RES and PST. Small nodes (squares) represent unique AR proteins found in at least one sampled metagenome, colored by predicted resistance mechanism. Large nodes represent individual human/animal (circle) or environmental (triangle) metagenomes, colored by habitat/cohort. Lines connecting samples and AR proteins represent a ShortBRED hit with an RPKM (reads per kilobase per million reads) of ≥10, colored by mechanism.