Chapter 3 Community composition

3.1 Metagenomics

load("resources/metagenomics/data_filtered.Rdata")

3.1.1 Taxonomy overview

Number of MAGs

genome_metadata %>% 
  nrow()%>% 
  cat()
135

Number of Archaea phyla

genome_metadata %>% 
  filter(domain == "Archaea")%>%
  dplyr::select(phylum) %>%
  unique() %>%
  pull() %>%
  length()%>% 
  cat()
0

Number of Bacteria phyla

genome_metadata %>% 
  filter(domain == "Bacteria")%>%
  dplyr::select(phylum) %>%
  unique() %>%
  pull() %>%
  length()%>% 
  cat()
13

3.1.1.1 Phylum level

genome_counts_filt %>%
  mutate_at(vars(-genome),  ~ . / sum(.)) %>% 
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% 
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% 
  left_join(., sample_metadata, by = join_by(sample == sample)) %>% 
  filter(count > 0) %>% #filter 0 counts
  ggplot(., aes(
    x = sample,
    y = count,
    fill = phylum,
    group = phylum
  )) + 
  geom_bar(stat = "identity",
           colour = "white",
           linewidth = 0.1) + 
  scale_fill_manual(values = phylum_colors) +
  facet_nested( ~ factor(
    Species,
    labels = c("Eb" = "Cnephaeus", "Ha" = "Hypsugo", "Pk" = "Pipistrellus")
  ), scales = "free") + 
  guides(fill = guide_legend(ncol = 1)) +
  theme(
    axis.text.x = element_blank(),
    axis.ticks.x = element_blank(),
    axis.title.x = element_blank(),
    panel.background = element_blank(),
    panel.border = element_blank(),
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    strip.background = element_rect(fill = "white"),
    strip.text = element_text(
      size = 12,
      lineheight = 0.6,
      face = "bold"
    ),
    axis.line = element_line(
      linewidth = 0.5,
      linetype = "solid",
      colour = "black"
    )
  ) +
  labs(fill = "Phylum", y = "Relative abundance", x = "Samples")

Grouping low-abundance bacteria

p1 <- genome_counts_filt %>%
  mutate_at(vars(-genome), ~ . / sum(.)) %>% 
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% 
  left_join(genome_metadata, by = join_by(genome == genome)) %>% 
  left_join(sample_metadata, by = join_by(sample == sample)) %>% 
  filter(count > 0) %>%
group_by(sample, phylum) %>%
  mutate(total_abundance = sum(count)) %>%
  ungroup() %>%
  mutate(phylum = if_else(total_abundance < 0.01, "Other", phylum)) %>%
  group_by(sample, phylum, Species) %>%
  summarise(count = sum(count), .groups = "drop") %>%
   ggplot(aes(
    x = sample,
    y = count,
    fill = phylum,
    group = phylum
  )) + 
  geom_bar(stat = "identity",
           colour = "white",
           linewidth = 0.1) + 
  scale_fill_manual(values = c(phylum_colors, "Other" = "grey50"),
                    drop = FALSE)+
  facet_nested(~ factor(
    Species,
    labels = c("Eb" = "Cnephaeus", "Ha" = "Hypsugo", "Pk" = "Pipistrellus")
  ), scales = "free") + 
  guides(fill = guide_legend(ncol = 1)) +
  theme(
    axis.text.x = element_blank(),
    axis.ticks.x = element_blank(),
    axis.title.x = element_blank(),
    panel.background = element_blank(),
    panel.border = element_blank(),
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    strip.background = element_rect(fill = "white"),
    strip.text = element_text(size = 12, lineheight = 0.6, face = "bold"),
    axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black")
  ) +
  labs(fill = "Phylum", y = "Relative abundance", x = "Samples")
#ggsave("community_plot_grouped_metagenomics.pdf", plot = p1, width = 12, height = 6)
p1

Phylum relative abundances

phylum_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>%
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample,phylum,Species) %>%
  summarise(relabun=sum(count))
phylum_summary %>%
  group_by(phylum) %>%
  summarise(
    Total_mean = mean(relabun * 100, na.rm = T),
    Total_sd = sd(relabun * 100, na.rm = T),
    Eb_mean = mean(relabun[Species == "Eb"] * 100, na.rm = T),
    Eb_sd = sd(relabun[Species == "Eb"] * 100, na.rm = T),
    Ha_mean = mean(relabun[Species == "Ha"] * 100, na.rm = T),
    Ha_sd = sd(relabun[Species == "Ha"] * 100, na.rm = T),
    Pk_mean = mean(relabun[Species == "Pk"] * 100, na.rm = T),
    Pk_sd = sd(relabun[Species == "Pk"] * 100, na.rm = T)
  ) %>%
  mutate(
    Total = str_c(round(Total_mean, 3), "±", round(Total_sd, 3)),
    Cnephaeus = str_c(round(Eb_mean, 3), "±", round(Eb_sd, 3)),
    Hypsugo = str_c(round(Ha_mean, 3), "±", round(Ha_sd, 3)),
    Pipistrellus = str_c(round(Pk_mean, 3), "±", round(Pk_sd, 3))
  ) %>%
  arrange(-Eb_mean) %>%
  dplyr::select(phylum,
                Total,
                Cnephaeus,
                Hypsugo,
                Pipistrellus) %>%
  tt()
phylum Total Cnephaeus Hypsugo Pipistrellus
Pseudomonadota 68.255±37.904 63.683±35.64 89.049±29.599 52.374±38.209
Bacillota 17.862±28.832 17.716±28.111 5.375±19.493 28.713±32.41
Desulfobacterota 3.981±10.582 7.227±13.106 0±0 5.944±13.024
Bacteroidota 6.774±17.384 5.695±9.903 5.263±22.942 8.569±14.844
Fusobacteriota 0.694±1.785 1.818±3.061 0±0 0.781±1.589
Campylobacterota 1.288±6.836 1.731±2.428 0±0 2.198±10.309
Elusimicrobiota 0.141±0.755 0.72±1.643 0±0 0±0
Synergistota 0.405±1.282 0.562±1.116 0±0 0.684±1.771
Planctomycetota 0.086±0.454 0.44±0.985 0±0 0±0
Deferribacterota 0.08±0.4 0.407±0.861 0±0 0±0
Actinomycetota 0.075±0.534 0±0 0.201±0.876 0±0
Cyanobacteriota 0.318±1.537 0±0 0±0 0.737±2.302
Spirochaetota 0.041±0.296 0±0 0.111±0.486 0±0

Number of different phyla in each bat species

phylum_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>%
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample,domain,phylum,Species) %>%
  summarise(relabun=sum(count))

phylum_summary %>% 
  filter(relabun > 0) %>% 
  group_by(Species,domain) %>% 
  summarise(n_phyla = n_distinct(phylum)) %>% 
  tt()
Species domain n_phyla
Eb Bacteria 10
Ha Bacteria 5
Pk Bacteria 8

3.1.1.2 Family level

Percentange of families in each group

family_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% 
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% 
  left_join(sample_metadata, by = join_by(sample == sample)) %>% 
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% 
  group_by(sample,family, Species) %>%
  summarise(relabun=sum(count))
family_summary %>%
  group_by(family) %>%
  summarise(
    Eb_mean = mean(relabun[Species == "Eb"] * 100, na.rm = T),
    Eb_sd = sd(relabun[Species == "Eb"] * 100, na.rm = T),
    Ha_mean = mean(relabun[Species == "Ha"] * 100, na.rm = T),
    Ha_sd = sd(relabun[Species == "Ha"] * 100, na.rm = T),
    Pk_mean = mean(relabun[Species == "Pk"] * 100, na.rm = T),
    Pk_sd = sd(relabun[Species == "Pk"] * 100, na.rm = T)
  ) %>%
  mutate(
    Cnephaeus = str_c(round(Eb_mean, 3), "±", round(Eb_sd, 3)),
    Hypsugo = str_c(round(Ha_mean, 3), "±", round(Ha_sd, 3)),
    Pipistrellus = str_c(round(Pk_mean, 3), "±", round(Pk_sd, 3))
  ) %>%
  arrange(-Eb_mean, -Ha_mean) %>%
  dplyr::select(family, Cnephaeus, Hypsugo, Pipistrellus) %>%
  tt()
family Cnephaeus Hypsugo Pipistrellus
Diplorickettsiaceae 33.448±40.33 24.089±41.769 10.097±24.365
Enterobacteriaceae 17.987±30.59 8.13±20.144 14.369±22.519
Mycoplasmataceae 8.829±18.638 4.422±19.277 0±0
Vibrionaceae 7.534±23.723 5.863±11.437 5.576±18.175
Desulfovibrionaceae 6.023±11.116 0±0 4.561±9.963
Enterococcaceae 4.692±10.65 0.602±2.624 3.243±11.687
Dysgonomonadaceae 2.721±6.637 0±0 3.84±7.171
Aeromonadaceae 1.626±4.965 5.844±13.778 0±0
Leptotrichiaceae 1.611±3.041 0±0 0.733±1.597
Helicobacteraceae 1.544±2.452 0±0 2.198±10.309
Halomonadaceae 1.351±4.273 0±0 0±0
Bacteroidaceae 1.332±4.049 0±0 0.32±1.501
Metamycoplasmataceae 1.211±3.83 0±0 3.313±15.537
Adiutricaceae 1.204±2.22 0±0 1.383±3.308
0.963±1.591 0±0 0.264±0.67
Tannerellaceae 0.857±1.866 0±0 2.727±6.739
Christensenellaceae 0.846±2.495 0±0 0±0
Elusimicrobiaceae 0.612±1.589 0±0 0±0
Synergistaceae 0.562±1.116 0±0 0.684±1.771
Rhodocyclaceae 0.548±1.298 0±0 0±0
SZUA-567 0.44±0.985 0±0 0±0
Lachnospiraceae 0.418±0.958 0±0 0.787±2.395
Burkholderiaceae 0.411±1.103 4.849±20.891 2.299±6.108
Mucispirillaceae 0.407±0.861 0±0 0±0
Erysipelotrichaceae 0.332±0.85 0±0 0.285±0.809
Ruminococcaceae 0.304±0.552 0±0 0.417±1.346
UBA932 0.297±0.484 0±0 0.991±2.93
Rikenellaceae 0.286±0.69 0±0 0±0
Oscillospiraceae 0.253±0.8 0±0 0.883±2.557
Fusobacteriaceae 0.207±0.458 0±0 0.048±0.225
Weeksellaceae 0.204±0.644 5.263±22.942 0.692±3.245
Campylobacteraceae 0.187±0.334 0±0 0±0
Acutalibacteraceae 0.178±0.296 0±0 0.074±0.24
CAG-508 0.176±0.555 0±0 0±0
Endomicrobiaceae 0.108±0.31 0±0 0±0
UBA660 0.083±0.229 0±0 0±0
CAG-239 0.081±0.257 0±0 0±0
Acetobacteraceae 0.053±0.103 3.841±16.741 0.008±0.038
Anaerotignaceae 0.039±0.125 0±0 0.208±0.565
Beijerinckiaceae 0.036±0.114 0±0 0.124±0.448
Rickettsiaceae 0±0 19.201±34.543 5.196±18.606
Chromatiaceae 0±0 10.155±30.073 0±0
Neisseriaceae 0±0 1.988±6.869 0±0
Morganellaceae 0±0 1.976±8.178 4.1±12.636
Rhizobiaceae 0±0 1.925±5.939 0.839±3.054
Anaplasmataceae 0±0 1.189±3.02 3.294±14.883
Streptococcaceae 0±0 0.351±1.529 1.768±8.172
Micrococcaceae 0±0 0.201±0.876 0±0
WRBN01 0±0 0.111±0.486 0±0
Clostridiaceae 0±0 0±0 0.206±0.966
Cyanobiaceae 0±0 0±0 0.11±0.421
Gemellaceae 0±0 0±0 1.591±4.739
Microcoleaceae 0±0 0±0 0.628±2.159
Mycoplasmoidaceae 0±0 0±0 15.785±29.329
Pasteurellaceae 0±0 0±0 6.36±15.418

3.1.1.3 Genus level

Percetange of genera in each group

genus_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),  ~ . / sum(.)) %>%
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample, phylum, genus, Species) %>%
  summarise(relabun = sum(count))

genus_summary %>%
  group_by(genus) %>%
  summarise(
    Eb_mean = mean(relabun[Species == "Eb"] * 100, na.rm = T),
    Eb_sd = sd(relabun[Species == "Eb"] * 100, na.rm = T),
    Ha_mean = mean(relabun[Species == "Ha"] * 100, na.rm = T),
    Ha_sd = sd(relabun[Species == "Ha"] * 100, na.rm = T),
    Pk_mean = mean(relabun[Species == "Pk"] * 100, na.rm = T),
    Pk_sd = sd(relabun[Species == "Pk"] * 100, na.rm = T)
  ) %>%
  mutate(
    Cnephaeus = str_c(round(Eb_mean, 3), "±", round(Eb_sd, 3)),
    Hypsugo = str_c(round(Ha_mean, 3), "±", round(Ha_sd, 3)),
    Pipistrellus = str_c(round(Pk_mean, 3), "±", round(Pk_sd, 3))
  ) %>%
  arrange(-Eb_mean, -Ha_mean) %>%
  dplyr::select(genus, Cnephaeus, Hypsugo, Pipistrellus) %>% 
  tt()
genus Cnephaeus Hypsugo Pipistrellus
Aquirickettsiella 33.448±40.33 24.089±41.769 10.097±24.365
Spiroplasma 8.747±18.476 0±0 0±0
Vibrio 7.534±23.723 5.863±11.437 5.576±18.175
Enterococcus 4.692±10.65 0.602±2.624 3.243±11.687
Jejubacter 4.268±9 0±0 0±0
Escherichia 3.416±10.802 0±0 0.317±1.488
Pseudocitrobacter 3.293±9.507 0±0 0.006±0.028
Frigididesulfovibrio 2.803±4.353 0±0 1.129±2.876
Dysgonomonas 2.721±6.637 0±0 3.84±7.171
Serratia 2.389±7.462 6.416±19.813 2.331±10.5
WRHT01 1.656±3.44 0±0 2.264±5.141
Aeromonas 1.626±4.965 5.844±13.778 0±0
Sebaldella 1.611±3.041 0±0 0.733±1.597
FLUQ01 1.563±3.576 0±0 1.167±2.563
Helicobacter_C 1.544±2.452 0±0 0±0
Zymobacter 1.351±4.273 0±0 0±0
UBA710 1.211±3.83 0±0 3.313±15.537
Adiutrix 1.204±2.22 0±0 1.383±3.308
Proteus 1.195±3.78 0±0 5.613±15.739
Bacteroides 1.053±3.329 0±0 0.32±1.501
Tannerella 0.857±1.866 0±0 1.972±5.493
QANA01 0.846±2.495 0±0 0±0
CALYQQ01 0.809±1.751 0±0 0±0
Enterobacillus 0.787±1.934 0±0 0±0
GCA-022846635 0.706±1.692 0±0 0±0
Citrobacter 0.653±1.233 0±0 0.11±0.405
0.638±1.527 3.27±16.196 0.928±2.976
UBA1174 0.497±1.233 0±0 0±0
Klebsiella 0.471±1.038 0±0 4.061±13.147
JAJBSZ01 0.44±0.985 0±0 0±0
Saezia 0.411±1.103 0±0 0.574±1.417
Breznakia 0.332±0.85 0±0 0.285±0.809
JAJQAW01 0.286±0.69 0±0 0±0
UBA1794 0.279±0.732 0±0 0±0
JAAYCI01 0.27±0.56 0±0 0.042±0.199
Fusobacterium 0.207±0.458 0±0 0.048±0.225
Apibacter 0.204±0.644 5.263±22.942 0.692±3.245
Scatolibacter 0.178±0.296 0±0 0.074±0.24
Elusimicrobium 0.116±0.366 0±0 0±0
Endomicrobium 0.108±0.31 0±0 0±0
Edwardiiplasma 0.082±0.258 4.422±19.277 0±0
CHH4-2 0.082±0.258 0±0 0±0
WQUU01 0.07±0.222 0±0 0.51±1.604
Entomobacter 0.053±0.103 0±0 0.008±0.038
JAHZDZ01 0.039±0.125 0±0 0.208±0.565
WRAV01 0.034±0.108 0±0 0.374±1.343
Lawsonibacter 0.03±0.096 0±0 0.087±0.306
Rickettsia 0±0 19.201±34.543 5.196±18.606
Neisseria 0±0 1.988±6.869 0±0
Arsenophonus 0±0 1.924±8.188 0±0
Orbus 0±0 1.359±5.923 0±0
Wolbachia 0±0 1.189±3.02 0.389±1.286
Caballeronia 0±0 0.883±3.849 0±0
Providencia 0±0 0.356±1.55 1.931±9.058
Lactococcus 0±0 0.351±1.529 1.768±8.172
Tokpelaia_A 0±0 0.215±0.939 0±0
Acaricomes 0±0 0.201±0.876 0±0
JAHHUI01 0±0 0.111±0.486 0±0
Paraburkholderia 0±0 0.054±0.233 0.979±4.41
Morganella 0±0 0.053±0.23 4.1±12.636
Aggregatibacter 0±0 0±0 2.526±9.217
DFXE01 0±0 0±0 0.755±3.543
Malacoplasma 0±0 0±0 15.785±29.329
Mesenet 0±0 0±0 2.906±13.629
NHYM01 0±0 0±0 2.198±10.309
Pasteurella 0±0 0±0 3.834±13.155
Planktothrix 0±0 0±0 0.628±2.159
Sarcina 0±0 0±0 0.206±0.966
Trinickia 0±0 0±0 0.747±2.486
Vulcanococcus 0±0 0±0 0.11±0.421

3.1.2 MAGs

Number of mags and distinct taxonomy

bats = c("Eb", "Pk", "Ha")

total_mags <- data.frame(
  Bat = character(),
  MAGs = numeric(),
  Phylum = numeric(),
  Family = numeric(),
  Genus = numeric()
)

preabs_table <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("genome")  %>%
  left_join(genome_metadata, by = join_by("genome" == "genome"))

phylum <- preabs_table %>%
  distinct(phylum)

family <- preabs_table %>%
  distinct(phylum, class, order, family)

genus <- preabs_table %>%
  distinct(phylum, class, order, family, genus)

total_mags <- rbind(
  total_mags,
  data.frame(
    Bat = "Total",
    MAGs = nrow(preabs_table),
    Phylum = nrow(phylum),
    Family = nrow(family),
    Genus = nrow(genus)
  )
)

for (bat in bats) {
  number <- preabs_table %>%
    select({{bat}}) %>%
    filter(. >= 1)
  
  phylum <- preabs_table %>%
    select({{bat}}, phylum) %>%
    filter(!!sym(bat) >= 1) %>%
    distinct(phylum)
  
  family <- preabs_table %>%
    select({{bat}}, phylum, class, order, family) %>%
    filter(!!sym(bat) >= 1) %>%
    distinct(phylum, class, order, family)
  
  genus <- preabs_table %>%
    select({{bat}}, phylum, class, order, family, genus) %>%
    filter(!!sym(bat) >= 1) %>%
    distinct(phylum, class, order, family, genus)
  
  total_mags <- rbind(
    total_mags,
    data.frame(
      Bat = bat,
      MAGs = nrow(number),
      Phylum = nrow(phylum),
      Family = nrow(family),
      Genus = nrow(genus)
    )
  )
}
bats = c("Eb", "Pk", "Ha")

no_annotation <- data.frame(Bat = character(),
                            No_genus = numeric(),
                            No_species = numeric())

preabs_table <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("genome")  %>%
  left_join(genome_metadata, by = join_by("genome" == "genome"))

genus <- preabs_table %>%
    filter(genus=="")


species <- preabs_table %>%
  filter(species=="")

no_annotation <- rbind(no_annotation,
                       data.frame(
                         Bat = "Total",
                         No_genus = nrow(genus),
                         No_species = nrow(species)
                       ))

for (bat in bats) {
  number <- preabs_table %>%
    select({{bat}}) %>%
    filter(. >= 1)
  
  genus <- preabs_table %>%
    select({{bat}}, phylum, class, order, family, genus) %>%
    filter(!!sym(bat) >= 1) %>%
  filter(genus=="")
  
  species <- preabs_table %>%
    filter(!!sym(bat) >= 1) %>%
  filter(species=="")
  
  no_annotation <- rbind(no_annotation,
                         data.frame(
                           Bat = bat,
                           No_genus = nrow(genus),
                           No_species = nrow(species)
                         ))
}

Total percentage of MAGs without genus-level annotation

nongenera <- genome_metadata %>%
  filter(genus=="") %>% 
  summarize(Mag_nogenera = n()) %>%
  pull()
nmags <- total_mags %>%
  filter(Bat == "Total") %>%
  select(MAGs) %>%
  pull()
perct <- nongenera * 100 / nmags
cat(perct)
20.74074

Percentage of MAGs without genus-level annotation by phylum

total_mag_phylum <- genome_metadata %>%
  group_by(phylum) %>%
  summarize(Total_MAGs = n())

genome_metadata %>%
    filter(genus=="")%>%
  group_by(phylum) %>%
  summarize(MAGs_nogenus = n()) %>%
  left_join(total_mag_phylum, by = join_by(phylum == phylum)) %>%
  mutate(Percentage_nogenus = 100 * MAGs_nogenus / Total_MAGs) %>%
  tt()
phylum MAGs_nogenus Total_MAGs Percentage_nogenus
Bacillota 11 34 32.352941
Bacteroidota 1 19 5.263158
Campylobacterota 1 3 33.333333
Deferribacterota 2 2 100.000000
Pseudomonadota 12 51 23.529412
Synergistota 1 1 100.000000

Number of bacterial species

genome_metadata %>% 
  filter(domain == "Bacteria")%>%
  dplyr::select(species) %>%
  unique() %>%
  pull() %>%
  length() %>% 
  cat()
36

Total percentage of MAGs without species-level annotation

nonspecies <- genome_metadata %>%
  filter(species=="") %>%
  summarize(Mag_nospecies = n()) %>%
  pull()
perct <- nonspecies * 100 / nmags
cat(perct)
72.59259

MAGs without species-level annotation

total_mag_phylum <- genome_metadata %>%
  group_by(phylum) %>%
  summarize(MAGs_total = n())
genome_metadata %>%
  filter(species=="") %>%
  group_by(phylum) %>%
  summarize(MAGs_nospecies = n()) %>%
  left_join(total_mag_phylum, by = join_by(phylum == phylum)) %>%
  mutate(species_annotated = MAGs_total - MAGs_nospecies) %>%
  mutate(Percentage_nospecies = 100 * MAGs_nospecies / MAGs_total) %>%
  mutate(Percentage_species = 100 - 100 * MAGs_nospecies / MAGs_total) %>%
  tt()
phylum MAGs_nospecies MAGs_total species_annotated Percentage_nospecies Percentage_species
Actinomycetota 1 1 0 100.00000 0.00000
Bacillota 29 34 5 85.29412 14.70588
Bacteroidota 13 19 6 68.42105 31.57895
Campylobacterota 3 3 0 100.00000 0.00000
Cyanobacteriota 2 2 0 100.00000 0.00000
Deferribacterota 2 2 0 100.00000 0.00000
Desulfobacterota 14 14 0 100.00000 0.00000
Elusimicrobiota 4 4 0 100.00000 0.00000
Fusobacteriota 1 2 1 50.00000 50.00000
Planctomycetota 1 1 0 100.00000 0.00000
Pseudomonadota 27 51 24 52.94118 47.05882
Synergistota 1 1 0 100.00000 0.00000

3.1.3 Summary table

bats = c("Eb", "Pk", "Ha")

single_sp <- data.frame(Bat = character(), Single_species = numeric())

table_upset_analysis <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample")

unique_all <- table_upset_analysis %>%
  filter(rowSums(across(Eb:Pk)) == 1)

single_sp <- rbind(single_sp, data.frame(Bat = "Total", Single_species = nrow(unique_all)))
  
for (bat in bats) {
  unique <- table_upset_analysis %>%
    filter(rowSums(across(Eb:Pk)) == 1) %>%
    select(all_of(bat)) %>%
    filter(. > 0) %>%
    nrow()
  
  single_sp <- rbind(single_sp, data.frame(Bat = bat, Single_species = unique))
}
single_ind <- data.frame(Bat = character(), Single_individual = numeric())

freq_table <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("asv")

singleton_filt <- freq_table %>%
  rowwise() %>%
  mutate(row_sum = sum(c_across(-asv))) %>% 
  filter(row_sum == 1) %>%
  column_to_rownames(var = "asv")

single_ind <- rbind(single_ind, data.frame(
  Bat = "Total",
  Single_individual = nrow(singleton_filt) 
))

for (bat in bats) {
  single_filt <- singleton_filt %>%
    select(bat) %>%
    filter(. == 1)
  
  single_ind <- rbind(single_ind, data.frame(
    Bat = bat,
    Single_individual = nrow(single_filt)
  ))
}
summary_table <- total_mags %>%
  left_join(., no_annotation, by = "Bat") %>%
  left_join(., single_ind, by = "Bat") %>%
  left_join(., single_sp, by = "Bat")
summary_table %>% 
  tt()
Bat MAGs Phylum Family Genus No_genus No_species Single_individual Single_species
Total 135 13 58 89 28 98 34 82
Eb 92 10 43 61 20 73 14 49
Pk 69 8 38 54 12 44 11 19
Ha 30 5 18 24 5 13 9 14 
summary_table %>%
  select(-Phylum, -Family, -Genus) %>%
  rowwise() %>%
  mutate(Mag_perc=round(MAGs*100/135, 2))%>%
  mutate(No_genus_perc = round(No_genus * 100 / MAGs, 2)) %>%
  mutate(No_species_perc = round(No_species * 100 / MAGs, 2)) %>%
  mutate(Single_individual_perc = round(Single_individual * 100 / MAGs, 2)) %>%
  mutate(Single_species_perc = round(Single_species * 100 / MAGs, 2)) %>%
  mutate(Single_individual_per_Single_species = round(Single_individual * 100 /
           Single_species, 2)) %>%
  select(1,7:12) %>% 
  tt()
Bat Mag_perc No_genus_perc No_species_perc Single_individual_perc Single_species_perc Single_individual_per_Single_species
Total 100.00 20.74 72.59 25.19 60.74 41.46
Eb 68.15 21.74 79.35 15.22 53.26 28.57
Pk 51.11 17.39 63.77 15.94 27.54 57.89
Ha 22.22 16.67 43.33 30.00 46.67 64.29

3.1.4 Read fractions

microbial_fraction %>%
  select(sample,lowqual_bases,host_bases,unmapped_bases,mapped_bases) %>% 
    pivot_longer(!sample, names_to = "fraction", values_to = "value") %>%
    group_by(sample) %>%
  mutate(value = value / sum(value)) %>% 
  ungroup() %>%
    mutate(fraction = factor(fraction, levels = c("lowqual_bases","host_bases","unmapped_bases","mapped_bases"))) %>%
  inner_join(sample_metadata,by="sample") %>% 
    ggplot(., aes(x = sample, y = value, fill=fraction)) +
  geom_bar(position="stack", stat = "identity") +
  scale_fill_manual(name="Sequence type",
                    breaks=c("lowqual_bases","host_bases","unmapped_bases","mapped_bases"),
                    labels=c("Low quality","Mapped to host","Unmapped","Mapped to MAGs"),
                    values=c("#CCCCCC", "#bcdee1", "#d8b8a3","#93655c"))+
  facet_grid(. ~ factor(Species, labels=c("Eb" = "Cnephaeus bottae", "Ha" = "Hypsugo ariel", "Pk" = "Pipistrellus kuhlii")), scales = "free")+
  labs(x = "Samples", y = "Amount of data (GB)") +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1, size=6),
        legend.position = "bottom")

microbial_fraction %>%
  mutate(host_fraction=host_bases/(lowqual_bases+host_bases+unmapped_bases+mapped_bases)*100) %>% 
  mutate(mapped_fraction=mapped_bases/(lowqual_bases+host_bases+unmapped_bases+mapped_bases)*100) %>% 
  select(sample,host_fraction,mapped_fraction) %>% 
    pivot_longer(!sample, names_to = "fraction", values_to = "value") %>%
  group_by(fraction) %>% 
  summarise(min=min(value),max=max(value)) %>% 
  tt()
fraction min max
host_fraction 0.3060190 75.50400
mapped_fraction 0.1151187 85.66364

3.1.5 Estimated vs recovered proportion

microbial_fraction %>% 
    mutate(mapped_microbial_fraction = ifelse(estimated_microbial_fraction == 0, 0, mapped_microbial_fraction)) %>% 
    mutate(estimated_microbial_fraction = ifelse(estimated_microbial_fraction == 0, NA, estimated_microbial_fraction)) %>% 
    mutate(estimated_microbial_fraction = ifelse(estimated_microbial_fraction < mapped_microbial_fraction, NA, estimated_microbial_fraction)) %>% 
    mutate(estimated_microbial_fraction = ifelse(estimated_microbial_fraction > 100, 100, estimated_microbial_fraction)) %>%
  select(sample,estimated_microbial_fraction,mapped_microbial_fraction) %>% 
    pivot_longer(!sample, names_to = "proportion", values_to = "value") %>%
    mutate(proportion = factor(proportion, levels = c("mapped_microbial_fraction","estimated_microbial_fraction"))) %>%
  inner_join(sample_metadata,by="sample") %>%
    ggplot(., aes(x = value, y = sample, color=proportion)) +
  geom_line(aes(group = sample), color = "#f8a538") +
  geom_point() +
  scale_color_manual(name="Proportion",
                    breaks=c("mapped_microbial_fraction","estimated_microbial_fraction"),
                    labels=c("Recovered","Estimated"),
                    values=c("#52e1e8", "#876b53"))+
  facet_grid(rows = vars(Species), space = "free", scales = "free", 
           labeller = labeller(Species = c(Eb = "Cnephaeus bottae", Ha = "Hypsugo ariel", Pk = "Pipistrellus kuhlii")))+  
  theme_classic() +
  labs(y = "Samples", x = "Prokaryotic fraction (%)") +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1, size=6),legend.position = "right")

3.1.6 Domain-adjusted mapping rate

microbial_fraction %>% 
  mutate(damr=ifelse(mapped_microbial_fraction>estimated_microbial_fraction,100,mapped_microbial_fraction/estimated_microbial_fraction*100)) %>% 
  inner_join(sample_metadata,by="sample") %>% 
  summarise(mean=mean(damr),sd=sd(damr)) %>% 
  tt()
mean sd
84.89668 20.58994 
microbial_fraction %>%
  mutate(damr=ifelse(mapped_microbial_fraction>estimated_microbial_fraction,100,mapped_microbial_fraction/estimated_microbial_fraction*100)) %>%
  inner_join(sample_metadata,by="sample") %>%
  mutate(Species = factor(Species, levels = c("Eb", "Ha", "Pk"), labels = c("Cnephaeus bottae", "Hypsugo ariel", "Pipistrellus kuhlii"))) %>% 
  group_by(Species) %>% 
  summarise(mean=mean(damr),sd=sd(damr)) %>% 
  tt()
Species mean sd
Cnephaeus bottae 77.87083 28.17509
Hypsugo ariel 83.77217 18.58653
Pipistrellus kuhlii 90.28633 17.14514 
microbial_fraction %>% 
  mutate(damr=ifelse(mapped_microbial_fraction>estimated_microbial_fraction,100,mapped_microbial_fraction/estimated_microbial_fraction*100)) %>% 
  inner_join(sample_metadata,by="sample") %>% 
  kruskal.test(damr ~ Species)

    Kruskal-Wallis rank sum test

data:  .
Kruskal-Wallis chi-squared = 558.6, df = 16, p-value < 2.2e-16

3.2 Amplicon

3.2.1 Taxonomy overview

load("resources/amplicon/data_standard_filt.Rdata")

Number of ASV

genome_metadata %>% 
  nrow() %>% 
  cat()
3250

Number of phyla

genome_metadata %>% 
  distinct(phylum) %>% 
  nrow() %>% 
  cat()
27

Number of Archaea phyla

genome_metadata %>% 
  filter(domain == "Archaea")%>%
  dplyr::select(phylum) %>%
  unique() %>%
  pull() %>%
  length()%>% 
  cat()
4
genome_metadata %>% 
  filter(domain == "Archaea")%>%
  dplyr::select(phylum) %>%
  unique() %>%
  pull() 
[1] "Halobacterota"    "Thermoplasmatota" "Euryarchaeota"    "Crenarchaeota"

Number of Bacteria phyla

genome_metadata %>% 
  filter(domain == "Bacteria")%>%
  dplyr::select(phylum) %>%
  unique() %>%
  pull() %>%
  length()%>% 
  cat()
23

3.2.1.1 Phylum level

genome_counts_filt %>%
  mutate_at(vars(-genome),  ~ . / sum(.)) %>% 
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% 
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% 
  left_join(., sample_metadata, by = join_by(sample == sample)) %>% 
  filter(count > 0) %>% #filter 0 counts
  ggplot(., aes(
    x = sample,
    y = count,
    fill = phylum,
    group = phylum
  )) + 
  geom_bar(stat = "identity",
           colour = "white",
           linewidth = 0.1) + 
  scale_fill_manual(values = phylum_colors) +
  facet_nested( ~ factor(
    Species,
    labels = c("Eb" = "Cnephaeus", "Ha" = "Hypsugo", "Pk" = "Pipistrellus")
  ), scales = "free") + 
  guides(fill = guide_legend(ncol = 1)) +
  theme(
    axis.text.x = element_blank(),
    axis.ticks.x = element_blank(),
    axis.title.x = element_blank(),
    panel.background = element_blank(),
    panel.border = element_blank(),
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    legend.text = element_text(size = 6),
    strip.background = element_rect(fill = "white"),
    strip.text = element_text(
      size = 12,
      lineheight = 0.6,
      face = "bold"
    ),
    axis.line = element_line(
      linewidth = 0.5,
      linetype = "solid",
      colour = "black"
    )
  ) +
  labs(fill = "Phylum", y = "Relative abundance", x = "Samples")+
  guides(fill = guide_legend(ncol = 2))

Grouping low-abundance bacteria

p1 <- genome_counts_filt %>%
  mutate_at(vars(-genome), ~ . / sum(.)) %>% 
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% 
  left_join(genome_metadata, by = join_by(genome == genome)) %>% 
  left_join(sample_metadata, by = join_by(sample == sample)) %>% 
  filter(count > 0) %>%
group_by(sample, phylum) %>%
  mutate(total_abundance = sum(count)) %>%
  ungroup() %>%
  mutate(phylum = if_else(total_abundance < 0.01, "Other", phylum)) %>%
  group_by(sample, phylum, Species) %>%
  summarise(count = sum(count), .groups = "drop") %>%
   ggplot(aes(
    x = sample,
    y = count,
    fill = phylum,
    group = phylum
  )) + 
  geom_bar(stat = "identity",
           colour = "white",
           linewidth = 0.1) + 
  scale_fill_manual(values = c(phylum_colors, "Other" = "grey50"),
                    drop = FALSE)+
  facet_nested(~ factor(
    Species,
    labels = c("Eb" = "Cnephaeus", "Ha" = "Hypsugo", "Pk" = "Pipistrellus")
  ), scales = "free") + 
  guides(fill = guide_legend(ncol = 1)) +
  theme(
    axis.text.x = element_blank(),
    axis.ticks.x = element_blank(),
    axis.title.x = element_blank(),
    panel.background = element_blank(),
    panel.border = element_blank(),
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    legend.text = element_text(size = 6),
    strip.background = element_rect(fill = "white"),
    strip.text = element_text(
      size = 12,
      lineheight = 0.6,
      face = "bold"
    ),
    axis.line = element_line(
      linewidth = 0.5,
      linetype = "solid",
      colour = "black"
    )
  ) +
  labs(fill = "Phylum", y = "Relative abundance", x = "Samples")+
  guides(fill = guide_legend(ncol = 2))

#ggsave("community_plot_grouped_standard.pdf", plot = p1, width = 12, height = 6)
p1

Phylum relative abundances

phylum_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),  ~ . / sum(.)) %>%
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample, phylum, Species) %>%
  summarise(relabun = sum(count))
phylum_summary %>%
  group_by(phylum) %>%
  summarise(
    Total_mean = mean(relabun * 100, na.rm = T),
    Total_sd = sd(relabun * 100, na.rm = T),
    Eb_mean = mean(relabun[Species == "Eb"] * 100, na.rm = T),
    Eb_sd = sd(relabun[Species == "Eb"] * 100, na.rm = T),
    Ha_mean = mean(relabun[Species == "Ha"] * 100, na.rm = T),
    Ha_sd = sd(relabun[Species == "Ha"] * 100, na.rm = T),
    Pk_mean = mean(relabun[Species == "Pk"] * 100, na.rm = T),
    Pk_sd = sd(relabun[Species == "Pk"] * 100, na.rm = T)
  ) %>%
  mutate(
    Total = str_c(round(Total_mean, 3), "±", round(Total_sd, 3)),
    Cnephaeus = str_c(round(Eb_mean, 3), "±", round(Eb_sd, 3)),
    Hypsugo = str_c(round(Ha_mean, 3), "±", round(Ha_sd, 3)),
    Pipistrellus = str_c(round(Pk_mean, 3), "±", round(Pk_sd, 3))
  ) %>%
  arrange(-Eb_mean) %>%
  dplyr::select(phylum, Total, Cnephaeus, Hypsugo, Pipistrellus) %>% 
  tt()
phylum Total Cnephaeus Hypsugo Pipistrellus
Pseudomonadota 58.827±25.938 53.556±30.577 67.53±18.837 53.708±28.067
Bacillota 26.432±20.949 25.457±23.76 22.92±16.074 29.909±23.606
Bacteroidota 4.871±7.764 5.564±8.462 5.333±8.497 4.157±7.072
Fusobacteriota 1.832±4.279 5.056±6.787 0.381±0.927 1.62±4.027
Desulfobacterota 2.108±4.598 4.45±5.809 0.327±0.939 2.581±5.422
Patescibacteria 0.478±2.558 2.197±5.659 0.05±0.151 0.067±0.295
Rs-K70 termite group 0.947±2.854 1.379±3.224 0.372±1.305 1.247±3.605
Synergistota 0.364±0.935 0.671±1.258 0.167±0.702 0.394±0.949
Planctomycetota 0.177±0.476 0.603±0.816 0.015±0.059 0.123±0.37
Campylobacterota 1.088±6.268 0.529±0.911 0.265±0.676 2.053±9.543
Verrucomicrobiota 0.338±1.919 0.137±0.347 0.095±0.368 0.639±2.904
Cyanobacteriota 1.062±4.766 0.118±0.29 0.64±2.365 1.856±6.928
Elusimicrobiota 0.022±0.126 0.106±0.28 0±0 0.002±0.01
Actinomycetota 0.779±1.853 0.101±0.266 1.617±2.797 0.362±0.634
Deferribacterota 0.009±0.049 0.043±0.107 0±0 0.001±0.005
Halobacterota 0.48±2.926 0.017±0.048 0.181±0.666 0.949±4.427
Spirochaetota 0.092±0.499 0.013±0.042 0.023±0.101 0.188±0.753
Apal-E12 0.001±0.004 0.003±0.01 0±0 0±0
Bdellovibrionota 0.006±0.028 0±0 0.005±0.015 0.009±0.041
Chloroflexi 0.005±0.017 0±0 0.012±0.027 0.002±0.006
Crenarchaeota 0.002±0.011 0±0 0.002±0.009 0.003±0.014
Deinococcota 0.02±0.13 0±0 0.053±0.212 0±0
Euryarchaeota 0.024±0.124 0±0 0±0 0.056±0.186
Myxococcota 0.004±0.021 0±0 0.011±0.035 0.001±0.003
Sumerlaeota 0.001±0.004 0±0 0.002±0.007 0±0
Thermoplasmatota 0.031±0.221 0±0 0.001±0.003 0.072±0.336
Thermotogota 0±0.003 0±0 0±0 0.001±0.004

Number of phyla in each bat species

phylum_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>%
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  mutate(Species = factor(Species, levels = c("Eb", "Ha", "Pk"), labels = c("Cnephaeus bottae", "Hypsugo ariel", "Pipistrellus kuhlii"))) %>% 
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample,domain,phylum,Species) %>%
  summarise(relabun=sum(count))

phylum_summary %>% 
  filter(relabun > 0) %>% 
  group_by(Species,domain) %>% 
  summarise(n_phyla = n_distinct(phylum)) %>% 
  tt()
Species domain n_phyla
Cnephaeus bottae Archaea 1
Cnephaeus bottae Bacteria 17
Hypsugo ariel Archaea 3
Hypsugo ariel Bacteria 19
Pipistrellus kuhlii Archaea 4
Pipistrellus kuhlii Bacteria 20

3.2.1.2 Family level

Percentage of families in each group

family_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),  ~ . / sum(.)) %>% 
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% 
  left_join(sample_metadata, by = join_by(sample == sample)) %>% 
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% 
  group_by(sample, phylum, family, Species) %>%
  summarise(relabun = sum(count))
family_summary %>%
  group_by(phylum,family) %>%
  summarise(
    Eb_mean = mean(relabun[Species == "Eb"] * 100, na.rm = T),
    Eb_sd = sd(relabun[Species == "Eb"] * 100, na.rm = T),
    Ha_mean = mean(relabun[Species == "Ha"] * 100, na.rm = T),
    Ha_sd = sd(relabun[Species == "Ha"] * 100, na.rm = T),
    Pk_mean = mean(relabun[Species == "Pk"] * 100, na.rm = T),
    Pk_sd = sd(relabun[Species == "Pk"] * 100, na.rm = T)
  ) %>%
  mutate(
    Cnephaeus = str_c(round(Eb_mean, 3), "±", round(Eb_sd, 3)),
    Hypsugo = str_c(round(Ha_mean, 3), "±", round(Ha_sd, 3)),
    Pipistrellus = str_c(round(Pk_mean, 3), "±", round(Pk_sd, 3))
  ) %>%
  arrange(-Pk_mean) %>%
  dplyr::select(family, Cnephaeus, Hypsugo, Pipistrellus) %>%
  tt()
phylum family Cnephaeus Hypsugo Pipistrellus
Pseudomonadota Enterobacteriaceae 26.696±31.681 8.835±13.588 13.236±22.967
Pseudomonadota Morganellaceae 0.286±0.615 4.137±6.829 9.532±19.056
Pseudomonadota Yersiniaceae 0.222±0.476 9.423±14.297 6.636±18.125
Bacillota Enterococcaceae 6.978±10.459 2.886±4.693 5.421±10.611
Bacillota Streptococcaceae 0.512±0.901 2.154±3.463 4.843±15.641
Pseudomonadota Diplorickettsiaceae 14.286±27.8 0.202±0.499 4.667±20.883
Bacillota Bacillaceae 0.461±0.701 7.363±9.575 4.638±14.908
Bacillota Lachnospiraceae 5.117±11.828 2.332±5.596 4.138±8.838
Pseudomonadota Rickettsiaceae 0.048±0.147 6.599±15.053 4.098±13.243
Pseudomonadota Pasteurellaceae 0.443±1.394 4.54±9.866 3.52±6.119
Pseudomonadota Vibrionaceae 3.255±10.077 5.495±8.448 3.049±11.084
Desulfobacterota Desulfovibrionaceae 4.398±5.781 0.286±0.935 2.515±5.329
Bacillota Mycoplasmataceae 1.26±3.488 0.045±0.168 2.387±11.173
Bacteroidota Dysgonomonadaceae 1.595±1.962 2.478±7.724 2.301±5.02
Bacillota Ruminococcaceae 3.508±4.163 0.945±2.097 2.278±4.42
Campylobacterota Helicobacteraceae 0.442±0.841 0±0 2.05±9.544
Bacillota Clostridiaceae 1.502±2.586 1.234±4.078 1.75±4.45
Fusobacteriota Leptotrichiaceae 3.604±6.968 0.218±0.727 1.352±3.946
Rs-K70 termite group NA 1.379±3.224 0.372±1.305 1.247±3.605
Pseudomonadota Rhizobiaceae 0.215±0.229 2.599±7.706 1.202±3.953
Pseudomonadota Burkholderiaceae 0.254±0.546 2.297±7.944 1.186±3.201
Cyanobacteriota Microcystaceae 0±0 0.003±0.014 1.047±4.878
Pseudomonadota Erwiniaceae 0.043±0.099 1.272±2.659 1.034±1.874
Bacillota Vagococcaceae 0.217±0.457 0.205±0.658 0.994±3.417
Pseudomonadota NA 0.736±1.123 4.956±11.019 0.878±1.892
Halobacterota Methanosarcinaceae 0.017±0.048 0±0 0.855±4.01
Pseudomonadota Acetobacteraceae 0.204±0.38 2±7.283 0.832±2.495
Bacteroidota Weeksellaceae 0.572±1.608 2.205±4.911 0.722±2.954
Verrucomicrobiota Simkaniaceae 0±0 0±0 0.619±2.904
Pseudomonadota Pseudomonadaceae 0.234±0.441 1.456±3.927 0.574±2.481
Pseudomonadota Aeromonadaceae 1.876±5.145 4.415±8.898 0.551±2.065
Cyanobacteriota Phormidiaceae 0±0 0.026±0.072 0.525±1.881
Bacillota Lactobacillaceae 0.2±0.31 2.206±5.685 0.511±2.072
Pseudomonadota Orbaceae 0.002±0.008 0.875±3.12 0.461±2.14
Bacillota Oscillospiraceae 0.119±0.281 0.007±0.031 0.45±1.08
Bacillota Christensenellaceae 0.749±0.905 0.016±0.033 0.418±1.093
Bacteroidota Bacteroidaceae 1.85±3.83 0.014±0.046 0.409±1.391
Synergistota Synergistaceae 0.671±1.258 0.167±0.702 0.394±0.949
Bacillota Aerococcaceae 0.029±0.061 0.555±0.835 0.349±0.873
Bacteroidota Williamwhitmaniaceae 0.041±0.054 0.003±0.015 0.329±1.437
Bacteroidota Tannerellaceae 0.51±0.813 0.044±0.191 0.322±0.969
Pseudomonadota Cardiobacteriaceae 0±0 0±0 0.308±1.409
Pseudomonadota Rhodobacteraceae 0.026±0.062 0.064±0.071 0.297±1.114
Bacillota Entomoplasmataceae 0±0 2.237±7.773 0.289±1.333
Fusobacteriota Fusobacteriaceae 1.453±2.58 0.164±0.629 0.267±1.17
Cyanobacteriota Cyanobiaceae 0±0 0.041±0.088 0.266±1.15
Pseudomonadota Wohlfahrtiimonadaceae 0.204±0.633 0.014±0.047 0.258±1.06
Bacillota Staphylococcaceae 0.202±0.629 0.065±0.117 0.253±0.57
Bacillota NA 0.989±1.939 0.128±0.257 0.216±0.428
Pseudomonadota Anaplasmataceae 0.001±0.004 0.265±0.599 0.204±0.463
Pseudomonadota Beijerinckiaceae 0±0 0.007±0.015 0.193±0.72
Pseudomonadota Oxalobacteraceae 0.131±0.307 1.461±5.324 0.189±0.669
Pseudomonadota Comamonadaceae 0.032±0.063 0.585±1.518 0.183±0.76
Bacillota Acidaminococcaceae 0.426±0.51 0.004±0.016 0.179±0.371
Spirochaetota Brevinemataceae 0±0 0.023±0.101 0.174±0.754
Bacillota [Eubacterium] coprostanoligenes group 0.003±0.007 0±0 0.137±0.426
Pseudomonadota Halomonadaceae 2.434±7.5 2.113±5.914 0.121±0.493
Pseudomonadota Moraxellaceae 0.124±0.187 0.954±2.712 0.112±0.229
Bacillota Peptostreptococcaceae 0.445±0.823 0.018±0.038 0.086±0.226
Actinomycetota Corynebacteriaceae 0.018±0.052 0.265±0.351 0.086±0.132
Bacillota Erysipelotrichaceae 1.583±3.987 0.276±0.555 0.08±0.191
Planctomycetota NA 0.603±0.816 0.011±0.046 0.077±0.312
Bacillota Anaerovoracaceae 0.353±0.742 0.004±0.013 0.074±0.21
Pseudomonadota Neisseriaceae 0±0 1.619±3.584 0.074±0.219
Halobacterota Methanospirillaceae 0±0 0±0 0.074±0.338
Thermoplasmatota Methanomethylophilaceae 0±0 0±0 0.072±0.336
Patescibacteria Saccharimonadaceae 0.537±1.613 0.04±0.153 0.061±0.281
Bacillota [Clostridium] methylpentosum group 0.177±0.334 0±0 0.06±0.163
Bacillota Peptococcaceae 0.018±0.047 0.01±0.044 0.057±0.195
Euryarchaeota Methanobacteriaceae 0±0 0±0 0.056±0.186
Bacillota Monoglobaceae 0.106±0.284 0.003±0.014 0.056±0.192
Bacillota Hydrogenoanaerobacterium 0.003±0.011 0.002±0.008 0.054±0.142
Desulfobacterota NA 0.052±0.102 0±0 0.053±0.17
Pseudomonadota Budviciaceae 0.035±0.095 0.023±0.078 0.05±0.184
Actinomycetota Streptomycetaceae 0±0 0.053±0.079 0.05±0.133
Pseudomonadota Nitrosomonadaceae 0.094±0.246 0.006±0.016 0.048±0.136
Actinomycetota NA 0.011±0.017 0.117±0.388 0.047±0.092
Planctomycetota Phycisphaeraceae 0±0 0±0 0.046±0.217
Pseudomonadota Rhodocyclaceae 0.589±1.562 0.115±0.309 0.043±0.177
Actinomycetota Brevibacteriaceae 0.029±0.091 0.001±0.004 0.042±0.149
Bacillota Sporomusaceae 0±0 0±0 0.042±0.127
Bacteroidota Microscillaceae 0±0 0±0 0.041±0.195
Bacillota Erysipelatoclostridiaceae 0.224±0.612 0.025±0.082 0.035±0.098
Actinomycetota Micrococcaceae 0.011±0.033 0.768±2.709 0.031±0.083
Pseudomonadota Pectobacteriaceae 0.116±0.285 0.239±0.613 0.027±0.094
Pseudomonadota Caulobacteraceae 0.003±0.008 0.007±0.021 0.027±0.128
Actinomycetota Dermabacteraceae 0.012±0.038 0±0 0.021±0.073
Bacillota Pelotomaculaceae 0±0 0±0 0.02±0.092
Cyanobacteriota Chroococcidiopsaceae 0±0 0.54±2.34 0.018±0.081
Actinomycetota Coriobacteriales Incertae Sedis 0.001±0.003 0.004±0.015 0.018±0.083
Halobacterota Methanocorpusculaceae 0±0 0±0 0.017±0.079
Bacillota Spiroplasmataceae 0.006±0.017 0.01±0.03 0.016±0.06
Actinomycetota Microbacteriaceae 0.004±0.011 0.013±0.024 0.015±0.053
Pseudomonadota Xanthomonadaceae 0.01±0.022 0.122±0.337 0.015±0.054
Spirochaetota Spirochaetaceae 0.013±0.042 0±0 0.014±0.056
Pseudomonadota Sutterellaceae 0±0 0±0 0.013±0.063
Pseudomonadota Aquaspirillaceae 0.797±2.52 0±0 0.013±0.054
Pseudomonadota Hafniaceae 0±0 0.564±1.437 0.013±0.043
Pseudomonadota Rhizobiales Incertae Sedis 0±0 0.003±0.008 0.013±0.059
Bacillota Planococcaceae 0.015±0.037 0.022±0.058 0.012±0.038
Actinomycetota Actinomycetaceae 0±0 0.165±0.511 0.012±0.042
Bacteroidota Rikenellaceae 0.218±0.394 0.126±0.437 0.012±0.03
Actinomycetota Dietziaceae 0.012±0.039 0±0 0.012±0.031
Bacillota Anaerofustaceae 0±0 0±0 0.011±0.053
Pseudomonadota AB1 0±0 0±0 0.01±0.045
Bacillota Syntrophomonadaceae 0±0 0±0 0.01±0.026
Bacillota Listeriaceae 0±0 0±0 0.009±0.03
Bacillota Carnobacteriaceae 0±0 0.018±0.076 0.009±0.041
Pseudomonadota Alcaligenaceae 0.054±0.11 0.042±0.121 0.008±0.016
Bacteroidota Sphingobacteriaceae 0.001±0.004 0±0 0.008±0.032
Verrucomicrobiota Chthoniobacteraceae 0±0 0.004±0.018 0.007±0.03
Patescibacteria NA 1.657±4.079 0.008±0.014 0.007±0.017
Pseudomonadota Holosporaceae 0±0 0.002±0.007 0.007±0.031
Bacillota Desulfitobacteriaceae 0±0 0±0 0.006±0.03
Desulfobacterota Desulfobulbaceae 0±0 0.021±0.093 0.006±0.03
Bacillota Defluviitaleaceae 0.015±0.034 0±0 0.006±0.024
Desulfobacterota Desulfomicrobiaceae 0±0 0.02±0.087 0.006±0.024
Pseudomonadota SM2D12 0±0 0±0 0.006±0.027
Bdellovibrionota Silvanigrellaceae 0±0 0.002±0.007 0.005±0.023
Bacteroidota Flavobacteriaceae 0.516±1.606 0±0 0.004±0.012
Actinomycetota Pseudonocardiaceae 0±0 0.03±0.038 0.004±0.015
Verrucomicrobiota Chlamydiaceae 0±0 0±0 0.004±0.02
Actinomycetota Micromonosporaceae 0±0 0.001±0.006 0.004±0.019
Actinomycetota Nocardiaceae 0±0 0.002±0.008 0.004±0.013
Actinomycetota Rubrobacteriaceae 0±0 0.05±0.214 0.004±0.013
Verrucomicrobiota Terrimicrobiaceae 0.112±0.353 0.002±0.007 0.003±0.016
Crenarchaeota Nitrososphaeraceae 0±0 0.002±0.009 0.003±0.014
Actinomycetota Ilumatobacteraceae 0±0 0.002±0.01 0.003±0.016
Pseudomonadota Sphingomonadaceae 0±0 0.029±0.049 0.003±0.011
Bacillota Hungateiclostridiaceae 0±0 0.001±0.003 0.003±0.013
Bacillota Family XI 0.076±0.24 0.091±0.229 0.003±0.007
Actinomycetota Geodermatophilaceae 0±0 0.039±0.085 0.003±0.012
Halobacterota Halomicrobiaceae 0±0 0.028±0.114 0.003±0.01
Bdellovibrionota Bdellovibrionaceae 0±0 0±0 0.003±0.012
Pseudomonadota Elioraeaceae 0±0 0±0 0.003±0.012
Bacteroidota Chitinophagaceae 0±0 0.014±0.03 0.002±0.009
Verrucomicrobiota Akkermansiaceae 0.023±0.048 0.068±0.295 0.002±0.012
Campylobacterota Arcobacteraceae 0.017±0.04 0±0 0.002±0.011
Actinomycetota Glycomycetaceae 0±0 0±0 0.002±0.011
Elusimicrobiota Endomicrobiaceae 0.009±0.021 0±0 0.002±0.01
Pseudomonadota Geminicoccaceae 0±0 0±0 0.002±0.01
Pseudomonadota Caedibacteraceae 0±0 0±0 0.002±0.01
Pseudomonadota Hyphomicrobiaceae 0±0 0±0 0.002±0.01
Verrucomicrobiota Rubritaleaceae 0±0 0.003±0.011 0.002±0.005
Bacillota Butyricicoccaceae 0.009±0.029 0±0 0.002±0.005
Bacillota Exiguobacteraceae 0±0 0.012±0.036 0.002±0.008
Pseudomonadota Methylophilaceae 0±0 0.001±0.003 0.002±0.008
Bacillota Eubacteriaceae 0.146±0.449 0.004±0.012 0.002±0.008
Pseudomonadota Fokiniaceae 0±0 0.003±0.013 0.002±0.007
Bacteroidota Blattabacteriaceae 0.017±0.054 0.408±1.773 0.001±0.007
Bacteroidota Prevotellaceae 0±0 0.011±0.032 0.001±0.007
Actinomycetota Nocardiopsaceae 0.003±0.011 0.016±0.066 0.001±0.006
Bdellovibrionota Oligoflexaceae 0±0 0±0 0.001±0.006
Bacteroidota Barnesiellaceae 0±0 0±0 0.001±0.005
Halobacterota Haloferacaceae 0±0 0.112±0.48 0.001±0.005
Chloroflexi Ktedonobacteraceae 0±0 0±0 0.001±0.005
Deferribacterota Deferribacteraceae 0.043±0.107 0±0 0.001±0.005
Bacillota Desulfurisporaceae 0±0 0±0 0.001±0.005
Bacillota Syntrophobotulaceae 0±0 0±0 0.001±0.005
Bacillota type III 0±0 0.003±0.009 0.001±0.004
Thermotogota Fervidobacteriaceae 0±0 0±0 0.001±0.004
Bacteroidota Hymenobacteraceae 0±0 0±0 0.001±0.004
Desulfobacterota Desulfarculaceae 0±0 0±0 0.001±0.004
Chloroflexi Caldilineaceae 0±0 0±0 0.001±0.004
Bacteroidota COB P4-1 termite group 0±0 0±0 0.001±0.003
Actinomycetota Nocardioidaceae 0±0 0.02±0.054 0.001±0.003
Bacillota Gemellaceae 0±0 0.002±0.009 0.001±0.003
Actinomycetota Sporichthyaceae 0±0 0.004±0.014 0.001±0.003
Pseudomonadota Labraceae 0±0 0±0 0.001±0.003
Pseudomonadota Steroidobacteraceae 0±0 0±0 0.001±0.003
Pseudomonadota TRA3-20 0±0 0±0 0.001±0.003
Myxococcota Polyangiaceae 0±0 0±0 0.001±0.003
Actinomycetota Thermomonosporaceae 0±0 0.002±0.009 0.001±0.003
Bacteroidota Cytophagaceae 0±0 0±0 0±0.002
Bdellovibrionota NA 0±0 0.002±0.011 0±0.002
Bacteroidota Marinifilaceae 0.017±0.038 0.012±0.053 0±0.002
Pseudomonadota Methylococcaceae 0±0 0±0 0±0.002
Campylobacterota Campylobacteraceae 0.025±0.055 0.263±0.677 0±0.002
Pseudomonadota Shewanellaceae 0±0 0.007±0.026 0±0.002
Actinomycetota 67-14 0±0 0.005±0.02 0±0
Actinomycetota Bifidobacteriaceae 0±0 0.012±0.044 0±0
Actinomycetota Cellulomonadaceae 0±0 0.005±0.02 0±0
Actinomycetota Eggerthellaceae 0±0 0.001±0.003 0±0
Actinomycetota Intrasporangiaceae 0±0 0.003±0.011 0±0
Actinomycetota Kineosporiaceae 0±0 0.013±0.058 0±0
Actinomycetota Nakamurellaceae 0±0 0.001±0.003 0±0
Actinomycetota Promicromonosporaceae 0±0 0.004±0.016 0±0
Actinomycetota Solirubrobacteraceae 0±0 0.007±0.033 0±0
Actinomycetota Streptosporangiaceae 0±0 0.004±0.018 0±0
Actinomycetota Tsukamurellaceae 0±0 0.011±0.047 0±0
Apal-E12 NA 0.003±0.01 0±0 0±0
Bacillota Alkaliphilus 0±0 0.001±0.004 0±0
Bacillota Gottschalkia 0±0 0.014±0.053 0±0
Bacillota Paenibacillaceae 0.002±0.005 0.009±0.038 0±0
Bacillota Sporolactobacillaceae 0±0 0.002±0.009 0±0
Bacillota TC1 0.006±0.019 0±0 0±0
Bacillota Thermoactinomycetaceae 0±0 0.001±0.006 0±0
Bacillota Veillonellaceae 0±0 0.01±0.024 0±0
Bacteroidota Balneolaceae 0±0 0.001±0.003 0±0
Bacteroidota CR-115 0.005±0.01 0±0 0±0
Bacteroidota Cryomorphaceae 0±0 0.001±0.004 0±0
Bacteroidota Cyclobacteriaceae 0±0 0.002±0.009 0±0
Bacteroidota M2PB4-65 termite group 0.008±0.024 0±0 0±0
Bacteroidota Marinilabiliaceae 0.041±0.101 0±0 0±0
Bacteroidota Paludibacteraceae 0.128±0.273 0±0 0±0
Bacteroidota Porphyromonadaceae 0.001±0.004 0.001±0.004 0±0
Bacteroidota NA 0.043±0.079 0.012±0.054 0±0
Bdellovibrionota Bacteriovoracaceae 0±0 0.001±0.003 0±0
Campylobacterota Sulfurimonadaceae 0±0 0.002±0.01 0±0
Campylobacterota Sulfurospirillaceae 0.045±0.129 0±0 0±0
Chloroflexi A4b 0±0 0.002±0.009 0±0
Chloroflexi AKIW781 0±0 0.003±0.01 0±0
Chloroflexi JG30-KF-CM45 0±0 0.001±0.003 0±0
Chloroflexi Thermomicrobiaceae 0±0 0.002±0.007 0±0
Chloroflexi NA 0±0 0.004±0.017 0±0
Cyanobacteriota Cyanobacteriaceae 0±0 0.003±0.008 0±0
Cyanobacteriota Desertifilaceae 0±0 0.001±0.005 0±0
Cyanobacteriota Leptolyngbyaceae 0±0 0.002±0.006 0±0
Cyanobacteriota Limnotrichaceae 0±0 0.009±0.041 0±0
Cyanobacteriota Nodosilineaceae 0.005±0.016 0.006±0.014 0±0
Cyanobacteriota Synechococcaceae 0.023±0.072 0±0 0±0
Cyanobacteriota Thermosynechococcaceae 0±0 0.001±0.005 0±0
Cyanobacteriota Vampirovibrionaceae 0±0 0.001±0.005 0±0
Cyanobacteriota NA 0.091±0.286 0.006±0.027 0±0
Deinococcota Deinococcaceae 0±0 0.003±0.014 0±0
Deinococcota Trueperaceae 0±0 0.049±0.198 0±0
Elusimicrobiota Elusimicrobiaceae 0.097±0.28 0±0 0±0
Halobacterota Haloadaptaceae 0±0 0.013±0.056 0±0
Halobacterota Halococcaceae 0±0 0.029±0.119 0±0
Myxococcota Haliangiaceae 0±0 0.003±0.011 0±0
Myxococcota Nannocystaceae 0±0 0.001±0.004 0±0
Myxococcota Sandaracinaceae 0±0 0.008±0.033 0±0
Patescibacteria LWQ8 0.003±0.008 0.001±0.005 0±0
Planctomycetota CPla-3 termite group 0±0 0.001±0.004 0±0
Planctomycetota Pirellulaceae 0±0 0.004±0.013 0±0
Pseudomonadota Alcanivoracaceae1 0±0 0.014±0.054 0±0
Pseudomonadota Azospirillaceae 0±0 0.005±0.014 0±0
Pseudomonadota Candidatus Hepatincola 0±0 0.001±0.003 0±0
Pseudomonadota Cellvibrionaceae 0±0 0.003±0.012 0±0
Pseudomonadota Chitinibacteraceae 0±0 0.039±0.171 0±0
Pseudomonadota Chromatiaceae 0.006±0.02 0±0 0±0
Pseudomonadota Chromobacteriaceae 0±0 0.045±0.156 0±0
Pseudomonadota Devosiaceae 0.007±0.022 0.017±0.065 0±0
Pseudomonadota Legionellaceae 0±0 0.002±0.008 0±0
Pseudomonadota Marinobacteraceae 0±0 0.001±0.004 0±0
Pseudomonadota Methylophagaceae 0.001±0.005 0±0 0±0
Pseudomonadota Microbulbiferaceae 0±0 0.005±0.02 0±0
Pseudomonadota Midichloriaceae 0±0 0.002±0.01 0±0
Pseudomonadota Nitrosococcaceae 0±0 0.001±0.003 0±0
Pseudomonadota Pseudohongiellaceae 0±0 0.001±0.003 0±0
Pseudomonadota Puniceispirillales Incertae Sedis 0±0 0.001±0.003 0±0
Pseudomonadota Reyranellaceae 0.002±0.005 0.002±0.009 0±0
Pseudomonadota Rhodospirillaceae 0.091±0.233 0.047±0.158 0±0
Pseudomonadota Unknown Family 0±0 0.001±0.005 0±0
Sumerlaeota Sumerlaeaceae 0±0 0.002±0.007 0±0
Thermoplasmatota NA 0±0 0.001±0.003 0±0
Verrucomicrobiota 01D2Z36 0±0 0.001±0.006 0±0
Verrucomicrobiota DEV007 0±0 0.014±0.059 0±0
Verrucomicrobiota Pedosphaeraceae 0±0 0.002±0.006 0±0
Verrucomicrobiota Puniceicoccaceae 0.003±0.009 0±0 0±0
Verrucomicrobiota Xiphinematobacteraceae 0±0 0.001±0.003 0±0
Verrucomicrobiota NA 0±0 0.001±0.003 0±0

3.2.1.3 Genus level

Percetage of genera in each species

genus_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),  ~ . / sum(.)) %>%
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>%
  left_join(sample_metadata, by = join_by(sample == sample)) %>%
  left_join(genome_metadata, by = join_by(genome == genome)) %>%
  group_by(sample, phylum, genus, Species) %>%
  summarise(relabun = sum(count))

genus_summary %>%
  group_by(genus) %>%
  summarise(
    Eb_mean = mean(relabun[Species == "Eb"] * 100, na.rm = T),
    Eb_sd = sd(relabun[Species == "Eb"] * 100, na.rm = T),
    Ha_mean = mean(relabun[Species == "Ha"] * 100, na.rm = T),
    Ha_sd = sd(relabun[Species == "Ha"] * 100, na.rm = T),
    Pk_mean = mean(relabun[Species == "Pk"] * 100, na.rm = T),
    Pk_sd = sd(relabun[Species == "Pk"] * 100, na.rm = T)
  ) %>%
  mutate(
    Cnephaeus = str_c(round(Eb_mean, 3), "±", round(Eb_sd, 3)),
    Hypsugo = str_c(round(Ha_mean, 3), "±", round(Ha_sd, 3)),
    Pipistrellus = str_c(round(Pk_mean, 3), "±", round(Pk_sd, 3))
  ) %>%
  arrange(-Pk_mean) %>%
  dplyr::select(genus, Cnephaeus, Hypsugo, Pipistrellus) %>%
  left_join(., genome_metadata[c(3, 7)] %>% unique(), by = join_by(genus == genus)) %>% 
  tt()
genus Cnephaeus Hypsugo Pipistrellus phylum
Serratia 0.222±0.476 9.053±14.403 6.497±18.165 Pseudomonadota
Morganella 0.015±0.033 2.014±6.106 5.676±14.84 Pseudomonadota
Enterococcus 6.978±10.459 2.886±4.693 5.42±10.612 Bacillota
Lactococcus 0.511±0.895 2.038±3.505 4.831±15.637 Bacillota
Bacillus 0.435±0.69 7.278±9.503 4.626±14.907 Bacillota
Rickettsiella 14.286±27.8 0.11±0.44 4.463±20.908 Pseudomonadota
Rickettsia 0.048±0.147 6.599±15.053 4.098±13.243 Pseudomonadota
Vibrio 3.255±10.077 5.495±8.448 3.048±11.084 Pseudomonadota
Enterobacter 15.421±26.452 4.974±10.787 2.813±6.494 Pseudomonadota
Lachnoclostridium 3.641±9.837 0.525±2.016 2.808±7.314 Bacillota
Klebsiella 2.1±2.958 0.639±2.775 2.736±9.216 Pseudomonadota
Proteus 0.106±0.296 0.338±1.256 2.697±7.262 Pseudomonadota
Vespertiliibacter 0.443±1.394 1.874±2.993 2.603±5.092 Pseudomonadota
Desulfovibrio 4.184±5.541 0.278±0.931 2.395±5.102 Desulfobacterota
Mycoplasma 1.232±3.399 0.001±0.003 2.375±11.126 Bacillota
Dysgonomonas 1.534±1.883 2.435±7.724 2.25±5.037 Bacteroidota
Helicobacter 0.442±0.841 0±0 2.05±9.544 Campylobacterota
Lelliottia 0.102±0.203 0.046±0.098 1.801±5.685 Pseudomonadota
Mangrovibacter 3.928±9.942 0.012±0.037 1.604±6.392 Pseudomonadota
Candidatus Soleaferrea 1.146±2.28 0.734±1.963 1.581±3.896 Bacillota
Sebaldella 3.604±6.968 0.046±0.141 1.351±3.946 Fusobacteriota
Microcystis PCC-7914 0±0 0.003±0.014 1.046±4.878 Cyanobacteriota
Vagococcus 0.217±0.457 0.205±0.658 0.994±3.417 Bacillota
Candidatus Arthromitus 0.561±1.774 1.059±4.077 0.925±4.056 Bacillota
Burkholderia-Caballeronia-Paraburkholderia 0±0 0.454±1.002 0.881±3.082 Pseudomonadota
Providencia 0.164±0.354 0.604±1.58 0.875±3.459 Pseudomonadota
Methanimicrococcus 0.017±0.048 0±0 0.855±4.01 Halobacterota
Clostridium sensu stricto 1 0.877±1.977 0.155±0.539 0.826±2.049 Bacillota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Pseudomonadota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Rs-K70 termite group
NA 0.735±2.405 0.997±5.046 0.717±3.21 Bacillota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Bacteroidota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Planctomycetota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Desulfobacterota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Actinomycetota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Patescibacteria
NA 0.735±2.405 0.997±5.046 0.717±3.21 Cyanobacteriota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Synergistota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Thermoplasmatota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Verrucomicrobiota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Myxococcota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Halobacterota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Apal-E12
NA 0.735±2.405 0.997±5.046 0.717±3.21 Bdellovibrionota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Spirochaetota
NA 0.735±2.405 0.997±5.046 0.717±3.21 Chloroflexi
Apibacter 0.512±1.618 0.77±2.187 0.681±2.952 Bacteroidota
Candidatus Fritschea 0±0 0±0 0.619±2.904 Verrucomicrobiota
Commensalibacter 0±0 0.233±0.508 0.611±2.479 Pseudomonadota
Tyzzerella 0.087±0.168 1.75±5.168 0.578±1.805 Bacillota
Aeromonas 1.876±5.145 4.415±8.898 0.551±2.065 Pseudomonadota
Azomonas 0±0 0±0 0.531±2.49 Pseudomonadota
Planktothrix NIVA-CYA 15 0±0 0±0 0.484±1.883 Cyanobacteriota
Liquorilactobacillus 0.056±0.178 0±0 0.458±1.979 Bacillota
Gilliamella 0±0 0.415±1.807 0.456±2.141 Pseudomonadota
Bacteroides 1.85±3.83 0.014±0.046 0.409±1.391 Bacteroidota
Pantoea 0.015±0.041 0.317±0.877 0.376±0.791 Pseudomonadota
Plesiomonas 0.029±0.092 0.005±0.022 0.341±1.6 Pseudomonadota
Suttonella 0±0 0±0 0.308±1.409 Pseudomonadota
Candidatus Tammella 0.639±1.252 0.156±0.663 0.289±0.64 Synergistota
Mesoplasma 0±0 2.224±7.761 0.282±1.307 Bacillota
Fusobacterium 1.29±2.394 0.164±0.629 0.267±1.17 Fusobacteriota
Cyanobium PCC-6307 0±0 0.041±0.088 0.266±1.15 Cyanobacteriota
Paracoccus 0.007±0.022 0.013±0.03 0.235±1.104 Pseudomonadota
Anaerosporobacter 0.26±0.745 0±0 0.211±0.586 Bacillota
Wolbachia 0.001±0.004 0.265±0.599 0.204±0.463 Pseudomonadota
Incertae Sedis 0.482±0.606 0.014±0.042 0.202±0.609 Bacillota
Diplorickettsia 0±0 0.088±0.273 0.201±0.941 Pseudomonadota
NK4A214 group 0.051±0.156 0±0 0.184±0.596 Bacillota
Microvirga 0±0 0±0 0.178±0.723 Pseudomonadota
Brevinema 0±0 0.023±0.101 0.174±0.754 Spirochaetota
Staphylococcus 0.168±0.527 0.035±0.059 0.162±0.455 Bacillota
Erwinia 0.004±0.013 0.222±0.482 0.16±0.652 Pseudomonadota
Candidatus Nasuia 0±0 1.213±5.288 0.144±0.672 Pseudomonadota
Ignatzschineria 0.011±0.035 0±0 0.141±0.663 Pseudomonadota
Rahnella1 0±0 0.37±1.585 0.139±0.65 Pseudomonadota
Escherichia-Shigella 0.233±0.735 0.014±0.037 0.138±0.63 Pseudomonadota
Koukoulia 0.188±0.593 0.004±0.011 0.117±0.416 Pseudomonadota
Christensenellaceae R-7 group 0.241±0.45 0.009±0.026 0.116±0.522 Bacillota
Lachnospiraceae UCG-010 0.002±0.006 0±0 0.113±0.3 Bacillota
Bavariicoccus 0±0 0.032±0.138 0.112±0.472 Bacillota
Zymobacter 2.434±7.5 0.799±2.003 0.107±0.493 Pseudomonadota
Acinetobacter 0.124±0.187 0.743±2.714 0.107±0.228 Pseudomonadota
Roseomonas 0±0 0.003±0.008 0.096±0.446 Pseudomonadota
Romboutsia 0.445±0.823 0.011±0.027 0.085±0.226 Bacillota
Papillibacter 0.014±0.045 0.007±0.031 0.077±0.239 Bacillota
Methanospirillum 0±0 0±0 0.074±0.338 Halobacterota
Corynebacterium 0.018±0.052 0.068±0.091 0.068±0.119 Actinomycetota
Intestinimonas 0.003±0.006 0±0 0.066±0.233 Bacillota
Citrobacter 0.028±0.062 0±0 0.061±0.12 Pseudomonadota
Candidatus Saccharimonas 0.533±1.614 0±0 0.06±0.281 Patescibacteria
Methanobrevibacter 0±0 0±0 0.056±0.186 Euryarchaeota
Monoglobus 0.106±0.284 0.003±0.014 0.056±0.192 Bacillota
Breznakia 1.149±3.202 0.047±0.204 0.053±0.169 Bacillota
Candidatus Methanoplasma 0±0 0±0 0.051±0.241 Thermoplasmatota
Proteiniphilum 0±0 0.044±0.094 0.05±0.17 Bacteroidota
Streptomyces 0±0 0.049±0.08 0.049±0.134 Actinomycetota
Rosenbergiella 0±0 0.012±0.036 0.045±0.211 Pseudomonadota
CL500-3 0±0 0±0 0.043±0.204 Planctomycetota
Oxalobacter 0.131±0.307 0.011±0.046 0.043±0.099 Pseudomonadota
Brevibacterium 0.029±0.091 0.001±0.004 0.042±0.149 Actinomycetota
Anaerovorax 0.068±0.154 0±0 0.042±0.116 Bacillota
Tychonema CCAP 1459-11B 0±0 0.02±0.071 0.041±0.183 Cyanobacteriota
Leminorella 0.005±0.016 0.018±0.076 0.038±0.178 Pseudomonadota
Paludicola 0.676±1.954 0.025±0.057 0.037±0.112 Bacillota
Tabrizicola 0±0 0.008±0.036 0.035±0.166 Pseudomonadota
Erysipelatoclostridium 0.054±0.1 0.025±0.082 0.035±0.098 Bacillota
Colidextribacter 0.04±0.125 0±0 0.033±0.102 Bacillota
Moheibacter 0±0 0±0 0.033±0.125 Bacteroidota
Pseudomonas 0.234±0.441 1.443±3.901 0.031±0.074 Pseudomonadota
Asaia 0.123±0.388 0.002±0.01 0.029±0.089 Pseudomonadota
Pectobacterium 0.027±0.086 0.021±0.049 0.027±0.094 Pseudomonadota
[Eubacterium] brachy group 0.108±0.216 0.001±0.004 0.026±0.072 Bacillota
Phenylobacterium 0±0 0±0 0.022±0.102 Pseudomonadota
Brachybacterium 0.012±0.038 0±0 0.021±0.073 Actinomycetota
Pelotomaculum 0±0 0±0 0.02±0.092 Bacillota
Kosakonia 0±0 0±0 0.019±0.078 Pseudomonadota
Cosenzaea 0±0 0.003±0.015 0.019±0.068 Pseudomonadota
Lacticaseibacillus 0.027±0.073 0.685±1.618 0.019±0.088 Bacillota
Methanocorpusculum 0±0 0±0 0.017±0.079 Halobacterota
Anaerotruncus 0.002±0.005 0.013±0.055 0.017±0.054 Bacillota
Spiroplasma 0.006±0.017 0.01±0.03 0.016±0.06 Bacillota
Micrococcus 0±0 0.062±0.14 0.015±0.052 Actinomycetota
Pseudoxanthomonas 0±0 0.005±0.023 0.015±0.054 Pseudomonadota
Nosocomiicoccus 0±0 0±0 0.014±0.056 Bacillota
Hafnia-Obesumbacterium 0±0 0.564±1.437 0.013±0.043 Pseudomonadota
Polynucleobacter 0±0 0.003±0.009 0.013±0.052 Pseudomonadota
Salmonella 0.285±0.544 0.399±0.743 0.013±0.056 Pseudomonadota
Raoultibacter 0.001±0.003 0.004±0.015 0.012±0.058 Actinomycetota
Pragia 0.03±0.095 0.005±0.022 0.012±0.058 Pseudomonadota
Weissella 0.049±0.146 0.007±0.02 0.012±0.043 Bacillota
Streptococcus 0.002±0.006 0.116±0.177 0.012±0.027 Bacillota
Dendrosporobacter 0±0 0±0 0.012±0.035 Bacillota
Simonsiella 0±0 0±0 0.012±0.056 Pseudomonadota
Dietzia 0.012±0.039 0±0 0.012±0.031 Actinomycetota
Rubritepida 0±0 0±0 0.012±0.055 Pseudomonadota
Methylocystis 0±0 0.004±0.015 0.011±0.043 Pseudomonadota
Anaerofustis 0±0 0±0 0.011±0.053 Bacillota
Kocuria 0±0 0.04±0.108 0.011±0.033 Actinomycetota
Alpinimonas 0±0 0±0 0.011±0.051 Actinomycetota
Chelonobacter 0±0 0.025±0.085 0.011±0.036 Pseudomonadota
Erysipelothrix 0.046±0.127 0.001±0.003 0.011±0.05 Bacillota
Alistipes 0.212±0.386 0.005±0.018 0.011±0.029 Bacteroidota
Ureaplasma 0.028±0.09 0±0 0.01±0.048 Bacillota
Carnimonas 0±0 0±0 0.01±0.048 Pseudomonadota
Rhodobacter 0.019±0.06 0.004±0.016 0.01±0.031 Pseudomonadota
Pelospora 0±0 0±0 0.009±0.025 Bacillota
Listeria 0±0 0±0 0.009±0.03 Bacillota
Carnobacterium 0±0 0±0 0.009±0.041 Bacillota
Sediminispirochaeta 0±0 0±0 0.008±0.038 Spirochaetota
Turicibacter 0.361±0.798 0.07±0.142 0.007±0.018 Bacillota
Phreatobacter 0±0 0±0 0.007±0.033 Pseudomonadota
Levilactobacillus 0±0 0±0 0.007±0.033 Bacillota
Ochrobactrum 0.022±0.065 0±0 0.007±0.033 Pseudomonadota
Planomicrobium 0±0 0.019±0.054 0.007±0.031 Bacillota
LD29 0±0 0.004±0.018 0.006±0.03 Verrucomicrobiota
Desulfosporosinus 0±0 0±0 0.006±0.03 Bacillota
Desulfobulbus 0±0 0.021±0.093 0.006±0.03 Desulfobacterota
Entomoplasma 0±0 0.013±0.057 0.006±0.026 Bacillota
Defluviitaleaceae UCG-011 0.015±0.034 0±0 0.006±0.024 Bacillota
Desulfomicrobium 0±0 0.02±0.087 0.006±0.024 Desulfobacterota
Sphingobacterium 0±0 0±0 0.006±0.028 Bacteroidota
Pseudorhodobacter 0±0 0.008±0.02 0.006±0.019 Pseudomonadota
Comamonas 0±0 0±0 0.005±0.022 Pseudomonadota
Psychrobacter 0±0 0.003±0.012 0.005±0.024 Pseudomonadota
Virgibacillus 0.003±0.007 0.01±0.026 0.005±0.016 Bacillota
ZOR0006 0.027±0.077 0.158±0.457 0.005±0.016 Bacillota
Falsochrobactrum 0±0 0±0 0.005±0.02 Pseudomonadota
[Eubacterium] fissicatena group 0±0 0±0 0.005±0.022 Bacillota
Leuconostoc 0±0 0±0 0.005±0.022 Bacillota
GKS98 freshwater group 0.008±0.017 0.003±0.01 0.005±0.012 Pseudomonadota
Rubellimicrobium 0±0 0.013±0.043 0.004±0.021 Pseudomonadota
Fructilactobacillus 0±0 0.002±0.006 0.004±0.021 Bacillota
Flavimaricola 0±0 0±0 0.004±0.02 Pseudomonadota
Chlamydia 0±0 0±0 0.004±0.02 Verrucomicrobiota
Actinoplanes 0±0 0±0 0.004±0.019 Actinomycetota
Gordonia 0±0 0±0 0.004±0.013 Actinomycetota
Chryseobacterium 0.061±0.191 0.98±4.167 0.004±0.014 Bacteroidota
Rhodovarius 0±0 0±0 0.004±0.018 Pseudomonadota
Rubrobacter 0±0 0.05±0.214 0.004±0.013 Actinomycetota
Pluralibacter 0±0 0±0 0.004±0.017 Pseudomonadota
Candidatus Aquiluna 0±0 0±0 0.004±0.017 Actinomycetota
Actinomyces 0±0 0.165±0.511 0.003±0.011 Actinomycetota
Terrimicrobium 0.112±0.353 0.002±0.007 0.003±0.016 Verrucomicrobiota
Pseudorhizobium 0±0 0.029±0.126 0.003±0.016 Pseudomonadota
Lachnospiraceae NK4A136 group 0±0 0±0 0.003±0.016 Bacillota
Companilactobacillus 0.012±0.027 0±0 0.003±0.016 Bacillota
CL500-29 marine group 0±0 0.002±0.01 0.003±0.016 Actinomycetota
Halomonas 0±0 1.314±5.653 0.003±0.016 Pseudomonadota
Harryflintia 0±0 0±0 0.003±0.015 Bacillota
Planococcus 0.002±0.006 0.003±0.012 0.003±0.013 Bacillota
Allorhizobium-Neorhizobium-Pararhizobium-Rhizobium 0.04±0.119 0.019±0.043 0.003±0.012 Pseudomonadota
Orbus 0±0 0.036±0.141 0.003±0.014 Pseudomonadota
Jeotgalicoccus 0.002±0.005 0±0 0.003±0.014 Bacillota
Lechevalieria 0±0 0.004±0.011 0.003±0.014 Actinomycetota
SM1A02 0±0 0±0 0.003±0.013 Planctomycetota
Gemmobacter 0±0 0.01±0.028 0.003±0.013 Pseudomonadota
Parabacteroides 0.334±0.6 0.014±0.06 0.003±0.013 Bacteroidota
Lactonifactor 0±0 0±0 0.003±0.012 Bacillota
Flavobacterium 0±0 0±0 0.003±0.008 Bacteroidota
Peptoniphilus 0±0 0.022±0.095 0.003±0.007 Bacillota
Brucella 0±0 0±0 0.003±0.012 Pseudomonadota
Klenkia 0±0 0±0 0.003±0.012 Actinomycetota
Halomarina 0±0 0.026±0.114 0.003±0.01 Halobacterota
Bdellovibrio 0±0 0±0 0.003±0.012 Bdellovibrionota
Elioraea 0±0 0±0 0.003±0.012 Pseudomonadota
Domibacillus 0.004±0.014 0±0 0.002±0.012 Bacillota
Lactobacillus 0±0 0.035±0.078 0.002±0.009 Bacillota
Akkermansia 0.023±0.048 0.068±0.295 0.002±0.012 Verrucomicrobiota
Candidatus Nitrocosmicus 0±0 0.002±0.009 0.002±0.009 Crenarchaeota
Pseudarcobacter 0±0 0±0 0.002±0.011 Campylobacterota
Salilacibacter 0±0 0±0 0.002±0.011 Actinomycetota
Azospira 0±0 0±0 0.002±0.01 Pseudomonadota
Porphyrobacter 0±0 0.009±0.04 0.002±0.01 Pseudomonadota
Uruburuella 0±0 0±0 0.002±0.01 Pseudomonadota
Neokomagataea 0±0 0±0 0.002±0.01 Pseudomonadota
Endomicrobium 0.009±0.021 0±0 0.002±0.01 Elusimicrobiota
Arboricoccus 0±0 0±0 0.002±0.01 Pseudomonadota
Massilia 0±0 0.004±0.013 0.002±0.01 Pseudomonadota
Glutamicibacter 0.007±0.023 0±0 0.002±0.007 Actinomycetota
Caedibacter 0±0 0±0 0.002±0.01 Pseudomonadota
Hyphomicrobium 0±0 0±0 0.002±0.01 Pseudomonadota
Shimwellia 0.024±0.068 0.107±0.459 0.002±0.01 Pseudomonadota
Buttiauxella 0±0 0.003±0.01 0.002±0.009 Pseudomonadota
Luteolibacter 0±0 0.003±0.011 0.002±0.005 Verrucomicrobiota
UCG-009 0.009±0.029 0±0 0.002±0.005 Bacillota
Testudinibacter 0±0 0.01±0.044 0.002±0.008 Pseudomonadota
Soonwooa 0±0 0.024±0.08 0.002±0.008 Bacteroidota
Exiguobacterium 0±0 0.012±0.036 0.002±0.008 Bacillota
Methylotenera 0±0 0.001±0.003 0.002±0.008 Pseudomonadota
CAG-352 0±0 0±0 0.002±0.008 Bacillota
Pseudarthrobacter 0±0 0.004±0.011 0.002±0.008 Actinomycetota
Pseudoramibacter 0±0 0±0 0.002±0.008 Bacillota
Candidatus Lariskella 0±0 0.003±0.013 0.002±0.007 Pseudomonadota
Candidatus Sulcia 0.017±0.054 0.408±1.773 0.001±0.007 Bacteroidota
Neisseria 0±0 0.002±0.007 0.001±0.006 Pseudomonadota
Nocardiopsis 0.003±0.011 0.014±0.059 0.001±0.006 Actinomycetota
Rikenellaceae RC9 gut group 0.006±0.02 0.115±0.434 0.001±0.004 Bacteroidota
Synechocystis PCC-6803 0±0 0±0 0.001±0.006 Cyanobacteriota
Crenotalea 0±0 0±0 0.001±0.006 Bacteroidota
Pseudogracilibacillus 0±0 0±0 0.001±0.006 Bacillota
Verticiella 0.005±0.014 0±0 0.001±0.005 Pseudomonadota
Haloterrigena 0±0 0.042±0.185 0.001±0.005 Halobacterota
Catenococcus 0±0 0±0 0.001±0.005 Pseudomonadota
Mucispirillum 0.043±0.107 0±0 0.001±0.005 Deferribacterota
Sinomicrobium 0±0 0±0 0.001±0.005 Bacteroidota
C39 0±0 0±0 0.001±0.005 Pseudomonadota
Orrella 0±0 0±0 0.001±0.005 Pseudomonadota
Candidatus Nitrososphaera 0±0 0±0 0.001±0.005 Crenarchaeota
Desulfurispora 0±0 0±0 0.001±0.005 Bacillota
Saccharothrix 0±0 0.008±0.028 0.001±0.005 Actinomycetota
Syntrophobotulus 0±0 0±0 0.001±0.005 Bacillota
966-1 0±0 0±0 0.001±0.004 Pseudomonadota
Leptotrichia 0±0 0.172±0.725 0.001±0.004 Fusobacteriota
Candidatus Regiella 0±0 0±0 0.001±0.004 Pseudomonadota
Fervidobacterium 0±0 0±0 0.001±0.004 Thermotogota
Adhaeribacter 0±0 0±0 0.001±0.004 Bacteroidota
Pedobacter 0±0 0±0 0.001±0.004 Bacteroidota
Prevotella 0±0 0.007±0.026 0.001±0.004 Bacteroidota
Eikenella 0±0 0±0 0.001±0.004 Pseudomonadota
Myroides 0.509±1.608 0±0 0.001±0.004 Bacteroidota
Lawsonella 0±0 0.001±0.002 0.001±0.004 Actinomycetota
Robbsia 0.001±0.004 1.644±7.165 0.001±0.004 Pseudomonadota
Arcticibacter 0±0 0±0 0.001±0.004 Bacteroidota
TM7a 0.004±0.012 0.04±0.153 0.001±0.003 Patescibacteria
Syntrophomonas 0±0 0±0 0.001±0.003 Bacillota
Alloprevotella 0±0 0±0 0.001±0.003 Bacteroidota
Gemella 0±0 0.002±0.009 0.001±0.003 Bacillota
Kribbella 0±0 0±0 0.001±0.003 Actinomycetota
Segetibacter 0±0 0±0 0.001±0.003 Bacteroidota
Sphingomonas 0±0 0.013±0.025 0.001±0.003 Pseudomonadota
Aquibacillus 0±0 0±0 0.001±0.003 Bacillota
Labrys 0±0 0±0 0.001±0.003 Pseudomonadota
hgcI clade 0±0 0.004±0.014 0.001±0.003 Actinomycetota
Sorangium 0±0 0±0 0.001±0.003 Myxococcota
Taibaiella 0±0 0±0 0.001±0.003 Bacteroidota
Spirillospora 0±0 0±0 0.001±0.003 Actinomycetota
Weeksella 0±0 0.01±0.043 0.001±0.003 Bacteroidota
Cytophaga 0±0 0±0 0±0.002 Bacteroidota
Chthoniobacter 0±0 0±0 0±0.002 Verrucomicrobiota
Sanguibacteroides 0.001±0.004 0±0 0±0.002 Bacteroidota
Alsobacter 0±0 0±0 0±0.002 Pseudomonadota
Methyloparacoccus 0±0 0±0 0±0.002 Pseudomonadota
Campylobacter 0.025±0.055 0.263±0.677 0±0.002 Campylobacterota
Candidatus Udaeobacter 0±0 0±0 0±0.002 Verrucomicrobiota
Shewanella 0±0 0.007±0.026 0±0.002 Pseudomonadota
Pseudonocardia 0±0 0±0 0±0.002 Actinomycetota
Acaricomes 0±0 0.627±2.731 0±0 Actinomycetota
Achromobacter 0±0 0.036±0.112 0±0 Pseudomonadota
Actinobacillus 0±0 0.039±0.169 0±0 Pseudomonadota
Actinomadura 0±0 0.002±0.009 0±0 Actinomycetota
Actinopolyspora 0±0 0.006±0.027 0±0 Actinomycetota
Actinorectispora 0±0 0.001±0.007 0±0 Actinomycetota
Acuticoccus 0±0 0.001±0.005 0±0 Pseudomonadota
Alcaligenes 0.01±0.032 0±0 0±0 Pseudomonadota
Alcanivorax 0±0 0.014±0.054 0±0 Pseudomonadota
Aliihoeflea 0±0 0.003±0.015 0±0 Pseudomonadota
Aliterella 0±0 0.002±0.007 0±0 Cyanobacteriota
Alkanindiges 0±0 0.121±0.427 0±0 Pseudomonadota
Allokutzneria 0±0 0.002±0.008 0±0 Actinomycetota
Ammoniphilus 0.002±0.005 0.003±0.013 0±0 Bacillota
Anaerobacillus 0.004±0.014 0.002±0.009 0±0 Bacillota
Apilactobacillus 0.002±0.007 0.159±0.694 0±0 Bacillota
Aquabacterium 0±0 0.001±0.003 0±0 Pseudomonadota
Aquicella 0±0 0.004±0.014 0±0 Pseudomonadota
Arcobacter 0.017±0.04 0±0 0±0 Campylobacterota
Arsenophonus 0±0 0.995±3.047 0±0 Pseudomonadota
Arthrobacter 0±0 0.015±0.042 0±0 Actinomycetota
Arthrospira PCC-7345 0±0 0.005±0.02 0±0 Cyanobacteriota
Aurantimonas 0±0 0.001±0.005 0±0 Pseudomonadota
Aurantisolimonas 0±0 0.001±0.002 0±0 Bacteroidota
Aureimonas 0±0 0.006±0.026 0±0 Pseudomonadota
Auricoccus-Abyssicoccus 0±0 0.002±0.009 0±0 Bacillota
Azoarcus 0.572±1.51 0.015±0.05 0±0 Pseudomonadota
BIyi10 0±0 0.001±0.003 0±0 Pseudomonadota
Bartonella 0.018±0.038 0.591±2.183 0±0 Pseudomonadota
Bilophila 0±0 0.003±0.015 0±0 Desulfobacterota
Blastococcus 0±0 0.034±0.086 0±0 Actinomycetota
Blastopirellula 0±0 0.002±0.007 0±0 Planctomycetota
Bordetella 0.002±0.005 0±0 0±0 Pseudomonadota
Brevundimonas 0.003±0.008 0.005±0.02 0±0 Pseudomonadota
Caenimonas 0±0 0.001±0.006 0±0 Pseudomonadota
Candidatus Bacilloplasma 0±0 0.045±0.167 0±0 Bacillota
Candidatus Limnoluna 0±0 0.003±0.013 0±0 Actinomycetota
Candidatus Midichloria 0±0 0.002±0.01 0±0 Pseudomonadota
Candidatus Purcelliella 0±0 0.076±0.331 0±0 Pseudomonadota
Candidatus Vestibaculum 0.106±0.218 0±0 0±0 Bacteroidota
Candidatus Vidania 0±0 0.232±1.008 0±0 Pseudomonadota
Candidatus Xiphinematobacter 0±0 0.001±0.003 0±0 Verrucomicrobiota
Castellaniella 0±0 0.001±0.005 0±0 Pseudomonadota
Cellulomonas 0±0 0.002±0.009 0±0 Actinomycetota
Cellulosilyticum 0±0 0.001±0.003 0±0 Bacillota
Cerasicoccus 0.003±0.009 0±0 0±0 Verrucomicrobiota
Cetobacterium 0.163±0.515 0±0 0±0 Fusobacteriota
Chishuiella 0±0 0.069±0.297 0±0 Bacteroidota
Chitinibacter 0±0 0.039±0.171 0±0 Pseudomonadota
Chroococcidiopsis SAG 2023 0±0 0.471±2.054 0±0 Cyanobacteriota
Citreicella 0±0 0.001±0.004 0±0 Pseudomonadota
Cloacibacterium 0±0 0.001±0.005 0±0 Bacteroidota
Clostridium sensu stricto 2 0±0 0.015±0.067 0±0 Bacillota
Clostridium sensu stricto 7 0±0 0.005±0.021 0±0 Bacillota
Conchiformibius 0±0 1.148±3.618 0±0 Pseudomonadota
Conexibacter 0±0 0.002±0.007 0±0 Actinomycetota
Conservatibacter 0±0 0.002±0.007 0±0 Pseudomonadota
Constrictibacter 0±0 0.001±0.003 0±0 Pseudomonadota
Coprobacillus 0.002±0.007 0±0 0±0 Bacillota
Corticibacter 0±0 0.161±0.42 0±0 Pseudomonadota
Cyanobacterium PCC-7202 0±0 0.002±0.007 0±0 Cyanobacteriota
Deinococcus 0±0 0.003±0.014 0±0 Deinococcota
Devosia 0.005±0.016 0.008±0.037 0±0 Pseudomonadota
Elizabethkingia 0±0 0.002±0.008 0±0 Bacteroidota
Elusimicrobium 0.097±0.28 0±0 0±0 Elusimicrobiota
Empedobacter 0±0 0.001±0.003 0±0 Bacteroidota
Enterobacillus 1.47±4.481 0.017±0.072 0±0 Pseudomonadota
Enteroscipio 0±0 0.001±0.003 0±0 Actinomycetota
Epulopiscium 0.04±0.125 0±0 0±0 Bacillota
Eubacterium 0.146±0.449 0.004±0.012 0±0 Bacillota
Falsibacillus 0±0 0.003±0.011 0±0 Bacillota
Family XIII AD3011 group 0±0 0.002±0.008 0±0 Bacillota
Flavisolibacter 0±0 0.003±0.014 0±0 Bacteroidota
Fretibacterium 0.008±0.026 0±0 0±0 Synergistota
Frigoribacterium 0±0 0.003±0.012 0±0 Actinomycetota
Frisingicoccus 0.002±0.006 0±0 0±0 Bacillota
Fructobacillus 0±0 0.218±0.363 0±0 Bacillota
Gallicola 0.029±0.091 0.069±0.214 0±0 Bacillota
Geminocystis PCC-6308 0±0 0.001±0.004 0±0 Cyanobacteriota
Geodermatophilus 0±0 0.001±0.006 0±0 Actinomycetota
Gracilibacillus 0.003±0.009 0±0 0±0 Bacillota
Haematospirillum 0±0 0.047±0.158 0±0 Pseudomonadota
Haemophilus 0±0 0.009±0.017 0±0 Pseudomonadota
Haladaptatus 0±0 0.013±0.056 0±0 Halobacterota
Halalkalicoccus 0±0 0.027±0.119 0±0 Halobacterota
Haliangium 0±0 0.003±0.011 0±0 Myxococcota
Halobacillus 0.001±0.004 0.001±0.004 0±0 Bacillota
Halobellus 0±0 0.001±0.006 0±0 Halobacterota
Halococcus 0±0 0.001±0.005 0±0 Halobacterota
Halohasta 0±0 0.001±0.006 0±0 Halobacterota
Halolamina 0±0 0.01±0.043 0±0 Halobacterota
Halomicrobium 0±0 0.002±0.008 0±0 Halobacterota
Halorussus 0±0 0.019±0.085 0±0 Halobacterota
Halostagnicola 0±0 0.024±0.105 0±0 Halobacterota
Halovivax 0±0 0.007±0.028 0±0 Halobacterota
Haoranjiania 0±0 0.005±0.016 0±0 Bacteroidota
Herbinix 0±0 0.006±0.027 0±0 Bacillota
Holzapfelia 0.032±0.102 1.025±4.47 0±0 Bacillota
Isobaculum 0±0 0.018±0.076 0±0 Bacillota
Izhakiella 0±0 0.559±2.416 0±0 Pseudomonadota
Kibdelosporangium 0±0 0.001±0.003 0±0 Actinomycetota
Kingella 0±0 0.001±0.002 0±0 Pseudomonadota
Kluyvera 0±0 0.007±0.028 0±0 Pseudomonadota
Kurthia 0.003±0.01 0±0 0±0 Bacillota
Lachnospiraceae AC2044 group 0.036±0.095 0.002±0.007 0±0 Bacillota
Lachnospiraceae UCG-007 0±0 0.001±0.003 0±0 Bacillota
Lactiplantibacillus 0.004±0.013 0.003±0.014 0±0 Bacillota
Lampropedia 0±0 0.004±0.017 0±0 Pseudomonadota
Latilactobacillus 0.005±0.014 0.051±0.193 0±0 Bacillota
Legionella 0±0 0.002±0.008 0±0 Pseudomonadota
Leptolyngbya ANT.L52.2 0±0 0.001±0.005 0±0 Cyanobacteriota
Leucobacter 0.004±0.011 0±0 0±0 Actinomycetota
Limnothrix 0±0 0.009±0.041 0±0 Cyanobacteriota
Lonsdalea 0±0 0.001±0.006 0±0 Pseudomonadota
Loriellopsis LF-B5 0±0 0.001±0.005 0±0 Cyanobacteriota
Luteimonas 0.001±0.004 0.025±0.101 0±0 Pseudomonadota
Lyngbya PCC-7419 0±0 0.001±0.005 0±0 Cyanobacteriota
Lysinibacillus 0.005±0.017 0.001±0.002 0±0 Bacillota
Lysobacter 0.001±0.004 0.001±0.002 0±0 Pseudomonadota
MND1 0±0 0.001±0.005 0±0 Pseudomonadota
Marinobacter 0±0 0.001±0.004 0±0 Pseudomonadota
Mesorhizobium 0±0 0.011±0.047 0±0 Pseudomonadota
Methylophaga 0.001±0.005 0±0 0±0 Pseudomonadota
Microbulbifer 0±0 0.005±0.02 0±0 Pseudomonadota
Modestobacter 0±0 0.004±0.011 0±0 Actinomycetota
Mucinivorans 0±0 0.001±0.004 0±0 Bacteroidota
Murinocardiopsis 0±0 0.002±0.007 0±0 Actinomycetota
Nakamurella 0±0 0.001±0.003 0±0 Actinomycetota
Nannocystis 0±0 0.001±0.004 0±0 Myxococcota
Natronorubrum 0±0 0.003±0.013 0±0 Halobacterota
Niabella 0±0 0.006±0.024 0±0 Bacteroidota
Nitrolancea 0±0 0.002±0.007 0±0 Chloroflexi
Nocardia 0±0 0.001±0.005 0±0 Actinomycetota
Nocardioides 0±0 0.02±0.054 0±0 Actinomycetota
Nodosilinea PCC-7104 0.005±0.016 0.006±0.014 0±0 Cyanobacteriota
Nonomuraea 0±0 0.004±0.018 0±0 Actinomycetota
Noviherbaspirillum 0±0 0.001±0.005 0±0 Pseudomonadota
Oceanobacillus 0±0 0.013±0.047 0±0 Bacillota
Odoribacter 0.016±0.035 0.012±0.053 0±0 Bacteroidota
Ornithinibacillus 0±0 0.002±0.007 0±0 Bacillota
PMMR1 0±0 0.001±0.006 0±0 Pseudomonadota
Paenalcaligenes 0.007±0.017 0±0 0±0 Pseudomonadota
Paenochrobactrum 0.016±0.051 0±0 0±0 Pseudomonadota
Palleronia-Pseudomaribius 0±0 0.003±0.013 0±0 Pseudomonadota
Paludibacter 0.001±0.003 0±0 0±0 Bacteroidota
Parapusillimonas 0.018±0.039 0.002±0.007 0±0 Pseudomonadota
Pararhodospirillum 0.01±0.032 0±0 0±0 Pseudomonadota
Pelagibacterium 0.002±0.006 0.006±0.028 0±0 Pseudomonadota
Peptococcus 0±0 0.01±0.044 0±0 Bacillota
Peredibacter 0±0 0.001±0.003 0±0 Bdellovibrionota
Perlucidibaca 0±0 0.002±0.007 0±0 Pseudomonadota
Phyllobacterium 0±0 0.023±0.102 0±0 Pseudomonadota
Pirellula 0±0 0.001±0.003 0±0 Planctomycetota
Polymorphobacter 0±0 0.004±0.018 0±0 Pseudomonadota
Porphyromonas 0±0 0.001±0.004 0±0 Bacteroidota
Prevotella_7 0±0 0.004±0.015 0±0 Bacteroidota
Promicromonospora 0±0 0.004±0.016 0±0 Actinomycetota
Propionivibrio 0±0 0.006±0.025 0±0 Pseudomonadota
Pseudaminobacter 0±0 0.004±0.018 0±0 Pseudomonadota
Pseudocitrobacter 1.178±2.746 0.055±0.239 0±0 Pseudomonadota
Psychroglaciecola 0±0 0.001±0.005 0±0 Pseudomonadota
Pullulanibacillus 0±0 0.002±0.009 0±0 Bacillota
Pygmaiobacter 0.003±0.009 0±0 0±0 Bacillota
Quadrisphaera 0±0 0.013±0.058 0±0 Actinomycetota
Ralstonia 0±0 0.004±0.019 0±0 Pseudomonadota
Ramlibacter 0.007±0.023 0±0 0±0 Pseudomonadota
Raoultella 0.109±0.344 0.001±0.006 0±0 Pseudomonadota
Reyranella 0.002±0.005 0.002±0.009 0±0 Pseudomonadota
Rhodococcus 0±0 0.001±0.003 0±0 Actinomycetota
Rhodoluna 0±0 0.003±0.014 0±0 Actinomycetota
Rhodopirellula 0±0 0.001±0.006 0±0 Planctomycetota
Rhodospirillum 0.056±0.176 0±0 0±0 Pseudomonadota
Robinsoniella 0.011±0.035 0±0 0±0 Bacillota
Roseofilum AO1-A 0±0 0.001±0.005 0±0 Cyanobacteriota
Roseovarius 0±0 0.001±0.006 0±0 Pseudomonadota
Rothia 0±0 0.017±0.045 0±0 Actinomycetota
Rs-D38 termite group 0.022±0.038 0±0 0±0 Bacteroidota
Ruminococcus 0±0 0.013±0.059 0±0 Bacillota
SH3-11 0±0 0.001±0.005 0±0 Verrucomicrobiota
SN8 0±0 0.026±0.089 0±0 Pseudomonadota
SZB85 0±0 0.001±0.003 0±0 Pseudomonadota
Saccharopolyspora 0±0 0.002±0.007 0±0 Actinomycetota
Salinarimonas 0±0 0.001±0.005 0±0 Pseudomonadota
Salinicoccus 0±0 0.001±0.005 0±0 Bacillota
Sandaracinobacter 0±0 0.002±0.009 0±0 Pseudomonadota
Secundilactobacillus 0.011±0.034 0.019±0.051 0±0 Bacillota
Shimazuella 0±0 0.001±0.006 0±0 Bacillota
Shuttleworthia 0.002±0.007 0±0 0±0 Bacillota
Siccibacter 0.018±0.037 0.03±0.121 0±0 Pseudomonadota
Silvanigrella 0±0 0.002±0.007 0±0 Bdellovibrionota
Skermanella 0±0 0.005±0.014 0±0 Pseudomonadota
Snodgrassella 0±0 0.002±0.009 0±0 Pseudomonadota
Sodalis 0.089±0.282 0.216±0.608 0±0 Pseudomonadota
Solirubrobacter 0±0 0.006±0.026 0±0 Actinomycetota
Stenotrophomonas 0.008±0.016 0.007±0.017 0±0 Pseudomonadota
Stenoxybacter 0±0 0.011±0.05 0±0 Pseudomonadota
Sulfurimonas 0±0 0.002±0.01 0±0 Campylobacterota
Sulfurospirillum 0.045±0.129 0±0 0±0 Campylobacterota
Sumerlaea 0±0 0.002±0.007 0±0 Sumerlaeota
Synechococcus PCC-7942 0.023±0.072 0±0 0±0 Cyanobacteriota
Tamaricihabitans 0±0 0.001±0.006 0±0 Actinomycetota
Tatumella 0±0 0.004±0.018 0±0 Pseudomonadota
Terribacillus 0.008±0.027 0±0 0±0 Bacillota
Thiolamprovum 0.006±0.02 0±0 0±0 Pseudomonadota
Tissierella 0.047±0.15 0±0 0±0 Bacillota
Trabulsiella 0±0 0.062±0.271 0±0 Pseudomonadota
Treponema 0.013±0.042 0±0 0±0 Spirochaetota
Truepera 0±0 0.049±0.198 0±0 Deinococcota
Tsukamurella 0±0 0.011±0.047 0±0 Actinomycetota
Tuzzerella 0.002±0.005 0±0 0±0 Bacillota
Veillonella 0±0 0.01±0.024 0±0 Bacillota
Vogesella 0±0 0.045±0.156 0±0 Pseudomonadota
Wohlfahrtiimonas 0.003±0.01 0.011±0.047 0±0 Pseudomonadota
dgA-11 gut group 0±0 0.005±0.021 0±0 Bacteroidota

3.2.2 ASVs

Number of ASVs and distinct taxonomy

bats = c("Eb", "Pk", "Ha")

total_asvs <- data.frame(
  Bat = character(),
  MAGs = numeric(),
  Phylum = numeric(),
  Family = numeric(),
  Genus = numeric()
)

preabs_table <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("genome")  %>%
  left_join(genome_metadata, by = join_by("genome" == "genome")) 
# %>% 
#   filter(domain=="Bacteria")

phylum <- preabs_table %>%
  distinct(phylum)

family <- preabs_table %>%
  distinct(phylum, class, order, family)

genus <- preabs_table %>%
  distinct(phylum, class, order, family, genus)

total_asvs <- rbind(
  total_asvs,
  data.frame(
    Bat = "Total",
    ASVs = nrow(preabs_table),
    Phylum = nrow(phylum),
    Family = nrow(family),
    Genus = nrow(genus)
  )
)

for (bat in bats) {
  number <- preabs_table %>%
    select({{bat}}) %>%
    filter(. >= 1)
  
  phylum <- preabs_table %>%
    select({{bat}}, phylum) %>%
    filter(!!sym(bat) >= 1) %>%
    distinct(phylum)
  
  family <- preabs_table %>%
    select({{bat}}, phylum, class, order, family) %>%
    filter(!!sym(bat) >= 1) %>%
    distinct(phylum, class, order, family)
  
  genus <- preabs_table %>%
    select({{bat}}, phylum, class, order, family, genus) %>%
    filter(!!sym(bat) >= 1) %>%
    distinct(phylum, class, order, family, genus)
  
  total_asvs <- rbind(
    total_asvs,
    data.frame(
      Bat = bat,
      ASVs = nrow(number),
      Phylum = nrow(phylum),
      Family = nrow(family),
      Genus = nrow(genus)
    )
  )
}
bats = c("Eb", "Pk", "Ha")

no_annotation <- data.frame(Bat = character(),
                            No_genus = numeric(),
                            No_species = numeric())

preabs_table <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("genome")  %>%
  left_join(genome_metadata, by = join_by("genome" == "genome"))
# %>% 
#   filter(domain=="Bacteria")

genus <- preabs_table  %>%
  filter(is.na(genus))

species <- preabs_table  %>%
  filter(is.na(species))

no_annotation <- rbind(no_annotation,
                       data.frame(
                         Bat = "Total",
                         No_genus = nrow(genus),
                         No_species = nrow(species)
                       ))

for (bat in bats) {
  number <- preabs_table %>%
    select({{bat}}) %>%
    filter(. >= 1)
  
  genus <- preabs_table %>%
    select({{bat}}, phylum, class, order, family, genus) %>%
    filter(!!sym(bat) >= 1) %>%
  filter(is.na(genus))
  
  species <- preabs_table %>%
    filter(!!sym(bat) >= 1) %>%
  filter(is.na(species))
  
  no_annotation <- rbind(no_annotation,
                         data.frame(
                           Bat = bat,
                           No_genus = nrow(genus),
                           No_species = nrow(species)
                         ))
}

Total percentage of ASVs without genus-level annotation

nongenera <- genome_metadata %>% 
#  filter(domain=="Bacteria") %>%
  filter(is.na(genus)) %>% 
  summarize(ASV_nogenera = n()) %>%
  pull()
nasvs <- total_asvs %>%
  filter(Bat == "Total") %>%
  select(ASVs) %>%
  pull()
perct <- nongenera * 100 / nasvs
cat(perct)
30.24615

Percentage of ASVs without genus-level annotation by phylum

total_asv_phylum <- genome_metadata %>% 
#  filter(domain=="Bacteria") %>%
  group_by(phylum) %>%
  summarize(Total_ASVs = n())
genome_metadata %>% 
 # filter(domain=="Bacteria") %>%
  filter(is.na(genus)) %>% 
  group_by(phylum) %>%
  summarize(ASVs_nogenus = n()) %>%
  left_join(total_asv_phylum, by = join_by(phylum == phylum)) %>%
  mutate(Percentage_nogenus = 100 * ASVs_nogenus / Total_ASVs) %>%
  tt()
phylum ASVs_nogenus Total_ASVs Percentage_nogenus
Actinomycetota 48 206 23.300971
Apal-E12 1 1 100.000000
Bacillota 423 1162 36.402754
Bacteroidota 61 375 16.266667
Bdellovibrionota 4 7 57.142857
Chloroflexi 8 9 88.888889
Cyanobacteriota 13 46 28.260870
Desulfobacterota 36 165 21.818182
Halobacterota 1 30 3.333333
Myxococcota 1 4 25.000000
Patescibacteria 27 46 58.695652
Planctomycetota 56 65 86.153846
Pseudomonadota 269 1003 26.819541
Rs-K70 termite group 15 15 100.000000
Spirochaetota 2 5 40.000000
Synergistota 11 24 45.833333
Thermoplasmatota 2 3 66.666667
Verrucomicrobiota 5 30 16.666667

Number of bacterial species

genome_metadata %>% 
  filter(domain == "Bacteria")%>%
  dplyr::select(species) %>%
  unique() %>%
  pull() %>%
  length() %>% 
  cat()
154

Total percentage of MAGs without species-level annotation

nonspecies <- genome_metadata %>% 
#  filter(domain=="Bacteria")%>%
  filter(is.na(species)) %>%
  summarize(ASV_nospecies = n()) %>%
  pull()
perct <- nonspecies * 100 / nasvs
cat(perct)
94.33846

ASVs without species-level annotation

total_mag_phylum <- genome_metadata %>% 
#  filter(domain=="Bacteria") %>%
  group_by(phylum) %>%
  summarize(ASVs_total = n())

genome_metadata %>% 
#  filter(domain=="Bacteria")%>%
  filter(is.na(species)) %>%
  group_by(phylum) %>%
  summarize(ASVs_nospecies = n()) %>%
  left_join(total_mag_phylum, by = join_by(phylum == phylum)) %>%
  mutate(Species_annotated = ASVs_total - ASVs_nospecies) %>%
  mutate(Percentage_nospecies = 100 * ASVs_nospecies / ASVs_total) %>%
  mutate(Percentage_species = 100 - 100 * ASVs_nospecies / ASVs_total) %>%
  tt()
phylum ASVs_nospecies ASVs_total Species_annotated Percentage_nospecies Percentage_species
Actinomycetota 185 206 21 89.80583 10.194175
Apal-E12 1 1 0 100.00000 0.000000
Bacillota 1120 1162 42 96.38554 3.614458
Bacteroidota 355 375 20 94.66667 5.333333
Bdellovibrionota 7 7 0 100.00000 0.000000
Campylobacterota 9 12 3 75.00000 25.000000
Chloroflexi 9 9 0 100.00000 0.000000
Crenarchaeota 3 3 0 100.00000 0.000000
Cyanobacteriota 44 46 2 95.65217 4.347826
Deferribacterota 6 6 0 100.00000 0.000000
Deinococcota 5 5 0 100.00000 0.000000
Desulfobacterota 165 165 0 100.00000 0.000000
Elusimicrobiota 5 5 0 100.00000 0.000000
Euryarchaeota 3 3 0 100.00000 0.000000
Fusobacteriota 14 18 4 77.77778 22.222222
Halobacterota 30 30 0 100.00000 0.000000
Myxococcota 4 4 0 100.00000 0.000000
Patescibacteria 46 46 0 100.00000 0.000000
Planctomycetota 65 65 0 100.00000 0.000000
Pseudomonadota 912 1003 91 90.92722 9.072782
Rs-K70 termite group 15 15 0 100.00000 0.000000
Spirochaetota 5 5 0 100.00000 0.000000
Sumerlaeota 1 1 0 100.00000 0.000000
Synergistota 24 24 0 100.00000 0.000000
Thermoplasmatota 3 3 0 100.00000 0.000000
Verrucomicrobiota 30 30 0 100.00000 0.000000

3.2.3 Summary table

bats = c("Eb", "Pk", "Ha")

single_sp <- data.frame(Bat = character(), Single_species = numeric())

# bacteria <- genome_metadata %>%
#  filter(domain=="Bacteria")

table_upset_analysis <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
#  filter(genome %in% bacteria$genome) %>% 
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample")

unique_all <- table_upset_analysis %>%
  filter(rowSums(across(Eb:Pk)) == 1)

single_sp <- rbind(single_sp, data.frame(Bat = "Total",
                                         Single_species = nrow(unique_all)))
  
for (bat in bats) {
  unique <- table_upset_analysis %>%
    filter(rowSums(across(Eb:Pk)) == 1) %>%
    column_to_rownames(., "sample") %>% 
    select(bat) %>%
    filter(. > 0) %>%
    nrow()
  single_sp <- rbind(single_sp, data.frame(Bat = bat, Single_species = unique))
}
single_ind <- data.frame(Bat = character(), Single_individual = numeric())

freq_table <- genome_counts_filt %>%
  mutate(across(-genome, ~ . / sum(.))) %>%
#  filter(genome %in% bacteria$genome) %>% 
  column_to_rownames("genome") %>%
  mutate(across(everything(), ~ as.integer(. > 0))) %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("sample") %>%
  left_join(sample_metadata[c("sample", "Species")], by = "sample") %>%
  group_by(Species) %>%
  summarize(across(-sample, sum), .groups = "drop") %>%
  column_to_rownames("Species") %>%
  t() %>%
  as.data.frame() %>%
  rownames_to_column("asv")

singleton_filt <- freq_table %>%
  rowwise() %>%
  mutate(row_sum = sum(c_across(-asv))) %>%
  filter(row_sum == 1) %>%
  column_to_rownames(var = "asv")  %>%
  filter(row_sum == 1)

single_ind <- rbind(single_ind, data.frame(
  Bat = "Total",
  Single_individual = nrow(singleton_filt)
))
     
for (bat in bats) {
  singleton_filt <- freq_table %>%
    rowwise() %>%
    mutate(row_sum = sum(c_across(-asv))) %>%
    filter(row_sum == 1) %>%
    column_to_rownames(var = "asv")  %>%
    select(bat) %>%
    filter(. == 1)
  
  single_ind <- rbind(single_ind, data.frame(
    Bat = bat,
    Single_individual = nrow(singleton_filt) 
  ))
}
summary_table_ampli <- total_asvs %>%
  left_join(., no_annotation, by = "Bat") %>%
  left_join(., single_ind, by = "Bat") %>%
  left_join(., single_sp, by = "Bat") %>%
  mutate(Bat = recode(Bat, 
                      Eb = "Cnephaeus bottae",
                      Ha = "Hypsugo ariel",
                      Pk = "Pipistrellus kuhlii"))
summary_table_ampli %>% 
  tt()
Bat ASVs Phylum Family Genus No_genus No_species Single_individual Single_species
Total 3250 27 298 646 983 3066 2467 2832
Cnephaeus bottae 1130 18 138 247 383 1076 693 858
Pipistrellus kuhlii 1341 24 197 364 425 1266 887 989
Hypsugo ariel 1310 22 215 437 287 1202 887 985 
total_asv <- genome_metadata %>% 
#  filter(domain=="Bacteria") %>% 
  nrow()
summary_table_ampli %>% 
  select(-Phylum,-Family, -Genus) %>% 
  rowwise() %>% 
  mutate(ASV_perc=round(ASVs*100/total_asv, 2))%>% 
  mutate(No_genus_perc=round(No_genus*100/ASVs, 2))%>% 
  mutate(No_species_perc=round(No_species*100/ASVs, 2)) %>% 
  mutate(Single_individual_perc=round(Single_individual*100/ASVs, 2))%>% 
  mutate(Single_species_perc=round(Single_species*100/ASVs, 2)) %>% 
  mutate(Single_individual_per_unique=round(Single_individual*100/Single_species, 2)) %>% 
  select(1,7:12) %>% 
  tt()
Bat ASV_perc No_genus_perc No_species_perc Single_individual_perc Single_species_perc Single_individual_per_unique
Total 100.00 30.25 94.34 75.91 87.14 87.11
Cnephaeus bottae 34.77 33.89 95.22 61.33 75.93 80.77
Pipistrellus kuhlii 41.26 31.69 94.41 66.14 73.75 89.69
Hypsugo ariel 40.31 21.91 91.76 67.71 75.19 90.05

3.2.4 Archaea

Number of ASV

genome_metadata %>% 
  filter(domain == "Archaea")%>%
  nrow() %>% 
  cat()
39

Archaeal ASVs present in more than one individual

genome_archaea <- genome_metadata %>% 
  filter(domain == "Archaea")

genome_counts_filt %>% 
  filter(genome %in% genome_archaea$genome) %>%
  mutate(across(-genome, ~ ifelse(. > 0, 1, 0)))%>%
  mutate(count = rowSums(across(-genome))) %>% 
  select(genome, count) %>% 
  filter(count>1)
    genome count
1  ASV_125     2
2 ASV_1615     2
3 ASV_1719     2

Presence of archaeal ASVs

genome_counts_filt %>% 
  filter(genome %in% genome_archaea$genome) %>% 
  select(
    genome,
    where(~ sum(. > 0) > 0)
  ) %>%
  mutate(across(-genome, ~ ifelse(. > 0, 1, 0))) %>% 
  select(-genome) %>% 
  colSums() %>% 
  as.data.frame() %>% 
  rename(archaea=1) %>% 
  rownames_to_column("sample") %>% 
  left_join(., sample_metadata[c(1,6)], by="sample") %>% 
  tt()
sample archaea species_name
H45 1 Hypsugo ariel
H43 1 Hypsugo ariel
P75 1 Pipistrellus kuhlii
H09 20 Hypsugo ariel
P45 1 Pipistrellus kuhlii
E48 1 Eptesicus bottae
H34 1 Hypsugo ariel
P09 1 Pipistrellus kuhlii
P36 9 Pipistrellus kuhlii
P58 2 Pipistrellus kuhlii
E34 1 Eptesicus bottae
P48 1 Pipistrellus kuhlii
H12 1 Hypsugo ariel
P47 1 Pipistrellus kuhlii

Number of archaeal ASVs in each species

genome_counts_filt %>% 
  filter(genome %in% genome_archaea$genome) %>% 
  select(
    genome,
    where(~ sum(. > 0) > 0)
  ) %>%
  mutate(across(-genome, ~ ifelse(. > 0, 1, 0))) %>% 
  select(-genome) %>% 
  colSums() %>% 
  as.data.frame() %>% 
  rename(archaea=1) %>% 
  rownames_to_column("sample") %>% 
  left_join(., sample_metadata[c(1,6)], by="sample") %>% 
  group_by(species_name) %>% 
  summarise(asv=sum(archaea)) %>% 
  tt()
species_name asv
Eptesicus bottae 2
Hypsugo ariel 24
Pipistrellus kuhlii 16

Number of individuals with archaeal ASVs

genome_counts_filt %>% 
  filter(genome %in% genome_archaea$genome) %>% 
  select(
    genome,
    where(~ sum(. > 0) > 0)
  ) %>%
  mutate(across(-genome, ~ ifelse(. > 0, 1, 0))) %>% 
  select(-genome) %>% 
  colSums() %>% 
  as.data.frame() %>% 
  rename(archaea=1) %>% 
  rownames_to_column("sample") %>% 
  left_join(., sample_metadata[c(1,6)], by="sample") %>% 
  group_by(species_name) %>% 
  summarise(indiv=n()) %>% 
  tt()
species_name indiv
Eptesicus bottae 2
Hypsugo ariel 5
Pipistrellus kuhlii 7

Mean presence of archaeal ASVs

genome_counts_filt %>% 
  filter(genome %in% genome_archaea$genome) %>% 
  mutate(across(-genome, ~ ifelse(. > 0, 1, 0))) %>% 
  select(-genome) %>% 
  colSums() %>% 
  as.data.frame() %>% 
  rename(archaea=1) %>% 
  rownames_to_column("sample") %>% 
  left_join(., sample_metadata[c(1,6)], by="sample") %>% 
  summarise(mean=mean(archaea), sd=sd(archaea)) %>% 
  tt()
mean sd
0.8235294 3.037801

Mean presence of archaeal ASVs per species

genome_counts_filt %>% 
  filter(genome %in% genome_archaea$genome) %>% 
  mutate(across(-genome, ~ ifelse(. > 0, 1, 0))) %>% 
  select(-genome) %>% 
  colSums() %>% 
  as.data.frame() %>% 
  rename(archaea=1) %>% 
  rownames_to_column("sample") %>% 
  left_join(., sample_metadata[c(1,6)], by="sample") %>% 
  group_by(species_name) %>% 
  summarise(mean=mean(archaea), sd=sd(archaea)) %>% 
  tt()
species_name mean sd
Eptesicus bottae 0.2000000 0.421637
Hypsugo ariel 1.2631579 4.556340
Pipistrellus kuhlii 0.7272727 1.931735 
genome_archaea %>% 
  distinct(genus) %>% 
  tt()
genus
Methanimicrococcus
Candidatus Methanoplasma
Methanospirillum
Halalkalicoccus
NA
Halorussus
Haloterrigena
Methanobrevibacter
Methanocorpusculum
Candidatus Nitrocosmicus
Halolamina
Haladaptatus
Halostagnicola
Candidatus Nitrososphaera
Halovivax
Halohasta
Halomarina
Natronorubrum
Halomicrobium
Halococcus
Halobellus 
genome_counts_filt %>% 
  filter(genome %in% genome_archaea$genome) %>% 
  select(
    genome,
    where(~ sum(. > 0) > 0)
  ) %>%
  mutate(across(-genome, ~ ifelse(. > 0, 1, 0))) %>%
  mutate(count = rowSums(across(-genome))) %>% 
  select(genome, count) %>% 
  arrange(-count)  %>% 
  tt()
genome count
ASV_125 2
ASV_1615 2
ASV_1719 2
ASV_110 1
ASV_314 1
ASV_532 1
ASV_931 1
ASV_1141 1
ASV_1576 1
ASV_1577 1
ASV_1682 1
ASV_1828 1
ASV_1900 1
ASV_2079 1
ASV_2083 1
ASV_2189 1
ASV_2275 1
ASV_2310 1
ASV_2603 1
ASV_2694 1
ASV_2895 1
ASV_3016 1
ASV_3129 1
ASV_3291 1
ASV_3302 1
ASV_3526 1
ASV_3933 1
ASV_3974 1
ASV_4014 1
ASV_4020 1
ASV_4124 1
ASV_4256 1
ASV_4709 1
ASV_5015 1
ASV_5233 1
ASV_5680 1
ASV_5741 1
ASV_6829 1
ASV_6937 1