Chapter 6 Taxonomic composition

load("data/metagenomics/data.Rdata")

6.0.1 Taxonomy barplot per individual

genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  left_join(., sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  filter(!is.na(count)) %>%
  ggplot(aes(y=count,x=sample, fill=phylum, group=phylum)) + #grouping enables keeping the same sorting of taxonomic units
    geom_bar(stat="identity", colour="white", linewidth=0.1) + #plot stacked bars with white borders
    scale_fill_manual(values=phylum_colors) +
    labs(x = "Relative abundance", y ="Samples") +
    facet_nested(. ~ bat_species,  scales="free", space="free") + #facet per day and treatment
    scale_y_continuous(expand = c(0.001, 0.001)) +
    theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
          axis.title.x = element_blank(),
          panel.background = element_blank(),
          panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(linewidth = 0.5, linetype = "solid", colour = "black"),
          legend.position = "none",
          strip.background.x=element_rect(color = NA, fill= "#f4f4f4"))

6.1 Taxonomy boxplot

6.1.1 Family

family_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(., genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,family) %>%
  summarise(relabun=sum(count))

family_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(family) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    mutate(family= sub("^f__", "", family)) %>%
    arrange(-mean) %>%
    tt()

family	mean	sd
Diplorickettsiaceae	2.066430e-01	0.3630831186
Enterobacteriaceae	1.893277e-01	0.3066240395
Rickettsiaceae	8.145172e-02	0.2374167586
Vibrionaceae	7.972825e-02	0.2063738722
Mycoplasmoidaceae	4.314658e-02	0.1816972619
Chromatiaceae	3.786770e-02	0.1871226759
Desulfovibrionaceae	2.805650e-02	0.0759014047
Pasteurellaceae	2.746922e-02	0.1061643096
Weeksellaceae	2.724435e-02	0.1486394013
Burkholderiaceae	2.703566e-02	0.1383404820
Mycoplasmataceae	2.582675e-02	0.1187781701
Enterococcaceae	2.018684e-02	0.0706119540
Aeromonadaceae	2.015713e-02	0.0692033892
Dysgonomonadaceae	1.896333e-02	0.0497917479
Metamycoplasmataceae	1.831217e-02	0.1281864393
Helicobacteraceae	1.630153e-02	0.1107680426
Anaplasmataceae	1.554908e-02	0.0927522928
Tannerellaceae	1.549917e-02	0.0535737293
Acetobacteraceae	1.360257e-02	0.0967742539
Adiutricaceae	1.182852e-02	0.0349008385
Rhizobiaceae	9.108139e-03	0.0366543408
Leptotrichiaceae	7.074750e-03	0.0196300205
Bacteroidaceae	6.853804e-03	0.0364486712
Lachnospiraceae	6.496660e-03	0.0247911875
Synergistaceae	5.587881e-03	0.0174072370
UBA932	5.565920e-03	0.0216533335
Neisseriaceae	5.157037e-03	0.0268237187
Streptococcaceae	3.499662e-03	0.0202503299
Oscillospiraceae	2.692306e-03	0.0115704557
	2.309250e-03	0.0058956882
Burkholderiaceae_B	2.235806e-03	0.0071724137
Gemellaceae	2.121398e-03	0.0106187686
Rhodocyclaceae	1.968326e-03	0.0113503074
Halomonadaceae	1.883561e-03	0.0134513161
Microcoleaceae	1.849207e-03	0.0092981482
Ruminococcaceae	1.549323e-03	0.0059246842
Erysipelotrichaceae	1.340191e-03	0.0046796931
Acutalibacteraceae	1.217931e-03	0.0040092177
Elusimicrobiaceae	1.081020e-03	0.0070276238
Christensenellaceae	9.622707e-04	0.0065229596
Micrococcaceae	8.277861e-04	0.0059115751
SZUA-567	7.768563e-04	0.0041153802
Mucispirillaceae	7.025020e-04	0.0035261340
Fusobacteriaceae	6.907455e-04	0.0029637575
WRBN01	3.657439e-04	0.0026119337
Beijerinckiaceae	3.384698e-04	0.0016917143
Anaerotignaceae	3.244078e-04	0.0012663030
Rikenellaceae	3.236972e-04	0.0017316093
Clostridiaceae	2.328503e-04	0.0016628836
Cyanobiaceae	1.713001e-04	0.0009579297
Endomicrobiaceae	1.568425e-04	0.0010127663
CAG-508	9.142321e-05	0.0006528923
Campylobacteraceae	8.972836e-05	0.0004001237
UBA660	7.911019e-05	0.0005125600
CAG-239	7.629402e-05	0.0005448483

family_arrange <- family_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(family) %>%
    summarise(mean=sum(relabun)) %>%
    arrange(-mean) %>%
    select(family) %>%
    mutate(family= sub("^f__", "", family)) %>%
    pull()

family_summary %>%
    left_join(genome_metadata %>% select(family,phylum) %>% unique(),by=join_by(family==family)) %>%
    left_join(sample_metadata,by=join_by(sample==sample)) %>%
    mutate(family= sub("^f__", "", family)) %>%
    filter(family %in% family_arrange[1:20]) %>%
    mutate(family=factor(family,levels=rev(family_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=family, group=family, color=phylum, fill=phylum)) +
        scale_color_manual(values=phylum_colors[-8]) +
        scale_fill_manual(values=phylum_colors[-8]) +
        geom_boxplot(alpha=0.2) +
        geom_jitter(alpha=0.5) + 
        facet_nested(. ~ bat_species)+
        theme_minimal() +
        theme(legend.position = "none")

6.1.2 Genus

genus_summary <- genome_counts_filt %>%
  mutate_at(vars(-genome),~./sum(.)) %>% #apply TSS nornalisation
  pivot_longer(-genome, names_to = "sample", values_to = "count") %>% #reduce to minimum number of columns
  left_join(sample_metadata, by = join_by(sample == sample)) %>% #append sample metadata
  left_join(genome_metadata, by = join_by(genome == genome)) %>% #append genome metadata
  group_by(sample,genus) %>%
  summarise(relabun=sum(count)) %>%
  filter(genus != "g__")

genus_summary %>%
    filter(!is.na(relabun)) %>%
    group_by(genus) %>%
    summarise(mean=mean(relabun),sd=sd(relabun)) %>%
    arrange(-mean) %>%
    tt()

genus	mean	sd
g__Aquirickettsiella	2.066430e-01	0.3630831186
g__Rickettsia	8.145172e-02	0.2374167586
g__Vibrio	7.972825e-02	0.2063738722
g__Malacoplasma	4.314658e-02	0.1816972619
g__Serratia	3.781432e-02	0.1442735807
g__Klebsiella	3.527392e-02	0.1609844058
g__Proteus	3.502862e-02	0.1388093531
g__Apibacter	2.724435e-02	0.1486394013
g__Aeromonas	2.015713e-02	0.0692033892
g__Dysgonomonas	1.896333e-02	0.0497917479
g__UBA710	1.831217e-02	0.1281864393
g__Morganella	1.639039e-02	0.0700801355
g__Enterococcus	1.584941e-02	0.0498525505
g__NHYM01	1.552127e-02	0.1108440094
g__Edwardiiplasma	1.517989e-02	0.1073274591
g__Aggregatibacter	1.425805e-02	0.0847502171
g__Tannerella	1.333155e-02	0.0496532992
g__Pasteurella	1.321117e-02	0.0668769540
g__Providencia	1.317104e-02	0.0825454378
g__FLUQ01	1.244851e-02	0.0380568384
g__Mesenet	1.197438e-02	0.0855141593
g__Arsenophonus	1.191432e-02	0.0823521277
g__Adiutrix	1.182852e-02	0.0349008385
g__Spiroplasma	1.064685e-02	0.0532973801
g__Jejubacter	9.570393e-03	0.0478520370
g__Pseudocitrobacter	8.760620e-03	0.0574285139
g__Frigididesulfovibrio	7.889555e-03	0.0203162078
g__WRHT01	7.718438e-03	0.0221726222
g__Sebaldella	7.074750e-03	0.0196300205
g__Paraburkholderia	6.910657e-03	0.0459867188
g__Bacteroides	5.902028e-03	0.0311091136
g__Citrobacter_A	5.809507e-03	0.0216896385
g__Escherichia	5.512404e-03	0.0357559173
g__Neisseria	5.157037e-03	0.0268237187
g__Caballeronia	3.971317e-03	0.0283608787
g__Orbus	3.915117e-03	0.0279595306
g__Wolbachia	3.574704e-03	0.0121363242
g__Lactococcus	3.499662e-03	0.0202503299
g__CALYQQ01	3.073067e-03	0.0165504095
g__Enterococcus_B	2.505891e-03	0.0178956403
g__Enterobacillus	2.297797e-03	0.0121221737
g__Saezia	2.235806e-03	0.0071724137
g__DFXE01	2.167618e-03	0.0154798861
g__Trinickia	2.120753e-03	0.0106036233
g__WQUU01	1.905223e-03	0.0087650731
g__Zymobacter	1.883561e-03	0.0134513161
g__Planktothrix	1.849207e-03	0.0092981482
g__Enterococcus_D	1.831542e-03	0.0108315120
g__Breznakia	1.340191e-03	0.0046796931
g__Scatolibacter	1.217931e-03	0.0040092177
g__WRAV01	1.054847e-03	0.0056761271
g__QANA01	9.622707e-04	0.0065229596
g__UBA1794	9.517755e-04	0.0059502884
g__Acaricomes	8.277861e-04	0.0059115751
g__GCA-022846635	7.962132e-04	0.0044153137
g__UBA1174	7.876488e-04	0.0049458893
g__Helicobacter_C	7.802691e-04	0.0028054940
g__JAJBSZ01	7.768563e-04	0.0041153802
g__Fusobacterium_A	6.907455e-04	0.0029637575
g__Tokpelaia_A	5.169962e-04	0.0036920911
g__JAAYCI01	4.944755e-04	0.0019868365
g__JAHHUI01	3.657439e-04	0.0026119337
g__JAHZDZ01	3.244078e-04	0.0012663030
g__JAJQAW01	3.236972e-04	0.0017316093
g__Elusimicrobium	2.933708e-04	0.0020950863
g__Sarcina	2.328503e-04	0.0016628836
g__Vulcanococcus	1.713001e-04	0.0009579297
g__Lawsonibacter	1.704014e-04	0.0008167847
g__Endomicrobium	1.568425e-04	0.0010127663
g__CHH4-2	1.498779e-04	0.0010703421
g__Entomobacter	5.048026e-05	0.0001942887
g__Fusobacterium_C	0.000000e+00	0.0000000000
g__Helicobacter_G	0.000000e+00	0.0000000000
g__Photobacterium	0.000000e+00	0.0000000000

genus_arrange <- genus_summary %>%
    group_by(genus) %>%
    summarise(mean=sum(relabun)) %>%
    filter(genus != "g__")%>%
    arrange(-mean) %>%
    select(genus) %>%
    mutate(genus= sub("^g__", "", genus)) %>%
    pull()

genus_summary %>%
    left_join(genome_metadata %>% select(genus,phylum) %>% unique(),by=join_by(genus==genus)) %>%
    left_join(sample_metadata,by=join_by(sample==sample)) %>%
    mutate(genus= sub("^g__", "", genus)) %>%
    filter(genus %in% genus_arrange[1:20]) %>%
    mutate(genus=factor(genus,levels=rev(genus_arrange[1:20]))) %>%
    filter(relabun > 0) %>%
    ggplot(aes(x=relabun, y=genus, group=genus, color=phylum)) +
        scale_color_manual(values=phylum_colors) +
        #geom_boxplot() +
        geom_jitter(alpha=0.5) + 
        facet_nested(. ~ bat_species)+
        theme_minimal()