Stat: Import data (phyloseq_import_data.py v5.1.0)

## Import packages
library(phyloseq)
library(ggplot2)
library(ape)

## Settin variables
  ## The ASV abundance matrix with taxonomy annotation file (biom format)
  # biomfile <- ""

  ## The sample metadata file(TSV format)
  # samplefile <- ""

  ## (optional) the ASV tree file (nwk format). Write "None" if you do not have any tree
  # treefile <- ""

  ## The ordered taxonomic levels stored in BIOM. Each level is separated by one space.
  ## default : "Kingdom Phylum Class Order Family Genus Species"
  # ranks <- ""

  ## Do you want to normalise your data ? "True" or "False"
  # normalisation <- ""

## Create input and parameters dataframe
  # params <- data.frame( "biomfile" = biomfile, "samplefile" = samplefile, "tree" = tree, "ranks" = ranks, "normalisation" = normalisation)


## Import data
biomfile <- params$biomfile
data     <- import_biom(biomfile)
sampledata <- read.csv(params$samplefile, sep = "\t", row.names = 1, check.names = FALSE)

# if taxonomy starts with k__ it means that its Greengenes like format
# import need to be done using parse_taxonomy_greengenes function
# in this case user taxonomic rank names are ignored
tax      <- tax_table(data)[[1]]
if ((gregexpr('k__', tax))[[1]][1]>0) { 
  cat("Warning : Taxonomic affiliations come from Greengenes database, user specified ranks names are ignored.")
  data <- import_biom(biomfile, parseFunction = parse_taxonomy_greengenes)
} else {
## else, custumize rank name with the user specified ranks variable
  new_rank <- as.list(strsplit(params$ranks, " ")[[1]])
  colnames(tax_table(data)) <- new_rank
}

Warning : Taxonomic affiliations come from Greengenes database, user specified ranks names are ignored.

## add sample name to metadata, as SampleID variable
sampledata$SampleID <- rownames(sampledata)
sample_data(data) <- sampledata

## add tree metadata if available
if (params$treefile != "None"){
  treefile <- read.tree(params$treefile)
  phy_tree(data) <- treefile
}

## change de sample metadata order as in input samplefile
for ( variable in sample_variables(data)){
  variable.order = as.vector(unique(sampledata[,variable]))
  sample_data(data)[,variable] <- factor(get_variable(data, variable),levels=variable.order)
}

## remove empty samples
empty_samples <- sample_names(data)[which(sample_sums(data)==0)]
sample_to_keep <- sample_names(data)[which(sample_sums(data)>0)]
data <- prune_samples(sample_to_keep, data)

empty_taxa <- taxa_names(data)[which(taxa_sums(data)==0)]
taxa_to_keep <- taxa_names(data)[which(taxa_sums(data)>0)]
data <- prune_taxa(taxa_to_keep, data)

## abundance normalisation
if(params$normalisation){ data <- rarefy_even_depth(data, rngseed = 1121983)}

## save phyloseq object in Rdata file
save(data, file=params$outputRdata)

Switch theme Default Coral Gold Steel

Summary

data

phyloseq-class experiment-level object
otu_table()   OTU Table:         [ 507 taxa and 64 samples ]
sample_data() Sample Data:       [ 64 samples by 4 sample variables ]
tax_table()   Taxonomy Table:    [ 507 taxa by 7 taxonomic ranks ]
phy_tree()    Phylogenetic Tree: [ 507 tips and 506 internal nodes ]

if(length(empty_samples) > 0) {cat(paste('Remove empty samples: ', paste(empty_samples, collapse=",")))}
if(length(empty_taxa) > 0) {cat(paste('Remove empty taxa: ', paste(empty_taxa, collapse=",")))}

Remove empty taxa:  otu_01781

if(params$normalisation){cat(paste('Number of sequences in each sample after normalisation: ', head(sample_sums(data))[[1]]))}

Ranks Names

cat(paste('Rank names : ',paste(rank_names(data),collapse=', ')))

Rank names :  Kingdom, Phylum, Class, Order, Family, Genus, Species

Sample metadata

variables <- sample_variables(data)
cat(paste('Sample variables: ', paste(variables, collapse=', ' )))

Sample variables:  EnvType, Description, FoodType, SampleID

for (var in variables){
  cat(paste(var,': ',paste(levels(factor(get_variable(data, varName = var))),collapse=', '), '\n\n'))
}

EnvType :  BoeufHache, VeauHache, DesLardons, MerguezVolaille, SaumonFume, FiletSaumon, FiletCabillaud, Crevette 

Description :  LOT1, LOT3, LOT4, LOT5, LOT6, LOT7, LOT8, LOT10, LOT2, LOT9 

FoodType :  Meat, Seafood 

SampleID :  BHT0.LOT01, BHT0.LOT03, BHT0.LOT04, BHT0.LOT05, BHT0.LOT06, BHT0.LOT07, BHT0.LOT08, BHT0.LOT10, VHT0.LOT01, VHT0.LOT02, VHT0.LOT03, VHT0.LOT04, VHT0.LOT06, VHT0.LOT07, VHT0.LOT08, VHT0.LOT10, DLT0.LOT01, DLT0.LOT03, DLT0.LOT04, DLT0.LOT05, DLT0.LOT06, DLT0.LOT07, DLT0.LOT08, DLT0.LOT10, MVT0.LOT01, MVT0.LOT03, MVT0.LOT05, MVT0.LOT06, MVT0.LOT07, MVT0.LOT08, MVT0.LOT09, MVT0.LOT10, SFT0.LOT01, SFT0.LOT02, SFT0.LOT03, SFT0.LOT04, SFT0.LOT05, SFT0.LOT06, SFT0.LOT07, SFT0.LOT08, FST0.LOT01, FST0.LOT02, FST0.LOT03, FST0.LOT05, FST0.LOT06, FST0.LOT07, FST0.LOT08, FST0.LOT10, FCT0.LOT01, FCT0.LOT02, FCT0.LOT03, FCT0.LOT05, FCT0.LOT06, FCT0.LOT07, FCT0.LOT08, FCT0.LOT10, CDT0.LOT02, CDT0.LOT04, CDT0.LOT05, CDT0.LOT06, CDT0.LOT07, CDT0.LOT08, CDT0.LOT09, CDT0.LOT10 

Plot tree

if(params$treefile!="None"){
  p <- plot_tree(data, color=rank_names(data)[2]) + 
          ggtitle(paste("Phylogenetic tree colored by", rank_names(data)[2])) + 
          theme(plot.title = element_text(hjust = 0.5))
  plot(p)
}

if(params$treefile=="None"){
  cat("There is no phylogenetic tree in the object you have provided.")
}

Reproducibility token

sessioninfo::session_info()

─ Session info ───────────────────────────────────────────────────────────────
 setting  value
 version  R version 4.1.2 (2021-11-01)
 os       Ubuntu 24.04.2 LTS
 system   x86_64, linux-gnu
 ui       X11
 language fr_FR:en
 collate  en_US.utf8
 ctype    en_US.utf8
 tz       Europe/Paris
 date     2026-01-14
 pandoc   2.19.2 @ /home/maria/miniforge3/envs/frogs@5.1.0/bin/ (via rmarkdown)

─ Packages ───────────────────────────────────────────────────────────────────
 package          * version   date (UTC) lib source
 ade4               1.7-22    2023-02-06 [1] CRAN (R 4.1.3)
 ape              * 5.7-1     2023-03-13 [1] CRAN (R 4.1.3)
 Biobase            2.54.0    2021-10-26 [1] Bioconductor
 BiocGenerics       0.40.0    2021-10-26 [1] Bioconductor
 biomformat         1.22.0    2021-10-26 [1] Bioconductor
 Biostrings         2.62.0    2021-10-26 [1] Bioconductor
 bitops             1.0-7     2021-04-24 [1] CRAN (R 4.1.3)
 bslib              0.5.0     2023-06-09 [1] CRAN (R 4.1.3)
 cachem             1.0.8     2023-05-01 [1] CRAN (R 4.1.3)
 cli                3.6.1     2023-03-23 [1] CRAN (R 4.1.3)
 cluster            2.1.4     2022-08-22 [1] CRAN (R 4.1.3)
 codetools          0.2-19    2023-02-01 [1] CRAN (R 4.1.3)
 colorspace         2.1-0     2023-01-23 [1] CRAN (R 4.1.3)
 crayon             1.5.2     2022-09-29 [1] CRAN (R 4.1.3)
 data.table         1.14.8    2023-02-17 [1] CRAN (R 4.1.3)
 digest             0.6.31    2022-12-11 [1] CRAN (R 4.1.3)
 dplyr              1.1.2     2023-04-20 [1] CRAN (R 4.1.3)
 evaluate           0.21      2023-05-05 [1] CRAN (R 4.1.3)
 fansi              1.0.4     2023-01-22 [1] CRAN (R 4.1.3)
 farver             2.1.1     2022-07-06 [1] CRAN (R 4.1.3)
 fastmap            1.1.1     2023-02-24 [1] CRAN (R 4.1.3)
 foreach            1.5.2     2022-02-02 [1] CRAN (R 4.1.3)
 generics           0.1.3     2022-07-05 [1] CRAN (R 4.1.3)
 GenomeInfoDb       1.30.1    2022-01-30 [1] Bioconductor
 GenomeInfoDbData   1.2.7     2026-01-14 [1] Bioconductor
 ggplot2          * 3.4.2     2023-04-03 [1] CRAN (R 4.1.3)
 glue               1.6.2     2022-02-24 [1] CRAN (R 4.1.3)
 gtable             0.3.3     2023-03-21 [1] CRAN (R 4.1.3)
 highr              0.10      2022-12-22 [1] CRAN (R 4.1.3)
 htmltools          0.5.5     2023-03-23 [1] CRAN (R 4.1.3)
 igraph             1.3.5     2022-09-22 [1] CRAN (R 4.1.3)
 IRanges            2.28.0    2021-10-26 [1] Bioconductor
 iterators          1.0.14    2022-02-05 [1] CRAN (R 4.1.3)
 jquerylib          0.1.4     2021-04-26 [1] CRAN (R 4.1.3)
 jsonlite           1.8.5     2023-06-05 [1] CRAN (R 4.1.3)
 knitr              1.43      2023-05-25 [1] CRAN (R 4.1.3)
 labeling           0.4.2     2020-10-20 [1] CRAN (R 4.1.3)
 lattice            0.21-8    2023-04-05 [1] CRAN (R 4.1.3)
 lifecycle          1.0.3     2022-10-07 [1] CRAN (R 4.1.3)
 magrittr           2.0.3     2022-03-30 [1] CRAN (R 4.1.3)
 MASS               7.3-58.3  2023-03-07 [1] CRAN (R 4.1.3)
 Matrix             1.5-4.1   2023-05-18 [1] CRAN (R 4.1.3)
 mgcv               1.8-42    2023-03-02 [1] CRAN (R 4.1.3)
 multtest           2.50.0    2021-10-26 [1] Bioconductor
 munsell            0.5.0     2018-06-12 [1] CRAN (R 4.1.3)
 nlme               3.1-162   2023-01-31 [1] CRAN (R 4.1.3)
 permute            0.9-7     2022-01-27 [1] CRAN (R 4.1.3)
 phyloseq         * 1.38.0    2021-10-26 [1] Bioconductor
 pillar             1.9.0     2023-03-22 [1] CRAN (R 4.1.3)
 pkgconfig          2.0.3     2019-09-22 [1] CRAN (R 4.1.3)
 plyr               1.8.8     2022-11-11 [1] CRAN (R 4.1.3)
 R6                 2.5.1     2021-08-19 [1] CRAN (R 4.1.3)
 Rcpp               1.0.10    2023-01-22 [1] CRAN (R 4.1.3)
 RCurl              1.98-1.12 2023-03-27 [1] CRAN (R 4.1.3)
 reshape2           1.4.4     2020-04-09 [1] CRAN (R 4.1.3)
 rhdf5              2.38.1    2022-03-10 [1] Bioconductor
 rhdf5filters       1.6.0     2021-10-26 [1] Bioconductor
 Rhdf5lib           1.16.0    2021-10-26 [1] Bioconductor
 rlang              1.1.1     2023-04-28 [1] CRAN (R 4.1.3)
 rmarkdown          2.22      2023-06-01 [1] CRAN (R 4.1.3)
 rstudioapi         0.14      2022-08-22 [1] CRAN (R 4.1.3)
 S4Vectors          0.32.4    2022-03-24 [1] Bioconductor
 sass               0.4.6     2023-05-03 [1] CRAN (R 4.1.3)
 scales             1.2.1     2022-08-20 [1] CRAN (R 4.1.3)
 sessioninfo        1.2.2     2021-12-06 [1] CRAN (R 4.1.3)
 stringi            1.7.6     2021-11-29 [1] CRAN (R 4.1.1)
 stringr            1.5.0     2022-12-02 [1] CRAN (R 4.1.3)
 survival           3.5-5     2023-03-12 [1] CRAN (R 4.1.3)
 tibble             3.2.1     2023-03-20 [1] CRAN (R 4.1.3)
 tidyselect         1.2.0     2022-10-10 [1] CRAN (R 4.1.3)
 utf8               1.2.3     2023-01-31 [1] CRAN (R 4.1.3)
 vctrs              0.6.2     2023-04-19 [1] CRAN (R 4.1.3)
 vegan              2.6-4     2022-10-11 [1] CRAN (R 4.1.3)
 withr              2.5.0     2022-03-03 [1] CRAN (R 4.1.3)
 xfun               0.39      2023-04-20 [1] CRAN (R 4.1.3)
 XVector            0.34.0    2021-10-26 [1] Bioconductor
 yaml               2.3.7     2023-01-23 [1] CRAN (R 4.1.3)
 zlibbioc           1.40.0    2021-10-26 [1] Bioconductor

 [1] /home/maria/miniforge3/envs/frogs@5.1.0/lib/R/library

──────────────────────────────────────────────────────────────────────────────