Stat: Alpha Diversity Visualisation(phyloseq_alpha_diversity.py v5.1.0)

## Import packages
library(phyloseq)
library(ggplot2)
library(vegan)
source(file.path(params$libdir, "graphical_methods.R"))
## Alternative to source all extra function from a github repo
## source("https://raw.githubusercontent.com/mahendra-mariadassou/phyloseq-extended/master/load-extra-functions.R")

## Setting variables
  ## The Phyloseq object (format rdata)
  # phyloseq <- ""

  ## The experiment variable that you want to analyse
  # varExp <- ""

  ## "The alpha diversity indices to compute. Multiple indice may be indicated by separating them by a comma.
  ## Available indices are : Observed, Chao1, Shannon, InvSimpson, Simpson, ACE, Fisher
  # measures <- ""

## Create input and parameters dataframe
  # params <- data.frame( "phyloseq" = phylose, "measures" = measures, "varExp" = varExp)

## Load data
load(params$phyloseq)

## Convert measures to list
measures <- as.list(strsplit(params$measures, ",")[[1]])

## Compute numeric values of alpha diversity indices
alpha.diversity <- estimate_richness(data, measures = measures)

## Export diversity indices to text file
write.table(alpha.diversity, params$fileAlpha, sep="\t", quote = FALSE, col.names = NA)

Switch theme Default Coral Gold Steel

Richness plot

p <- plot_richness(data, x = params$varExp, color = params$varExp, measures = measures) + ggtitle(paste("Alpha diversity distribution by", params$varExp))+ theme(plot.title = element_text(hjust = 0.5))
plot(p)

Richness plot with boxplot

p <- p + geom_boxplot(alpha = 0.2) +
         geom_point()+ theme_grey() +
         theme(axis.text.x = element_text(angle=90, hjust=0.5)) +
         theme(plot.title = element_text(hjust = 0.5))
plot(p)

Alpha Diversity Indice Anova Analysis

anova_data <- cbind(sample_data(data), alpha.diversity)
anova_data$Depth <- sample_sums(data)

variables <- paste(sep=" + ", "Depth", params$varExp )

## Perform ANOVA on observed richness, which effects are significant
for (m in measures){
    f <- paste(m," ~ ", variables)
    cat(sep = "", "###############################################################\n#Perform ANOVA on ",m,", which effects are significant\nanova.",m," <-aov( ",f,", anova_data)\nsummary(anova.",m,")\n")
    anova_res <- aov( as.formula(f), anova_data)
    res <- summary(anova_res)
    print(res)
    cat("\n\n")
}

###############################################################
#Perform ANOVA on Observed, which effects are significant
anova.Observed <-aov( Observed  ~  Depth + EnvType, anova_data)
summary(anova.Observed)
            Df Sum Sq Mean Sq F value   Pr(>F)    
Depth        1  97970   97970 203.414  < 2e-16 ***
EnvType      7  18148    2593   5.383 9.78e-05 ***
Residuals   55  26490     482                     
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1


###############################################################
#Perform ANOVA on Chao1, which effects are significant
anova.Chao1 <-aov( Chao1  ~  Depth + EnvType, anova_data)
summary(anova.Chao1)
            Df Sum Sq Mean Sq F value   Pr(>F)    
Depth        1  79015   79015 100.129 5.45e-14 ***
EnvType      7  13764    1966   2.492   0.0269 *  
Residuals   55  43403     789                     
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1


###############################################################
#Perform ANOVA on Shannon, which effects are significant
anova.Shannon <-aov( Shannon  ~  Depth + EnvType, anova_data)
summary(anova.Shannon)
            Df Sum Sq Mean Sq F value   Pr(>F)    
Depth        1  7.699   7.699  16.895 0.000133 ***
EnvType      7 11.333   1.619   3.553 0.003209 ** 
Residuals   55 25.064   0.456                     
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Rarefaction curves

##code of Mahendra Mariadassou, INRA

## Import additionnal packages
# library(parallel)

## Rarefaction curve, ggplot style (additionnal phyloseq-extend function, not yet released)
ggrare <- function(physeq, step = 10, label = NULL, color = NULL, plot = TRUE, parallel = FALSE, se = TRUE) {
    ## Args:
    ## - physeq: phyloseq class object, from which abundance data are extracted
    ## - step: Step size for sample size in rarefaction curves
    ## - label: Default `NULL`. Character string. The name of the variable
    ##          to map to text labels on the plot. Similar to color option
    ##          but for plotting text.
    ## - color: (Optional). Default ‘NULL’. Character string. The name of the
    ##          variable to map to colors in the plot. This can be a sample
    ##          variable (among the set returned by
    ##          ‘sample_variables(physeq)’ ) or taxonomic rank (among the set
    ##          returned by ‘rank_names(physeq)’).
    ##
    ##          Finally, The color scheme is chosen automatically by
    ##          ‘link{ggplot}’, but it can be modified afterward with an
    ##          additional layer using ‘scale_color_manual’.
    ## - color: Default `NULL`. Character string. The name of the variable
    ##          to map to text labels on the plot. Similar to color option
    ##          but for plotting text.
    ## - plot:  Logical, should the graphic be plotted.
    ## - parallel: should rarefaction be parallelized (using parallel framework)
    ## - se:    Default TRUE. Logical. Should standard errors be computed. 
    ## require vegan
    x <- as(otu_table(physeq), "matrix")
    if (taxa_are_rows(physeq)) { x <- t(x) }

    ## This script is adapted from vegan `rarecurve` function
    tot <- rowSums(x)
    S   <- rowSums(x > 0)
    nr  <- nrow(x)

    rarefun <- function(i) {
        # cat(paste("rarefying sample", rownames(x)[i]), sep = "\n")
        n <- seq(1, tot[i], by = step)
        if (n[length(n)] != tot[i]) {
            n <- c(n, tot[i])
        }
        y <- rarefy(x[i, ,drop = FALSE], n, se = se)
        if (nrow(y) != 1) {
        rownames(y) <- c(".S", ".se")
            return(data.frame(t(y), Size = n, Sample = rownames(x)[i]))
        } else {
            return(data.frame(.S = y[1, ], Size = n, Sample = rownames(x)[i]))
        }
    }
    if (parallel) {
        out <- mclapply(seq_len(nr), rarefun, mc.preschedule = FALSE)
    } else {
        out <- lapply(seq_len(nr), rarefun)
    }
    df <- do.call(rbind, out)
    
    ## Get sample data 
    if (!is.null(sample_data(physeq, FALSE))) {
        sdf <- as(sample_data(physeq), "data.frame")
        sdf$Sample <- rownames(sdf)
        data <- merge(df, sdf, by = "Sample")
        labels <- data.frame(x = tot, y = S, Sample = rownames(x))
        labels <- merge(labels, sdf, by = "Sample")
    }
    
    ## Add, any custom-supplied plot-mapped variables
    if( length(color) > 1 ){
        data$color <- color
        names(data)[names(data)=="color"] <- deparse(substitute(color))
        color <- deparse(substitute(color))
    }
    if( length(label) > 1 ){
        labels$label <- label
        names(labels)[names(labels)=="label"] <- deparse(substitute(label))
        label <- deparse(substitute(label))
    }
    
    p <- ggplot(data = data, aes_string(x = "Size", y = ".S", group = "Sample", color = color))
    p <- p + labs(x = "Sample Size", y = "ASV Richness")
    if (!is.null(label)) {
        p <- p + geom_text(data = labels, aes_string(x = "x", y = "y", label = label, color = color),
                           size = 4, hjust = 0)
    }
    p <- p + geom_line()
    if (se) { ## add standard error if available
        p <- p + geom_ribbon(aes_string(ymin = ".S - .se", ymax = ".S + .se", color = NULL, fill = color), alpha = 0.2)
    }
    if (plot) {
        plot(p)
    }
    invisible(p)
}

rare.level <- sample_sums(data)[[1]]
facet <- paste('facet_wrap(~',params$varExp,')')

p <- ggrare(data, step = 500, color = params$varExp, plot = FALSE) + 
        geom_vline(xintercept = rare.level, color = "gray60") + eval(parse(text = facet))

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 6

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 10

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 8

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 6

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 16

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 6

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 7

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 9

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 6

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 5

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 7

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 6

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 4

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 2

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning in rarefy(x[i, , drop = FALSE], n, se = se): most observed count data
have counts 1, but smallest count is 3

Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
ℹ Please use tidy evaluation idioms with `aes()`.
ℹ See also `vignette("ggplot2-in-packages")` for more information.
This warning is displayed once every 8 hours.
Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
generated.

plot(p)

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

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