miga-base 0.4.3.0 → 0.5.0.0

data/utils/enveomics/build_enveomics_r.bash

@@ -29,16 +29,17 @@ echo '
 \format{A data frame with 16 rows (times) and 10 rows (times and OD_600nm).}
 \keyword{datasets}
 ' > man/growth.curves.Rd
-echo "
-library(inlinedocs)
-package.skeleton.dx('./');
-" | R --vanilla
-cat man/enveomics.R-package.Rd | tr -d '\r' \
-  | grep -v '^}$' | grep -v '^\\author{' \
-  | grep -v '^Maintainer' \
-  | perl -pe 's/^\\keyword/}\n\\author{Luis M. Rodriguez-R <lmrodriguezr\@gmail.com> [aut, cre]}\n\n\\keyword/' \
-  | perl -lwe '$/=\0; $_=<>; s/^\\details{\n+([^}].*\n+)*}\n+//mg; print' \
-  > o && mv o man/enveomics.R-package.Rd
+echo 'roxygen2::roxygenise();' | R --vanilla
+#echo "
+#library(inlinedocs)
+#package.skeleton.dx('./');
+#" | R --vanilla
+#cat man/enveomics.R-package.Rd | tr -d '\r' \
+#  | grep -v '^}$' | grep -v '^\\author{' \
+#  | grep -v '^Maintainer' \
+#  | perl -pe 's/^\\keyword/}\n\\author{Luis M. Rodriguez-R <lmrodriguezr\@gmail.com> [aut, cre]}\n\n\\keyword/' \
+#  | perl -lwe '$/=\0; $_=<>; s/^\\details{\n+([^}].*\n+)*}\n+//mg; print' \
+#  > o && mv o man/enveomics.R-package.Rd
 #[[ ! -d inst/doc ]] && mkdir -p inst/doc
 #pandoc -o inst/doc/enveomics.R.pdf -f markdown_github README.md
 

data/utils/enveomics/enveomics.R/DESCRIPTION

@@ -1,5 +1,5 @@
 Package: enveomics.R
-Version: 1.4.4
+Version: 1.7.0
 Authors@R: c(person("Luis M.","Rodriguez-R",role=c("aut","cre"),
 	   email="lmrodriguezr@gmail.com"))
 Title: Various Utilities for Microbial Genomics and Metagenomics
@@ -26,5 +26,6 @@ Suggests:
    gplots,
    optparse
 License: Artistic-2.0
-LazyLoad: yes
+LazyData: yes
 Encoding: UTF-8
+RoxygenNote: 6.1.1

data/utils/enveomics/enveomics.R/R/autoprune.R

@@ -1,121 +1,155 @@
+#' Enveomics: Prune Dist
+#' 
+#' Automatically prunes a tree, to keep representatives of each clade.
+#'
+#' @param t A \strong{phylo} object or a path to the Newick file.
+#' @param dist.quantile The quantile of edge lengths.
+#' @param min_dist The minimum distance to allow between two tips.
+#' If not set, \code{dist.quantile} is used instead to calculate it.
+#' @param quiet Boolean indicating if the function must run without output.
+#' @param max_iters Maximum number of iterations.
+#' @param min_nodes_random 
+#' Minimum number of nodes to trigger \emph{tip-pairs} nodes sampling. 
+#' This sampling is less reproducible and more computationally expensive,
+#' but it's the only solution if the cophenetic matrix exceeds \code{2^31-1} 
+#' entries; above that, it cannot be represented in R.
+#' @param random_nodes_frx 
+#' Fraction of the nodes to be sampled if more than \code{min_nodes_random}.
+#'
+#' @return Returns a pruned \strong{phylo} object.
+#'
+#' @author Luis M. Rodriguez-R [aut, cre]
+#'
+#' @export
 
 enve.prune.dist <- function
-### Automatically prunes a tree, to keep representatives of each clade.
-   (t,
-### A `phylo` object or a path to the Newick file.
-   dist.quantile=0.25,
-### The quantile of edge lengths.
-   min_dist,
-### The minimum distance to allow between two tips. If not set, dist.quantile is
-### used instead to calculate it.
-   quiet=FALSE,
-### Boolean indicating if the function must run without output.
-   max_iters=100,
-### Maximum number of iterations.
-   min_nodes_random=4e4,
-### Minimum number of nodes to trigger "tip-pairs" nodes sampling. This sampling
-### is less reproducible and more computationally expensive, but it's the only
-### solution if the cophenetic matrix exceeds 2^31-1 entries; above that, it
-### cannot be represented in R.
-   random_nodes_frx=1
-### Fraction of the nodes to be sampled if more than `min_nodes_random`.
-   ){
-   if(!requireNamespace("ape", quietly=TRUE))
-      stop('Unavailable ape library.');
-   if(is.character(t)) t <- ape::read.tree(t)
-   if(missing(min_dist)){
-      if(dist.quantile>0){
-	 min_dist <- as.numeric(quantile(t$edge.length, dist.quantile));
+(t,
+ dist.quantile=0.25,
+ min_dist,
+ quiet=FALSE,
+ max_iters=100,
+ min_nodes_random=4e4,
+ random_nodes_frx=1
+){
+  if(!requireNamespace("ape", quietly=TRUE))
+    stop('Unavailable ape library.');
+  if(is.character(t)) t <- ape::read.tree(t)
+  if(missing(min_dist)){
+    if(dist.quantile>0){
+      min_dist <- as.numeric(quantile(t$edge.length, dist.quantile));
+    }else{
+      min_dist <- as.numeric(min(t$edge.length[t$edge.length>0]));
+    }
+  }
+  if(!quiet) cat('\nObjective minimum distance: ',min_dist,', initial tips: ',length(t$tip.label),'\n', sep='');
+  round=1;
+  while(round <= max_iters){
+    if(length(t$tip.label) > min_nodes_random){
+      if(!quiet) cat('  | Iter: ',round-1,', Tips: ', length(t$tip.label),
+                     ', reducing tip-pairs.\n', sep='');
+      rnd.nodes <- sample(t$tip.label, length(t$tip.label)*random_nodes_frx);
+      t <- enve.__prune.reduce(t, rnd.nodes, min_dist, quiet);
+    }else{
+      if(!quiet) cat(' Gathering distances...\r');
+      d <- cophenetic(t);
+      diag(d) <- NA;
+      if(!quiet) cat('  | Iter: ',round-1,', Tips: ', length(t$tip.label),
+                     ', Median distance: ', median(d, na.rm=TRUE),
+                     ', Minimum distance: ', min(d, na.rm=TRUE),
+                     '\n', sep='');
+      # Run iteration
+      if(min(d, na.rm=TRUE) < min_dist){
+        t <- enve.__prune.iter(t, d, min_dist, quiet);
       }else{
-         min_dist <- as.numeric(min(t$edge.length[t$edge.length>0]));
+        break;
       }
-   }
-   if(!quiet) cat('\nObjective minimum distance: ',min_dist,', initial tips: ',length(t$tip.label),'\n', sep='');
-   round=1;
-   while(round <= max_iters){
-      if(length(t$tip.label) > min_nodes_random){
-	 if(!quiet) cat('  | Iter: ',round-1,', Tips: ', length(t$tip.label),
-	 	', reducing tip-pairs.\n', sep='');
-         rnd.nodes <- sample(t$tip.label, length(t$tip.label)*random_nodes_frx);
-	 t <- enve.__prune.reduce(t, rnd.nodes, min_dist, quiet);
-      }else{
-	 if(!quiet) cat(' Gathering distances...\r');
-	 d <- cophenetic(t);
-	 diag(d) <- NA;
-	 if(!quiet) cat('  | Iter: ',round-1,', Tips: ', length(t$tip.label),
-		', Median distance: ', median(d, na.rm=TRUE),
-      		', Minimum distance: ', min(d, na.rm=TRUE),
-		'\n', sep='');
-	 # Run iteration
-	 if(min(d, na.rm=TRUE) < min_dist){
-	    t <- enve.__prune.iter(t, d, min_dist, quiet);
-	 }else{
-	    break;
-	 }
-      }
-      round <- round + 1;
-   }
-   return(t);
-### Returns a pruned phylo object.
+    }
+    round <- round + 1;
+  }
+  return(t);
 }
 
+#' Enveomics: Prune Reduce (Internal Function)
+#' 
+#' Internal function for \code{\link{enve.prune.dist}}.
+#'
+#' @param t A \strong{phylo} object
+#' @param nodes Vector of nodes
+#' @param min_dist Minimum distance
+#' @param quiet If running quietly
+#' 
+#' @author Luis M. Rodriguez-R [aut, cre]
+#'
+#' @export
+
 enve.__prune.reduce <- function
-### Internal function for enve.prune.dist
-   (t, nodes, min_dist, quiet){
-   if(!quiet) pb <- txtProgressBar(1, length(nodes), style=3);
-   for(i in 1:length(nodes)){
-      node.name <- nodes[i];
-      if(!quiet) setTxtProgressBar(pb, i);
-      # Get node ID
-      node <- which(t$tip.label==node.name);
-      if(length(node)==0) next;
-      # Get parent and distance to parent
-      parent.node <- t$edge[ t$edge[,2]==node, 1];
-      # Get edges to parent
-      parent.edges <- which(t$edge[,1]==parent.node);
-      stopit <- FALSE;
-      for(j in parent.edges){
-	 for(k in parent.edges){
-	    if(j != k & t$edge[j,2]<length(t$tip.label) & t$edge[k,2]<length(t$tip.label) & sum(t$edge.length[c(j,k)]) < min_dist){
-	       t <- ape::drop.tip(t, t$edge[k,2]);
-	       stopit <- TRUE;
-	       break;
-	    }
-	 }
-	 if(stopit) break;
+(t, nodes, min_dist, quiet){
+  if(!quiet) pb <- txtProgressBar(1, length(nodes), style=3);
+  for(i in 1:length(nodes)){
+    node.name <- nodes[i];
+    if(!quiet) setTxtProgressBar(pb, i);
+    # Get node ID
+    node <- which(t$tip.label==node.name);
+    if(length(node)==0) next;
+    # Get parent and distance to parent
+    parent.node <- t$edge[ t$edge[,2]==node, 1];
+    # Get edges to parent
+    parent.edges <- which(t$edge[,1]==parent.node);
+    stopit <- FALSE;
+    for(j in parent.edges){
+      for(k in parent.edges){
+        if(j != k & t$edge[j,2]<length(t$tip.label) & t$edge[k,2]<length(t$tip.label) & sum(t$edge.length[c(j,k)]) < min_dist){
+          t <- ape::drop.tip(t, t$edge[k,2]);
+          stopit <- TRUE;
+          break;
+        }
       }
-   }
-   if(!quiet) cat('\n');
-   return(t);
+      if(stopit) break;
+    }
+  }
+  if(!quiet) cat('\n');
+  return(t);
 }
 
+#' Enveomics: Prune Iter (Internal Function)
+#' 
+#' Internal function for \code{\link{enve.prune.dist}}.
+#'
+#' @param t A \strong{phylo} object
+#' @param dist Cophenetic distance matrix
+#' @param min_dist Minimum distance
+#' @param quiet If running quietly
+#' 
+#' @author Luis M. Rodriguez-R [aut, cre]
+#'
+#' @export
+
 enve.__prune.iter <- function
-### Internal function for enve.prune.dist
-   (t,
-   dist,
-   min_dist,
-   quiet){
-   ori_len <- length(t$tip.label);
-   # Prune
-   if(!quiet) pb <- txtProgressBar(1, ncol(dist)-1, style=3);
-   ignore <- c();
-   for(i in 1:(ncol(dist)-1)){
-      if(i %in% ignore) next;
-      for(j in (i+1):nrow(dist)){
-	 if(dist[j, i]<min_dist){
-	    t <- ape::drop.tip(t, rownames(dist)[j]);
-	    ignore <- c(ignore, j);
-	    break;
-	 }
+(t,
+ dist,
+ min_dist,
+ quiet){
+  ori_len <- length(t$tip.label);
+  # Prune
+  if(!quiet) pb <- txtProgressBar(1, ncol(dist)-1, style=3);
+  ignore <- c();
+  for(i in 1:(ncol(dist)-1)){
+    if(i %in% ignore) next;
+    for(j in (i+1):nrow(dist)){
+      if(dist[j, i]<min_dist){
+        t <- ape::drop.tip(t, rownames(dist)[j]);
+        ignore <- c(ignore, j);
+        break;
       }
-      if(!quiet) setTxtProgressBar(pb, i);
-   }
-   if(!quiet) cat('\n');
-   # Check if it droped tips
-   cur_len <- length(t$tip.label);
-   if(cur_len == ori_len){
-      stop("Internal error: small edge found in tree, with no equivalent in distance matrix.\n");
-   }
-   return(t);
+    }
+    if(!quiet) setTxtProgressBar(pb, i);
+  }
+  if(!quiet) cat('\n');
+  # Check if it droped tips
+  cur_len <- length(t$tip.label);
+  if(cur_len == ori_len){
+    stop("Internal error: small edge found in tree, with no equivalent in distance matrix.\n");
+  }
+  return(t);
 }
 

data/utils/enveomics/enveomics.R/R/barplot.R

@@ -1,61 +1,91 @@
+#' Enveomics: Barplot
+#' 
+#' Creates nice barplots from tab-delimited tables.
+#'
+#' @param x Can be either the input data or the path to the file containing 
+#' the table. 
+#' \itemize{
+#'    \item{If it contains the data, it must be a data frame or an
+#'    object coercible to a data frame.} 
+#'    \item{If it is a path, it must point to a
+#'    tab-delimited file containing a header (first row) and row names 
+#'    (first column).}
+#'    }
+#' @param sizes  A numeric vector containing the real size of the samples
+#' (columns) in the same order of the input table. If set, the values are
+#' assumed to be 100\%. Otherwise, the sum of the columns is used.
+#' @param top Maximum number of categories to display. Any additional
+#' categories will be listed as "Others".
+#' @param colors.per.group Number of categories in the first two saturation 
+#' groups of colors. The third group contains the remaining categories if 
+#' needed.
+#' @param bars.width Width of the barplot with respect to the legend.
+#' @param legend.ncol Number of columns in the legend.
+#' @param other.col Color of the "Others" category.
+#' @param add.trend Controls if semi-transparent areas are to be plotted
+#' between the bars to connect the regions (trend regions).
+#' @param organic.trend Controls if the trend regions are to be smoothed 
+#' (curves). By default, trend regions have straight edges. If \code{TRUE}, 
+#' forces \code{add.trend=TRUE}.
+#' @param sort.by Any function that takes a numeric vector and returns a
+#' numeric scalar. This function is applied to each row, and the resulting
+#' values are used to sort the rows (decreasingly). Good options include: 
+#' \code{sd, min, max, mean, median}.
+#' @param min.report Minimum percentage to report the value in the plot.
+#' Any value above 100 indicates that no values are to be reported.
+#' @param order Controls how the rows should be ordered. 
+#' \itemize{
+#'    \item{If \code{NULL} 
+#'    (default), \code{sort.by} is applied per row and the results are 
+#'    sorted decreasingly.}
+#'    \item{If \code{NA}, no sorting is performed, i.e., the original
+#'    order is respected.}
+#'    \item{If a vector is provided, it is assumed to be the 
+#'    custom order to be used (either by numeric index or by row names).}
+#'    }
+#' @param col Colors to use. If provided, overrides the variables \code{top}
+#' and \code{colors.per.group}, but \code{other.col} is still used if the 
+#' vector is insufficient for all the rows. An additional palette is available with
+#' \code{col='coto'} (contributed by Luis (Coto) Orellana).
+#' @param ... Any additional parameters to be passed to barplot.
+#' 
+#' @author Luis M. Rodriguez-R [aut, cre]
+#' 
+#' @examples
+#' # Load data
+#' data("phyla.counts", package="enveomics.R", envir=environment())
+#' # Create a barplot sorted by variance with organic trends
+#' enve.barplot(
+#'     phyla.counts, # Counts of phyla in four sites
+#'     sizes=c(250,100,75,200), # Total sizes of the datasets of each site
+#'     bars.width=2, # Decrease from default, so the names are fully displayed
+#'     organic.trend=TRUE, # Nice curvy background
+#'     sort.by=var # Sort by variance across sites
+#'     )
+#'
+#' @export
 
-enve.barplot <- structure(function(
-    ### Creates nice barplots from tab-delimited tables
-    x,
-    ### Can be either the input data or the path to the file containing the
-    ### table. If it contains the data, it must be a data frame or an object
-    ### coercible to data frame. If it is a path, it must point to a
-    ### tab-delimited file containing header (first row) and row names (first
-    ### column).
-    sizes,
-    ### A numeric vector containing the real size of the samples (columns) in
-    ### the same order of the input table. If set, the values are assumed to be
-    ### 100%, otherwise the sum of the columns is used.
-    top=25,
-    ### Maximum number of categories to display. Any additional categories will
-    ### be listed as "Others".
-    colors.per.group=9,
-    ### Number of categories in the first two saturation groups of colors. The
-    ### third group contains the remaining categories if needed.
-    bars.width=4,
-    ### Width of the barplot with respect to the legend.
-    legend.ncol=1,
-    ### Number of columns in the legend.
-    other.col='#000000',
-    ### Color of the "Others" category.
-    add.trend=FALSE,
-    ### Controls if semi-transparent areas are to be plotted between the bars to
-    ### connect the regions (trend regions).
-    organic.trend=FALSE,
-    ### Controls if the trend regions are to be smoothed (curves). By default,
-    ### trend regions have straight edges. If TRUE, forces add.trend=TRUE.
-    sort.by=median,
-    ### Any function that takes a numeric vector and returns a numeric scalar.
-    ### This function is applied to each row, and the resulting values are used
-    ### to sort the rows (decreasingly). Good options include: sd, min, max,
-    ### mean, median.
-    min.report=101,
-    ### Minimum percentage to report the value in the plot. Any value above 100
-    ### indicates that no values are to be reported.
-    order=NULL,
-    ### Controls how the rows should be ordered. If NULL (default), sort.by is
-    ### applied per row and the results are sorted decreasingly. If NA, no
-    ### sorting is performed, i.e., the original order is respected. If a vector
-    ### is provided, it is assumed to be the custom order to be used (either by
-    ### numeric index or by row names).
-    col,
-    ### Colors to use. If provided, overrides the variables `top` and
-    ### `colors.per.group`, but `other.col` is still used if the vector is
-    ### insufficient for all the rows. An additional palette is available with
-    ### col='coto' (contributed by Luis (Coto) Orellana).
-    ...
-    ### Any additional parameters to be passed to `barplot`.
-    ){
-   
+enve.barplot <- function(
+  x,
+  sizes,
+  top=25,
+  colors.per.group=9,
+  bars.width=4,
+  legend.ncol=1,
+  other.col='#000000',
+  add.trend=FALSE,
+  organic.trend=FALSE,
+  sort.by=median,
+  min.report=101,
+  order=NULL,
+  col,
+  ...
+){
+  
   # Read input
   if(is.character(x)){
     c <- read.table(x, sep='\t', header=TRUE, row.names=1, quote='',
-      comment.char='')
+                    comment.char='')
   }else{
     c <- as.data.frame(x)
   }
@@ -63,29 +93,29 @@ enve.barplot <- structure(function(
   p <- c
   for (i in 1:ncol(c)) p[, i] <- c[, i]*100/sizes[i]
   if(top > nrow(p)) top = nrow(p)
-
+  
   # Sort
   if(is.null(order[1])){
     p <- p[order(apply(p, 1, sort.by)), ]
   }else if(is.na(order[1])){
-      
+    
   }else{
     p <- p[order, ]
   }
   if(organic.trend) add.trend=TRUE
-   
+  
   # Colors
   if(is.null(top)) top <- nrow(p)
   if(missing(col)){
     color.col <- rainbow(min(colors.per.group, top), s=1, v=4/5)
     if(top > colors.per.group) color.col <- c(color.col,
-          rainbow(min(colors.per.group*2, top)-colors.per.group, s=3/4, v=3/5))
+                                              rainbow(min(colors.per.group*2, top)-colors.per.group, s=3/4, v=3/5))
     if(top > colors.per.group*2) color.col <- c(color.col,
-          rainbow(top-colors.per.group*2, s=1, v=1.25/4))
+                                                rainbow(top-colors.per.group*2, s=1, v=1.25/4))
   }else if(length(col)==1 & col[1]=="coto"){
     color.col <- c("#5BC0EB","#FDE74C","#9BC53D","#E55934","#FA7921","#EF476F",
-                    "#FFD166","#06D6A0","#118AB2","#073B4C","#264653","#2A9D8F",
-                    "#E9C46A","#F4A261","#E76F51")
+                   "#FFD166","#06D6A0","#118AB2","#073B4C","#264653","#2A9D8F",
+                   "#E9C46A","#F4A261","#E76F51")
     color.col <- head(color.col, n=nrow(p))
     top <- length(color.col)
   }else{
@@ -93,14 +123,14 @@ enve.barplot <- structure(function(
     color.col <- tail(color.col, n=nrow(p))
     top <- length(color.col)
   }
-
+  
   # Plot
   layout(matrix(1:2, nrow=1), widths=c(bars.width,1))
   mar <- par('mar')
   par(mar=c(5,4,4,0)+0.1)
   mp <- barplot(as.matrix(p),
-    col=rev(c(color.col, rep(other.col, nrow(p)-length(color.col)))),
-    border=NA,space=ifelse(add.trend,ifelse(organic.trend,0.75,0.5),0.2), ...)
+                col=rev(c(color.col, rep(other.col, nrow(p)-length(color.col)))),
+                border=NA,space=ifelse(add.trend,ifelse(organic.trend,0.75,0.5),0.2), ...)
   if(add.trend || min.report < max(p)){
     color.alpha <- enve.col.alpha(c(color.col, other.col), 1/4)
     if(top < nrow(p)){
@@ -120,46 +150,35 @@ enve.barplot <- structure(function(
           for(j in 2:ncol(p)){
             x <- c(x, seq(mp[j-1]+spc, mp[j]-spc, length.out=22))
             y1 <- c(y1, cf[j-1]-f[j-1],
-                (tanh(seq(-2.5,2.5,length.out=20))/2+.5)*
-                  ((cf[j]-f[j])-(cf[j-1]-f[j-1]))+(cf[j-1]-f[j-1]), cf[j]-f[j])
+                    (tanh(seq(-2.5,2.5,length.out=20))/2+.5)*
+                      ((cf[j]-f[j])-(cf[j-1]-f[j-1]))+(cf[j-1]-f[j-1]), cf[j]-f[j])
             y2 <- c(y2, cf[j-1],
-                (tanh(seq(-2.5,2.5,length.out=20))/2+.5)*
-                  (cf[j]-cf[j-1])+(cf[j-1]), cf[j])
+                    (tanh(seq(-2.5,2.5,length.out=20))/2+.5)*
+                      (cf[j]-cf[j-1])+(cf[j-1]), cf[j])
           }
           x <- c(x, mp[length(mp)]+spc)
           y1 <- c(y1, cf[length(cf)]-f[length(f)])
           y2 <- c(y2, cf[length(cf)])
           polygon(c(x, rev(x)), c(y1, rev(y2)), col=color.alpha[nrow(p)-i+1],
-              border=NA)
+                  border=NA)
         }else if(add.trend){
           x <- rep(mp, each=2)+c(-0.5,0.5)
           if(add.trend) polygon(c(x, rev(x)),
-              c(rep(cf-f, each=2), rev(rep(cf, each=2))),
-              col=color.alpha[nrow(p)-i+1], border=NA)
+                                c(rep(cf-f, each=2), rev(rep(cf, each=2))),
+                                col=color.alpha[nrow(p)-i+1], border=NA)
         }
         text(mp, cf-f/2, ifelse(f>min.report, signif(f, 3), ''), col='white')
       }
     }
   }
-   
+  
   # Legend
   par(mar=rep(0,4)+0.1)
   plot(1, t='n', bty='n', xlab='', ylab='', xaxt='n', yaxt='n')
   nam <- rownames(p[nrow(p):(nrow(p)-top+1), ])
   if(top < nrow(p)) nam <- c(nam,
-      paste('Other (',nrow(p)-length(color.col),')', sep=''))
+                             paste('Other (',nrow(p)-length(color.col),')', sep=''))
   legend('center', col=c(color.col, other.col), legend=nam, pch=15, bty='n',
-    pt.cex=2, ncol=legend.ncol)
+         pt.cex=2, ncol=legend.ncol)
   par(mar=mar)
-}, ex=function(){
-  # Load data
-  data("phyla.counts", package="enveomics.R", envir=environment())
-  # Create a barplot sorted by variance with organic trends
-  enve.barplot(phyla.counts, # Counts of phyla in four sites
-    sizes=c(250,100,75,200), # Total sizes of the datasets of each site
-    bars.width=2, # Decrease from default, so the names are fully displayed
-    organic.trend=TRUE, # Nice curvy background
-    sort.by=var # Sort by variance across sites
-  )
-})
-
+}