miga-base 1.2.17.1 → 1.2.17.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 608607327562dd08edc9f866aeeb566407eb85f0adcf8538c37789962c387f72
-  data.tar.gz: b21cb37dcae1eab3551d2058f21543221a9b6b9a5b6c834074a4d7c6c60a7102
+  metadata.gz: 50f8bda6b07f6b7da95f3342e96b290c401a8810c35e2406309d28559111de2d
+  data.tar.gz: 99dd4709f330f90fc71b213c42ce60bade2ac32127fb123ae450cb0a54885176
 SHA512:
-  metadata.gz: 6708285348840ed44251d64d003c477a0887db497ccfaf97ce17f398b650156420897fc07036cbc395b4107c71bdb6638ad756442e364e530363a36aca8ec9a3
-  data.tar.gz: fce107bebd89fd53f07d0ca5b814564b76c00b6faacbb0c89b91c0a114b2c5d5911b446fa27f1db5cecab3d74dee2ab3c2d6b10538a3e33056ab2b2ba766c2e9
+  metadata.gz: 18666049e37b300ceaf367cd1fa1847556a1a84a6878095b9e931c6665f1559a427e00a844ec764de470ab25b92ebd1c48753b782a89c779a4974f2eb63b5385
+  data.tar.gz: c2b4d46070dc7fa7bef02dc7a4147472a32d1863dd86871a2c29c9fde4a1ea906f3d29659bbadab24ebcd57095d3db826120bff8bb831994d6dc6f372d6b569e

data/lib/miga/version.rb

@@ -12,7 +12,7 @@ module MiGA
   # - String indicating release status:
   #   - rc* release candidate, not released as gem
   #   - [0-9]+ stable release, released as gem
-  VERSION = [1.2, 17, 1].freeze
+  VERSION = [1.2, 17, 2].freeze
 
   ##
   # Nickname for the current major.minor version.
@@ -20,7 +20,7 @@ module MiGA
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2023, 2, 14)
+  VERSION_DATE = Date.new(2023, 2, 21)
 
   ##
   # References of MiGA

data/utils/enveomics/Manifest/Tasks/mapping.json

@@ -2,33 +2,61 @@
   "tasks": [
     {
       "task": "BedGraph.tad.rb",
-      "description": ["Estimates the truncated average sequencing depth (TAD)",
-        "from a BedGraph file."],
-      "warn": ["This script doesn't consider zero-coverage positions if",
+      "description": [
+        "Estimates the truncated average sequencing depth (TAD)",
+        "from a BedGraph file."
+      ],
+      "warn": [
+        "This script doesn't consider zero-coverage positions if",
         "missing from the file. If you produce your BedGraph file with",
         "bedtools genomecov and want to consider zero-coverage position, be",
-        "sure to use -bga (not -bg)."],
-      "see_also": ["BedGraph.window.rb",
-        "BlastTab.seqdepth.pl", "BlastTab.seqdepth_ZIP.pl"],
+        "sure to use -bga (not -bg)."
+      ],
+      "see_also": [
+        "BedGraph.window.rb", "BlastTab.seqdepth.pl", "BlastTab.seqdepth_ZIP.pl"
+      ],
       "help_arg": "--help",
       "options": [
         {
           "opt": "--input",
           "arg": "in_file",
           "mandatory": true,
-          "description": "Input BedGraph file."
+          "description": [
+            "Input BedGraph file.",
+            "Supports compression with .gz extension, use - for STDIN."
+          ]
+        },
+        {
+          "opt": "--output",
+          "arg": "out_file",
+          "default": "-",
+          "description": [
+            "Output tab-delimited values (by default, STDOUT).",
+            "Supports compression with .gz extension, use - for STDOUT."
+          ]
         },
         {
           "opt": "--range",
           "arg": "float",
           "default": 0.5,
-          "description": ["Central range to consider, between 0 and 1. By",
-            "default: inter-quartile range (0.5)."]
+          "description": [
+            "Central range to consider, between 0 and 1.",
+            "By default: inter-quartile range (0.5)."
+          ]
+        },
+        {
+          "opt": "--name",
+          "arg": "string",
+          "description": [
+            "Name (ID) of the sequence, added as first column."
+          ]
         },
         {
           "opt": "--per-seq",
-          "description": ["Calculate averages per reference sequence, not",
-            "total. Assumes a sorted BedGraph file."]
+          "description": [
+            "Calculate averages per reference sequence, not total.",
+            "Assumes a sorted BedGraph file."
+          ]
         },
         {
           "opt": "--length",

data/utils/enveomics/Manifest/Tasks/remote.json

@@ -184,7 +184,8 @@
     {
       "task": "SRA.download.bash",
       "description": ["Downloads the set of runs from a project, sample, or",
-        "experiment in SRA."],
+        "experiment in SRA. If the expected file already exists, skips the",
+        "file if the MD5 hash matches."],
       "help_arg": "",
       "requires": [
         {

data/utils/enveomics/Scripts/BedGraph.tad.rb

@@ -1,93 +1,138 @@
 #!/usr/bin/env ruby
 
-require 'optparse'
+$VERSION = 1.01
+$:.push File.expand_path('../lib', __FILE__)
+require 'enveomics_rb/enveomics'
 
-o = {range: 0.5, perseq: false, length: false}
-ARGV << '-h' if ARGV.empty?
-OptionParser.new do |opt|
-  opt.banner = "
-  Estimates the truncated average sequencing depth (TAD) from a BedGraph file.
+o = { range: 0.5, perseq: false, length: false, o: '-' }
+OptionParser.new do |opts|
+  opts.version = $VERSION
+  banner = <<~BANNER
+    Estimates the truncated average sequencing depth (TAD) from a BedGraph file
 
-  IMPORTANT: This script doesn't consider zero-coverage positions if missing
-  from the file. If you produce your BedGraph file with bedtools genomecov and
-  want to consider zero-coverage position, be sure to use -bga (not -bg).
+    IMPORTANT: This script doesn't consider zero-coverage positions if missing
+    from the file. If you produce your BedGraph file with bedtools genomecov and
+    want to consider zero-coverage position, be sure to use -bga (not -bg).
+  BANNER
+  Enveomics.opt_banner(opts, banner, "#{File.basename($0)} [options]")
 
-  Usage: #{$0} [options]"
-  opt.separator ''
-  opt.on('-i', '--input PATH',
-    'Input BedGraph file (mandatory).'){ |v| o[:i]=v }
-  opt.on('-r', '--range FLOAT',
-    'Central range to consider, between 0 and 1.',
-    "By default: #{o[:range]} (inter-quartile range)."
-    ){ |v| o[:range]=v.to_f }
-  opt.on('-s', '--per-seq',
-    'Calculate averages per reference sequence, not total.',
-    'Assumes a sorted BedGraph file.'
-    ){ |v| o[:perseq] = v }
-  opt.on('-l', '--length',
-    'Add sequence length to the output.'){ |v| o[:length] = v }
-  opt.on('-h', '--help', 'Display this screen.') do
-    puts opt
+  opts.separator 'Mandatory'
+  opts.on(
+    '-i', '--input PATH',
+    'Input BedGraph file',
+    'Supports compression with .gz extension, use - for STDIN'
+  ) { |v| o[:i] = v }
+
+  opts.separator ''
+  opts.separator 'Other Options'
+  opts.on(
+    '-o', '--out PATH',
+    'Output tab-delimited values (by default, STDOUT)',
+    'Supports compression with .gz extension, use - for STDOUT'
+  ) { |v| o[:o] = v }
+  opts.on(
+    '-r', '--range FLOAT', Float,
+    'Central range to consider, between 0 and 1',
+    "By default: #{o[:range]} (inter-quartile range)"
+  ) { |v| o[:range] = v }
+  opts.on(
+    '-n', '--name STRING',
+    'Name (ID) of the sequence (added as first column)'
+  ) { |v| o[:name] = v }
+  opts.on(
+    '-s', '--per-seq',
+    'Calculate averages per reference sequence, not total',
+    'Assumes a sorted BedGraph file'
+  ) { |v| o[:perseq] = v }
+  opts.on(
+    '-l', '--length',
+    'Add sequence length to the output'
+  ) { |v| o[:length] = v }
+  opts.on(
+    '-b', '--breadth',
+    'Add sequencing breadth to the output'
+  ) { |v| o[:breadth] = v }
+  opts.on('-h', '--help', 'Display this screen') do
+    puts opts
     exit
   end
-  opt.separator ''
+  opts.separator ''
 end.parse!
-abort '-i is mandatory.' if o[:i].nil?
+raise Enveomics::OptionError.new('-i is mandatory') if o[:i].nil?
 
+##
+# Pad an array to include all index values up to +r+ entries:
+# - d:   Array of [ depth => counts ]
+# - idx: Array of [ depth, depth, ... ]
+# - r:   Expected number of entries in the array
 def pad(d, idx, r)
   idx.each do |i|
     next if d[i].nil?
+
     d[i] -= r
     break unless d[i] < 0
+
     r = -d[i]
     d[i] = nil
   end
   d
 end
 
+##
+# Report the results for:
+# - sq: Contig ID
+# - d:  Array of [ depth => counts ]
+# - ln: Length of the sequence
+# - o:  CLI Options
 def report(sq, d, ln, o)
   # Estimate padding ranges
-  pad = (1.0-o[:range])/2.0
-  r = (pad*ln).round
+  pad = (1.0 - o[:range]) / 2.0
+  r = (pad * ln).round
+  zeroes = d[0].to_i
 
-  # Pad
-  d = pad(d, d.each_index.to_a, r+0)
-  d = pad(d, d.each_index.to_a.reverse, r+0)
+  # Pad (truncation)
+  d = pad(d, d.each_index.to_a, r + 0)
+  d = pad(d, d.each_index.to_a.reverse, r + 0)
 
   # Average
   y = [0.0]
   unless d.compact.empty?
-    s = d.each_with_index.to_a.map{ |v,i| v.nil? ? 0 : i*v }.inject(0,:+)
-    y[0] = s.to_f/d.compact.inject(:+)
+    s = d.each_with_index.to_a.map { |v, i| v.nil? ? 0 : i * v }.inject(0, :+)
+    y[0] = s.to_f / d.compact.inject(:+)
   end
 
   # Report
   y.unshift(sq) if o[:perseq]
+  y.unshift(o[:name]) if o[:name]
   y << ln if o[:length]
-  puts y.join("\t")
+  y << (ln - zeroes).to_f / ln if o[:breadth]
+  y.join("\t")
 end
 
 # Read BedGraph
-d  = []
+d  = [] # [ depth => count ]
 ln = 0
 pre_sq = nil
-File.open(o[:i], "r") do |ifh|
-  ifh.each_line do |i|
-    next if i =~ /^#/
-    r  = i.chomp.split("\t")
-    sq = r.shift
-    if o[:perseq] and !pre_sq.nil? and pre_sq!=sq
-      report(pre_sq, d, ln, o)
-      d  = []
-      ln = 0
-    end
-    r.map! { |j| j.to_i }
-    l = r[1]-r[0]
-    d[ r[2] ] ||= 0
-    d[ r[2] ]  += l
-    ln += l
-    pre_sq = sq
+ifh = reader(o[:i])
+ofh = writer(o[:o])
+ifh.each_line do |i|
+  next if i =~ /^#/
+  r  = i.chomp.split("\t")
+  sq = r.shift # Contig ID
+  if o[:perseq] && !pre_sq.nil? && pre_sq != sq
+    ofh.puts(report(pre_sq, d, ln, o))
+    d  = []
+    ln = 0
   end
+  r.map!(&:to_i) # From, To, Depth
+  l = r[1] - r[0] # Window length: To - From
+  d[ r[2] ] ||= 0
+  d[ r[2] ]  += l # Add these "l" positions with depth "Depth"
+  ln += l
+  pre_sq = sq
 end
-report(pre_sq, d, ln, o)
+ofh.puts(report(pre_sq, d, ln, o))
+
+ifh.close
+ofh.close
 

data/utils/enveomics/Scripts/SRA.download.bash

@@ -4,13 +4,14 @@ DATA_LINK="https://www.ebi.ac.uk/ena/portal/api/filereport"
 DATA_OPS="result=read_run&fields=run_accession,fastq_ftp,fastq_md5"
 SRX=$1
 DIR=${2:-$SRX}
-VERSION=1.0
+VERSION=2.0
 
 if [[ "$SRX" == "" ]] ; then
 echo "
 [Enveomics Collection: $(basename "$0" .bash) $VERSION]
 
 Downloads the set of runs from a project, sample, or experiment in SRA.
+If the expected file already exists, skips the file if the MD5 hash matches.
 
 Usage:
 $(basename "$0") <SRA-ID>[ <dir>]
@@ -42,9 +43,20 @@ tail -n +2 "$DIR/srr_list.txt" | while read ln ; do
   echo "o $srr" >&2
   for uri in $(echo "$ftp" | tr ";" " ") ; do
     file="$dir/$(basename $uri)"
+
+    # Check if it exists and it's complete
+    if [[ -s "$file" ]] ; then
+      md5obs=$(md5value "$file" 2> /dev/null)
+      if [[ "$md5;" == "$md5obs;"* ]] ; then
+        md5=$(echo "$md5" | perl -pe 's/^[^;]+;//')
+        continue
+      fi
+    fi
+
+    # Otherwise, download and check MD5
     curl "$uri" -o "$file"
     md5obs=$(md5value "$file" 2> /dev/null)
-    if [[ "$md5" == "$md5obs"* ]] ; then
+    if [[ "$md5;" == "$md5obs;"* ]] ; then
       md5=$(echo "$md5" | perl -pe 's/^[^;]+;//')
     else
       echo "Corrupt file: $file" >&2

data/utils/enveomics/enveomics.R/DESCRIPTION

@@ -1,7 +1,7 @@
 Package: enveomics.R
-Version: 1.8.0
-Authors@R: c(person("Luis M.","Rodriguez-R",role=c("aut","cre"),
-	   email="lmrodriguezr@gmail.com"))
+Version: 1.9.0
+Authors@R: c(person("Luis M.", "Rodriguez-R", role = c("aut", "cre"),
+	   email = "lmrodriguezr@gmail.com"))
 Title: Various Utilities for Microbial Genomics and Metagenomics
 Description: A collection of functions for microbial ecology and other
    applications of genomics and metagenomics. Companion package for the
@@ -9,7 +9,7 @@ Description: A collection of functions for microbial ecology and other
    <DOI:10.7287/peerj.preprints.1900v1>).
 Author: Luis M. Rodriguez-R [aut, cre]
 Maintainer: Luis M. Rodriguez-R <lmrodriguezr@gmail.com>
-URL: http://enve-omics.ce.gatech.edu/enveomics
+URL: http://enve-omics.ce.gatech.edu/enveomics/
 Depends:
    R (>= 2.9),
    stats,
@@ -28,4 +28,4 @@ Suggests:
 License: Artistic-2.0
 LazyData: yes
 Encoding: UTF-8
-RoxygenNote: 7.0.2
+RoxygenNote: 7.1.2

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

@@ -22,134 +22,146 @@
 #'
 #' @export
 
-enve.prune.dist <- function
-(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))
+enve.prune.dist <- function(
+  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$edge.length>0]));
+  if (is.character(t)) t <- ape::read.tree(t)
+  if (missing(min_dist)) {
+    if (dist.quantile > 0) {
+      min_dist <- as.numeric(quantile(t$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='');
+  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;
+      if (min(d, na.rm = TRUE) < min_dist) {
+        t <- enve.__prune.iter(t, d, min_dist, quiet)
+      } else {
+        break
       }
     }
-    round <- round + 1;
+    round <- round + 1
   }
-  return(t);
+  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
+#' @param t A \strong{phylo} object.
+#' @param nodes Vector of nodes.
+#' @param min_dist Minimum distance.
+#' @param quiet If running quietly.
+#' 
+#' @return A \strong{phylo} object.
 #' 
 #' @author Luis M. Rodriguez-R [aut, cre]
 #'
 #' @export
 
-enve.__prune.reduce <- function
-(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);
+enve.__prune.reduce <- function(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$tip.label==node.name);
-    if(length(node)==0) next;
+    node <- which(t$tip.label == node.name)
+    if (length(node) == 0) next
+
     # Get parent and distance to parent
-    parent.node <- t$edge[ t$edge[,2]==node, 1];
+    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$edge[k,2]);
-          stopit <- TRUE;
-          break;
+    parent.edges <- which(t$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;
+      if (stopit) break
     }
   }
-  if(!quiet) cat('\n');
-  return(t);
+  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
+#' @param t A \strong{phylo} object.
+#' @param dist Cophenetic distance matrix.
+#' @param min_dist Minimum distance.
+#' @param quiet If running quietly.
+#' 
+#' @return Returns a \strong{phylo} object.
 #' 
 #' @author Luis M. Rodriguez-R [aut, cre]
 #'
 #' @export
 
-enve.__prune.iter <- function
-(t,
- dist,
- min_dist,
- quiet){
-  ori_len <- length(t$tip.label);
+enve.__prune.iter <- function(t, dist, min_dist, quiet) {
+  ori_len <- length(t$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) 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) setTxtProgressBar(pb, i)
   }
-  if(!quiet) cat('\n');
+  if(!quiet) cat("\n")
+
   # Check if it droped tips
-  cur_len <- length(t$tip.label);
-  if(cur_len == ori_len){
-    stop("Internal error: small edge found in tree, with no equivalent in distance matrix.\n");
+  cur_len <- length(t$tip.label)
+  if (cur_len == ori_len){
+    stop(
+      "Internal error: small edge found in tree, with no equivalent in distance matrix.\n"
+    )
   }
-  return(t);
+  return(t)
 }