miga-base 1.3.9.7 → 1.3.9.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 39f349118de256f22be42c19f16576b65e9f6836b54e2cab6cd999b93ffa19b6
-  data.tar.gz: 2e44d103abb4156239e98a56287d7ce198c6277dc9eab25c4ed0921831112048
+  metadata.gz: 6f778c1cf98987c440f71da2da7cfa760279c90009f58cc9abfbe9bb129fec97
+  data.tar.gz: bf128ed11141faa28decc79f80d7426a16e113c8d6b381885815ba98a98e5a4f
 SHA512:
-  metadata.gz: 6eba0f2cc60647f500f4f9d0c237e88b69de370c8fb95f481a36e85d3967993396a32361f88050b56719413bf0c850e9252275a85b8b067283f19bb38c959d1f
-  data.tar.gz: 37407d26955546c95d9f6eb95b841273a7cb08c6a78d04aa4174d902cc2eaced33749a6d4b0a74b4462e715ce6986799e961c20708f7c8796977a324b2d1a687
+  metadata.gz: ac2ab474cfdb3667d187f71b787d3cd30685198def25beb20cee58f964fbeec3071733637c14a6722c21c74fd3e1bfa4efb8f0920b36f4d6ebb3b2e0b3eef4c9
+  data.tar.gz: eefb0c999194af805699c7a538d8992c9795447f7a5c81decfc2d85750618e57b116ab56f8c34a2478366ec9efce585649c6f78d1aec44c39c4f8633e3494384

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 = [1.3, 9, 7].freeze
+  VERSION = [1.3, 9, 8].freeze
 
   ##
   # Nickname for the current major.minor version.
@@ -20,7 +20,7 @@ module MiGA
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2024, 1, 29)
+  VERSION_DATE = Date.new(2024, 1, 30)
 
   ##
   # References of MiGA

data/utils/enveomics/Scripts/BlastTab.recplot2.R

@@ -6,9 +6,10 @@
 #= Load stuff
 suppressPackageStartupMessages(library(enveomics.R))
 args <- commandArgs(trailingOnly = FALSE)
-enveomics_R <- file.path(dirname(
-  sub("^--file=", "", args[grep("^--file=", args)])),
-  "lib", "enveomics.R")
+enveomics_R <- file.path(
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
+)
 
 #= Generate interface
 opt <- enve.cliopts(enve.recplot2,

data/utils/enveomics/Scripts/Newick.autoprune.R

@@ -7,9 +7,10 @@
 
 #= Load stuff
 args <- commandArgs(trailingOnly = F)  
-enveomics_R <- file.path(dirname(
-   sub("^--file=", "", args[grep("^--file=", args)])),
-   "lib", "enveomics.R")
+enveomics_R <- file.path(
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
+)
 source(file.path(enveomics_R, "R", "cliopts.R"))
 source(file.path(enveomics_R, "R", "autoprune.R"))
 

data/utils/enveomics/Scripts/RecPlot2.compareIdentities.R

@@ -7,20 +7,34 @@
 
 #= Load stuff
 args <- commandArgs(trailingOnly = F)  
-enveomics_R <- file.path(dirname(
-   sub("^--file=", "", args[grep("^--file=", args)])),
-   "lib", "enveomics.R")
+enveomics_R <- file.path(
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
+)
 library(methods)
 source(file.path(enveomics_R, "R", "cliopts.R"))
 source(file.path(enveomics_R, "R", "recplot2.R"))
 
 #= Generate interface
-opt <- enve.cliopts(enve.recplot2.compareIdentities,
-   file.path(enveomics_R, "man", "enve.recplot2.compareIdentities.Rd"),
-   positional_arguments=2,
-   usage="usage: %prog [options] recplot-A.Rdata recplot-B.Rdata",
-   number=c("pseudocounts", "max.deviation"), ignore=c("x", "y"),
-   p_desc="Calculates the difference between identity distributions of two recruitment plots.")
+opt <- enve.cliopts(
+  enve.recplot2.compareIdentities,
+  file.path(enveomics_R, "man", "enve.recplot2.compareIdentities.Rd"),
+  positional_arguments = 2,
+  usage  = "usage: %prog [options] recplot-A.Rdata recplot-B.Rdata",
+  number = c("pseudocounts", "max.deviation"),
+  ignore = c("x", "y"),
+  p_desc = "Calculates the difference between identity distributions of two recruitment plots.",
+  o_desc = list(
+    method = paste(
+      "Distance method to use. This should be (an unambiguous abbreviation of)",
+      "one of: \"hellinger\" (Hellinger, 1090, doi:10.1515/crll.1909.136.210),",
+      "\"bhattacharyya\" (Bhattacharyya, 1943, Bull. Calcutta Math. Soc. 35),",
+      "\"kl\" or \"kullback-leibler\" (Kullback & Leibler, 1951,",
+      "doi:10.1214/aoms/1177729694), \"euclidean\"",
+      sep = "\n		"
+    )
+  )
+)
 
 #= Run it!
 load(opt$args[1])

data/utils/enveomics/Scripts/TRIBS.plot-test.R

@@ -8,9 +8,10 @@
 #= Load stuff
 suppressPackageStartupMessages(library(enveomics.R))
 args <- commandArgs(trailingOnly = F)  
-enveomics_R <- file.path(dirname(
-   sub("^--file=", "", args[grep("^--file=", args)])),
-   "lib", "enveomics.R")
+enveomics_R <- file.path(
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
+)
 
 #= Generate interface
 opt <- enve.cliopts(plot.enve.TRIBStest,

data/utils/enveomics/Scripts/TRIBS.test.R

@@ -8,9 +8,10 @@
 #= Load stuff
 suppressPackageStartupMessages(library(enveomics.R))
 args <- commandArgs(trailingOnly = F)  
-enveomics_R <- file.path(dirname(
-   sub("^--file=", "", args[grep("^--file=", args)])),
-   "lib", "enveomics.R")
+enveomics_R <- file.path(
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
+)
 
 #= Generate interface
 opt <- suppressWarnings(enve.cliopts(enve.tribs,

data/utils/enveomics/Scripts/Table.barplot.R

@@ -7,21 +7,31 @@
 
 #= Load stuff
 args <- commandArgs(trailingOnly = F)  
-enveomics_R <- file.path(dirname(
-   sub("^--file=", "", args[grep("^--file=", args)])),
-   "lib", "enveomics.R")
+enveomics_R <- file.path(
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
+)
 source(file.path(enveomics_R, "R", "cliopts.R"))
 source(file.path(enveomics_R, "R", "utils.R"))
 source(file.path(enveomics_R, "R", "barplot.R"))
 
 #= Generate interface
-opt <- enve.cliopts(enve.barplot,
-   file.path(enveomics_R, "man", "enve.barplot.Rd"),
-   positional_arguments=c(1,3),
-   usage="usage: %prog [options] output.pdf [width height]",
-   mandatory=c("x"), vectorize=c("sizes","order","col"),
-   number=c("sizes","order"),
-   o_desc=list(x="A tab-delimited file containing header (first row) and row names (first column)."))
+opt <- enve.cliopts(
+  enve.barplot,
+  file.path(enveomics_R, "man", "enve.barplot.Rd"),
+  positional_arguments = c(1, 3),
+  usage     = "usage: %prog [options] output.pdf [width height]",
+  mandatory = c("x"),
+  vectorize = c("sizes", "order", "col"),
+  number    = c("sizes", "order"),
+  o_desc    = list(
+    x = paste(
+      "A tab-delimited file containing header (first row) and row names",
+      "(first column)."
+    ),
+    order = "If passed, the custom order to be used (as row indexes)"
+  )
+)
 
 #= Run it!
 args = as.list(opt$args)

data/utils/enveomics/Scripts/Table.df2dist.R

@@ -7,9 +7,10 @@
 
 #= Load stuff
 args <- commandArgs(trailingOnly = F)  
-enveomics_R <- file.path(dirname(
-   sub("^--file=", "", args[grep("^--file=", args)])),
-   "lib", "enveomics.R")
+enveomics_R <- file.path(
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
+)
 source(file.path(enveomics_R, "R", "cliopts.R"))
 source(file.path(enveomics_R, "R", "df2dist.R"))
 

data/utils/enveomics/Scripts/Table.prefScore.R

@@ -3,26 +3,26 @@
 #= Load stuff
 args <- commandArgs(trailingOnly = FALSE)  
 enveomics_R <- file.path(
-  dirname(sub('^--file=', '', args[grep('^--file=', args)])),
-  'lib',
-  'enveomics.R'
+  dirname(sub("^--file=", "", args[grep("^--file=", args)])),
+  "..", "enveomics.R"
 )
-for(file in c('cliopts.R','utils.R','prefscore.R'))
-  source(file.path(enveomics_R, 'R', file))
+for(file in c("cliopts.R", "utils.R", "prefscore.R")) {
+  source(file.path(enveomics_R, "R", file))
+}
 
 #= Generate interface
 opt <- enve.cliopts(
   enve.prefscore,
-  file.path(enveomics_R, 'man', 'enve.prefscore.Rd'),
+  file.path(enveomics_R, "man", "enve.prefscore.Rd"),
   positional_arguments = c(1, 4),
-  usage = 'usage: %prog [options] output.tsv [output.pdf [width height]]',
-  mandatory = c('x', 'set'),
-  number = c('signif.thr'),
-  ignore = c('plot'),
+  usage = "usage: %prog [options] output.tsv [output.pdf [width height]]",
+  mandatory = c("x", "set"),
+  number = c("signif.thr"),
+  ignore = c("plot"),
   o_desc = list(
-    x = 'A tab-delimited table of presence/absence (1/0) with species as rows and samples as columns.',
-    set = 'A list of sample names that constitute the test set, one per line',
-    ignore = 'A list of species to exclude from the analysis, one per line'
+    x = "A tab-delimited table of presence/absence (1/0) with species as rows and samples as columns.",
+    set = "A list of sample names that constitute the test set, one per line",
+    ignore = "A list of species to exclude from the analysis, one per line"
   )
 )
 

data/utils/enveomics/Scripts/ogs.stats.rb

@@ -1,127 +1,138 @@
 #!/usr/bin/env ruby
 
-#
-# @author: Luis M. Rodriguez-R
-# @license: Artistic-2.0
-#
+$:.push File.expand_path('../lib', __FILE__)
 
-$:.push File.expand_path(File.dirname(__FILE__) + '/lib')
+require 'enveomics_rb/enveomics'
 require 'enveomics_rb/og'
-require 'optparse'
 require 'json'
+$VERSION = 1.1
 
-o = {q:false, a:false}
-ARGV << '-h' if ARGV.size==0
+o = { q: false, a: false }
 OptionParser.new do |opts|
-  opts.banner = "
-Estimates some descriptive statistics on a set of Orthology Groups (OGs).
+  opts.version = $VERSION
+  cmd = File.basename($0)
+  Enveomics.opt_banner(
+    opts,
+    'Estimates some descriptive statistics on a set of Orthology Groups (OGs)',
+    "#{cmd} -o file.ogs [options]"
+  )
 
-Usage: #{$0} [options]"
-  opts.separator ""
-  opts.separator "Mandatory"
-  opts.on("-o", "--ogs FILE",
-    "Input file containing the precomputed OGs."){ |v| o[:ogs]=v }
-  opts.separator ""
-  opts.separator "Other Options"
-  opts.on("-j", "--json FILE", "Output file in JSON format."){ |v| o[:json]=v }
-  opts.on("-t", "--tab FILE","Output file in tabular format."){ |v| o[:tab]=v }
-  opts.on("-T", "--transposed-tab FILE",
-    "Output file in transposed tabular format."){ |v| o[:ttab]=v }
-  opts.on("-a", "--auto", "Run completely quietly (no STDERR or STDOUT)") do
+  opts.separator 'Mandatory'
+  opts.on(
+    '-o', '--ogs FILE',
+    'Input file containing the precomputed OGs',
+    'Supports compression with .gz extension, use - for STDIN'
+  ) { |v| o[:ogs] = v }
+  opts.separator ''
+  opts.separator 'Other Options'
+  opts.on(
+    '-j', '--json FILE', 'Output file in JSON format',
+    'Supports compression with .gz extension, use - for STDOUT'
+  ) { |v| o[:json] = v }
+  opts.on(
+    '-t', '--tab FILE', 'Output file in tabular format',
+    'Supports compression with .gz extension, use - for STDOUT'
+  ) { |v| o[:tab] = v }
+  opts.on(
+    '-T', '--transposed-tab FILE',
+    'Output file in transposed tabular format',
+    'Supports compression with .gz extension, use - for STDOUT'
+  ){  |v| o[:ttab] = v }
+  opts.on('-a', '--auto', 'Run completely quietly (no STDERR or STDOUT)') do
     o[:q] = true
     o[:a] = true
   end
-  opts.on("-q", "--quiet", "Run quietly (no STDERR output)."){ o[:q] = true }
-  opts.on("-h", "--help", "Display this screen.") do
+  opts.on('-q', '--quiet', 'Run quietly (no STDERR output)') { o[:q] = true }
+  opts.on('-h', '--help', 'Display this screen') do
     puts opts
     exit
   end
-  opts.separator ""
+  opts.separator ''
 end.parse!
-abort "-o is mandatory" if o[:ogs].nil?
 
-##### MAIN:
+raise Enveomics::OptionError.new('-i is mandatory') if o[:ogs].nil?
+
 begin
   # Initialize the collection of OGs.
   collection = OGCollection.new
-   
+
   # Read the pre-computed OGs
   $stderr.puts "Reading pre-computed OGs in '#{o[:ogs]}'." unless o[:q]
-  f = File.open(o[:ogs], "r")
+  f = reader(o[:ogs])
   h = f.gets.chomp.split /\t/
   while ln = f.gets
     collection << OG.new(h, ln.chomp.split(/\t/))
   end
   f.close
   $stderr.puts " Loaded OGs: #{collection.ogs.length}." unless o[:q]
-   
+
   # Estimate descriptive stats
   stat_name = {
-    genomes: "Number of genomes",
-    pan: "Pangenome (OGs)",
-    core: "Core genome (OGs)",
-    core90pc: "OGs in 90% of the genomes",
-    core80pc: "OGs in 80% of the genomes",
-    unus: "Unus genome, core genome discarding paralogs (OGs)",
-    avg: "Average number of OGs in a genome",
-    avg_pan: "Average genome (OGs) / Pangenome (OGs)",
-    core_avg: "Core genome (OGs) / Average genome (OGs)",
-    core_pan: "Core genome (OGs) / Pangenome (OGs)",
-    ogs_shannon: "Entropy of the OG frequencies (bits)"
+    genomes:     'Number of genomes',
+    pan:         'Pangenome (OGs)',
+    core:        'Core genome (OGs)',
+    core90pc:    'OGs in 90% of the genomes',
+    core80pc:    'OGs in 80% of the genomes',
+    unus:        'Unus genome, core genome discarding paralogs (OGs)',
+    avg:         'Average number of OGs in a genome',
+    avg_pan:     'Average genome (OGs) / Pangenome (OGs)',
+    core_avg:    'Core genome (OGs) / Average genome (OGs)',
+    core_pan:    'Core genome (OGs) / Pangenome (OGs)',
+    ogs_shannon: 'Entropy of the OG frequencies (bits)'
   }
   stats = {}
   stats[:genomes] = Gene.genomes.length
   stats[:pan] = collection.ogs.length
   stats[:core] = collection.ogs.map do |og|
     (og.genomes.length == Gene.genomes.length) ? 1 : 0
-  end.inject(0,:+)
+  end.inject(0, :+)
   stats[:core90pc] = collection.ogs.map do |og|
-    (og.genomes.length >= 0.9*Gene.genomes.length) ? 1 : 0
-  end.inject(0,:+)
+    (og.genomes.length >= 0.9 * Gene.genomes.length) ? 1 : 0
+  end.inject(0, :+)
   stats[:core80pc] = collection.ogs.map do |og|
-    (og.genomes.length >= 0.8*Gene.genomes.length) ? 1 : 0
-  end.inject(0,:+)
+    (og.genomes.length >= 0.8 * Gene.genomes.length) ? 1 : 0
+  end.inject(0, :+)
   stats[:unus] = collection.ogs.map do |og|
     (og.genomes.length != Gene.genomes.length) ? 0 :
-      (og.genes.all?{ |i| i.size==1 }) ? 1 : 0
-  end.inject(0,:+)
-  og_genomes = collection.ogs.map{ |og| og.genomes.length }.inject(0,:+)
-  stats[:avg] = og_genomes.to_f/Gene.genomes.length
-  stats[:avg_pan] = stats[:avg]/stats[:pan]
-  stats[:core_avg] = stats[:core].to_f/stats[:avg]
-  stats[:core_pan] = stats[:core].to_f/stats[:pan]
+      (og.genes.all? { |i| i.size == 1 }) ? 1 : 0
+  end.inject(0, :+)
+  og_genomes       = collection.ogs.map { |og| og.genomes.length }.inject(0, :+)
+  stats[:avg]      = og_genomes.to_f / Gene.genomes.length
+  stats[:avg_pan]  = stats[:avg] / stats[:pan]
+  stats[:core_avg] = stats[:core].to_f / stats[:avg]
+  stats[:core_pan] = stats[:core].to_f / stats[:pan]
   stats[:ogs_shannon] = -1 * collection.ogs.map do |og|
-    pi = og.genomes.length.to_f/Gene.genomes.length
+    pi = og.genomes.length.to_f / Gene.genomes.length
     pi * Math.log(pi)
-  end.inject(0.0,:+)
+  end.inject(0.0, :+)
 
   # Show result
-  $stderr.puts "Generating reports." unless o[:q]
-  stats.each_pair{ |k,v| puts " #{stat_name[k]}: #{v}" } unless o[:a]
+  $stderr.puts 'Generating reports' unless o[:q]
+  stats.each_pair { |k, v| puts " #{stat_name[k]}: #{v}" } unless o[:a]
 
   # Save results in JSON
   unless o[:json].nil?
-    ohf = File.open(o[:json], "w")
-    ohf.puts JSON.pretty_generate(stats)
+    ohf = writer(o[:json])
+    ohf.puts(JSON.pretty_generate(stats))
     ohf.close
   end
 
   # Save results in tab
   unless o[:tab].nil?
-    ohf = File.open(o[:tab], "w")
-    stats.each_pair{ |k,v| ohf.puts "#{k}\t#{v}" }
+    ohf = writer(o[:tab])
+    stats.each_pair { |k, v| ohf.puts "#{k}\t#{v}" }
     ohf.close
   end
 
   # Save results in T(tab)
   unless o[:ttab].nil?
-    ohf = File.open(o[:ttab], "w")
+    ohf = writer(o[:ttab])
     ohf.puts stats.keys.join("\t")
     ohf.puts stats.values.join("\t")
     ohf.close
   end
 
-  $stderr.puts "Done.\n" unless o[:q] 
+  $stderr.puts 'Done' unless o[:q] 
 rescue => err
   $stderr.puts "Exception: #{err}\n\n"
   err.backtrace.each { |l| $stderr.puts l + "\n" }

data/utils/enveomics/enveomics.R/DESCRIPTION

@@ -1,5 +1,5 @@
 Package: enveomics.R
-Version: 1.9.0
+Version: 1.9.1
 Authors@R: c(person("Luis M.", "Rodriguez-R", role = c("aut", "cre"),
 	   email = "lmrodriguezr@gmail.com"))
 Title: Various Utilities for Microbial Genomics and Metagenomics
@@ -28,4 +28,4 @@ Suggests:
 License: Artistic-2.0
 LazyData: yes
 Encoding: UTF-8
-RoxygenNote: 7.1.2
+RoxygenNote: 7.3.1

data/utils/enveomics/enveomics.R/R/cliopts.R

@@ -90,8 +90,8 @@ enve.cliopts <- function(
 
     optopt <- list(help = "")
     if (length(o_desc[[i]]) == 1) optopt$help <- o_desc[[i]]
-    if (!is.null(f[[i]]) && !suppressWarnings(is.na(f[[i]])) &&
-        is.logical(f[[i]])){
+    if (!is.null(f[[i]])[1] && !suppressWarnings(is.na(f[[i]]))[1] &&
+        is.logical(f[[i]])[1]){
       optopt$opt_str <- paste(ifelse(f[[i]], "--no-", "--"), flag, sep = "")
       optopt$action  <- ifelse(f[[i]], "store_false", "store_true")
     } else {

data/utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.mower.Rd

@@ -9,8 +9,8 @@ enve.recplot2.findPeaks.mower(
   min.points = 10,
   quant.est = c(0.002, 0.998),
   mlv.opts = list(method = "parzen"),
-  fitdist.opts.sn = list(distr = "sn", method = "qme", probs = c(0.1, 0.5, 0.8), start
-    = list(omega = 1, alpha = -1), lower = c(0, -Inf, -Inf)),
+  fitdist.opts.sn = list(distr = "sn", method = "qme", probs = c(0.1, 0.5, 0.8), start =
+    list(omega = 1, alpha = -1), lower = c(0, -Inf, -Inf)),
   fitdist.opts.norm = list(distr = "norm", method = "qme", probs = c(0.4, 0.6), start =
     list(sd = 1), lower = c(0, -Inf)),
   rm.top = 0.05,

data/utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd

@@ -17,8 +17,8 @@
   id.lim = range(x$id.breaks),
   pos.lim = range(x$pos.breaks),
   pos.units = c("Mbp", "Kbp", "bp"),
-  mar = list(`1` = c(5, 4, 1, 1) + 0.1, `2` = c(ifelse(any(layout == 1), 1, 5), 4, 4,
-    1) + 0.1, `3` = c(5, ifelse(any(layout == 1), 1, 4), 1, 2) + 0.1, `4` =
+  mar = list(`1` = c(5, 4, 1, 1) + 0.1, `2` = c(ifelse(any(layout == 1), 1, 5), 4, 4, 1)
+    + 0.1, `3` = c(5, ifelse(any(layout == 1), 1, 4), 1, 2) + 0.1, `4` =
     c(ifelse(any(layout == 1), 1, 5), ifelse(any(layout == 2), 1, 4), 4, 2) + 0.1, `5` =
     c(5, 3, 4, 1) + 0.1, `6` = c(5, 4, 4, 2) + 0.1),
   pos.splines = 0,

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.3.9.7
+  version: 1.3.9.8
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-01-29 00:00:00.000000000 Z
+date: 2024-01-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons
@@ -472,7 +472,6 @@ files:
 - utils/enveomics/Scripts/in_silico_GA_GI.pl
 - utils/enveomics/Scripts/lib/data/dupont_2012_essential.hmm.gz
 - utils/enveomics/Scripts/lib/data/lee_2019_essential.hmm.gz
-- utils/enveomics/Scripts/lib/enveomics.R
 - utils/enveomics/Scripts/lib/enveomics_rb/anir.rb
 - utils/enveomics/Scripts/lib/enveomics_rb/bm_set.rb
 - utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb

data/utils/enveomics/Scripts/lib/enveomics.R

@@ -1 +0,0 @@
-../../enveomics.R