miga-base 1.2.12.1 → 1.2.13.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 176a9a20427a4b14db0418fb1140025d2a5dc3737e4e6c55926524bd4d0f4d32
-  data.tar.gz: 4d1dca0ba71ea2ad86f4a4ffe5fbda8a8146f91464f092efe780ba92598bfd36
+  metadata.gz: c997637653ab5c7174be88b049f9ec78c432469a0bf08dc8c3572563480733b8
+  data.tar.gz: 731b7cad9da3266f2d21161dd5669d20214a648cded2a9cb9db3b0f23881a3fb
 SHA512:
-  metadata.gz: 521cb14499220bcf5cec8d5a532f7e8fe2708eac6ca7bdd53e5ca5472857d0a57f08750a232cbbd2cf704b082295a6668ec275e0956fc08a783dda13b0cc0471
-  data.tar.gz: 451d7f35d2e1666b3125fa58a85c171eb89310379a6acd67c1fd19bb0e1274e1cfe0a93775ccf42e93f03ea5f0e85b6045147fc8272b0d26e57bfdb97ecfa623
+  metadata.gz: af2b18c2d3153ee02a8a7aa6f79efda6f451678e63353e9a9e02b9248915d63536ab46aabe5d9e55d942da51d38d66df77c67aa25e15e2df604cf1e6af075dc3
+  data.tar.gz: 3cce4b8c2cce42a87d31e93c14c7c838ad40a90b5daa3c4220070cada7c0b092dfcc7c76e6c3744dcb9d144d9570e552046a6fec82cadfced72857814be27c8a

data/lib/miga/common/format.rb

@@ -155,6 +155,9 @@ class String
       .gsub(/g_c_(skew)/, 'G-C \\1')
       .gsub(/a_t_(skew)/, 'A-T \\1')
       .gsub(/x_content/, &:capitalize)
+      .gsub(/(^|_)([sl]su|a[an]i)(_|$)/, &:upcase)
+      .gsub(/^trna_/, 'tRNA ')
+      .gsub(/tRNA aa/, 'tRNA AA')
       .tr('_', ' ')
   end
 

data/lib/miga/dataset/base.rb

@@ -38,13 +38,13 @@ module MiGA::Dataset::Base
     cds: '06.cds',
     # Annotation
     essential_genes: '07.annotation/01.function/01.essential',
-    ssu: '07.annotation/01.function/02.ssu',
     mytaxa: '07.annotation/02.taxonomy/01.mytaxa',
     mytaxa_scan: '07.annotation/03.qa/02.mytaxa_scan',
     # Distances (for single-species datasets)
     taxonomy: '09.distances/05.taxonomy',
     distances: '09.distances',
-    # General statistics
+    # Post-QC
+    ssu: '07.annotation/01.function/02.ssu',
     stats: '90.stats'
   }
 
@@ -72,8 +72,8 @@ module MiGA::Dataset::Base
   # Returns an Array of tasks to be executed before project-wide tasks
   @@PREPROCESSING_TASKS = [
     :raw_reads, :trimmed_reads, :read_quality, :trimmed_fasta,
-    :assembly, :cds, :essential_genes, :ssu, :mytaxa, :mytaxa_scan,
-    :taxonomy, :distances, :stats
+    :assembly, :cds, :essential_genes, :mytaxa, :mytaxa_scan,
+    :taxonomy, :distances, :ssu, :stats
   ]
 
   ##

data/lib/miga/dataset/result.rb

@@ -295,9 +295,11 @@ module MiGA::Dataset::Result
     r = add_files_to_ds_result(
       MiGA::Result.new("#{base}.json"), name,
       longest_ssu_gene: '.ssu.fa',
-      gff: '.ssu.gff',
+      ssu_gff: '.ssu.gff', # DEPRECATED
+      gff: '.gff',
       all_ssu_genes: '.ssu.all.fa',
-      classification: '.rdp.tsv'
+      classification: '.rdp.tsv',
+      trna_list: '.trna.txt'
     )
     opts[:is_clean] ||= false
     r.clean! if opts[:is_clean]
@@ -384,10 +386,7 @@ module MiGA::Dataset::Result
   ##
   # Add result type +:stats+ at +base+ (no +_opts+ supported)
   def add_result_stats(base, _opts)
-    add_files_to_ds_result(
-      MiGA::Result.new("#{base}.json"), name,
-      trna_list: '.trna.txt'
-    )
+    MiGA::Result.new("#{base}.json")
   end
 
   ##

data/lib/miga/result/stats.rb

@@ -159,18 +159,52 @@ module MiGA::Result::Stats
   end
 
   def compute_stats_ssu
-    stats = { ssu: 0, complete_ssu: 0 }
+    stats = {
+      ssu: 0, complete_ssu: 0, ssu_fragment: 0.0,
+      lsu: 0, complete_lsu: 0, lsu_fragment: 0.0
+    }
+
     Zlib::GzipReader.open(file_path(:gff)) do |fh|
       fh.each_line do |ln|
         next if ln =~ /^#/
 
         rl = ln.chomp.split("\t")
-        len = (rl[4].to_i - rl[3].to_i).abs + 1
-        stats[:max_length] = [stats[:max_length] || 0, len].max
+        feat = Hash[rl[8].split(';').map { |i| i.split('=', 2) }]
+        subunit = feat['Name'] == '16S_rRNA' ? :ssu : :lsu
+        if subunit == :ssu
+          len = (rl[4].to_i - rl[3].to_i).abs + 1
+          stats[:max_length] = [stats[:max_length] || 0, len].max
+        end
         stats[:ssu] += 1
-        stats[:complete_ssu] += 1 unless rl[8] =~ /\(partial\)/
+        if feat['product'] =~ /\(partial\)/
+          if feat['note'] =~ /aligned only (\d+) percent/
+            fragment = $1.to_f
+            stats[:"#{subunit}_fragment"] ||= [fragment, '%']
+            if fragment > stats[:"#{subunit}_fragment"][0]
+              stats[:"#{subunit}_fragment"][0] = fragment
+            end
+          end
+        else
+          stats[:"complete_#{subunit}"] += 1
+          stats[:"#{subunit}_fragment"] = [100.0, '%']
+        end
       end
     end
+
+    Zlib::GzipReader.open(file_path(:trna_list)) do |fh|
+      no = 0
+      stats[:trna_count] = 0
+      aa = {}
+      fh.each_line do |ln|
+        next if (no += 1) < 4
+        stats[:trna_count] += 1
+        row = ln.chomp.split("\t")
+        next if row[9] == 'pseudo' || row[4] == 'Undet'
+        aa[row[4].gsub(/^f?([A-Za-z]+)[0-9]?/, '\1')] = true
+      end
+      stats[:trna_aa] = aa.size
+    end if file_path(:trna_list)
+
     stats
   end
 

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, 12, 1].freeze
+  VERSION = [1.2, 13, 0].freeze
 
   ##
   # Nickname for the current major.minor version.
@@ -20,7 +20,7 @@ module MiGA
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2022, 12, 30)
+  VERSION_DATE = Date.new(2022, 12, 31)
 
   ##
   # References of MiGA

data/scripts/ssu.bash

@@ -13,36 +13,56 @@ miga date > "$DATASET.start"
 
 fa="../../../05.assembly/$DATASET.LargeContigs.fna"
 if [[ -s $fa ]] ; then
+  # Get domain
+  d="$(miga ls -P "$PROJECT" -D "$DATASET" -m tax:d | awk '{print $2}')"
+  if [[ "$d" != "Bacteria" && "$d" != "Archaea" && "$d" != "Eukaryota" ]] ; then
+    d="Bacteria" # Assume Bacteria in the absence of additional information
+  fi
+
   # Run barrnap
-  barrnap --quiet --threads "$CORES" "$fa" | grep "^##gff\\|;product=16S " \
-    > "$DATASET.ssu.gff"
+  dom_opt="$(echo "$d" | perl -ne 'print lc' | head -c 3)"
+  barrnap --quiet --kingdom "$dom_opt" --threads "$CORES" "$fa" \
+    > "${DATASET}.gff"
 
   # Extract
-  bedtools getfasta -s "-fi" "$fa" -bed "$DATASET.ssu.gff" \
-    -fo "$DATASET.ssu.all.fa"
-  FastA.length.pl "$DATASET.ssu.all.fa" | sort -nr -k 2 | head -n 1 \
-    | cut -f 1 > "$DATASET.ssu.fa.id"
-  FastA.filter.pl "$DATASET.ssu.fa.id" "$DATASET.ssu.all.fa" > "$DATASET.ssu.fa"
-  rm "$DATASET.ssu.fa.id"
-  [[ -e "$fa.fai" ]] && rm "$fa.fai"
+  grep "^##gff\\|;product=16S " < "${DATASET}.gff" \
+    | bedtools getfasta -s "-fi" "$fa" -bed /dev/stdin \
+      -fo "${DATASET}.ssu.all.fa"
+  FastA.length.pl "${DATASET}.ssu.all.fa" | sort -nr -k 2 | head -n 1 \
+    | cut -f 1 > "${DATASET}.ssu.fa.id"
+  FastA.filter.pl "${DATASET}.ssu.fa.id" "${DATASET}.ssu.all.fa" \
+    > "${DATASET}.ssu.fa"
+  rm "${DATASET}.ssu.fa.id"
+  [[ -e "${fa}.fai" ]] && rm "${fa}.fai"
 
   # RDP classifier
-  if [[ "$MIGA_RDP" == "yes" && -s "$DATASET.ssu.all.fa" ]] ; then
+  if [[ "$MIGA_RDP" == "yes" && -s "${DATASET}.ssu.all.fa" ]] ; then
     java -jar "$MIGA_HOME/.miga_db/classifier.jar" classify \
-      -c 0.8 -f fixrank -g 16srrna -o "$DATASET.rdp.tsv" \
-      "$DATASET.ssu.all.fa"
+      -c 0.8 -f fixrank -g 16srrna -o "${DATASET}.rdp.tsv" \
+      "${DATASET}.ssu.all.fa"
     echo "# Version: $(perl -pe 's/.*://' \
           < "$MIGA_HOME/.miga_db/classifier.version.txt" \
           | grep . | paste - - | perl -pe 's/\t/; /')" \
-      >> "$DATASET.rdp.tsv"
+      >> "${DATASET}.rdp.tsv"
   fi
 
+  # tRNAscan-SE
+  dom_opt="-$(echo "$d" | perl -pe 's/(\S).*/$1/')"
+  out="${DATASET}.trna.txt"
+  # `echo O` is to avoid a hang from a pre-existing output file.
+  # This is better than pre-checking (and removing), because it avoids
+  # the (unlikely) scenario of a file racing (e.g., a file created right
+  # before tRNAscan-SE starts, or a `rm` failure).
+  #
+  # The trailing `|| true` is to treat failure as non-fatal
+  echo O | tRNAscan-SE $dom_opt -o "${DATASET}.trna.txt" -q "$fa" || true
+
   # Gzip
-  for x in ssu.gff ssu.all.fa rdp.tsv ; do
+  for x in gff ssu.all.fa rdp.tsv trna.txt ; do
     [[ -e "${DATASET}.${x}" ]] && gzip -9 -f "${DATASET}.${x}"
   done
 fi
 
 # Finalize
-miga date > "$DATASET.done"
+miga date > "${DATASET}.done"
 miga add_result -P "$PROJECT" -D "$DATASET" -r "$SCRIPT" -f

data/scripts/stats.bash

@@ -11,33 +11,8 @@ cd "$DIR"
 # Initialize
 miga date > "${DATASET}.start"
 
-# tRNAscan-SE
-fa="../05.assembly/${DATASET}.LargeContigs.fna"
-if [[ -s "$fa" ]] ; then
-  d="$(miga ls -P "$PROJECT" -D "$DATASET" -m tax:d | awk '{print $2}')"
-  if [[ "$d" == "Bacteria" || "$d" == "Archaea" || "$d" == "Eukaryota" ]] ; then
-    dom_opt="-$(echo "$d" | perl -pe 's/(\S).*/$1/')"
-    out="${DATASET}.trna.txt"
-    # `echo O` is to avoid a hang from a pre-existing output file.
-    # This is better than pre-checking (and removing), because it avoids
-    # the (unlikely) scenario of a file racing (e.g., a file created right
-    # before tRNAscan-SE starts, or a `rm` failure).
-    #
-    # The trailing `|| true` is to treat failure as non-fatal
-    echo O | tRNAscan-SE $dom_opt -o "$out" -q "$fa" || true
-    if [[ -s "$out" ]] ; then
-      cnt=$(tail -n +4 "$out" | wc -l | awk '{print $1}')
-      aa="$(tail -n +4 "$out" | grep -v 'pseudo$' | awk '{print $5}' \
-               | grep -v 'Undet' | perl -pe 's/^f?([A-Za-z]+)[0-9]?/$1/' \
-               | sort | uniq | wc -l | awk '{print $1}')"
-      miga edit -P "$PROJECT" -D "$DATASET" \
-        -m "trna_count=Int($cnt),trna_aa=Int($aa)"
-    fi
-  fi
-fi
-
 # Calculate statistics
-for i in raw_reads trimmed_fasta assembly cds essential_genes ssu distances taxonomy ; do
+for i in raw_reads trimmed_fasta assembly cds essential_genes distances taxonomy ssu ; do
   echo "# $i"
   miga stats --compute-and-save --ignore-empty -P "$PROJECT" -D "$DATASET" -r $i
 done

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.2.12.1
+  version: 1.2.13.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-12-30 00:00:00.000000000 Z
+date: 2022-12-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons