miga-base 1.3.18.0 → 1.3.19.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bf9ebc2ca06846d9b76c981c2a89896080690bc44d979ba28b4a9173f7386c7a
-  data.tar.gz: a156a4f0894f1988862b8daf296b916c80cf197eb36fb7c13c4698975403c35e
+  metadata.gz: 17006d8dcfa4831924a52e750945a9f7dd37aab9c25db9f46e8b679724fefe18
+  data.tar.gz: 5d06af895cd42a710c0a2fbf72a415858fde6efac771b8c9dac124ca7b35b228
 SHA512:
-  metadata.gz: b6e1318553d24d93af467670754e86e5281c7418d4242ad11b56125889188fb7cde48a1858f20e1b07bab04a372c4aac718e04c005bdfadccf641c15cd7cf2ed
-  data.tar.gz: e584f1b4442a099fb16c4b0c07515b9332867c5b72438bae9e33467f9d0911c7bd4811a6861121482cada1b88f44aaec2efd6d2f668fa6a05c722c9fe56995bc
+  metadata.gz: 8f128a71a9237728e2740e2066513f398c2c34ba067fc7d7cec3ccb06a397c6f41eedcdb4ea653c416f60de5fc43690419921c64d01301f1206ca56f07c62576
+  data.tar.gz: 6cd59ea9390942e428d060ae390fbf36fc7ad959c5bb9281577cbd85cf4ba4cf5df568b72fdce3dd8a6c92e69d23099d39f4375d435f2473fcf5806a2d7f6554

data/lib/miga/common/format.rb

@@ -23,8 +23,9 @@ module MiGA::Common::Format
   end
 
   ##
-  # Cleans a FastA file in place.
-  def clean_fasta_file(file)
+  # Cleans a FastA file in place, removing all sequences shorter than
+  # +min_len+
+  def clean_fasta_file(file, min_len = 1)
     tmp_fh = nil
     tmp_path = nil
     begin
@@ -39,19 +40,24 @@ module MiGA::Common::Format
         tmp_path = tmp_fh.path
         fh = File.open(file, 'r')
       end
-      buffer = ''.dup
+      next_seq = ['', '']
       fh.each_line do |ln|
         ln.chomp!
         if ln =~ /^>\s*(\S+)(.*)/
           id, df = $1, $2
-          tmp_fh.print buffer.wrap_width(80)
-          buffer = ''.dup
-          tmp_fh.puts ">#{id.gsub(/[^A-Za-z0-9_\|\.]/, '_')}#{df}"
+          if next_seq[1].length >= min_len
+            tmp_fh.puts next_seq[0]
+            tmp_fh.print next_seq[1].wrap_width(80)
+          end
+          next_seq = [">#{id.gsub(/[^A-Za-z0-9_\|\.]/, '_')}#{df}", '']
         else
-          buffer << ln.gsub(/[^A-Za-z\.\-]/, '')
+          next_seq[1] += ln.gsub(/[^A-Za-z\.\-]/, '')
         end
       end
-      tmp_fh.print buffer.wrap_width(80)
+      if next_seq[1].length >= min_len
+        tmp_fh.puts next_seq[0]
+        tmp_fh.print next_seq[1].wrap_width(80)
+      end
       tmp_fh.close
       fh.close
       FileUtils.mv(tmp_path, file)

data/lib/miga/dataset/result/add.rb

@@ -84,7 +84,7 @@ module MiGA::Dataset::Result::Add
     opts[:is_clean] ||= false
     r.clean! if opts[:is_clean]
     unless r.clean?
-      MiGA::MiGA.clean_fasta_file(r.file_path(:largecontigs))
+      MiGA::MiGA.clean_fasta_file(r.file_path(:largecontigs), 1000)
       r.clean!
     end
     r

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, 18, 0].freeze
+  VERSION = [1.3, 19, 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(2024, 7, 12)
+  VERSION_DATE = Date.new(2024, 7, 17)
 
   ##
   # References of MiGA

data/scripts/assembly.bash

@@ -58,7 +58,7 @@ if [[ -s "$DATASET/scaffold.fa" ]] ; then
 else
   ln -s "$DATASET/contig.fa" "$DATASET.AllContigs.fna"
 fi
-FastA.length.pl "$DATASET.AllContigs.fna" | awk '$2>=1000{print $1}' \
+FastA.length.pl "$DATASET.AllContigs.fna" | awk '$2 >= 1000 { print $1 }' \
   | FastA.filter.pl /dev/stdin "$DATASET.AllContigs.fna" \
   > "$DATASET.LargeContigs.fna"
 

data/test/result_stats_test.rb

@@ -83,7 +83,7 @@ class ResultStatsTest < Test::Unit::TestCase
     # Prepare result
     dir = 'data/05.assembly'
     fa = file_path(dir, '.LargeContigs.fna')
-    File.open(fa, 'w') { |fh| fh.puts '>1', 'ACTAC' }
+    File.open(fa, 'w') { |fh| fh.puts('>1', 'ACTAC' * 500) }
     touch_done(dir)
     r = dataset.add_result(:assembly)
 
@@ -91,15 +91,29 @@ class ResultStatsTest < Test::Unit::TestCase
     assert_equal({}, r[:stats])
     r.compute_stats
     assert_equal(1, r[:stats][:contigs])
-    assert_equal([5, 'bp'], r[:stats][:total_length])
+    assert_equal([2500, 'bp'], r[:stats][:total_length])
     assert_equal([40.0, '%'], r[:stats][:g_c_content])
   end
 
+  def test_large_contigs
+    # Prepare result
+    dir = 'data/05.assembly'
+    fa = file_path(dir, '.LargeContigs.fna')
+    File.open(fa, 'w') { |fh| fh.puts('>1', 'ACTAC' * 50) }
+    touch_done(dir)
+    r = dataset.add_result(:assembly)
+
+    # Test assertions
+    assert_equal({}, r[:stats])
+    r.compute_stats
+    assert_equal(0, r[:stats][:contigs])
+  end
+
   def test_cds
     # Prepare result
     dir = 'data/06.cds'
     fa = file_path(dir, '.faa')
-    File.open(fa, 'w') { |fh| fh.puts '>1', 'M' }
+    File.open(fa, 'w') { |fh| fh.puts('>1', 'M' * 500) }
     gff = file_path(dir, '.gff3.gz')
     Zlib::GzipWriter.open(gff) do |fh|
       fh.puts '# Model Data: a=b;transl_table=11;'
@@ -111,7 +125,7 @@ class ResultStatsTest < Test::Unit::TestCase
     assert_equal({}, r[:stats])
     r.compute_stats
     assert_equal(1, r[:stats][:predicted_proteins])
-    assert_equal([1.0, 'aa'], r[:stats][:average_length])
+    assert_equal([500.0, 'aa'], r[:stats][:average_length])
     assert_nil(r[:stats][:coding_density])
     test_assembly
     r.compute_stats

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: miga-base
 version: !ruby/object:Gem::Version
-  version: 1.3.18.0
+  version: 1.3.19.0
 platform: ruby
 authors:
 - Luis M. Rodriguez-R
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-07-12 00:00:00.000000000 Z
+date: 2024-07-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: daemons