viral_seq 1.10.0 → 1.10.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d940e5f465cba40def34166fe50e0a21b1c62a1fff8e0be8abdabb7b4c4aab77
-  data.tar.gz: 7e4be6ec82d9081a1ea3130eed49dcaac080608e481c7520b43c2e58a50e379d
+  metadata.gz: 727ed9feb929e077b25cfd2a83661dccb88f1fd8c503635f14c948d71f6f2519
+  data.tar.gz: 6f1a69d0abeeabcad8107c3bbe515e9f909cd46b6732cdff66827ff4993e7efd
 SHA512:
-  metadata.gz: 15805b09c96b6d1bff023a82948f23ceb584c60ffb21b85e59d6f4ddc2e2394045a29788a7c5811c714afedfae6405c36b88e0bcadce0d1408068418c497e596
-  data.tar.gz: '0871676e5ee49fa14f84ec3c109172d964efac18f3f104ec38ad52daa69b9ef85a935c35ca2377d261b38edc5d8d438469b2360ec791a902116f60c8daeef5c2'
+  metadata.gz: a2a7dd1af8b9022f2b6cadec96be4f49985681d6d98e2b152fc2a12844573218eff17cf6db089ebacb84ea5284c47be254981ddf406e22989647eb4c07fb3285
+  data.tar.gz: 024f6066ecec3c5caed0277e10f0aaba596b3d95487e342885a325a1f9bfec7feb1c777eec2a4fbe26c2eb0ad55c8d437c6df6511a5c1c523d43a5d089eeef91

data/.gitignore

@@ -11,3 +11,5 @@
 
 # gem files
 *.gem
+
+.DS_Store

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    viral_seq (1.10.1)
+    viral_seq (1.10.0)
       colorize (~> 0.1)
       combine_pdf (~> 1.0, >= 1.0.0)
       muscle_bio (= 0.4)

data/README.md

@@ -191,7 +191,16 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
 
 ## Updates
 
-### Version-1.10.1
+### Version-1.10.3-12112025
+
+1. Bug fix for SDRM pipeline.
+2. Add a function in `locator` tool to export sequences in positive sense direction.
+
+### Version-1.10.2-07210225
+
+1. Fixed a bug processing parameters for HIV sequence QC.
+
+### Version-1.10.1-05012025
 
 1. Added quality filter for Illumina 2-color sequencing platforms (filter poly-G and poly-C)
 2. Replaced `MuscleBio` with [`VirustLocator`]("https://github.com/ViralSeq/virust-locator-ruby") for faster and more accurate pairwise alignment.

data/bin/locator

@@ -76,6 +76,10 @@ begin
   else
     csv_file = seq_file + ".csv"
   end
+  
+  fasta_file = csv_file.sub(/\.csv$/i, '.direction.fasta')
+
+  fasta_handle = File.open(fasta_file, 'w')
 
   unless File.exist?(seq_file)
     raise StandardError.new("Input file sequence file not found".red.bold)
@@ -92,9 +96,19 @@ begin
   locs = seqs.loc(opt)
   head = ["title", "sequence", "ref", "direction", "start", "end", "similarity", "indel", "aligned_input", "aligned_ref"]
   locs.unshift(head)
+
+  directional_fasta = []
   data = CSV.generate do |csv|
-    locs.each {|loc| csv << loc}
+    locs.each do |loc| 
+      csv << loc
+      directional_fasta << loc[1]
+      directional_fasta << loc[8].tr("-", "") # remove gaps for aligned_input
+    end
+  end
+  directional_fasta[2..-1].each do |line|
+    fasta_handle.puts line
   end
+  fasta_handle.close
 
   File.write(csv_file, data)
   puts "Output file found at #{csv_file.green.bold}"

data/bin/tcs_sdrm

@@ -12,10 +12,10 @@
 #     ├── lib1_IN
 #     ├── lib1_V1V3
 #   ├── lib2
-#     ├── lib1_RT
-#     ├── lib1_PR
-#     ├── lib1_IN
-#     ├── lib1_V1V3
+#     ├── lib2_RT
+#     ├── lib2_PR
+#     ├── lib2_IN
+#     ├── lib2_V1V3
 #   ├── ...
 #
 # output data in a new dir as 'libs_dir_SDRM'
@@ -37,7 +37,7 @@ r_version = ViralSeq::R.check_R
 ViralSeq::R.check_R_packages
 
 def abstract_line(data)
-  return_data = data[3] + data[2] + data[4] + ":" +
+  data[3] + data[2] + data[4] + ":" +
                 (data[6].to_f * 100).round(2).to_s + "(" +
                 (data[7].to_f * 100).round(2).to_s + "-" +
                 (data[8].to_f * 100).round(2).to_s + "); "
@@ -143,7 +143,7 @@ libs.each do |lib|
     seq_basename.gsub!(/\_P17/i, "_CA")
     region = version_config.query_region(region_name.to_s)
 
-    puts "prcessing region: " + region.region
+    puts "processing region: " + region.region
 
     sh = ViralSeq::SeqHash.fa(path_to_file)
 

data/lib/viral_seq/hivdr.rb

@@ -492,7 +492,7 @@ module ViralSeq
 
         self.dna_hash.each do |k,v|
             r1_seqs[k] = v[0,r1_length]
-            r2_seqs[k] = v[r1_length, r2_length]
+            r2_seqs[k] = v[-r2_length..-1] # to ensure the length from the end. Sometimes the platform will return sequence with one extra base.
         end
 
         r1_sh = ViralSeq::SeqHash.new(r1_seqs)

data/lib/viral_seq/recency_report.rb

@@ -106,7 +106,7 @@ module ViralSeq
         )
 
         formatted_text(
-          text_format2("P17", log[:pi_P17], log[:dist20_P17], log[:tcs_P17])
+          text_format2("CA", log[:pi_CA], log[:dist20_CA], log[:tcs_CA])
         )
 
         move_down 30

data/lib/viral_seq/seq_hash.rb

@@ -1440,8 +1440,10 @@ module ViralSeq
     def position_helper(position)
       if position.is_a?(Range)
         return position
-      elsif position.is_a?(Integer)
+      elsif position.is_a?(Integer) && position > 0
         return position..position
+      elsif position.is_a?(Integer) && position == 0
+        return 0..1000000
       elsif position.is_a?(String)
         return position.to_i..position.to_i
       elsif position.is_a?(Array)

data/lib/viral_seq/seq_hash_pair.rb

@@ -250,7 +250,7 @@ module ViralSeq
 
     private
     # determine overlap size from @dna_hash
-    def determine_overlap_pid_pair(seq_pair_hash, diff = 0.0)
+    def determine_overlap_pid_pair(seq_pair_hash, diff = 0.02)
       overlaps = []
       seq_pair_hash.each do |_seq_name, seq_pair|
         overlap_list = []

data/lib/viral_seq/tcs_dr.rb

@@ -65,7 +65,7 @@ module ViralSeq
          :TCS_QC=>true,
          :ref_genome=>"HXB2",
          :ref_start=>6585,
-         :ref_end=>7205..7210,
+         :ref_end=>7208,
          :indel=>true,
          :trim=>false},
          {:region=>"CA",
@@ -146,7 +146,7 @@ module ViralSeq
         :TCS_QC=>true,
         :ref_genome=>"HXB2",
         :ref_start=>6585,
-        :ref_end=>7205..7210,
+        :ref_end=>7208,
         :indel=>true,
         :trim=>false},
         {:region=>"CA",
@@ -226,7 +226,7 @@ module ViralSeq
         :TCS_QC=>true,
         :ref_genome=>"HXB2",
         :ref_start=>6585,
-        :ref_end=>7205..7210,
+        :ref_end=>7208,
         :indel=>true,
         :trim=>false},
         {:region=>"CA",
@@ -307,7 +307,7 @@ module ViralSeq
         :TCS_QC=>true,
         :ref_genome=>"HXB2",
         :ref_start=>6585,
-        :ref_end=>7205..7210,
+        :ref_end=>7208,
         :indel=>true,
         :trim=>false},
         {:region=>"CA",

data/lib/viral_seq/tcs_json.rb

@@ -101,10 +101,10 @@ module ViralSeq
 
               data[:ref_genome] = get_ref
 
-              print "reference 5'end ref position or posiiton range, 0 if no need to match this end \n> "
+              print "reference 5'end ref position or position range, 0 if no need to match this end \n> "
               data[:ref_start] = gets.chomp.rstrip.to_i
 
-              print "reference 3'end ref position or posiiton range: 0 if no need to match this end \n> "
+              print "reference 3'end ref position or position range: 0 if no need to match this end \n> "
               data[:ref_end] = gets.chomp.rstrip.to_i
 
               print "allow indels? (default as yes) Y/N \n> "