viral_seq 1.2.5 → 1.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5fef5f765c741aa14885673a2f980726956ae341a39926929d10ac0c7b4a6ece
-  data.tar.gz: d1e0cb4b691d4aff657209f5f87f02653421dc1bf9ba6dd4f87e43320ad143d5
+  metadata.gz: 2ccdd3f318deb458540b703ae00afcbdd195a92145c22dfb6c95ad14ac366146
+  data.tar.gz: 4f131cd69fef8548c1a466c2e23be008b08bed50ca78ef12195e4d4b39e052eb
 SHA512:
-  metadata.gz: 98b18297e15a5fb0eff8706029dcfdecdc5c39df28b6ae3ea8fe5b7611f63f91276f7ed5e459a478b1af25ec25662804290decc923b1c52f946a184d197807be
-  data.tar.gz: 7e359a05ff783971beced635cb2d913c4a9b418391425eba5ce9344b0137b989ea007d1ed5dc07a677a1775d9c73055aad552e971a89ca2207156db5233b243f
+  metadata.gz: 4cb44299c0061794b8c32c23c850cd9c53eb9245d7124ed75d35367225e600e2c630df9853d13a8003a8a1c6c793edea58a188871f328866043132585846e825
+  data.tar.gz: 92594266725b7691c5203cd478e84a0fea7fc6d08124efad6311a4e2bdcc7dbd0d6218a54e5b63d19e3c3a8ad789c49906388bac7ff59611bc5810e1c614d8ef

data/README.md

@@ -179,11 +179,32 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
 
 ## Updates
 
+### Version 1.2.9-08022021
+
+  1. Fixed a bug when reading the input primer sequences in lowercases.
+  2. Fix a bug in the method ViralSeq::Math::RandomGaussian
+
+### Version 1.2.8-07292021
+
+  1. Fixed an issue when reading .fastq files containing blank_lines.
+
+### Version 1.2.7-07152021
+
+  1. Optimzed the workflow of the `tcs` pipeline on raw data with uneven lengths.
+  `tcs` version to v2.3.6.
+
+
+### Version 1.2.6-07122021
+
+  1. Optimized the workflow of the `tcs` pipeline in the "end-join/QC/Trimming" section.
+  `tcs` version to v2.3.5.
+
+
 ### Version 1.2.5-06232021
 
   1. Add error rescue and report in the `tcs` pipeline.
     error messages are stored in the .tcs_error file. `tcs` pipeline updated to v2.3.4.
-  2. Use simple majority for the consensus cut-off in the default setting of the `tcs -dr` pipeline. 
+  2. Use simple majority for the consensus cut-off in the default setting of the `tcs -dr` pipeline.
 
 ### Version 1.2.2-05272021
 

data/bin/tcs

@@ -137,7 +137,7 @@ begin
   end
 
   primers = params[:primer_pairs]
-  if primers.empty?
+  if primers.empty? or primers.nil?
     ViralSeq::TcsCore.log_and_abort log, "No primer information. Script terminated."
   end
 
@@ -152,8 +152,8 @@ begin
     primer[:region] ? region = primer[:region] : region = "region"
     summary_json[:primer_set_name] = region
 
-    cdna_primer = primer[:cdna]
-    forward_primer = primer[:forward]
+    cdna_primer = primer[:cdna].upcase
+    forward_primer = primer[:forward].upcase
 
     export_raw = primer[:export_raw]
     limit_raw = primer[:limit_raw]
@@ -353,7 +353,8 @@ begin
       r1_seq_length = consensus_filtered.values[0][0].size
       r2_seq_length = consensus_filtered.values[0][1].size
     else
-      next
+      r1_seq_length = "n/a"
+      r2_seq_length = "n/a"
     end
     log.puts Time.now.to_s + "\t" + "R1 sequence #{r1_seq_length} bp"
     log.puts Time.now.to_s + "\t" + "R1 sequence #{r2_seq_length} bp"
@@ -415,71 +416,65 @@ begin
         joined_sh_raw = end_join(out_dir_raw, primer[:end_join_option], primer[:overlap])
       end
 
-    else
-      File.open(outfile_log, "w") do |f|
-        f.puts JSON.pretty_generate(summary_json)
-      end
-      next
-    end
-
-    if primer[:TCS_QC]
-      ref_start = primer[:ref_start]
-      ref_end = primer[:ref_end]
-      ref_genome = primer[:ref_genome].to_sym
-      indel = primer[:indel]
-      if ref_start == 0
-        ref_start = 0..(ViralSeq::RefSeq.get(ref_genome).size - 1)
-      end
-      if ref_end == 0
-        ref_end = 0..(ViralSeq::RefSeq.get(ref_genome).size - 1)
-      end
-      if primer[:end_join_option] == 1 and primer[:overlap] == 0
-        r1_sh = ViralSeq::SeqHash.fa(outfile_r1)
-        r2_sh = ViralSeq::SeqHash.fa(outfile_r2)
-        r1_sh = r1_sh.hiv_seq_qc(ref_start, (0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), indel, ref_genome)
-        r2_sh = r2_sh.hiv_seq_qc((0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), ref_end, indel, ref_genome)
-        new_r1_seq = r1_sh.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
-        new_r2_seq = r2_sh.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
-        joined_seq = {}
-        new_r1_seq.each do |seq_name, seq|
-          next unless seq
-          next unless new_r2_seq[seq_name]
-          joined_seq[seq_name] = seq + new_r2_seq[seq_name]
+      if primer[:TCS_QC]
+        ref_start = primer[:ref_start]
+        ref_end = primer[:ref_end]
+        ref_genome = primer[:ref_genome].to_sym
+        indel = primer[:indel]
+        if ref_start == 0
+          ref_start = 0..(ViralSeq::RefSeq.get(ref_genome).size - 1)
+        end
+        if ref_end == 0
+          ref_end = 0..(ViralSeq::RefSeq.get(ref_genome).size - 1)
         end
-        joined_sh = ViralSeq::SeqHash.new(joined_seq)
-
-        if export_raw
-          r1_sh_raw = ViralSeq::SeqHash.fa(outfile_raw_r1)
-          r2_sh_raw = ViralSeq::SeqHash.fa(outfile_raw_r2)
-          r1_sh_raw = r1_sh_raw.hiv_seq_qc(ref_start, (0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), indel, ref_genome)
-          r2_sh_raw = r2_sh_raw.hiv_seq_qc((0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), ref_end, indel, ref_genome)
-          new_r1_seq_raw = r1_sh_raw.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
-          new_r2_seq_raw = r2_sh_raw.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
-          joined_seq_raw = {}
-          new_r1_seq_raw.each do |seq_name, seq|
+        if primer[:end_join_option] == 1
+          r1_sh = ViralSeq::SeqHash.fa(outfile_r1)
+          r2_sh = ViralSeq::SeqHash.fa(outfile_r2)
+          r1_sh = r1_sh.hiv_seq_qc(ref_start, (0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), indel, ref_genome)
+          r2_sh = r2_sh.hiv_seq_qc((0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), ref_end, indel, ref_genome)
+          new_r1_seq = r1_sh.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
+          new_r2_seq = r2_sh.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
+          joined_seq = {}
+          new_r1_seq.each do |seq_name, seq|
             next unless seq
-            next unless new_r2_seq_raw[seq_name]
-            joined_seq_raw[seq_name] = seq + new_r2_seq_raw[seq_name]
+            next unless new_r2_seq[seq_name]
+            joined_seq[seq_name] = seq + new_r2_seq[seq_name]
           end
-          joined_sh_raw = ViralSeq::SeqHash.new(joined_seq_raw)
-        end
-      else
-        joined_sh = joined_sh.hiv_seq_qc(ref_start, ref_end, indel, ref_genome)
+          joined_sh = ViralSeq::SeqHash.new(joined_seq)
+
+          if export_raw
+            r1_sh_raw = ViralSeq::SeqHash.fa(outfile_raw_r1)
+            r2_sh_raw = ViralSeq::SeqHash.fa(outfile_raw_r2)
+            r1_sh_raw = r1_sh_raw.hiv_seq_qc(ref_start, (0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), indel, ref_genome)
+            r2_sh_raw = r2_sh_raw.hiv_seq_qc((0..(ViralSeq::RefSeq.get(ref_genome).size - 1)), ref_end, indel, ref_genome)
+            new_r1_seq_raw = r1_sh_raw.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
+            new_r2_seq_raw = r2_sh_raw.dna_hash.each_with_object({}) {|(k, v), h| h[k[0..-4]] = v}
+            joined_seq_raw = {}
+            new_r1_seq_raw.each do |seq_name, seq|
+              next unless seq
+              next unless new_r2_seq_raw[seq_name]
+              joined_seq_raw[seq_name] = seq + new_r2_seq_raw[seq_name]
+            end
+            joined_sh_raw = ViralSeq::SeqHash.new(joined_seq_raw)
+          end
+        else
+          joined_sh = joined_sh.hiv_seq_qc(ref_start, ref_end, indel, ref_genome)
 
-        if export_raw
-          joined_sh_raw = joined_sh_raw.hiv_seq_qc(ref_start, ref_end, indel, ref_genome)
+          if export_raw
+            joined_sh_raw = joined_sh_raw.hiv_seq_qc(ref_start, ref_end, indel, ref_genome)
+          end
         end
-      end
 
-      log.puts Time.now.to_s + "\t" + "Paired TCS number after QC based on reference genome: " + joined_sh.size.to_s
-      summary_json[:combined_tcs_after_qc] = joined_sh.size
-      if primer[:trim]
-        trim_start = primer[:trim_ref_start]
-        trim_end = primer[:trim_ref_end]
-        trim_ref = primer[:trim_ref].to_sym
-        joined_sh = joined_sh.trim(trim_start, trim_end, trim_ref)
-        if export_raw
-          joined_sh_raw = joined_sh_raw.trim(trim_start, trim_end, trim_ref)
+        log.puts Time.now.to_s + "\t" + "Paired TCS number after QC based on reference genome: " + joined_sh.size.to_s
+        summary_json[:combined_tcs_after_qc] = joined_sh.size
+        if primer[:trim]
+          trim_start = primer[:trim_ref_start]
+          trim_end = primer[:trim_ref_end]
+          trim_ref = primer[:trim_ref].to_sym
+          joined_sh = joined_sh.trim(trim_start, trim_end, trim_ref)
+          if export_raw
+            joined_sh_raw = joined_sh_raw.trim(trim_start, trim_end, trim_ref)
+          end
         end
       end
 
@@ -487,11 +482,13 @@ begin
       if export_raw
         joined_sh_raw.write_nt_fa(File.join(out_dir_raw, "combined.raw.fasta"))
       end
+
     end
 
     File.open(outfile_log, "w") do |f|
       f.puts JSON.pretty_generate(summary_json)
     end
+
   end
 
   unless options[:keep]

data/lib/viral_seq/math.rb

@@ -31,7 +31,7 @@ module ViralSeq
       def rand
         if (@compute_next_pair = !@compute_next_pair)
           theta = 2 * ::Math::PI * @rng.call
-          scale = @sd * ::Math.sqrt(-2 * Math.log(1 - @rng.call))
+          scale = @sd * ::Math.sqrt(-2 * ::Math.log(1 - @rng.call))
           @g1 = @mean + scale * ::Math.sin(theta)
           @g0 = @mean + scale * ::Math.cos(theta)
         else

data/lib/viral_seq/seq_hash.rb

@@ -116,6 +116,8 @@ module ViralSeq
 
       File.open(fastq_file,'r') do |file|
         file.readlines.collect do |line|
+          line.tr!("\u0000","")
+          next if line == "\n"
           count +=1
           count_m = count % 4
           if count_m == 1
@@ -397,7 +399,9 @@ module ViralSeq
       (0..(seq_length - 1)).each do |position|
         all_base = []
         seq_array.each do |seq|
-          all_base << seq[position]
+          if seq[position]
+            all_base << seq[position]
+          end
         end
         base_count = all_base.count_freq
         max_base_list = []

data/lib/viral_seq/tcs_core.rb

@@ -305,7 +305,8 @@ module ViralSeq
       end
 
       def general_filter(seq)
-        if seq.size < $platform_sequencing_length
+        return false unless seq
+        if seq.size < ($platform_sequencing_length - 10)
           return false
         elsif seq[1..-2] =~ /N/ # sequences with ambiguities except the 1st and last position removed
           return false

data/lib/viral_seq/version.rb

@@ -2,6 +2,6 @@
 # version info and histroy
 
 module ViralSeq
-  VERSION = "1.2.5"
-  TCS_VERSION = "2.3.4"
+  VERSION = "1.2.9"
+  TCS_VERSION = "2.3.8"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: viral_seq
 version: !ruby/object:Gem::Version
-  version: 1.2.5
+  version: 1.2.9
 platform: ruby
 authors:
 - Shuntai Zhou
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-06-23 00:00:00.000000000 Z
+date: 2021-08-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler