viral_seq 1.2.6 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: aee2536198f5579951f7c5f5f1b97ed27fb0bf5459e6dbfe79137a030951d443
-  data.tar.gz: 9ab9b69adf228d3429e02e5d47674ce0a0d137fa6231d940ef8d6cc9abfa1cdf
+  metadata.gz: a6ff64bcbe0e019c4e6842feae4c775e5975307a51ca111ea6629de5f918a163
+  data.tar.gz: 464d2eeacc49243722c8f8121df7a118c9a433da8df0e2f02e6c5195aa03e1a9
 SHA512:
-  metadata.gz: d9b5def3e29f819b6d83902676e80fa2d81531cb44132942244125f6b63110d66389e7f9c61d6e9ea3d80ece57d22d95d5c3948c3f7f71d48835b2714794ffe0
-  data.tar.gz: 44b996d9caf9029f2ef522d9058410cdc3b4ec253ccc7bacca5d9ecf66f487624b0b6d18c960b6c7a0af7bfcd2bc72c8c02df59d3c4c7834ab80d4a9eed2a424
+  metadata.gz: 9b0da2b42f7c1fb039995fa017cd6535a1253c6352be2f502ecf3ef25cbdc4bcdd7b8497e68ed00eab82e67007751be9474cc8a6f06ace3386a81456dae19a4e
+  data.tar.gz: df93fd5689cfc8e6b5248febd0a57961cb6773b0e939cb3c980b9b13cae60ca9177209f24acd13e94748733c6c7dee165b89a86c4505f961618d68c4a05782d2

data/README.md

@@ -179,6 +179,25 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
 
 ## Updates
 
+### Version 1.3.0-08302021
+
+  1. Fixed a bug in the `tcs` pipeline. 
+
+### 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.

data/bin/tcs

@@ -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"
@@ -400,7 +401,11 @@ begin
       when 4
         joined_sh = shp.join2(model: :indiv)
       end
-      return joined_sh
+      if joined_sh
+        return joined_sh
+      else
+        joined_sh = ViralSeq::SeqHash.new
+      end
     end
 
     if primer[:end_join]
@@ -426,7 +431,7 @@ begin
         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
+        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)

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 = "1.2.6"
-  TCS_VERSION = "2.3.5"
+  VERSION = "1.3.0"
+  TCS_VERSION = "2.3.8"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: viral_seq
 version: !ruby/object:Gem::Version
-  version: 1.2.6
+  version: 1.3.0
 platform: ruby
 authors:
 - Shuntai Zhou
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-07-12 00:00:00.000000000 Z
+date: 2021-08-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler