viral_seq 1.0.6 → 1.0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: df8d50f2dfbf0f2e7e1efcf66c8a91c286c7b5029533b725a4a33219882748bb
-  data.tar.gz: 4061c3875d4629025d1ccc216a54fdb7a011d397408a3ecb15125475e9f262e9
+  metadata.gz: bb326c97b25326286a51ec63583983a20dfebee2513fd8811bc855ec21ac0b5d
+  data.tar.gz: e9870bbaa8c17ba51d53e790ca8189e2dd362911e1b5cfcd4806a3bc68ccf369
 SHA512:
-  metadata.gz: a52087ced9fe258ef5bab4449b90e964ff9a557292dc1ce679aae03a56bd2570fdf1221e7026fec2b1ccb49ad2a9ff076338a397982e47c46877e2cdfb4e6d2e
-  data.tar.gz: 792cb9424fd46d536d0b95cfc90914a8548ee5ea6d1c3efe45cccd1d01c6dbd6b7a7ee0ba1be010bd6cf7a3ea201f4850803c28f16889b5286e1e458a774c8f1
+  metadata.gz: ff6e5727484687db04180a1ef9d3204e9ed02d9b1a98862bdb8796255680aca1e830667429a57db116702793dc55eeb7cc84800c39b27f8e2773186e1a638988
+  data.tar.gz: 86d0b03af6335cc91e38bc54a8c1fa7e2c84d430dc0adb02e4dc3819ebb188a0e8ae1e4c76c71e5066cac51675e0a45f9ee5a9b0bbd2de8b26da4fa04fe95d85

data/Gemfile.lock

@@ -1,12 +1,14 @@
 PATH
   remote: .
   specs:
-    viral_seq (1.0.5)
+    viral_seq (1.0.7)
+      colorize (~> 0.1)
       muscle_bio (~> 0.4)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    colorize (0.8.1)
     diff-lcs (1.3)
     muscle_bio (0.4.0)
     rake (10.5.0)
@@ -34,4 +36,4 @@ DEPENDENCIES
   viral_seq!
 
 BUNDLED WITH
-   2.0.2
+   2.1.4

data/README.md

@@ -14,7 +14,7 @@ Specifically for Primer-ID sequencing and HIV drug resistance analysis.
 
     #!/usr/bin/env ruby
     require 'viral_seq'
-    
+
 #### Use executable `locator` to get the coordinates of the sequences on HIV/SIV reference genome from a FASTA file through a terminal
 
     $ locator -i sequence.fasta -o sequence.fasta.csv
@@ -51,6 +51,13 @@ Specifically for Primer-ID sequencing and HIV drug resistance analysis.
 
 ## Updates
 
+Version 1.0.7-01282020:
+
+    1. Several methods added, including
+        ViralSeq::SeqHash#error_table
+        ViralSeq::SeqHash#random_select
+    2. Improved performance for several functions.
+
 Version 1.0.6-07232019:
 
     1. Several methods added to ViralSeq::SeqHash, including
@@ -58,7 +65,7 @@ Version 1.0.6-07232019:
         ViralSeq::SeqHash#+
         ViralSeq::SeqHash#write_nt_fa
         ViralSeq::SeqHash#mutation
-    2. Update documentations and rspec samples. 
+    2. Update documentations and rspec samples.
 
 Version 1.0.5-07112019:
 

data/bin/locator

@@ -3,13 +3,14 @@
 require 'viral_seq'
 require 'csv'
 require 'optparse'
+require 'colorize'
 
 def myparser
   options = {}
   OptionParser.new do |opts|
-    opts.banner = "Usage: locator -i [nt_sequence_fasta_file] -o [locator_info_csv_file] -r [reference_genome_option]"
+    opts.banner = "#{"Usage:".red.bold} locator #{"-i".blue.bold} [nt_sequence_fasta_file] #{"-o".blue.bold} [locator_info_csv_file] #{"-r".blue.bold} [reference_genome_option]"
 
-    opts.on('-i', '--infile FASTA_FILE', 'nt sequence file in FASTA format') do |i|
+    opts.on('-i', '--infile FASTA_FILE', "#{"nt sequence".blue.bold} file in FASTA format") do |i|
       options[:infile] = i
     end
 
@@ -17,7 +18,7 @@ def myparser
       options[:outfile] = o
     end
 
-    opts.on('-r', '--ref_option OPTION', 'reference genome option, choose from `HXB2` (default), `NL43`, `MAC239`') do |o|
+    opts.on('-r', '--ref_option OPTION', "reference genome option, choose from #{"`HXB2` (default), `NL43`, `MAC239`".blue.bold}") do |o|
       options[:ref_option] = o.to_sym
     end
 
@@ -35,9 +36,9 @@ def myparser
   return options
 end
 
-puts "\nSequence Locator (RubyGem::ViralSeq Version #{ViralSeq::VERSION}) by Shuntai Zhou"
-puts "See details at https://github.com/ViralSeq/viral_seq\n"
-puts "Resembling Sequence Locator from LANL (https://www.hiv.lanl.gov/content/sequence/LOCATE/locate.html)\n\n"
+puts "\n" + "Sequence Locator (RubyGem::ViralSeq Version #{ViralSeq::VERSION})".red.bold + " by " + "Shuntai Zhou".blue.bold
+puts "See details at " +  "https://github.com/ViralSeq/viral_seq\n".blue
+puts "Resembling" + " Sequence Locator ".magenta.bold + "from LANL" + " (https://www.hiv.lanl.gov/content/sequence/LOCATE/locate.html)\n".blue
 
 ARGV << '-h' if ARGV.size == 0
 
@@ -47,7 +48,7 @@ begin
   if options[:infile]
     seq_file = options[:infile]
   else
-    raise StandardError.new("Input file sequence file not found")
+    raise StandardError.new("Input file sequence file not found".red.bold)
   end
 
   if options[:outfile]
@@ -57,14 +58,14 @@ begin
   end
 
   unless File.exist?(seq_file)
-    raise StandardError.new("Input file sequence file not found")
+    raise StandardError.new("Input file sequence file not found".red.bold)
   end
 
   seqs = ViralSeq::SeqHash.fa(seq_file)
   opt =  options[:ref_option] ? options[:ref_option] : :HXB2
 
   unless [:HXB2, :NL43, :MAC239].include? opt
-    puts "Reference option #{opt} not recognized, using `:HXB2` as the reference genome."
+    puts "Reference option `#{opt}` not recognized, using `HXB2` as the reference genome.".red.bold
     opt = :HXB2
   end
 
@@ -76,6 +77,7 @@ begin
   end
 
   File.write(csv_file, data)
+  puts "Output file found at #{csv_file.green.bold}"
 rescue StandardError => e
   puts e.message
   puts "\n"

data/lib/viral_seq/muscle.rb

@@ -39,8 +39,8 @@ module ViralSeq
 
     def self.align(ref_seq = "", test_seq = "", path_to_muscle = false)
       temp_dir = Dir.home
-      temp_file = temp_dir + "/_temp_muscle_in"
-      temp_aln = temp_dir + "/_temp_muscle_aln"
+      temp_file = File.join(temp_dir, "_temp_muscle_in")
+      temp_aln = File.join(temp_dir, "_temp_muscle_aln")
       name = ">test"
       temp_in = File.open(temp_file,"w")
       temp_in.puts ">ref"

data/lib/viral_seq/seq_hash.rb

@@ -248,10 +248,12 @@ module ViralSeq
     def translate(codon_position = 0)
       seqs = self.dna_hash
       @aa_hash = {}
-      seqs.each do |name, seq|
-        s = ViralSeq::Sequence.new(name, seq)
+      seqs.uniq_hash.each do |seq, array_of_name|
+        s = ViralSeq::Sequence.new('name', seq)
         s.translate(codon_position)
-        @aa_hash[name] = s.aa_string
+        array_of_name.each do |name|
+          @aa_hash[name] = s.aa_string
+        end
       end
       return nil
     end # end of #translate
@@ -332,12 +334,13 @@ module ViralSeq
     def stop_codon(codon_position = 0)
       self.translate(codon_position)
       keys = []
-      self.aa_hash.each do |k,v|
-        keys << k if v.include?('*')
+      aa_seqs = self.aa_hash
+      aa_seqs.uniq_hash.each do |seq,array_of_name|
+        keys += array_of_name if seq.include?('*')
       end
       seqhash1 = self.sub(keys)
       seqhash1.title = self.title + "_stop"
-      keys2 = self.aa_hash.keys - keys
+      keys2 = aa_seqs.keys - keys
       seqhash2 = self.sub(keys2)
       return [seqhash1, seqhash2]
     end #end of #stop_codon
@@ -904,11 +907,11 @@ module ViralSeq
     # @return [ViralSeq::SeqHash] a new SeqHash object containing nt or aa sequences without gaps
     # @example gap strip for an array of sequences
     #   array = ["AACCGGTT", "A-CCGGTT", "AAC-GGTT", "AACCG-TT", "AACCGGT-"]
-    #   array = { AACCGGTT
-    #             A-CCGGTT
-    #             AAC-GGTT
-    #             AACCG-TT
-    #             AACCGGT- }
+    #   array = %w{ AACCGGTT
+    #               A-CCGGTT
+    #               AAC-GGTT
+    #               AACCG-TT
+    #               AACCGGT- }
     #   my_seqhash = ViralSeq::SeqHash.array(array)
     #   puts my_seqhash.gap_strip.dna_hash.values
     #     ACGT
@@ -963,12 +966,11 @@ module ViralSeq
     # @param (see #gap_strip)
     # @return [ViralSeq::SeqHash] a new SeqHash object containing nt or aa sequences without gaps at the ends
     # @example gap strip for an array of sequences only at the ends
-    #   array = ["AACCGGTT", "A-CCGGTT", "AAC-GGTT", "AACCG-TT", "AACCGGT-"]
-    #   array = { AACCGGTT
-    #             A-CCGGTT
-    #             AAC-GGTT
-    #             AACCG-TT
-    #             AACCGGT- }
+    #   array = %w{ AACCGGTT
+    #               A-CCGGTT
+    #               AAC-GGTT
+    #               AACCG-TT
+    #               AACCGGT- }
     #   my_seqhash = ViralSeq::SeqHash.array(array)
     #   puts my_seqhash.gap_strip_ends.dna_hash.values
     #     AACCGGT
@@ -1048,6 +1050,99 @@ module ViralSeq
       return new_seqhash
     end
 
+    # return an table of frequencies of nucleotides at each position.
+    # @param ref [String] a reference sequence to compare with, default as the sample consensus sequence
+    # @param head [Boolean] if the head of table is included.
+    # @return [Array] a two-dimension array of the frequency table,
+    #  including the following info:
+    #    position on the sequence (starting from 1)
+    #    consensus nucleotide
+    #    total sequence numbers
+    #    percentage of A, shows "-" if agrees with consensus
+    #    percentage of C, shows "-" if agrees with consensus
+    #    percentage of G, shows "-" if agrees with consensus
+    #    percentage of T, shows "-" if agrees with consensus
+    #
+    # @example error table for an array of sequences
+    #   array = %w{ AACCGGTT
+    #               AGCCGGTT
+    #               AACTGCTT
+    #               AACCGTTA
+    #               AACCGGTA }
+    #   my_seqhash = ViralSeq::SeqHash.array(array)
+    #   my_seqhash.error_table.each {|r| puts r.join(',')}
+    #     position,consensus,total_seq_number,A,C,G,T
+    #     1,A,5,-,,,
+    #     2,A,5,-,,0.2,
+    #     3,C,5,,-,,
+    #     4,C,5,,-,,0.2
+    #     5,G,5,,,-,
+    #     6,G,5,,0.2,-,0.2
+    #     7,T,5,,,,-
+    #     8,T,5,0.4,,,-
+
+    def error_table(ref = self.consensus, head = true)
+
+      table = []
+      if head
+        table << %w{
+          position
+          consensus
+          total_seq_number
+          A
+          C
+          G
+          T
+        }
+      end
+      ref_size = ref.size
+
+      (0..(ref_size - 1)).each do |position|
+        ref_base = ref[position]
+        nts = []
+
+        self.dna_hash.each do |_k,v|
+          nts << v[position]
+        end
+
+        freq = nts.count_freq
+        freq2 = {}
+
+        freq.each do |nt,c|
+          if nt == ref_base
+            freq2[nt] = '-'
+          else
+            freq2[nt] = (c/(self.size).to_f)
+          end
+        end
+
+        table << [(position + 1),ref_base,self.size,freq2['A'],freq2['C'],freq2['G'],freq2['T']]
+      end
+
+      return table
+
+    end # end of error_table
+
+    # randomly select n number of sequences from the orginal SeqHash object
+    # @param n [Integer] number of sequences to randomly select
+    # @return [ViralSeq::SeqHash] a new SeqHash object with randomly selected sequences
+
+    def random_select(n = 100)
+      new_sh = ViralSeq::SeqHash.new
+      dna_hash = self.dna_hash
+      aa_hash = self.aa_hash
+      qc_hash = self.qc_hash
+
+      keys = dna_hash.keys.sample(n)
+
+      keys.each do |k|
+        new_sh.dna_hash[k] = dna_hash[k]
+        new_sh.aa_hash[k] = aa_hash[k]
+        new_sh.qc_hash[k] = qc_hash[k]
+      end
+      new_sh.title = self.title + "_" + n.to_s
+      return new_sh
+    end
 
 
     # start of private functions

data/lib/viral_seq/seq_hash_pair.rb

@@ -7,7 +7,7 @@ module ViralSeq
   # @example join the paired-end sequences with an overlap of 100 bp
   #   my_seqhashpair.join1(100)
   # @example join the paired-end sequences with unknown overlap, each pair of sequences has its own overlap size
-  #   my_seqhashpair.join1(:indiv)
+  #   my_seqhashpair.join2(model: :indiv)
 
   class SeqHashPair
 
@@ -104,17 +104,21 @@ module ViralSeq
       raise ArgumentError.new(":overlap has to be Integer, input #{overlap} invalid.") unless overlap.is_a? Integer
       raise ArgumentError.new(":diff has to be float or integer, input #{diff} invalid.") unless (diff.is_a? Integer or diff.is_a? Float)
       joined_seq = {}
-      seq_pair_hash.each do |seq_name, seq_pair|
+      seq_pair_hash.uniq_hash.each do |seq_pair, seq_names|
         r1_seq = seq_pair[0]
         r2_seq = seq_pair[1]
         if overlap.zero?
-          joined_seq[seq_name] = r1_seq + r2_seq
+          joined_sequence = r1_seq + r2_seq
         elsif r1_seq[-overlap..-1].compare_with(r2_seq[0,overlap]) <= (overlap * diff)
-          joined_seq[seq_name] = r1_seq + r2_seq[overlap..-1]
+          joined_sequence= r1_seq + r2_seq[overlap..-1]
         else
           next
         end
+        seq_names.each do |seq_name|
+          joined_seq[seq_name] = joined_sequence
+        end
       end
+
       joined_seq_hash = ViralSeq::SeqHash.new
       joined_seq_hash.dna_hash = joined_seq
       joined_seq_hash.title = self.title + "_joined"
@@ -139,7 +143,7 @@ module ViralSeq
     #   my_seqhashpair = ViralSeq::SeqHashPair.new(paired_seq2)
     #   my_seqhashpair.join2.dna_hash
     #   => {">pair4"=>"AAAGGGGGGGGGGTT", ">pair5"=>"AAAAAAGGGGTTTTT", ">pair6"=>"AAACAAGGGGTTTTT"}
-    #   my_seqhashpair.join2(model :indiv).dna_hash
+    #   my_seqhashpair.join2(model: :indiv).dna_hash
     #   => {">pair4"=>"AAAGGGGGGGTT", ">pair5"=>"AAAAAAGGGGTTTTT", ">pair6"=>"AAACAAGGGGTTTTT"}
 
     def join2(model: :con, diff: 0.0)

data/lib/viral_seq/version.rb

@@ -2,5 +2,5 @@
 # version info and histroy
 
 module ViralSeq
-  VERSION = "1.0.6"
+  VERSION = "1.0.7"
 end

data/viral_seq.gemspec

@@ -31,5 +31,9 @@ Gem::Specification.new do |spec|
 
   # muscle_bio gem required
   spec.add_runtime_dependency "muscle_bio", "~> 0.4"
+
+  # colorize gem required
+  spec.add_runtime_dependency "colorize", "~> 0.1"
+
   spec.requirements << 'R required for some functions'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: viral_seq
 version: !ruby/object:Gem::Version
-  version: 1.0.6
+  version: 1.0.7
 platform: ruby
 authors:
 - Shuntai Zhou
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-07-23 00:00:00.000000000 Z
+date: 2020-01-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -67,6 +67,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.4'
+- !ruby/object:Gem::Dependency
+  name: colorize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
 description: |-
   A Ruby Gem with bioinformatics tools for processing viral NGS data.
                             Specifically for Primer-ID sequencing and HIV drug resistance analysis.
@@ -124,7 +138,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements:
 - R required for some functions
-rubygems_version: 3.0.3
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: A Ruby Gem containing bioinformatics tools for processing viral NGS data.