viral_seq 1.0.9 → 1.0.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4921d3609d6ffc7fd6fbafd7a4a86e5818d47ed855393addd68b20f28b9d214f
-  data.tar.gz: a9e18c01b287885f8f6238343d9633a52d4ae5ea061347e73bd4f3e86788b2a4
+  metadata.gz: 14d880e9f39b2b87892bec9d4377b358643c880cf32c81872cff51e1007bc23b
+  data.tar.gz: 6ee1c3293e2b0403a2eac033335f7575625b2d35f32127b5b57be53e94b4ec7d
 SHA512:
-  metadata.gz: dd21b57e17751f6c3e475f05b7a565d295ac7592b7c02f8d89ed49192834bee444f08ee9ebf48e41922c8caaf37a03651d5d0c9aa89d97ccc2edb9aad8224d5f
-  data.tar.gz: d1162424ea877d9839c179cacc330c81cd3508fcff07b64a1e753c7c706485d1dcb9a6b60aec9ce02ed33b91bbd4386ed58329c17e247ba086e7d81ed107bfd4
+  metadata.gz: 951b75ced84aa21cf5650baa6970f60a617d3f29d20c14acadacefabea23d6b584f25990453c2008f30197aaef055a94edbdbb45494bb12b6343d90bc6bd45fb
+  data.tar.gz: 68ac69b4ebd5438a8f73780db823c94aa5a78c7c26d02cfd6bec979244dd1d6452c3698ade0606ddbbaccc480ad85e603171c11648dbb0110c2f5dbb3355bb35

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    viral_seq (1.0.9)
+    viral_seq (1.0.10)
       colorize (~> 0.1)
       muscle_bio (~> 0.4)
 

data/README.md

@@ -4,72 +4,76 @@ A Ruby Gem containing bioinformatics tools for processing viral NGS data.
 
 Specifically for Primer-ID sequencing and HIV drug resistance analysis.
 
-## Installation
+## Install
 
+```bash
     $ gem install viral_seq
+```
 
 ## Usage
 
-#### Load all ViralSeq classes by requiring 'viral_seq.rb'
+### Excutables
 
-```ruby
-#!/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
+Use executable `locator` to get the coordinates of the sequences on HIV/SIV reference genome from a FASTA file through a terminal
 
+```bash
     $ locator -i sequence.fasta -o sequence.fasta.csv
+```
 
+Use executable `tcs` pipeline to process Primer ID MiSeq sequencing data.
 
-#### Use executable `tcs` pipeline to process Primer ID MiSeq sequencing data. Parameter json file can be generated using `tcs_json_generator` or at https://tcs-dr-dept-tcs.cloudapps.unc.edu/generator.php
-
-    $ tcs params.json
-
-#### Use executable `tcs_json_generator` to generate params .json file for the `tcs` pipeline.
+```bash
+    $ tcs -p params.json # run TCS pipeline with params.json
+    $ tcs -j # CLI to generate params.json
+    $ tcs -h # print out the help
+```
 
-    $ tcs_json_generator
+## Some Examples
 
+Load all ViralSeq classes by requiring 'viral_seq.rb' in your Ruby scripts.
 
-## Some Examples
+```ruby
+#!/usr/bin/env ruby
+require 'viral_seq'
+```
 
-#### Load nucleotide sequences from a FASTA format sequence file
+Load nucleotide sequences from a FASTA format sequence file
 
 ```ruby
 my_seqhash = ViralSeq::SeqHash.fa('my_seq_file.fasta')
 ```
 
-#### Make an alignment (using MUSCLE)
+Make an alignment (using MUSCLE)
 
 ```ruby
 aligned_seqhash = my_seqhash.align
 ```
 
-#### Filter nucleotide sequences with the reference coordinates (HIV Protease)
+Filter nucleotide sequences with the reference coordinates (HIV Protease)
 
 ```ruby
 qc_seqhash = aligned_seqhash.hiv_seq_qc(2253, 2549, false, :HXB2)
 ```
 
-#### Further filter out sequences with Apobec3g/f hypermutations
+Further filter out sequences with Apobec3g/f hypermutations
 
 ```ruby
 qc_seqhash = qc_seqhash.a3g
 ```
 
-#### Calculate nucleotide diveristy π
+Calculate nucleotide diveristy π
 
 ```ruby
 qc_seqhash.pi
 ```
 
-#### Calculate cut-off for minority variants based on Poisson model
+Calculate cut-off for minority variants based on Poisson model
 
 ```ruby
 cut_off = qc_seqhash.pm
 ```
 
-#### Examine for drug resistance mutations for HIV PR region
+Examine for drug resistance mutations for HIV PR region
 
 ```ruby
 qc_seqhash.sdrm_hiv_pr(cut_off)
@@ -77,13 +81,22 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
 
 ## Updates
 
-Version 1.0.9-07182020:
+### Version 1.1.0-11112020:
+
+  1. Modularize TCS pipeline. Move key functions into /viral_seq/tcs_core.rb
+  2. `tcs_json_generator` is removed. This CLI is delivered within the `tcs` pipeline, by running `tcs -j`. The scripts are included in the /viral_seq/tcs_json.rb
+  3. consensus model now includes a true simple majority model, where no nt needs to be over 50% to be called.
+  4. a few optimizations.
+  5. TCS 2.1.0 delivered.
+  6. Tried parallel processing. Cannot achieve the goal because `parallel` gem by default can't pool data from memory of child processors and `in_threads` does not help with the speed. 
+
+### Version 1.0.9-07182020:
 
   1. Change ViralSeq::SeqHash#stop_codon and ViralSeq::SeqHash#a3g_hypermut return value to hash object.
 
   2. TCS pipeline updated to version 2.0.1. Add optional `export_raw: TRUE/FALSE` in json params. If `export_raw` is `TRUE`, raw sequence reads (have to pass quality filters) will be exported, along with TCS reads.
 
-Version 1.0.8-02282020:
+### Version 1.0.8-02282020:
 
   1. TCS pipeline (version 2.0.0) added as executable.
       tcs  -  main TCS pipeline script.
@@ -94,14 +107,14 @@ Version 1.0.8-02282020:
 
   3. Bug fix for several methods.
 
-Version 1.0.7-01282020:
+### 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:
+### Version 1.0.6-07232019:
 
   1. Several methods added to ViralSeq::SeqHash, including
       ViralSeq::SeqHash#size
@@ -110,33 +123,33 @@ Version 1.0.6-07232019:
       ViralSeq::SeqHash#mutation
   2. Update documentations and rspec samples.
 
-Version 1.0.5-07112019:
+### Version 1.0.5-07112019:
 
   1. Update ViralSeq::SeqHash#sequence_locator.
      Program will try to determine the direction (`+` or `-` of the query sequence)
   2. update executable `locator` to have a column of `direction` in output .csv file
 
-Version 1.0.4-07102019:
+### Version 1.0.4-07102019:
 
   1. Use home directory (Dir.home) instead of the directory of the script file for temp MUSCLE file.
   2. Fix bugs in bin `locator`
 
-Version 1.0.3-07102019:
+### Version 1.0.3-07102019:
 
   1. Bug fix.
 
-Version 1.0.2-07102019:
+### Version 1.0.2-07102019:
 
   1. Fixed a gem loading issue.
 
-Version 1.0.1-07102019:
+### Version 1.0.1-07102019:
 
   1. Add keyword argument :model to ViralSeq::SeqHashPair#join2.
   2. Add method ViralSeq::SeqHash#sequence_locator (also: #loc), a function to locate sequences on HIV/SIV reference genomes, as HIV Sequence Locator from LANL.
   3. Add executable 'locator'. An HIV/SIV sequence locator tool similar to LANL Sequence Locator.
   4. update documentations
 
-Version 1.0.0-07092019:
+### Version 1.0.0-07092019:
 
   1. Rewrote the whole ViralSeq gem, grouping methods into modules and classes under main Module::ViralSeq
 

data/bin/tcs

@@ -28,114 +28,79 @@
 require 'viral_seq'
 require 'json'
 require 'colorize'
+require 'OptionParser'
 
+options = {}
 
-# calculate consensus cutoff
+banner = '-'*50 + "\n" +
+        '| The TCS Pipeline ' + "Version #{ViralSeq::TCS_VERSION}".red.bold + " by " + "Shuntai Zhou".blue.bold + ' |' + "\n" +
+        '-'*50 + "\n"
 
-def calculate_cut_off(m, error_rate = 0.02)
-  n = 0
-  case error_rate
-  when 0.005...0.015
-    if m <= 10
-      n = 2
-    else
-      n = 1.09*10**-26*m**6 + 7.82*10**-22*m**5 - 1.93*10**-16*m**4 + 1.01*10**-11*m**3 - 2.31*10**-7*m**2 + 0.00645*m + 2.872
-    end
+OptionParser.new do |opts|
+  opts.banner = banner + "Usage: tcs -j"
+  opts.on "-j", "--json_generator", "Command line interfac to generate new params json file" do |j|
+    options[:json_generator] = true
+  end
 
-  when 0...0.005
-    if m <= 10
-      n = 2
-    else
-      n = -9.59*10**-27*m**6 + 3.27*10**-21*m**5 - 3.05*10**-16*m**4 + 1.2*10**-11*m**3 - 2.19*10**-7*m**2 + 0.004044*m + 2.273
-    end
+  opts.on("-p", "--params PARAMS_JSON", "Execute the pipeline with input params json file") do |p|
+    options[:params_json] = p
+  end
 
-  else
-    if m <= 10
-      n = 2
-    elsif m <= 8500
-      n = -1.24*10**-21*m**6 + 3.53*10**-17*m**5 - 3.90*10**-13*m**4 + 2.12*10**-9*m**3 - 6.06*10**-6*m**2 + 1.80*10**-2*m + 3.15
-    else
-      n = 0.0079 * m + 9.4869
-    end
+  opts.on("-h", "--help", "Prints this help") do
+    puts opts
+    exit
   end
 
-  n = n.round
-  n = 2 if n < 3
-  return n
-end
+  opts.on("-v", "--version", "Version info") do
+    puts "tcs version: " + ViralSeq::TCS_VERSION.red.bold
+    puts "viral_seq version: " + ViralSeq::VERSION.red.bold
+    exit
+  end
 
-puts "\n" + '-'*50
-puts '| The TCS Pipeline ' + "Version #{ViralSeq::TCS_VERSION}".red.bold + " by " + "Shuntai Zhou".blue.bold + ' |'
-puts '-'*50 + "\n"
+  # opts.on("--no-parallel", "toggle off parallel processing") do
+  #   options[:no_parallel] = true
+  # end
+end.parse!
 
-unless ARGV[0]
-  raise "No JSON param file found. Script terminated."
+if options[:json_generator]
+  params = ViralSeq::TcsJson.generate
+elsif (options[:params_json] && File.exist?(options[:params_json]))
+  params = JSON.parse(File.read(options[:params_json]), symbolize_names: true)
+else
+  abort "No params JSON file found. Script terminated.".red
 end
 
-params = JSON.parse(File.read(ARGV[0]), symbolize_names: true)
-
 indir = params[:raw_sequence_dir]
 
 unless File.exist?(indir)
-  raise "No input sequence directory found. Script terminated."
-end
-
-libname = File.basename(indir)
-
-# obtain R1 and R2 file path
-files = []
-Dir.chdir(indir) do
-  files = Dir.glob("*")
+  abort "No input sequence directory found. Script terminated.".red.bold
 end
 
-if files.empty?
-  raise "Input dir does not contain files. Script terminated."
-end
+# log file
 
-r1_f = ""
-r2_f = ""
-
-# unzip .fasta.gz
-def unzip_r(indir, f)
-  r_file = indir + "/" + f
-  if f =~ /.gz/
-    `gzip -d #{r_file}`
-    new_f = f.sub ".gz", ""
-    r_file = File.join(indir, new_f)
-  end
-  return r_file
-end
 runtime_log_file = File.join(indir,"runtime.log")
 log = File.open(runtime_log_file, "w")
 log.puts "TSC pipeline Version " + ViralSeq::TCS_VERSION.to_s
 log.puts "viral_seq Version " + ViralSeq::VERSION.to_s
 log.puts Time.now.to_s + "\t" + "Start TCS pipeline..."
 
+libname = File.basename indir
 
-files.each do |f|
-  t = f.split("_")
-  if t.size == 1
-    tag = f
-  else
-    tag = f.split("_")[1..-1].join("_")
-  end
+seq_files = ViralSeq::TcsCore.r1r2 indir
 
-  if tag =~ /r1/i
-    r1_f = unzip_r(indir, f)
-  elsif tag =~ /r2/i
-    r2_f = unzip_r(indir, f)
-  end
-end
-
-
-unless File.exist?(r1_f)
-  log.puts "R1 file not found. Script terminated."
-  raise "R1 file not found. Script terminated."
+if seq_files[:r1_file].size > 0 and seq_files[:r2_file].size > 0
+  r1_f = seq_files[:r1_file]
+  r2_f = seq_files[:r2_file]
+elsif seq_files[:r1_file].size > 0 and seq_files[:r2_file].empty?
+  exit_sig = "Missing R2 file. Aborted."
+elsif seq_files[:r2_file].size > 0 and seq_files[:r1_file].empty?
+  exit_sig = "Missing R1 file. Aborted."
+else
+  exit_sig = "Cannot determine R1 R2 file in #{indir}. Aborted."
 end
 
-unless File.exist?(r2_f)
-  log.puts "R2 file not found. Script terminated."
-  raise "R2 file not found. Script terminated."
+if exit_sig
+  ViralSeq::TcsCore.log_and_abort log, exit_sig
 end
 
 r1_fastq_sh = ViralSeq::SeqHash.fq(r1_f)
@@ -152,10 +117,10 @@ end
 
 primers = params[:primer_pairs]
 if primers.empty?
-  log.puts "No primer information. Script terminated."
-  raise "No primer information. Script terminated."
+  ViralSeq::TcsCore.log_and_abort log, "No primer information. Script terminated."
 end
 
+
 primers.each do |primer|
   summary_json = {}
   summary_json[:tcs_version] = ViralSeq::TCS_VERSION
@@ -179,66 +144,25 @@ primers.each do |primer|
   summary_json[:cdan_primer] = cdna_primer
   summary_json[:forward_primer] = forward_primer
 
-  primer[:majority] ? majority_cut_off = primer[:majority] : majority_cut_off = 0.5
+  primer[:majority] ? majority_cut_off = primer[:majority] : majority_cut_off = 0
   summary_json[:majority_cut_off] = majority_cut_off
 
   summary_json[:total_raw_sequence] = raw_sequence_number
 
   log.puts Time.now.to_s + "\t" +  "Porcessing #{region}..."
 
-  r1_raw = r1_fastq_sh.dna_hash
-  r2_raw = r2_fastq_sh.dna_hash
-
+  # filter R1
   log.puts Time.now.to_s + "\t" +  "filtering R1..."
-  # obtain biological forward primer sequence
-  if forward_primer.match(/(N+)(\w+)$/)
-    forward_n = $1.size
-    forward_bio_primer = $2
-  else
-    forward_n = 0
-    forward_bio_primer = forward_primer
-  end
-  forward_bio_primer_size = forward_bio_primer.size
-  forward_starting_number = forward_n + forward_bio_primer_size
-
-  # filter R1 sequences with forward primers.
-  forward_primer_ref = forward_bio_primer.nt_parser
-  r1_passed_seq = {}
-  r1_raw.each do |name,seq|
-    next if seq[1..-2] =~ /N/ # sequences with ambiguities except the 1st and last position removed
-    next if seq =~ /A{11}/ # a string of poly-A indicates adaptor sequence
-    next if seq =~ /T{11}/ # a string of poly-T indicates adaptor sequence
-
-    primer_region_seq = seq[forward_n, forward_bio_primer_size]
-    if primer_region_seq =~ forward_primer_ref
-      r1_passed_seq[name.split("\s")[0]] = seq
-    end
-  end
+  filter_r1 = ViralSeq::TcsCore.filter_r1(r1_fastq_sh, forward_primer)
+  r1_passed_seq = filter_r1[:r1_passed_seq]
   log.puts Time.now.to_s + "\t" +  "R1 filtered: #{r1_passed_seq.size.to_s}"
-
   summary_json[:r1_filtered_raw] = r1_passed_seq.size
 
+  # filter R2
   log.puts Time.now.to_s + "\t" +  "filtering R2..."
-  # obtain biological reverse primer sequence
-  cdna_primer.match(/(N+)(\w+)$/)
-  pid_length = $1.size
-  cdna_bio_primer = $2
-  cdna_bio_primer_size = cdna_bio_primer.size
-  reverse_starting_number = pid_length + cdna_bio_primer_size
-
-  # filter R2 sequences with cDNA primers.
-  cdna_primer_ref = cdna_bio_primer.nt_parser
-  r2_passed_seq = {}
-  r2_raw.each do |name, seq|
-    next if seq[1..-2] =~ /N/ # sequences with ambiguities except the 1st and last position removed
-    next if seq =~ /A{11}/ # a string of poly-A indicates adaptor sequence
-    next if seq =~ /T{11}/ # a string of poly-T indicates adaptor sequence
-
-    primer_region_seq = seq[pid_length, cdna_bio_primer_size]
-    if primer_region_seq =~ cdna_primer_ref
-      r2_passed_seq[name.split("\s")[0]] = seq
-    end
-  end
+  filter_r2 = ViralSeq::TcsCore.filter_r2(r2_fastq_sh, cdna_primer)
+  r2_passed_seq = filter_r2[:r2_passed_seq]
+  pid_length = filter_r2[:pid_length]
   log.puts Time.now.to_s + "\t" +  "R2 filtered: #{r2_passed_seq.size.to_s}"
   summary_json[:r2_filtered_raw] = r2_passed_seq.size
 
@@ -257,8 +181,8 @@ primers.each do |primer|
     r2_seq = r2_passed_seq[seqtag]
     pid = r2_seq[0, pid_length]
     id[seqtag] = pid
-    bio_r2[seqtag] = r2_seq[reverse_starting_number..-2]
-    bio_r1[seqtag] = r1_seq[forward_starting_number..-2]
+    bio_r2[seqtag] = r2_seq[filter_r2[:reverse_starting_number]..-2]
+    bio_r1[seqtag] = r1_seq[filter_r1[:forward_starting_number]..-2]
   end
 
   # TCS cut-off
@@ -278,11 +202,10 @@ primers.each do |primer|
   end
 
   max_id = primer_id_dis.keys.sort[-5..-1].mean
-  consensus_cutoff = calculate_cut_off(max_id,error_rate)
+  consensus_cutoff = ViralSeq::TcsCore.calculate_cut_off(max_id,error_rate)
   log.puts Time.now.to_s + "\t" +  "Consensus cut-off is #{consensus_cutoff.to_s}"
   summary_json[:consensus_cutoff] = consensus_cutoff
   summary_json[:length_of_pid] = pid_length
-
   log.puts Time.now.to_s + "\t" +  "Creating consensus..."
 
   # Primer ID over the cut-off
@@ -355,6 +278,8 @@ primers.each do |primer|
     consensus_name = ">" + primer_id + "_" + seq_with_same_primer_id.size.to_s + "_" + libname + "_" + region
     r1_consensus = ViralSeq::SeqHash.array(r1_sub_seq).consensus(majority_cut_off)
     r2_consensus = ViralSeq::SeqHash.array(r2_sub_seq).consensus(majority_cut_off)
+
+    # hide the following two lines if allowing sequence to have ambiguities.
     next if r1_consensus =~ /[^ATCG]/
     next if r2_consensus =~ /[^ATCG]/
 
@@ -404,6 +329,7 @@ primers.each do |primer|
   f1.close
   f2.close
 
+  # Primer ID distribution in .json file
   out_pid_json = File.join(out_dir_set, 'primer_id.json')
   pid_json = {}
   pid_json[:primer_id_in_use] = Hash[*(primer_id_in_use.sort_by {|k, v| [-v,k]}.flatten)]
@@ -413,11 +339,14 @@ primers.each do |primer|
     f.puts JSON.pretty_generate(pid_json)
   end
 
+  # start end-join
   def end_join(dir, option, overlap)
     shp = ViralSeq::SeqHashPair.fa(dir)
     case option
     when 1
       joined_sh = shp.join1()
+    when 2
+      joined_sh = shp.join1(overlap)
     when 3
       joined_sh = shp.join2
     when 4
@@ -489,9 +418,10 @@ primers.each do |primer|
       joined_sh = joined_sh.hiv_seq_qc(ref_start, ref_end, indel, ref_genome)
 
       if export_raw
-        joined_sh_raw = joined_sh.hiv_seq_qc(ref_start, ref_end, indel, ref_genome)
+        joined_sh_raw = joined_sh_raw.hiv_seq_qc(ref_start, ref_end, indel, ref_genome)
       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]
@@ -499,10 +429,11 @@ primers.each do |primer|
       trim_end = primer[:trim_ref_end]
       trim_ref = primer[:trim_ref].to_sym
       joined_sh = joined_sh.trim(trim_start, trim_end, trim_ref)
-    end
-    joined_sh.write_nt_fa(File.join(out_dir_consensus, "combined.fasta"))
-    if export_raw
-      joined_sh_raw.write_nt_fa(File.join(out_dir_raw, "combined.fasta"))
+      joined_sh.write_nt_fa(File.join(out_dir_consensus, "combined.fasta"))
+      if export_raw
+        joined_sh_raw = joined_sh_raw.trim(trim_start, trim_end, trim_ref)
+        joined_sh_raw.write_nt_fa(File.join(out_dir_raw, "combined.raw.fasta"))
+      end
     end
   end
 

data/lib/viral_seq.rb

@@ -35,5 +35,8 @@ require_relative "viral_seq/seq_hash_pair"
 require_relative "viral_seq/sequence"
 require_relative "viral_seq/string"
 require_relative "viral_seq/version"
+require_relative "viral_seq/tcs_core"
+require_relative "viral_seq/tcs_json"
+
 
 require "muscle_bio"

data/lib/viral_seq/seq_hash.rb

@@ -9,7 +9,7 @@ module ViralSeq
   #     # align with MUSCLE
   #   filtered_seqhash = aligned_pr_seqhash.hiv_seq_qc(2253, 2549, false, :HXB2)
   #     # filter nt sequences with the reference coordinates
-  #   filtered_seqhash = aligned_pr_seqhash.stop_codon[1]
+  #   filtered_seqhash = aligned_pr_seqhash.stop_codon[:without_stop_codon]
   #     # return a new ViralSeq::SeqHash object without stop codons
   #   filtered_seqhash = filtered_seqhash.a3g[1]
   #     # further filter out sequences with A3G hypermutations
@@ -351,7 +351,7 @@ module ViralSeq
 
 
     # create one consensus sequence from @dna_hash with an optional majority cut-off for mixed bases.
-    # @param cutoff [Float] majority cut-off for calling consensus bases. defult at simple majority (0.5), position with 15% "A" and 85% "G" will be called as "G" with 20% cut-off and as "R" with 10% cut-off.
+    # @param cutoff [Float] majority cut-off for calling consensus bases. defult at (0.5), position with 15% "A" and 85% "G" will be called as "G" with 20% cut-off and as "R" with 10% cut-off. Using (0) will return use simply majority rule (no cutoff)
     # @return [String] consensus sequence
     # @example consensus sequence from an array of sequences.
     #   seq_array = %w{ ATTTTTTTTT
@@ -383,11 +383,18 @@ module ViralSeq
         base_count = all_base.count_freq
         max_base_list = []
 
-        base_count.each do |k,v|
-          if v/seq_size.to_f >= cutoff
-            max_base_list << k
+        if cutoff.zero?
+          max_count = base_count.values.max
+          max_base_hash = base_count.select {|_k,v| v == max_count}
+          max_base_list = max_base_hash.keys
+        else
+          base_count.each do |k,v|
+            if v/seq_size.to_f >= cutoff
+              max_base_list << k
+            end
           end
         end
+
         consensus_seq += call_consensus_base(max_base_list)
       end
       return consensus_seq
@@ -398,7 +405,7 @@ module ViralSeq
     #   # control pattern: G[YN|RC] -> A[YN|RC]
     #   # use the sample consensus to determine potential a3g sites
     #   # Two criteria to identify hypermutation
-    #   # 1. Fisher's exact test on the frequencies of G to A mutation at A3G positons vs. non-A3G positions
+    #   # 1. Fisher's exact test on the frequencies of G to A mutation at A3G positions vs. non-A3G positions
     #   # 2. Poisson distribution of G to A mutations at A3G positions, outliers sequences
     #   # note:  criteria 2 only applies on a sequence file containing more than 20 sequences,
     #   #        b/c Poisson model does not do well on small sample size.

data/lib/viral_seq/seq_hash_pair.rb

@@ -80,6 +80,12 @@ module ViralSeq
       alias_method :fa, :new_from_fasta
     end
 
+    # the size of nt sequence hash of the SeqHashPair object
+    # @return [Integer] size of nt sequence hash of the SeqHash object
+    def size
+      self.dna_hash.size
+    end
+
     # Pair-end join function for KNOWN overlap size.
     # @param overlap [Integer] how many bases are overlapped. `0` means no overlap, R1 and R2 will be simply put together.
     # @param diff [Integer, Float] the maximum mismatch rate allowed for the overlapping region. default at 0.0, i.e. no mis-match allowed.

data/lib/viral_seq/tcs_core.rb

@@ -0,0 +1,303 @@
+module ViralSeq
+
+  # Core functions for `tcs` pipeline
+
+  class TcsCore
+    class << self
+
+      # methods to calculate TCS consensus cut-off based on the maximum numbers of PIDs and platform error rate.
+
+      def calculate_cut_off(m, error_rate = 0.02)
+        n = 0
+        case error_rate
+        when 0.005...0.015
+          if m <= 10
+            n = 2
+          else
+            n = 1.09*10**-26*m**6 + 7.82*10**-22*m**5 - 1.93*10**-16*m**4 + 1.01*10**-11*m**3 - 2.31*10**-7*m**2 + 0.00645*m + 2.872
+          end
+
+        when 0...0.005
+          if m <= 10
+            n = 2
+          else
+            n = -9.59*10**-27*m**6 + 3.27*10**-21*m**5 - 3.05*10**-16*m**4 + 1.2*10**-11*m**3 - 2.19*10**-7*m**2 + 0.004044*m + 2.273
+          end
+
+        else
+          if m <= 10
+            n = 2
+          elsif m <= 8500
+            n = -1.24*10**-21*m**6 + 3.53*10**-17*m**5 - 3.90*10**-13*m**4 + 2.12*10**-9*m**3 - 6.06*10**-6*m**2 + 1.80*10**-2*m + 3.15
+          else
+            n = 0.0079 * m + 9.4869
+          end
+        end
+
+        n = n.round
+        n = 2 if n < 3
+        return n
+      end
+
+      # identify which file in the directory is R1 file, and which is R2 file based on file names
+      # input as directory (Dir object or a string of path)
+      # by default, .gz files will be unzipped.
+      # return as an hash of {r1_file: file1, r1_file: file2}
+      def r1r2(directory, unzip = true)
+        files = []
+        Dir.chdir(directory) { files = Dir.glob "*" }
+        r1_file = ""
+        r2_file = ""
+        files.each do |f|
+          tag = parser_file_name(f)[:tag]
+
+          if tag.include? "R1"
+            unzip ? r1_file = unzip_r(directory, f) : r1_file = File.join(directory, f)
+          elsif tag.include? "R2"
+            unzip ? r2_file = unzip_r(directory, f) : r2_file = File.join(directory, f)
+          end
+        end
+        return { r1_file: r1_file, r2_file: r2_file }
+      end # end of ViralSeq:TcsCore.r1r2
+
+      # sort directories containing mulitple r1 and r2 files.
+      # use the library name (first string before "_") to seperate libraries
+      # out_dir is the Dir object or string of the output directory, by default named as directory + "_sorted"
+      # return a hash as { with_both_r1_r2: [lib1, lib2, ...], missing_r1: [lib1, lib2, ...], missing_r2: [lib1, lib2, ...], error: [lib1, lib2, ...]}
+
+      def sort_by_lib(directory, out_dir = directory + "_sorted")
+        Dir.mkdir(out_dir) unless File.directory?(out_dir)
+        files = []
+        Dir.chdir(directory) {files = Dir.glob("*")}
+
+        files.each do |file|
+          path = File.join(directory,file)
+          index = file.split("_")[0]
+          index_dir = File.join(out_dir, index)
+          Dir.mkdir(index_dir) unless File.directory?(index_dir)
+          File.rename(path, File.join(index_dir, file))
+        end
+
+        return_obj = { with_both_r1_r2: [],
+                       missing_r1: [],
+                       missing_r2: [],
+                       error: []
+                      }
+
+        libs = []
+        Dir.chdir(out_dir) { libs = Dir.glob('*') }
+        libs.each do |lib|
+          file_check = ViralSeq::TcsCore.r1r2(File.join(out_dir, lib))
+          if !file_check[:r1_file].empty? and !file_check[:r2_file].empty?
+            return_obj[:with_both_r1_r2] << lib
+          elsif file_check[:r1_file].empty? and !file_check[:r2_file].empty?
+            return_obj[:missing_r1] << lib
+          elsif file_check[:r2_file].empty? and !file_check[:r1_file].empty?
+            return_obj[:missing_r2] << lib
+          else
+            return_obj[:error] << lib
+          end
+        end
+        return return_obj
+      end
+
+      # sort array of file names to determine if there is potential errors
+      # input name_array array of file names
+      # output hash { }
+
+      def validate_file_name(name_array)
+        errors = { file_type_error: [] ,
+                   missing_r1_file: [] ,
+                   missing_r2_file: [] ,
+                   extra_r1_r2_file: [],
+                   no_region_tag: [] ,
+                   multiple_region_tag: []}
+
+        passed_libs = {}
+
+        name_with_r1_r2 = []
+
+        name_array.each do |name|
+          tag = parser_file_name(name)[:tag]
+          if name !~ /\.fastq\Z|\.fastq\.gz\Z/
+            errors[:file_type_error] << name
+          elsif tag.count("R1") == 0 and tag.count("R2") == 0
+            errors[:no_region_tag] << name
+          elsif tag.count("R1") > 0 and tag.count("R2") > 0
+            errors[:multiple_region_tag] << name
+          elsif tag.count("R1") > 1 or tag.count("R2") > 1
+            errors[:multiple_region_tag] << name
+          else
+            name_with_r1_r2 << name
+          end
+        end
+
+        libs = {}
+
+        name_with_r1_r2.map do |name|
+          libname = parser_file_name(name)[:libname]
+          libs[libname] ||= []
+          libs[libname] << name
+        end
+
+        libs.each do |libname, files|
+          count_r1_file = 0
+          count_r2_file = 0
+          files.each do |name|
+            tag = parser_file_name(name)[:tag]
+            if tag.include? "R1"
+              count_r1_file += 1
+            elsif tag.include? "R2"
+              count_r2_file += 1
+            end
+          end
+
+          if count_r1_file > 1 or count_r2_file > 1
+            errors[:extra_r1_r2_file] += files
+          elsif count_r1_file.zero?
+            errors[:missing_r1_file] += files
+          elsif count_r2_file.zero?
+            errors[:missing_r2_file] += files
+          else
+            passed_libs[libname] = files
+          end
+        end
+
+        passed_names = []
+
+        passed_libs.values.each { |names| passed_names += names}
+
+        if passed_names.size < name_array.size
+          pass = false
+        else
+          pass = true
+        end
+
+        return { errors: errors, all_pass: pass, passed_names: passed_names, passed_libs: passed_libs }
+      end
+
+      # filter r1 raw sequences for non-specific primers.
+      # input r1_sh, SeqHash obj.
+      # return filtered Hash of sequence name and seq pair, in the object { r1_filtered_seq: r1_filtered_seq_pair }
+
+      def filter_r1(r1_sh, forward_primer)
+        if forward_primer.match(/(N+)(\w+)$/)
+          forward_n = $1.size
+          forward_bio_primer = $2
+        else
+          forward_n = 0
+          forward_bio_primer = forward_primer
+        end
+        forward_bio_primer_size = forward_bio_primer.size
+        forward_starting_number = forward_n + forward_bio_primer_size
+        forward_primer_ref = forward_bio_primer.nt_parser
+
+        r1_passed_seq = {}
+        r1_raw = r1_sh.dna_hash
+
+        proc_filter = proc do |name|
+          seq = r1_raw[name]
+          next unless general_filter seq
+          primer_region_seq = seq[forward_n, forward_bio_primer_size]
+          if primer_region_seq =~ forward_primer_ref
+            new_name = remove_tag name
+            r1_passed_seq[new_name] = seq
+          end
+        end
+
+        r1_raw.keys.map do |name|
+          proc_filter.call name
+        end
+
+        return { r1_passed_seq: r1_passed_seq, forward_starting_number: forward_starting_number }
+      end # end of filter_r1
+
+      # filter r2 raw sequences for non-specific primers.
+      # input r2_sh, SeqHash obj.
+      # return filtered Hash of sequence name and seq pair, as well as the length of PID.
+      def filter_r2(r2_sh, cdna_primer)
+        r2_raw = r2_sh.dna_hash
+        cdna_primer.match(/(N+)(\w+)$/)
+        pid_length = $1.size
+        cdna_bio_primer = $2
+        cdna_bio_primer_size = cdna_bio_primer.size
+        reverse_starting_number = pid_length + cdna_bio_primer_size
+        cdna_primer_ref = cdna_bio_primer.nt_parser
+        r2_passed_seq = {}
+        proc_filter = proc do |name|
+          seq = r2_raw[name]
+          next unless general_filter seq
+          primer_region_seq = seq[pid_length, cdna_bio_primer_size]
+          if primer_region_seq =~ cdna_primer_ref
+            new_name = remove_tag name
+            r2_passed_seq[new_name] = seq
+          end
+        end
+
+        r2_raw.keys.map do |name|
+          proc_filter.call name
+        end
+
+        return { r2_passed_seq: r2_passed_seq, pid_length: pid_length, reverse_starting_number: reverse_starting_number }
+      end # end of filter_r2
+
+
+
+      # puts error message in the log file handler, and abort with the same infor
+
+      def log_and_abort(log, infor)
+        log.puts Time.now.to_s + "\t" + infor
+        log.close
+        abort infor.red.bold
+      end
+
+      private
+
+      def unzip_r(indir, f)
+        r_file = File.join(indir, f)
+        if f =~ /.gz/
+          `gzip -d #{r_file}`
+          new_f = f.sub ".gz", ""
+          r_file = File.join(indir, new_f)
+        end
+        return r_file
+      end
+
+      def parser_file_name(file_name)
+        t = file_name.split(".")[0].split("_")
+        if t.size == 1
+          libname = "lib"
+          tag = [ t[0].upcase ]
+        else
+          libname = t[0]
+          tag = t[1..-1].map(&:upcase)
+        end
+        return {libname: libname, tag: tag}
+      end
+
+      def general_filter(seq)
+        if seq[1..-2] =~ /N/ # sequences with ambiguities except the 1st and last position removed
+          return false
+        elsif seq =~ /A{11}/ # a string of poly-A indicates adaptor sequence
+          return false
+        elsif seq =~ /T{11}/ # a string of poly-T indicates adaptor sequence
+          return false
+        else
+          return true
+        end
+      end
+
+      # remove region info tags from the raw MiSeq sequences.
+      def remove_tag(seq_name)
+        if seq_name =~ /\s/
+          new_tag = $`
+        else
+          new_tag = seq_name[0..-3]
+        end
+      end
+
+    end # end of class << self
+
+  end # end of TcsCore module
+
+end # end of main module

data/lib/viral_seq/tcs_json.rb

@@ -0,0 +1,178 @@
+module ViralSeq
+  class TcsJson
+    class << self
+
+      def generate
+        puts '-'*58
+        puts '| JSON Parameter Generator for ' + "TCS #{ViralSeq::TCS_VERSION}".red.bold + " by " + "Shuntai Zhou".blue.bold + ' |'
+        puts '-'*58 + "\n"
+
+        param = {}
+
+        puts 'Enter the path to the directory that contains the MiSeq pair-end R1 and R2 .fastq or .fastq.gz file'
+        print '> '
+        param[:raw_sequence_dir] = gets.chomp.rstrip
+
+        puts 'Enter the estimated platform error rate (for TCS cut-off calculation), default as ' + '0.02'.red.bold
+        print '> '
+        input_error = gets.chomp.rstrip.to_f
+        if input_error == 0.0
+          param[:platform_error_rate] = 0.02
+        else
+          param[:platform_error_rate] = input_error
+        end
+
+        param[:primer_pairs] = []
+
+        loop do
+          data = {}
+          puts "Enter the name for the sequenced region: "
+          print '> '
+          data[:region] = gets.chomp.rstrip
+
+          puts "Enter the #{"cDNA".red.bold} primer sequence: "
+          print '> '
+          data[:cdna] = gets.chomp.rstrip
+
+          puts "Enter the #{"forward".blue.bold} primer sequence: "
+          print '> '
+          data[:forward] = gets.chomp.rstrip
+
+          puts "Enter supermajority cut-off (0.5 - 1.0). Default Simple Majority"
+          print '> '
+          mj = gets.chomp.rstrip.to_f
+          if (0.5..1.0).include?(mj)
+            data[:majority] = mj
+          else
+            data[:majority] = 0
+          end
+
+          print "Need end-join? Y/N \n> "
+          ej = gets.chomp.rstrip
+          if ej =~ /y|yes/i
+            data[:end_join] = true
+
+            print "End-join option? Choose from (1-4):\n
+            1: simple join, no overlap
+            2: known overlap \n
+            3: unknow overlap, use sample consensus to determine overlap, all sequence pairs have same overlap\n
+            4: unknow overlap, determine overlap by individual sequence pairs, sequence pairs can have different overlap\n
+            > "
+            ej_option = gets.chomp.rstrip
+            while ![1,2,3,4].include?(ej_option.to_i)
+              puts "Entered end-join option #{ej_option.red.bold} not valid (choose 1-4), try again"
+              ej_option = gets.chomp.rstrip.to_i
+            end
+            case ej_option.to_i
+            when 1
+              data[:end_join_option] = 1
+              data[:overlap] = 0
+            when 2
+              data[:end_join_option] = 1
+              print "overlap bases: \n> "
+              ol = gets.chomp.rstrip.to_i
+              data[:overlap] = ol
+            when 3
+              data[:end_join_option] = 3
+            when 4
+              data[:end_join_option] = 4
+            end
+
+            print "Need QC for TCS? (support for HIV-1 and SIV)? Y/N \n> "
+            qc = gets.chomp.rstrip
+            if qc =~ /y|yes/i
+              data[:TCS_QC] = true
+
+              data[:ref_genome] = get_ref
+
+              print "reference 5'end ref position or posiiton 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> "
+              data[:ref_end] = gets.chomp.rstrip.to_i
+
+              print "allow indels? (default as yes) Y/N \n> "
+              indel = gets.chomp.rstrip
+              if indel =~ /n|no/i
+                data[:indel] = false
+              else
+                data[:indel] = true
+              end
+            else
+              data[:TCS_QC] = false
+            end
+
+            print "Need trimming to a reference genome? Y/N \n> "
+            trim_option = gets.chomp.rstrip
+            if trim_option =~ /y|yes/i
+              data[:trim] = true
+              data[:trim_ref] = get_ref
+
+              print "reference 5'end ref position \n> "
+              data[:trim_ref_start] = gets.chomp.rstrip.to_i
+
+              print "reference 3'end ref position \n> "
+              data[:trim_ref_end] = gets.chomp.rstrip.to_i
+
+            else
+              data[:trim] = false
+            end
+
+          else
+            data[:end_join] = false
+          end
+
+          param[:primer_pairs] << data
+          print "Do you wish to conintue? Y/N \n> "
+          continue_sig = gets.chomp.rstrip
+          break unless continue_sig =~ /y|yes/i
+
+        end
+
+        puts "\nYour JSON string is:"
+        puts JSON.pretty_generate(param)
+
+        print "\nDo you wish to save it as a file? Y/N \n> "
+        save_option = gets.chomp.rstrip
+
+        if save_option =~ /y|yes/i
+          print "Path to save JSON file:\n> "
+          path = gets.chomp.rstrip
+          File.open(path, 'w') {|f| f.puts JSON.pretty_generate(param)}
+        end
+
+        print "\nDo you wish to execute tcs pipeline with the input params now? Y/N \n> "
+
+        rsp = gets.chomp.rstrip
+        if rsp =~ /y/i
+          return param
+        else
+          abort "Params json file generated. You can execute tcs pipeline using `tcs -p [params.json]`"
+        end
+
+      end
+
+      private
+      def get_ref
+        puts "Choose reference genome (1-3):"
+        puts "1. HIV-1 HXB2".red.bold
+        puts "2. HIV-1 NL4-3".blue.bold
+        puts "3. SIV MAC239".magenta.bold
+        print "> "
+        ref_option = gets.chomp.rstrip
+        while ![1,2,3].include?(ref_option.to_i)
+          print "Entered end-join option #{ref_option.to_s.red.bold} not valid (choose 1-3), try again\n> "
+          ref_option = gets.chomp.rstrip.to_i
+        end
+        ref = case ref_option.to_i
+              when 1
+                :HXB2
+              when 2
+                :NL43
+              when 3
+                :MAC239
+              end
+      end
+    end
+  end # end TcsJson
+end # end main module

data/lib/viral_seq/version.rb

@@ -2,6 +2,6 @@
 # version info and histroy
 
 module ViralSeq
-  VERSION = "1.0.9"
-  TCS_VERSION = "2.0.1"
+  VERSION = "1.0.10"
+  TCS_VERSION = "2.1.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: viral_seq
 version: !ruby/object:Gem::Version
-  version: 1.0.9
+  version: 1.0.10
 platform: ruby
 authors:
 - Shuntai Zhou
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-07-19 00:00:00.000000000 Z
+date: 2020-11-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -90,7 +90,6 @@ email:
 executables:
 - locator
 - tcs
-- tcs_json_generator
 extensions: []
 extra_rdoc_files: []
 files:
@@ -105,7 +104,6 @@ files:
 - Rakefile
 - bin/locator
 - bin/tcs
-- bin/tcs_json_generator
 - lib/viral_seq.rb
 - lib/viral_seq/constant.rb
 - lib/viral_seq/enumerable.rb
@@ -120,6 +118,8 @@ files:
 - lib/viral_seq/seq_hash_pair.rb
 - lib/viral_seq/sequence.rb
 - lib/viral_seq/string.rb
+- lib/viral_seq/tcs_core.rb
+- lib/viral_seq/tcs_json.rb
 - lib/viral_seq/version.rb
 - viral_seq.gemspec
 homepage: https://github.com/ViralSeq/viral_seq

data/bin/tcs_json_generator

@@ -1,166 +0,0 @@
-#!/usr/bin/env ruby
-
-# TCS pipeline JSON params generator.
-
-require 'viral_seq'
-require 'colorize'
-require 'json'
-
-def get_ref
-  puts "Choose reference genome (1-3):"
-  puts "1. HIV-1 HXB2".red.bold
-  puts "2. HIV-1 NL4-3".blue.bold
-  puts "3. SIV MAC239".magenta.bold
-  print "> "
-  ref_option = gets.chomp.rstrip
-  while ![1,2,3].include?(ref_option.to_i)
-    print "Entered end-join option #{ref_option.to_s.red.bold} not valid (choose 1-3), try again\n> "
-    ref_option = gets.chomp.rstrip.to_i
-  end
-  ref = case ref_option.to_i
-        when 1
-          :HXB2
-        when 2
-          :NL43
-        when 3
-          :MAC239
-        end
-end
-
-puts "\n" + '-'*58
-puts '| JSON Parameter Generator for ' + "TCS #{ViralSeq::TCS_VERSION}".red.bold + " by " + "Shuntai Zhou".blue.bold + ' |'
-puts '-'*58 + "\n"
-
-param = {}
-
-puts 'Enter the path to the directory that contains the MiSeq pair-end R1 and R2 .fastq or .fastq.gz file'
-print '> '
-param[:raw_sequence_dir] = gets.chomp.rstrip
-
-puts 'Enter the estimated platform error rate (for TCS cut-off calculation), default as ' + '0.02'.red.bold
-print '> '
-input_error = gets.chomp.rstrip.to_f
-if input_error == 0.0
-  param[:platform_error_rate] = 0.02
-else
-  param[:platform_error_rate] = input_error
-end
-
-param[:primer_pairs] = []
-
-loop do
-  data = {}
-  puts "Enter the name for the sequenced region: "
-  print '> '
-  data[:region] = gets.chomp.rstrip
-
-  puts "Enter the #{"cDNA".red.bold} primer sequence: "
-  print '> '
-  data[:cdna] = gets.chomp.rstrip
-
-  puts "Enter the #{"forward".blue.bold} primer sequence: "
-  print '> '
-  data[:forward] = gets.chomp.rstrip
-
-  puts "Enter supermajority cut-off (0.5 - 0.9). Default: " + "0.5".blue.bold + " (simple majority)"
-  print '> '
-  mj = gets.chomp.rstrip.to_f
-  if (0.5..0.9).include?(mj)
-    data[:majority] = mj
-  else
-    data[:majority] = 0.5
-  end
-
-  print "Need end-join? Y/N \n> "
-  ej = gets.chomp.rstrip
-  if ej =~ /y|yes/i
-    data[:end_join] = true
-
-    print "End-join option? Choose from (1-4):\n
-    1: simple join, no overlap
-    2: known overlap \n
-    3: unknow overlap, use sample consensus to determine overlap, all sequence pairs have same overlap\n
-    4: unknow overlap, determine overlap by individual sequence pairs, sequence pairs can have different overlap\n
-    > "
-    ej_option = gets.chomp.rstrip
-    while ![1,2,3,4].include?(ej_option.to_i)
-      puts "Entered end-join option #{ej_option.red.bold} not valid (choose 1-4), try again"
-      ej_option = gets.chomp.rstrip.to_i
-    end
-    case ej_option.to_i
-    when 1
-      data[:end_join_option] = 1
-      data[:overlap] = 0
-    when 2
-      data[:end_join_option] = 1
-      print "overlap bases: \n> "
-      ol = gets.chomp.rstrip.to_i
-      data[:overlap] = ol
-    when 3
-      data[:end_join_option] = 3
-    when 4
-      data[:end_join_option] = 4
-    end
-
-    print "Need QC for TCS? (support for HIV-1 and SIV)? Y/N \n> "
-    qc = gets.chomp.rstrip
-    if qc =~ /y|yes/i
-      data[:TCS_QC] = true
-
-      data[:ref_genome] = get_ref
-
-      print "reference 5'end ref position or posiiton 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> "
-      data[:ref_end] = gets.chomp.rstrip.to_i
-
-      print "allow indels? (default as yes) Y/N \n> "
-      indel = gets.chomp.rstrip
-      if indel =~ /n|no/i
-        data[:indel] = false
-      else
-        data[:indel] = true
-      end
-    else
-      data[:TCS_QC] = false
-    end
-
-    print "Need trimming to a reference genome? Y/N \n> "
-    trim_option = gets.chomp.rstrip
-    if trim_option =~ /y|yes/i
-      data[:trim] = true
-      data[:trim_ref] = get_ref
-
-      print "reference 5'end ref position \n> "
-      data[:trim_ref_start] = gets.chomp.rstrip.to_i
-
-      print "reference 3'end ref position \n> "
-      data[:trim_ref_end] = gets.chomp.rstrip.to_i
-
-    else
-      data[:trim] = false
-    end
-
-  else
-    data[:end_join] = false
-  end
-
-  param[:primer_pairs] << data
-  print "Do you wish to conintue? Y/N \n> "
-  continue_sig = gets.chomp.rstrip
-  break unless continue_sig =~ /y|yes/i
-
-end
-
-puts "\nYour JSON string is:"
-puts JSON.pretty_generate(param)
-
-print "\nDo you wish to save it as a file? Y/N \n> "
-save_option = gets.chomp.rstrip
-
-if save_option =~ /y|yes/i
-  print "Path to save JSON file:\n> "
-  path = gets.chomp.rstrip
-  File.open(path, 'w') {|f| f.puts JSON.pretty_generate(param)}
-end