viral_seq 1.8.1.1 → 1.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 11381ab74d67a54b5d922e8f1a7085866fe5349f4124a971b9dc64709fa763f1
-  data.tar.gz: dd578b649b9857cf1c7ff8a23fff62db51f665ef23c74c8000a2b4d7f4500f9e
+  metadata.gz: 5817b0c1bb2887e02c101dd1032ad1a5523d7390caa00c785050ad05e4bb77e7
+  data.tar.gz: 0e9e8c40625122a932f7e06062b4e129712d433dbf11dcd0b4b51d51ce80b514
 SHA512:
-  metadata.gz: add86e088cd1ef50c0ce546eb4f755b7b5725a072ddf1119982ec0cccd20246bc25aab077c51673032e442f098e15f4c40d9a526ff67af8a5514aab580f255a8
-  data.tar.gz: 4b6cdbe344c2835c3f07c10b86f33613e0d5cdba5a9405da50d9d7f208796da6cdee709993b465f72e2a14a49667ea5ddfed84ddaf8ff21bda4a09448ebdde1b
+  metadata.gz: 6abfc477dea09519649614f8300d17be470a2511f79d7ed33b794ba96ab721584a488b71c01040e6c55e92e9e22c5282afedbdf02b6889acfdb7fb6fcddecb0d
+  data.tar.gz: 861e6ff9b55be29357b677c270ea7c1cc20ff49960cd8f3429ceb323751c3ddd6a7c9a773a9c383da5abb5e8f99a5172cd74cb2a70d54a674eba2d1406d904ea

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    viral_seq (1.8.0.pre)
+    viral_seq (1.9.0)
       colorize (~> 0.1)
       combine_pdf (~> 1.0, >= 1.0.0)
       muscle_bio (= 0.4)

data/README.md

@@ -187,6 +187,12 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
 
 ## Updates
 
+### Version-1.9.0-11132024
+
+  1. `ViralSeq::TcsCore::validate_file_name` will not report errors when non-sequence data in the folder, instead these files will be ignored.
+  2. Rewrote the APIs for DRM analysis for HIV. Now uses version config files for the sequencing information and DRM list configure files for DRM interpretation. Two configure files are at located in `/lib/viral_seq/util/`
+  3. `tcs_sdrm` will take a second argument for DRM config versions. Currently supports `["v1", "v2", "v3"]`. Refer to the documentations of the APIs for the details.
+  4. Next update will use secondary command `tcs sdrm` to replace `tcs_sdrm`, and `tcs log` to replace `tcs_log`.
 
 ### Version-1.8.1-06042024
 

data/bin/tcs

@@ -299,11 +299,17 @@ begin
     distinct_to_raw = (primer_id_count.size/primer_id_list.size.to_f).round(3)
     summary_json[:distinct_to_raw] = distinct_to_raw
 
-    if primer_id_dis.keys.size < 5
+    if primer_id_count.keys.size < 5
       log.puts Time.now.to_s + "\t" +  "Less than 5 Primer IDs detected. Region #{region} aborted."
       next
     end
 
+    if primer_id_dis.keys.size < 5
+      log.puts Time.now.to_s + "\t" +  "Maximum frequency of Primer ID less than 5. Primer ID overloaded. Region #{region} aborted."
+      next
+    end
+
+
     max_id = primer_id_dis.keys.sort[-5..-1].mean
     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}"

data/bin/tcs_sdrm

@@ -21,7 +21,6 @@
 # output data in a new dir as 'libs_dir_SDRM'
 
 require 'viral_seq'
-require 'json'
 require 'csv'
 require 'fileutils'
 require 'prawn'
@@ -32,6 +31,8 @@ unless ARGV[0] && File.directory?(ARGV[0])
   abort "No sequence data provided. `tcs_sdrm` pipeline aborted. "
 end
 
+dr_version = ARGV[1] ? ARGV[1] : "V1"
+
 r_version = ViralSeq::R.check_R
 ViralSeq::R.check_R_packages
 
@@ -49,20 +50,22 @@ log << { time: Time.now }
 log << { viral_seq_version: ViralSeq::VERSION }
 log << { tcs_version: ViralSeq::TCS_VERSION }
 log << { R_version: r_version}
-sdrm_list = {}
-sdrm_list[:nrti] = ViralSeq::DRMs.sdrm_json(:nrti)
-sdrm_list[:nnrti] = ViralSeq::DRMs.sdrm_json(:nnrti)
-sdrm_list[:hiv_pr] = ViralSeq::DRMs.sdrm_json(:hiv_pr)
-sdrm_list[:hiv_in] = ViralSeq::DRMs.sdrm_json(:hiv_in)
+log << { DR_version: dr_version}
+
+version_config = ViralSeq::DrmVersion.config_version(dr_version)
+
+sdrm_list = version_config.pull_drm_json
 log << { sdrm_list: sdrm_list }
 
+regions = version_config.seq_drm_correlation.keys
+
 # input dir
 indir = ARGV[0]
 libs = Dir[indir + "/*"]
 log << { processed_libs: libs }
 
 #output dir
-outdir = indir + "_SDRM"
+outdir = indir + "_DRM_analysis"
 Dir.mkdir(outdir) unless File.directory?(outdir)
 
 libs.each do |lib|
@@ -85,7 +88,7 @@ libs.each do |lib|
 
   point_mutation_file = File.join(out_lib_dir, (lib_name + "_substitution.csv"))
   point_mutation_out = File.open(point_mutation_file, "w")
-  point_mutation_out.puts "region,TCS,AA position,wild type,mutation," +
+  point_mutation_out.puts "DRM_Class,TCS,AA position,wild type,mutation," +
                           "number,frequency,95% CI low,95% CI high,fdr,notes"
 
   linkage_file = File.join(out_lib_dir, (lib_name + "_linkage.csv"))
@@ -114,118 +117,65 @@ libs.each do |lib|
   aa_report_list = []
   summary_hash = {}
 
+  process_config = {}
+
   sub_seq_files.each do |sub_seq|
     seq_basename = File.basename(sub_seq)
-    seqs = ViralSeq::SeqHash.fa(sub_seq)
-    next if seqs.size < 3
+
     if seq_basename =~ /V1V3/i
-      summary_hash[:V1V3] = "#{seqs.size.to_s},NA,NA,NA,NA"
-      FileUtils.cp(sub_seq, filtered_seq_dir)
-    elsif seq_basename =~ /PR/i
-      a3g_check = seqs.a3g
-      a3g_seqs = a3g_check[:a3g_seq]
-      a3g_filtered_seqs = a3g_check[:filtered_seq]
-      stop_codon_check = a3g_filtered_seqs.stop_codon
-      stop_codon_seqs = stop_codon_check[:with_stop_codon]
-      filtered_seqs = stop_codon_check[:without_stop_codon]
-      poisson_minority_cutoff = filtered_seqs.pm
-      fdr_hash = filtered_seqs.fdr
-      summary_hash[:PR] = [
-                            seqs.size.to_s,
-                            a3g_seqs.size.to_s,
-                            stop_codon_seqs.size.to_s,
-                            filtered_seqs.size.to_s,
-                            poisson_minority_cutoff.to_s
-                          ].join(',')
-      next if filtered_seqs.size < 3
-      filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
-
-      sdrm = filtered_seqs.sdrm_hiv_pr(poisson_minority_cutoff, fdr_hash)
-      point_mutation_list += sdrm[0]
-      linkage_list += sdrm[1]
-      aa_report_list += sdrm[2]
-
-    elsif seq_basename =~/IN/i
-      a3g_check = seqs.a3g
-      a3g_seqs = a3g_check[:a3g_seq]
-      a3g_filtered_seqs = a3g_check[:filtered_seq]
-      stop_codon_check = a3g_filtered_seqs.stop_codon(2)
-      stop_codon_seqs = stop_codon_check[:with_stop_codon]
-      filtered_seqs = stop_codon_check[:without_stop_codon]
-      poisson_minority_cutoff = filtered_seqs.pm
-      fdr_hash = filtered_seqs.fdr
-      summary_hash[:IN] = [
-                            seqs.size.to_s,
-                            a3g_seqs.size.to_s,
-                            stop_codon_seqs.size.to_s,
-                            filtered_seqs.size.to_s,
-                            poisson_minority_cutoff.to_s
-                          ].join(',')
-      next if filtered_seqs.size < 3
-      filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
-
-      sdrm = filtered_seqs.sdrm_hiv_in(poisson_minority_cutoff, fdr_hash)
-      point_mutation_list += sdrm[0]
-      linkage_list += sdrm[1]
-      aa_report_list += sdrm[2]
-
-    elsif seq_basename =~/P17/i
-      a3g_check = seqs.a3g
-      a3g_seqs = a3g_check[:a3g_seq]
-      a3g_filtered_seqs = a3g_check[:filtered_seq]
-      stop_codon_check = a3g_filtered_seqs.stop_codon(2)
-      stop_codon_seqs = stop_codon_check[:with_stop_codon]
-      filtered_seqs = stop_codon_check[:without_stop_codon]
-      poisson_minority_cutoff = filtered_seqs.pm
-      fdr_hash = filtered_seqs.fdr
-      summary_hash[:P17] = [
-                            seqs.size.to_s,
-                            a3g_seqs.size.to_s,
-                            stop_codon_seqs.size.to_s,
-                            filtered_seqs.size.to_s,
-                            poisson_minority_cutoff.to_s
-                          ].join(',')
-      next if filtered_seqs.size < 3
-      filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
-
-    elsif seq_basename =~/RT/i
-      rt_seq1 = {}
-      rt_seq2 = {}
-      seqs.dna_hash.each do |k,v|
-        rt_seq1[k] = v[0,267]
-        rt_seq2[k] = v[267..-1]
+      seqs = ViralSeq::SeqHash.fa(sub_seq)
+      if seqs.size > 3
+        summary_hash["V1V3"] = "#{seqs.size.to_s},NA,NA,NA,NA"
+        FileUtils.cp(sub_seq, filtered_seq_dir)
+      end
+    end
+
+    seq_basename.gsub!(/\_P17/i, "_CA")
+    regions.each do |region|
+      if seq_basename =~ /\_#{region}/i
+        process_config[region] = sub_seq
       end
-      rt1 = ViralSeq::SeqHash.new(rt_seq1)
-      rt2 = ViralSeq::SeqHash.new(rt_seq2)
-      rt1_a3g = rt1.a3g
-      rt2_a3g = rt2.a3g
-      hypermut_seq_rt1 = rt1_a3g[:a3g_seq]
-      hypermut_seq_rt2 = rt2_a3g[:a3g_seq]
-      rt1_stop_codon = rt1.stop_codon(1)[:with_stop_codon]
-      rt2_stop_codon = rt2.stop_codon(2)[:with_stop_codon]
-      hypermut_seq_keys = (hypermut_seq_rt1.dna_hash.keys | hypermut_seq_rt2.dna_hash.keys)
-      stop_codon_seq_keys = (rt1_stop_codon.dna_hash.keys | rt2_stop_codon.dna_hash.keys)
-      reject_keys = (hypermut_seq_keys | stop_codon_seq_keys)
-      filtered_seqs = ViralSeq::SeqHash.new(seqs.dna_hash.reject {|k,v| reject_keys.include?(k) })
-      poisson_minority_cutoff = filtered_seqs.pm
-      fdr_hash = filtered_seqs.fdr
-      summary_hash[:RT] = [
-                            seqs.size.to_s,
-                            hypermut_seq_keys.size.to_s,
-                            stop_codon_seq_keys.size.to_s,
-                            filtered_seqs.size.to_s,
-                            poisson_minority_cutoff.to_s
-                          ].join(',')
-      next if filtered_seqs.size < 3
-      filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
-
-      sdrm = filtered_seqs.sdrm_hiv_rt(poisson_minority_cutoff, fdr_hash)
-      point_mutation_list += sdrm[0]
-      linkage_list += sdrm[1]
-      aa_report_list += sdrm[2]
     end
   end
 
+  process_config.each do |region_name, path_to_file|
+    seq_basename = File.basename(path_to_file)
+    seq_basename.gsub!(/\_P17/i, "_CA")
+    region = version_config.query_region(region_name.to_s)
+
+    puts "prcessing region: " + region.region
+
+    sh = ViralSeq::SeqHash.fa(path_to_file)
+
+    if sh.size < 3
+      puts "Less than 3 TCS for #{region.region}. Skipped."
+      next
+    end
+
+    run_filtering = sh.filter_for_drm(region)
+
+    summary_hash[region.region] = [
+      sh.size,
+      run_filtering[:a3g_seq].size,
+      run_filtering[:stop_codon_seq].size,
+      run_filtering[:filtered_seq].size,
+      run_filtering[:filtered_seq].pm
+    ].join(',')
+
+    if run_filtering[:filtered_seq].size < 1
+      puts "Warning: NO TCS passed the filter for #{region.region}. DRM analysis skipped."
+      next
+    end
+
+    run_filtering[:filtered_seq].write_nt_fa(File.join(filtered_seq_dir,seq_basename))
+
+    drm_results = run_filtering[:filtered_seq].drm(region)
+    point_mutation_list += drm_results[0]
+    linkage_list += drm_results[1]
+    aa_report_list += drm_results[2]
+
+  end
+
   point_mutation_list.each do |record|
     point_mutation_out.puts record.join(",")
   end
@@ -262,12 +212,13 @@ libs.each do |lib|
       pi_csv.each do |line|
         line.chomp!
         data = line.split(",")
-        tag = data[0].split("_")[-1].gsub(/\W/,"").to_sym
+        tag = data[0].split("_")[-1].gsub(/\W/,"")
         summary_hash[tag] += "," + data[1].to_f.round(4).to_s + "," + data[2].to_f.round(4).to_s
       end
-      [:PR, :RT, :IN, :V1V3, :P17].each do |regions|
-        next unless summary_hash[regions]
-        seq_summary_out.puts regions.to_s + "," + summary_hash[regions]
+      regions << "V1V3"
+      regions.each do |region|
+        next unless summary_hash[region]
+        seq_summary_out.puts region.to_s + "," + summary_hash[region]
       end
       File.unlink(out_r_csv)
     end
@@ -286,13 +237,13 @@ libs.each do |lib|
   tcs_RT = 0
   tcs_IN = 0
   tcs_V1V3 = 0
-  tcs_P17 = 0
+  tcs_CA = 0
   pi_RT = "NA"
   pi_V1V3 = "NA"
-  pi_P17 = "NA"
+  pi_CA = "NA"
   dist20_RT = "NA"
   dist20_V1V3 = "NA"
-  dist20_P17 = "NA"
+  dist20_CA = "NA"
   summary_lines.each do |line|
       data = line.chomp.split(",")
       if data[0] == "PR"
@@ -307,10 +258,10 @@ libs.each do |lib|
           tcs_V1V3 = data[1].to_i
           pi_V1V3 = data[6].to_f
           dist20_V1V3 = data[7].to_f
-      elsif data[0] == "P17"
-          tcs_P17 = data[4].to_i
-          pi_P17 = data[6].to_f
-          dist20_P17 = data[7].to_f
+      elsif data[0] == "CA"
+          tcs_CA = data[4].to_i
+          pi_CA = data[6].to_f
+          dist20_CA = data[7].to_f
       end
   end
 
@@ -334,6 +285,7 @@ libs.each do |lib|
   sdrm_PR = ""
   sdrm_RT = ""
   sdrm_IN = ""
+  sdrm_CA = ""
   sdrm_lines.each do |line|
       data = line.chomp.split(",")
       next if data[-1] == "*"
@@ -343,6 +295,8 @@ libs.each do |lib|
           sdrm_RT += abstract_line(data)
       elsif data[0] == "IN"
           sdrm_IN += abstract_line(data)
+      elsif data[0] == "CA"
+          sdrm_CA += abstract_line(data)
       end
   end
 
@@ -352,13 +306,13 @@ libs.each do |lib|
     tcs_RT: tcs_RT,
     tcs_IN: tcs_IN,
     tcs_V1V3: tcs_V1V3,
-    tcs_P17: tcs_P17,
+    tcs_CA: tcs_CA,
     pi_RT: pi_RT,
     pi_V1V3: pi_V1V3,
-    pi_P17: pi_P17,
+    pi_CA: pi_CA,
     dist20_RT: dist20_RT,
     dist20_V1V3: dist20_V1V3,
-    dist20_P17: dist20_P17,
+    dist20_CA: dist20_CA,
     recency: recency,
     dpi: dpi,
     dpi_lwr: dpi_lwr,
@@ -366,7 +320,8 @@ libs.each do |lib|
     possible_dual_infection: possible_dual_infection,
     sdrm_PR: sdrm_PR,
     sdrm_RT: sdrm_RT,
-    sdrm_IN: sdrm_IN
+    sdrm_IN: sdrm_IN,
+    sdrm_CA: sdrm_CA
   ]
 
   summary_json_out.puts JSON.pretty_generate(summary_json)
@@ -389,7 +344,7 @@ libs.each do |lib|
       file: point_mutation_file,
       newPDF: "",
       table_width: [60,50,70,65,65,60,75,70,70,70,45],
-      extra_text: "* Mutation below Poisson cut-off for minority mutations"
+      extra_text: "* Mutation below FDR significance cut-off for minority mutations"
     },
     {
       name: "linkage",
@@ -397,7 +352,6 @@ libs.each do |lib|
       file: linkage_file,
       newPDF: "",
       table_width: [55,50,250,60,80,80,80,45],
-      extra_text: "* Mutation below Poisson cut-off for minority mutations"
     }
   ]
 
@@ -433,7 +387,7 @@ libs.each do |lib|
   pdf << CombinePDF.load(out_r_pdf) if File.exist?(out_r_pdf)
 
   pdf.number_pages location: [:bottom_right],
-  number_format: "Swanstrom\'s lab HIV SDRM Pipeline, version #{$sdrm_version_number} by S.Z. and M.U.C.   Page %s",
+  number_format: "Swanstrom\'s lab HIV SDRM Pipeline, TCS version #{ViralSeq::TCS_VERSION}, DRM config version #{version_config.drm_version}, by S.Z. and M.U.C.   Page %s",
   font_size: 6,
   opacity: 0.5
 
@@ -448,4 +402,6 @@ log_file = File.join(File.dirname(indir), "sdrm_log.json")
 
 File.open(log_file, 'w') { |f| f.puts JSON.pretty_generate(log) }
 
+puts "TCS SDRM pipeline done. Exit 0."
+
 FileUtils.touch(File.join(outdir, ".done"))

data/lib/viral_seq/drm_region_config.rb

@@ -0,0 +1,83 @@
+
+module ViralSeq
+
+  # DRM configuration for each region
+
+  class DrmRegionConfig
+
+    # initialize DRM region configuration
+    # @param drm_version [String] version of the instance of DrmVersion
+    # @param region [String] name of the region
+    # @param drm_class [Array] classes of DRMs at this region
+    # @param drm_range [Hash] DRM range for each class of DRMs at this region
+    # @param drm_list [Hash] List of detailed DRM mutations for each DRM classes at this region
+    # @param seq_drm_corrlation [Hash] correlation of sequenced region and DRM class
+    # @param ref_info [Hash] information of the reference genome, including sequence coordinates on HXB2
+    def initialize(drm_version, region, drm_class, drm_range, drm_list, seq_coord, ref_info)
+      @drm_version = drm_version
+      @region = region
+      @drm_class = drm_class
+      @drm_range = drm_range
+      @drm_list = drm_list
+      @seq_coord = seq_coord
+      @ref_info = ref_info
+    end
+
+    attr_accessor :drm_version, :region, :drm_class, :drm_range, :drm_list, :seq_coord, :ref_info
+
+    # summarize the DRM information for the output as JSON for the specific version
+    # @return [Hash] json has for DRM inforation of each position
+    def drm_json
+      sdrm = self.drm_list
+      json_hash = {}
+      sdrm.each do |drm_class, drms|
+        json_hash[drm_class] = []
+        drms.each do |pos, muts|
+          mutation = {}
+          mutation[:position] = pos
+          mutation[:wildtypeCodon] = muts[0]
+          mutation[:mutationCodons] = muts[1]
+          json_hash[drm_class] << mutation
+        end
+      end
+      return json_hash
+    end
+
+    # calculate the length of R1 and R2 based on the sequence coordinates
+    # @return [Hash] {r1_length: [Integer], r2_length: [Integer]}
+    def r1_r2_length
+      seq_coord = self.seq_coord
+      return nil unless seq_coord["gap"]
+
+      r1_length = seq_coord["gap"]["minimum"] - seq_coord["minimum"]
+      r2_length = seq_coord["maximum"] - seq_coord["gap"]["maximum"]
+
+      return {r1_length: r1_length, r2_length: r2_length}
+    end #end of #r1_r2_length
+
+
+    # determine the reading frame number based on the sequence coordinates
+    # @return [Integer] reading frame of 0, 1 or 2
+    def get_reading_frame_number
+      m1 = (self.seq_coord["minimum"] - self.ref_info["ref_coord"][0]) % 3
+      if m1.zero?
+        n1 = 0
+      else
+        n1 = 3 - m1
+      end
+
+      if seq_coord["gap"]
+        m2 = (self.seq_coord["gap"]["maximum"] + 1 - self.ref_info["ref_coord"][0]) % 3
+        if m2.zero?
+          n2 = 0
+        else
+          n2 = 3 - m2
+        end
+        return [n1, n2]
+      else
+        return [n1]
+      end
+    end #end get_reading_frame_number
+
+  end
+end

data/lib/viral_seq/drm_version.rb

@@ -0,0 +1,120 @@
+
+module ViralSeq
+
+  # DRM version configuration.
+  # Configuration files are located at `lib/viral_seq/drm_versions_config.json`
+
+  class DrmVersion
+
+    # initialize a ViralSeq::DrmVersion instance
+    # @param drm_version [String] version of the instance of DrmVersion
+    # @param drm_range [Hash] region/class of DRM and the range of amino acid positions included in this version.
+    # @param seq_coord [Hash] region and its amplicon positions on HXB2 reference
+    # @param seq_drm_corrlation [Hash] correlation of sequenced region and DRM class
+    # @param ref_info [Hash] information of the reference genome, including sequence coordinates on HXB2
+    def initialize(drm_version, drm_range, seq_coord, seq_drm_correlation, ref_info)
+      @drm_version = drm_version
+      @drm_range = drm_range
+      @seq_coord = seq_coord
+      @seq_drm_correlation = seq_drm_correlation
+      @ref_info = ref_info
+    end
+
+    attr_accessor :drm_version, :drm_range, :seq_coord, :seq_drm_correlation, :ref_info
+
+    # construct an instance of ViralSeq::DrmVersion
+    # @param version_config_hash [Hash] json hash of stored version configurations.
+    # @return [ViralSeq::DrmVersion] an instance of constructed DrmVersion
+
+    def self.construct(version_config_hash)
+      drm_version = version_config_hash["version"]
+      drm_range = version_config_hash["DRM_range"]
+      seq_coord = version_config_hash["seq_coord"]
+      seq_drm_correlation = version_config_hash["seq_drm_correlation"]
+      ref_info = version_config_hash["ref_info"]
+      ViralSeq::DrmVersion.new(drm_version, drm_range, seq_coord, seq_drm_correlation, ref_info)
+    end
+
+    # construct a specific version of ViralSeq::DrmVersion
+    # @param v [String] version string
+    # @return [ViralSeq::DrmVersion] an instance of constructed DrmVersion
+
+    def self.config_version(v="v1")
+      v = v.downcase
+      v = "v1" if v == "v2"
+
+      drm_config = JSON.parse(
+        File.read(
+          File.join( ViralSeq.root, 'viral_seq', 'util', 'drm_versions_config.json')
+          )
+      )
+
+      drm_versions = {}
+
+      drm_config.each do |config|
+        drm_versions[config["version"]] = ViralSeq::DrmVersion.construct(config)
+      end
+
+      if drm_versions[v]
+        drm_versions[v]
+      else
+        abort (
+        "Version '#{v}' config not found. Program aborted. \nCurrent supported versions '#{drm_versions.keys.sort.join(", ")}'\nCheck documentations for details".red
+        )
+      end
+    end
+
+    # construct a ViralSeq::DrmRegionConfig instance from a specific version
+    # @param region [String] name of the region
+    # @return [ViralSeq::DrmRegionConfig] an instance of DrmRegionConfig
+
+    def query_region(region)
+      region = region.to_s.upcase
+      drm_classes = self.seq_drm_correlation[region]
+
+      if drm_classes.nil?
+        abort "Region not recognized by the specific DRM config version. Program aborted."
+      end
+
+      drm_range = {}
+      drm_list = {}
+
+      drm_classes.each do |drm_class|
+        drm_range[drm_class] = self.drm_range[drm_class]
+        drm_list_single_class = ViralSeq::DRMs.sdrm_hash(drm_class)
+
+        drm_list[drm_class] = drm_list_single_class.select { |k, _v| drm_range[drm_class].include? k }
+
+      end
+
+
+      seq_coord = self.seq_coord[region]
+
+      ref_info = {}
+      ref_info["ref_type"] = self.ref_info["ref_type"]
+      ref_info["ref_coord"] = self.ref_info["ref_coord"][region]
+
+
+      ViralSeq::DrmRegionConfig.new(
+        self.drm_version, region, drm_classes, drm_range, drm_list, seq_coord, ref_info
+      )
+    end
+
+    # summarize the DRM information for the output as JSON
+    # @return [Hash] json has for DRM inforation of each position
+
+    def pull_drm_json
+
+      summary_json_hash = {}
+
+      self.seq_drm_correlation.keys.each do |region|
+        summary_json_hash = summary_json_hash.merge query_region(region).drm_json
+      end
+
+      summary_json_hash
+
+    end
+
+  end # end of class
+
+end