viral_seq 1.0.13 → 1.2.0

data/lib/viral_seq.rb

@@ -37,6 +37,10 @@ require_relative "viral_seq/string"
 require_relative "viral_seq/version"
 require_relative "viral_seq/tcs_core"
 require_relative "viral_seq/tcs_json"
-
+require_relative "viral_seq/tcs_dr"
+require_relative "viral_seq/sdrm"
+require_relative "viral_seq/recency"
 
 require "muscle_bio"
+require "json"
+require "securerandom"

data/lib/viral_seq/constant.rb

@@ -1,11 +1,41 @@
 module ViralSeq
 
   # array for all amino acid one letter abbreviations
-
   AMINO_ACID_LIST = ["A", "C", "D", "E", "F", "G", "H", "I", "K", "L", "M", "N", "P", "Q", "R", "S", "T", "V", "W", "Y", "*"]
 
-  SDRM_HIV_PR_LIST = {}
-  SDRM_HIV_RT_LIST = {}
-  SDRM_HIV_IN_LIST = {}
-  
+  # R script for tcs_sdrm script
+
+  R_SCRIPT = 'setwd("PATH_TO_FASTA")
+              library(phangorn)
+              library(ape)
+              library(ggplot2)
+              library(scales)
+              library(ggforce)
+              library(cowplot)
+              library(magrittr)
+              library(gridExtra)
+              pdf("OUTPUT_PDF", onefile=T, width=11, height=8.5)
+              fileNames <- list.files()
+              for (fileName in fileNames) {
+              dna <- read.dna(fileName, format="fasta")
+              class(dna)
+              D<- dist.dna(dna, model="raw")
+              pi <- mean(D)
+              dist20 <- quantile(D, prob=c(0.20))
+              alldist <- data.frame(File=fileName, pi, dist20)
+              write.table(alldist,"OUTPUT_CSV",append=TRUE, sep = ",", row.names = FALSE, col.names=FALSE)
+              D2 <- dist.dna(dna, model="TN93")*100
+              def.par <- par(no.readonly = TRUE)
+              par(mfrow=c(1,2))
+              hist<-hist(D, main=fileName, xlab="% Pairwise Distance", ylab="Frequency", col="gray")
+              abline(v=dist20, col="royalblue",lwd=2)
+              abline(v=pi, col="red", lwd=2)
+              legend(x="topright", c("dist20", "pi"), col = c("royalblue", "red"), lwd = c(2,2), cex=0.5)
+              njtree<-NJ(D2)
+              njtreeplot <- plot(njtree, show.tip.label=F, "unrooted", main=fileName)
+              add.scale.bar(cex=0.7, font=2, col="red")
+              }
+              dev.off()'
+
+
 end

data/lib/viral_seq/hivdr.rb

@@ -1,6 +1,6 @@
 
 module ViralSeq
-  class SDRM
+  class SeqHash
 
     # functions to identify SDRMs from a ViralSeq::SeqHash object at HIV PR region.
     #   works for MPID-DR protocol (dx.doi.org/10.17504/protocols.io.useewbe)

data/lib/viral_seq/muscle.rb

@@ -39,8 +39,9 @@ module ViralSeq
 
     def self.align(ref_seq = "", test_seq = "", path_to_muscle = false)
       temp_dir = Dir.home
-      temp_file = File.join(temp_dir, "_temp_muscle_in")
-      temp_aln = File.join(temp_dir, "_temp_muscle_aln")
+      temp_name = "_"  + SecureRandom.alphanumeric
+      temp_file = File.join(temp_dir, temp_name)
+      temp_aln = File.join(temp_dir, (temp_name + "_aln"))
       name = ">test"
       temp_in = File.open(temp_file,"w")
       temp_in.puts ">ref"

data/lib/viral_seq/recency.rb

@@ -0,0 +1,52 @@
+module ViralSeq
+
+  # recency prediction function based on HIV MPID-NGS
+  # @see https://pubmed.ncbi.nlm.nih.gov/32663847 Ref: Zhou et al. J Infect Dis. 2021
+
+  module Recency
+
+    # @params tcs_RT [Integer] number of TCS at the RT region
+    # @params tcs_V1V3 [Integer] number of TCS at the V1V3 region
+    # @params pi_RT [Float] pairwise diversity at the RT region
+    # @params pi_V1V3 [Float] pairwise diversity at the V1V3 region
+    # @params dist20_RT [Float] dist20 at the RT region
+    # @params dist20_V1V3 [Float] dist20 at the V1V3 region
+    # @return [String] determination of the recency
+    
+    def self.define(tcs_RT: nil,
+                     tcs_V1V3: nil,
+                     pi_RT: nil,
+                     dist20_RT: nil,
+                     pi_V1V3: nil,
+                     dist20_V1V3: nil)
+      tcs_RT ||= 0
+      tcs_V1V3 ||= 0
+      if (tcs_RT >= 3 && pi_RT) and (tcs_V1V3 >= 3 && pi_V1V3)
+        if (pi_RT + pi_V1V3) < 0.0103
+            recency = "recent"
+        elsif (pi_RT + pi_V1V3) >= 0.0103 and (dist20_RT + dist20_V1V3) >= 0.006
+            recency = "chronic"
+        else
+            recency = "indeterminant"
+        end
+      elsif (tcs_RT >= 3 && pi_RT) and tcs_V1V3 < 3
+        if pi_RT < 0.0021
+          recency = "recent"
+        elsif pi_RT >= 0.0021 and dist20_RT >= 0.001
+          recency = "chronic"
+        else
+          recency = "indeterminant"
+        end
+      elsif (tcs_V1V3 >= 3 && pi_V1V3)
+        if pi_V1V3 >= 0.0103 and dist20_V1V3 >= 0.006
+          recency = "chronic"
+        else
+          recency = "insufficient data"
+        end
+      else
+        recency = "insufficient data"
+      end
+      return recency
+    end
+  end
+end

data/lib/viral_seq/sdrm.rb

@@ -1,43 +1,109 @@
 module ViralSeq
   class DRMs
-    def initialize (mutation_list = {})
-      @mutation_list = mutation_list
-    end
-
-    attr_accessor :mutation_list
-  end
+    class << self
 
-  def self.sdrm_hiv_pr(seq_hash)
-  end
-
-  def self.sdrm_hiv_rt(seq_hash)
-  end
+      # function to retrieve sdrm positions as a hash
+      # @param ref_option [Symbol], name of reference genomes, options are `:hiv_pr`, `:hiv_rt`, `:hiv_in`, `hcv_ns5a`
+      # @return [Hash] Hash of :position_number => [ 'wildtype_codon', ['mutation_codons']]
+      def sdrm_hash(options)
+        sdrm = {}
+        case options
+        when :hcv_ns5a
+          sdrm[28] = ['M',['T']]
+          sdrm[30] = ['L',['H','K','R','Q','A','S','D']]
+          sdrm[31] = ['L',['M','V','F']]
+          sdrm[32] = ['P',['L']]
+          sdrm[44] = ['K',['R']]
+          sdrm[58] = ['H',['D','P','S']]
+          sdrm[64] = ['T',['A','S']]
+          sdrm[77] = ['P',['A','S']]
+          sdrm[78] = ['R',['K']]
+          sdrm[79] = ['T',['A']]
+          sdrm[83] = ['T',['M']]
+          sdrm[85] = ['S',['N','H','Y']]
+          sdrm[92] = ['A',['P','T','K','E']]
+          sdrm[93] = ['Y',['C','F','H','N']]
+          sdrm[107] = ['K',['T','S']]
+          sdrm[121] = ['I',['V']]
+          sdrm[135] = ['T',['A']]
+        when :nrti
+          sdrm[41] = ['M',['L']]
+          sdrm[65] = ['K',['R']]
+          sdrm[67] = ['D',['N','G','E']]
+          sdrm[69] = ['T',['D']]
+          sdrm[70] = ['K',['R','E']]
+          sdrm[74] = ['L',['V','I']]
+          sdrm[75] = ['V',['M','T','A','S']]
+          sdrm[77] = ['F',['L']]
+          sdrm[115] = ['Y',['F']]
+          sdrm[116] = ['F',['Y']]
+          sdrm[151] = ['Q',['M']]
+          sdrm[184] = ['M',['V','I']]
+          sdrm[210] = ['L',['W']]
+          sdrm[215] = ["T",["Y","F","I","C","D","V","E"]]
+          sdrm[219] = ["K",["Q","E","N","R"]]
+        when :nnrti
+          sdrm[100] = ['L',['I']]
+          sdrm[101] = ['K',['E','P']]
+          sdrm[103] = ['K',['N','S']]
+          sdrm[106] = ['V',['M','A']]
+          sdrm[179] = ['V',['F','D']]
+          sdrm[181] = ['Y',['C','I','V']]
+          sdrm[188] = ['Y',['L','H','C']]
+          sdrm[190] = ['G',['A','S','E']]
+          sdrm[225] = ['P',['H']]
+          sdrm[230] = ['M',['L']]
+        when :hiv_pr
+          sdrm[23] = ['L',['I']]
+          sdrm[24] = ['L',['I']]
+          sdrm[30] = ['D',['N']]
+          sdrm[32] = ['V',['I']]
+          sdrm[46] = ['M',['I','L']]
+          sdrm[47] = ['I',['V','A']]
+          sdrm[48] = ['G',['V','M']]
+          sdrm[50] = ['I',['V','L']]
+          sdrm[53] = ['F',['L']]
+          sdrm[54] = ['I',['V','L','M','T','A','S']]
+          sdrm[73] = ['G',['S','T','C','A']]
+          sdrm[76] = ['L',['V']]
+          sdrm[82] = ['V',['A','T','S','F','L','C','M']]
+          sdrm[83] = ['N',['D']]
+          sdrm[84] = ['I',['V','A','C']]
+          sdrm[88] = ['N',['D','S']]
+          sdrm[90] = ['L',['M']]
+        when :hiv_in
+          sdrm[66] = ['T',['A','I','K']]
+          sdrm[74] = ['L',['M']]
+          sdrm[92] = ['E',['Q']]
+          sdrm[95] = ['Q',['K']]
+          sdrm[97] = ['T',['A']]
+          sdrm[121] = ['F',['Y']]
+          sdrm[140] = ['G',['A','S','C']]
+          sdrm[143] = ["Y",["C","H","R"]]
+          sdrm[147] = ['S',['G']]
+          sdrm[148] = ['Q',['H','K','R']]
+          sdrm[155] = ['N',['S','H']]
+        else raise "Input option `#{options}` for ViralSeq::Sequence.sdrm not supported"
+        end
+        return sdrm
+      end # end of #sdrm_hash
 
-  def self.sdrm_hiv_in(seq_hash)
-  end
-
-  def self.list_from_json(file)
-  end
-
-  def self.list_from_csv(file)
-  end
-
-  def self.export_list_hiv_pr(file, format = :json)
-    if foramt == :json
+      # function to export SDRM positions as json object
+      # @param (see #sdrm_hash)
+      # @return [Array] json Array of SDRM positions
 
+      def sdrm_json(options)
+        sdrm = ViralSeq::DRMs.sdrm_hash(options)
+        json_array = []
+        sdrm.each do |pos, muts|
+          mutation = {}
+          mutation[:position] = pos
+          mutation[:wildtypeCodon] = muts[0]
+          mutation[:mutationCodons] = muts[1]
+          json_array << mutation
+        end
+        return json_array
+      end
     end
   end
-
-  def self.export_list_hiv_rt(file, format = :json)
-
-  end
-
-  def self.export_list_hiv_in(file, format = :json)
-
-  end
-
-  def drm_analysis(seq_hash)
-    mutation_list = self.mutation_list
-
-  end
 end

data/lib/viral_seq/seq_hash.rb

@@ -11,7 +11,7 @@ module ViralSeq
   #     # filter nt sequences with the reference coordinates
   #   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]
+  #   filtered_seqhash = filtered_seqhash.a3g[:filtered_seq]
   #     # further filter out sequences with A3G hypermutations
   #   filtered_seqhash.pi
   #     # return pairwise diveristy π
@@ -187,6 +187,25 @@ module ViralSeq
       return new_seqhash
     end
 
+    # sample a certain number of sequences from a SeqHash object
+    # @param n [Integer] number of sequences to sample
+    # @return [ViralSeq::SeqHash] sampled SeqHash
+
+    def sample(n = 1)
+      keys = self.dna_hash.keys
+      sampled_keys = keys.sample(n)
+      sampled_nt = {}
+      sampled_aa = {}
+      sampled_qc = {}
+      sampled_title = self.title + "_sampled_" + n.to_s
+      sampled_keys.each do |k|
+        sampled_nt[k] = self.dna_hash[k]
+        sampled_aa[k] = self.aa_hash[k]
+        sampled_qc[k] = self.qc_hash[k]
+      end
+      return ViralSeq::SeqHash.new(sampled_nt, sampled_aa, sampled_qc, sampled_title, self.file)
+    end
+
     # write the nt sequences to a FASTA format file
     # @param file [String] path to the FASTA output file
     # @return [NilClass]
@@ -394,7 +413,6 @@ module ViralSeq
             end
           end
         end
-
         consensus_seq += call_consensus_base(max_base_list)
       end
       return consensus_seq
@@ -583,8 +601,8 @@ module ViralSeq
         temp_dir=File.dirname($0)
       end
 
-      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")
       File.open(temp_file, 'w'){|f| seq_hash.each {|k,v| f.puts k; f.puts v}}
       if path_to_muscle
         unless ViralSeq.check_muscle?(path_to_muscle)
@@ -742,6 +760,7 @@ module ViralSeq
       seq_hash_unique_pass = []
 
       seq_hash_unique.each do |seq|
+        next if seq.nil?
         loc = ViralSeq::Sequence.new('', seq).locator(ref_option, path_to_muscle)
         next unless loc # if locator tool fails, skip this seq.
         if start_nt.include?(loc[0]) && end_nt.include?(loc[1])
@@ -808,7 +827,7 @@ module ViralSeq
     end # end of locator
     alias_method :loc, :sequence_locator
 
-    # Remove squences with residual offspring Primer IDs.
+    # Remove sequences with residual offspring Primer IDs.
     #   Compare PID with sequences which have identical sequences.
     #   PIDs differ by 1 base will be recognized. If PID1 is x time (cutoff) greater than PID2, PID2 will be disgarded.
     #     each sequence tag starting with ">" and the Primer ID sequence
@@ -1155,6 +1174,7 @@ module ViralSeq
         new_sh.aa_hash[k] = aa_hash[k]
         new_sh.qc_hash[k] = qc_hash[k]
       end
+      new_sh.file = self.file
       new_sh.title = self.title + "_" + n.to_s
       return new_sh
     end

data/lib/viral_seq/seq_hash_pair.rb

@@ -110,19 +110,21 @@ 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.uniq_hash.each do |seq_pair, seq_names|
+      seq_pair_hash.each do |seq_name,seq_pair|
         r1_seq = seq_pair[0]
         r2_seq = seq_pair[1]
         if overlap.zero?
           joined_sequence = r1_seq + r2_seq
+        elsif diff.zero?
+          if r1_seq[-overlap..-1] == r2_seq[0,overlap]
+            joined_sequence= r1_seq + r2_seq[overlap..-1]
+          end
         elsif r1_seq[-overlap..-1].compare_with(r2_seq[0,overlap]) <= (overlap * diff)
           joined_sequence= r1_seq + r2_seq[overlap..-1]
         else
           next
         end
-        seq_names.each do |seq_name|
-          joined_seq[seq_name] = joined_sequence
-        end
+        joined_seq[seq_name] = joined_sequence if joined_sequence
       end
 
       joined_seq_hash = ViralSeq::SeqHash.new

data/lib/viral_seq/sequence.rb

@@ -113,7 +113,7 @@ module ViralSeq
     def sdrm(option, start_aa = 1)
       aa_array = self.aa_array
       out_hash = {}
-      sdrm = sdrm_hash(option)
+      sdrm = ViralSeq::DRMs.sdrm_hash(option)
       aa_length = aa_array.size
       end_aa = start_aa + aa_length - 1
       (start_aa..end_aa).each do |position|
@@ -535,88 +535,5 @@ module ViralSeq
       return aa_out
     end # end of #amino_acid_2
 
-    # sdrm position hash
-    def sdrm_hash(options)
-      sdrm = {}
-      case options
-      when :hcv_ns5a
-        sdrm[28] = ['M',['T']]
-        sdrm[30] = ['L',['H','K','R','Q','A','S','D']]
-        sdrm[31] = ['L',['M','V','F']]
-        sdrm[32] = ['P',['L']]
-        sdrm[44] = ['K',['R']]
-        sdrm[58] = ['H',['D','P','S']]
-        sdrm[64] = ['T',['A','S']]
-        sdrm[77] = ['P',['A','S']]
-        sdrm[78] = ['R',['K']]
-        sdrm[79] = ['T',['A']]
-        sdrm[83] = ['T',['M']]
-        sdrm[85] = ['S',['N','H','Y']]
-        sdrm[92] = ['A',['P','T','K','E']]
-        sdrm[93] = ['Y',['C','F','H','N']]
-        sdrm[107] = ['K',['T','S']]
-        sdrm[121] = ['I',['V']]
-        sdrm[135] = ['T',['A']]
-      when :nrti
-        sdrm[41] = ['M',['L']]
-        sdrm[65] = ['K',['R']]
-        sdrm[67] = ['D',['N','G','E']]
-        sdrm[69] = ['T',['D']]
-        sdrm[70] = ['K',['R','E']]
-        sdrm[74] = ['L',['V','I']]
-        sdrm[75] = ['V',['M','T','A','S']]
-        sdrm[77] = ['F',['L']]
-        sdrm[115] = ['Y',['F']]
-        sdrm[116] = ['F',['Y']]
-        sdrm[151] = ['Q',['M']]
-        sdrm[184] = ['M',['V','I']]
-        sdrm[210] = ['L',['W']]
-        sdrm[215] = ["T",["Y","F","I","C","D","V","E"]]
-        sdrm[219] = ["K",["Q","E","N","R"]]
-      when :nnrti
-        sdrm[100] = ['L',['I']]
-        sdrm[101] = ['K',['E','P']]
-        sdrm[103] = ['K',['N','S']]
-        sdrm[106] = ['V',['M','A']]
-        sdrm[179] = ['V',['F','D']]
-        sdrm[181] = ['Y',['C','I','V']]
-        sdrm[188] = ['Y',['L','H','C']]
-        sdrm[190] = ['G',['A','S','E']]
-        sdrm[225] = ['P',['H']]
-        sdrm[230] = ['M',['L']]
-      when :hiv_pr
-        sdrm[23] = ['L',['I']]
-        sdrm[24] = ['L',['I']]
-        sdrm[30] = ['D',['N']]
-        sdrm[32] = ['V',['I']]
-        sdrm[46] = ['M',['I','L']]
-        sdrm[47] = ['I',['V','A']]
-        sdrm[48] = ['G',['V','M']]
-        sdrm[50] = ['I',['V','L']]
-        sdrm[53] = ['F',['L']]
-        sdrm[54] = ['I',['V','L','M','T','A','S']]
-        sdrm[73] = ['G',['S','T','C','A']]
-        sdrm[76] = ['L',['V']]
-        sdrm[82] = ['V',['A','T','S','F','L','C','M']]
-        sdrm[83] = ['N',['D']]
-        sdrm[84] = ['I',['V','A','C']]
-        sdrm[88] = ['N',['D','S']]
-        sdrm[90] = ['L',['M']]
-      when :hiv_in
-        sdrm[66] = ['T',['A','I','K']]
-        sdrm[74] = ['L',['M']]
-        sdrm[92] = ['E',['Q']]
-        sdrm[95] = ['Q',['K']]
-        sdrm[97] = ['T',['A']]
-        sdrm[121] = ['F',['Y']]
-        sdrm[140] = ['G',['A','S','C']]
-        sdrm[143] = ["Y",["C","H","R"]]
-        sdrm[147] = ['S',['G']]
-        sdrm[148] = ['Q',['H','K','R']]
-        sdrm[155] = ['N',['S','H']]
-      else raise "Input option `#{options}` for ViralSeq::Sequence.sdrm not supported"
-      end
-      return sdrm
-    end
   end # end of ViralSeq::Sequence
 end # end of ViralSeq