viral_seq 1.0.5 → 1.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a13ba7912ee87511c2ecf19f07256d3a129661c6d7e180d57ecd1e34978386e6
-  data.tar.gz: 61e5ed6b423f0b64c53a6bb8e8ec3801bf7e093e4d0741bd71bf9fbfa24f1b55
+  metadata.gz: df8d50f2dfbf0f2e7e1efcf66c8a91c286c7b5029533b725a4a33219882748bb
+  data.tar.gz: 4061c3875d4629025d1ccc216a54fdb7a011d397408a3ecb15125475e9f262e9
 SHA512:
-  metadata.gz: f18d03220190bf1479ed29bd4d4b83777ffe5216951d38a91dd2afdc6c07b516883a8694291106b6fee2693a246b8a3c6a824786527cd03730f28f6777fa3231
-  data.tar.gz: 7fe146b081a7b633de963ed632bdcb548c71d1f401e227109d8745d23ad770d2099a2aa50bc4553a9450b260b7206892ed2a898d9154764aebe4094f38faeb44
+  metadata.gz: a52087ced9fe258ef5bab4449b90e964ff9a557292dc1ce679aae03a56bd2570fdf1221e7026fec2b1ccb49ad2a9ff076338a397982e47c46877e2cdfb4e6d2e
+  data.tar.gz: 792cb9424fd46d536d0b95cfc90914a8548ee5ea6d1c3efe45cccd1d01c6dbd6b7a7ee0ba1be010bd6cf7a3ea201f4850803c28f16889b5286e1e458a774c8f1

data/README.md

@@ -10,46 +10,55 @@ Specifically for Primer-ID sequencing and HIV drug resistance analysis.
 
 ## Usage
 
-Load all ViralSeq classes by requiring 'viral_seq.rb'
+#### Load all ViralSeq classes by requiring 'viral_seq.rb'
 
     #!/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
 
 ## Some Examples
 
-### Load nucleotide sequences from a FASTA format sequence file
+#### Load nucleotide sequences from a FASTA format sequence file
 
     my_seqhash = ViralSeq::SeqHash.fa('my_seq_file.fasta')
 
-### Make an alignment (using MUSCLE)
+#### Make an alignment (using MUSCLE)
 
     aligned_seqhash = my_seqhash.align
 
-### Filter nucleotide sequences with the reference coordinates (HIV Protease)
+#### Filter nucleotide sequences with the reference coordinates (HIV Protease)
 
     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
 
     qc_seqhash = qc_seqhash.a3g
 
-### Calculate nucleotide diveristy π
+#### Calculate nucleotide diveristy π
 
     qc_seqhash.pi
 
-### Calculate cut-off for minority variants based on Poisson model
+#### Calculate cut-off for minority variants based on Poisson model
 
     cut_off = qc_seqhash.pm
 
-### Examine for drug resistance mutations for HIV PR region
+#### Examine for drug resistance mutations for HIV PR region
 
     qc_seqhash.sdrm_hiv_pr(cut_off)
 
-### Use executable `locator` to get the coordinates of the sequences on HIV/SIV reference genome from a FASTA file through a terminal
+## Updates
 
-    $ locator -i sequence.fasta -o sequence.fasta.csv
+Version 1.0.6-07232019:
 
-## Updates
+    1. Several methods added to ViralSeq::SeqHash, including
+        ViralSeq::SeqHash#size
+        ViralSeq::SeqHash#+
+        ViralSeq::SeqHash#write_nt_fa
+        ViralSeq::SeqHash#mutation
+    2. Update documentations and rspec samples. 
 
 Version 1.0.5-07112019:
 

data/lib/viral_seq/hivdr.rb

@@ -5,6 +5,8 @@ module ViralSeq
     # 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)
     #   PR codon 1-99
+    #   RT codon 34-122 (HXB2 2650-2914) and 152-236(3001-3257)
+    #   IN codon 53-174 (HXB2 4384-4751)
     # @param cutoff [Integer] cut-off for minimal abundance of a mutation to be called as valid mutation,
     #   can be obtained using ViralSeq::SeqHash#poisson_minority_cutoff function
     # @return [Array] three elements `[point_mutation_list, linkage_list, report_list]`

data/lib/viral_seq/seq_hash.rb

@@ -166,6 +166,39 @@ module ViralSeq
       alias_method :array, :new_from_array
     end
 
+    # the size of nt sequence hash of the SeqHash object
+    # @return [Integer] size of nt sequence hash of the SeqHash object
+
+    def size
+      self.dna_hash.size
+    end
+
+    # combine SeqHash objects
+    # @param sh2 [ViralSeq::SeqHash] another SeqHash
+    # @return [ViralSeq::SeqHash] combined SeqHash
+
+    def +(sh2)
+      new_seqhash = ViralSeq::SeqHash.new
+      new_seqhash.dna_hash = self.dna_hash.merge(sh2.dna_hash)
+      new_seqhash.aa_hash = self.aa_hash.merge(sh2.aa_hash)
+      new_seqhash.title = self.title + "_with_" + sh2.title
+      new_seqhash.file = self.file + "," + sh2.file
+      return new_seqhash
+    end
+
+    # write the nt sequences to a FASTA format file
+    # @param file [String] path to the FASTA output file
+    # @return [NilClass]
+
+    def write_nt_fa(file)
+      File.open(file, 'w') do |f|
+        self.dna_hash.each do |k,v|
+          f.puts k
+          f.puts v
+        end
+      end
+    end
+
     # generate sequences in relaxed sequencial phylip format from a ViralSeq::SeqHash object
     # @return [String] relaxed sequencial phylip format in a String object
     # @example convert fasta format to relaxed sequencial phylip format
@@ -748,7 +781,7 @@ module ViralSeq
         s.rc!
         loc2 = s.locator(ref_option)
         loc1[2] >= loc2[2] ? (direction = :+; loc = loc1): (direction = :-; loc = loc2)
-    
+
         names.each do |name|
           out_array << ([title, name, ref_option.to_s, direction.to_s] + loc)
         end
@@ -999,6 +1032,21 @@ module ViralSeq
     end
 
 
+    # mutate @dna_hash based on the error_rate
+    # @param error_rate [Float] error rate used to mutate sequences.
+    # @return [ViralSeq::SeqHash] new SeqHash object of mutated sequences.
+
+    def mutation(error_rate = 0.01)
+      new_seqhash = ViralSeq::SeqHash.new
+      dna = {}
+      self.dna_hash.each do |name, seq|
+        dna[name + '_mut-' + error_rate.to_s] = seq.mutation(error_rate)
+      end
+      new_seqhash.dna_hash = dna
+      new_seqhash.title = self.title + "_mut-" + error_rate.to_s
+      new_seqhash.file = self.file
+      return new_seqhash
+    end
 
 
 

data/lib/viral_seq/version.rb

@@ -2,5 +2,5 @@
 # version info and histroy
 
 module ViralSeq
-  VERSION = "1.0.5"
+  VERSION = "1.0.6"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: viral_seq
 version: !ruby/object:Gem::Version
-  version: 1.0.5
+  version: 1.0.6
 platform: ruby
 authors:
 - Shuntai Zhou
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-07-11 00:00:00.000000000 Z
+date: 2019-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler