viral_seq 1.4.0 → 1.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2bf2afba235cb99f680f10e0913b8e0f715dd2f9c831f2dcba4534a2607685e6
-  data.tar.gz: 8995b0417a1f6ca4de39e26405ab012766a31b1460f5c1c6d11147271f587044
+  metadata.gz: c678fb3b1c37bd996ccf65f1b062a044e60eee32c01b0d75f7c9b7859c3136dd
+  data.tar.gz: 7e42acba2e2ae0e3f17a2786cfa1b5b4a376e0b5723c73ed83d32e9d93509c34
 SHA512:
-  metadata.gz: 233485f39d610945794a033c1d2c53680d753ca0284c6b0b9075295352ceb765df11727816dbc061429ccabfb03204c0db82a24a4d1c4a6ebd5a99df770253ff
-  data.tar.gz: ae029b7ae6f530e748ba256a4ba9bb4af95de7e57cbdf49808f1b257794f22830fe3ffbd636a742bd2bae6f5535539b08d0d042b3100ec2b5ef8b59d83098ead
+  metadata.gz: 527894489a0f2d899c449b802a6986f9ebad74fb324339c29a523f6a39cc2ce9d8639f39b837e32881e977e05ea639b4a3681d0b5cbdf87650f5749cfdc72b64
+  data.tar.gz: c6418b6b395fdc52e9ed53c4e26531f4baac0cf61356db83aa9089e3e37a348edc8f12d2ca1a6b9cc8d5609f1ff0bfd9ba3e98025c0e4d71d80702d662ecbaa6

data/README.md

@@ -179,6 +179,14 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
 
 ## Updates
 
+### Version 1.5.0-01042022
+
+  1. Added a function to calcute detection limit/sensitivity for minority variants (R required). `ViralSeq::TcsCore::detection_limit`
+  2. Added a function to get a sub SeqHash object given a range of nt positions. `ViralSeq::SeqHash#nt_range`
+  3. Added a function to quality check dna sequences comparing with sample consensus for indels. `ViralSeq::SeqHash#qc_indel`
+  4. Added a function for DNA variant analysis. Return a Hash object that can output as a JSON file. `ViralSeq::SeqHash#nt_variants`
+  5. Added a function to check the size of sequences of a SeqHash object. `ViralSeq::SeqHash#check_nt_size`
+
 ### Version 1.4.0-10132021
 
   1. Added a function to calculate false detectionr rate (FDR, aka, Benjamini-Hochberg correction) for minority mutations detected in the sequences. `ViralSeq::SeqHash#fdr`

data/bin/tcs

@@ -200,7 +200,7 @@ begin
     summary_json[:paired_raw_sequence] = paired_seq_number
     if paired_seq_number < raw_sequence_number * 0.001
       summary_json[:warnings] <<
-        "WARNING: Filtered raw sequneces less than 0.1% of the total raw sequences. Possible contamination."
+        "WARNING: Filtered raw sequences less than 0.1% of the total raw sequences. Possible contamination."
     end
 
     common_keys.each do |seqtag|

data/lib/viral_seq/seq_hash.rb

@@ -208,6 +208,31 @@ module ViralSeq
       return ViralSeq::SeqHash.new(sampled_nt, sampled_aa, sampled_qc, sampled_title, self.file)
     end
 
+    # return a new SeqHash object with given a range on the nt sequence position
+    # @param range [Range] range of positions on the nt sequence
+    # @return [ViralSeq::SeqHash] a sub SeqHash object
+
+    def nt_range(range)
+      dna_hash = self.dna_hash
+      new_hash = {}
+      dna_hash.each do |k,v|
+        new_hash[k] = v[range]
+      end
+      ViralSeq::SeqHash.new(new_hash)
+    end # end of #nt_range
+
+    # check the size range of the DNA sequences of the SeqHash object
+    # @return [Hash] Hash of {max: MAX_SIZE, min: MIN_SIZE}
+    
+    def check_nt_size
+      dna_hash = self.dna_hash
+      size_array = []
+      dna_hash.values.each do |v|
+        size_array << v.size
+      end
+      return { max: size_array.max, min: size_array.min }
+    end
+
     # write the nt sequences to a FASTA format file
     # @param file [String] path to the FASTA output file
     # @return [NilClass]
@@ -624,6 +649,67 @@ module ViralSeq
       end
     end #end of #fdr
 
+    # analysis for the nt sequence variants.
+    # @return [Hash] An Hash with information of variant analysis. Key/values of the return object see /docs/variants_structure.pdf
+
+    def nt_variants
+      return_obj = {}
+      nt_hash = self.dna_hash
+      tcs_number = self.size
+      dl = ViralSeq::TcsCore.detection_limit(tcs_number)
+      fdr_hash = self.fdr
+      pm_cut_off = self.pm
+      con = self.consensus
+      return_obj[:tcs_number] = tcs_number
+      return_obj[:lower_detection_limit] = dl
+      return_obj[:pm_cut_off] = pm_cut_off
+      return_obj[:positions] = []
+      cis = {}
+
+      (0..(con.size - 1)).each do |p|
+        position_obj = {}
+        position_obj[:position] = p + 1
+        position_obj[:tcs_number] = tcs_number
+        position_obj[:lower_detection_limit] = dl
+        position_obj[:pm_cut_off] = (pm_cut_off == Float::INFINITY ? pm_cut_off.to_s : pm_cut_off)
+
+        nts = []
+        dna_hash.each do |n,s|
+          nts << s[p]
+        end
+        freq_hash = nts.count_freq
+        [:A, :C, :G, :T, :-].each do |k|
+          v = freq_hash[k.to_s]
+          position_obj[k] = {}
+          position_obj[k][:count] = v
+          if v > 0
+            if cis[[v, tcs_number]]
+              ci = cis[[v, tcs_number]]
+            else
+              ci = ViralSeq::Math::BinomCI.new(v, tcs_number)
+              cis[[v, tcs_number]] = ci
+            end
+            position_obj[k][:freq] = ci.mean.round(4)
+            position_obj[k][:freq_ci_low] = ci.lower.round(4)
+            position_obj[k][:freq_ci_high] = ci.upper.round(4)
+            position_obj[k][:greater_than_pm] = (v >= pm_cut_off ? true : false)
+            position_obj[k][:fdr] = fdr_hash[v]
+          else
+            position_obj[k][:freq] = 0
+            position_obj[k][:freq_ci_low] = 0
+            position_obj[k][:freq_ci_high] = 0
+            position_obj[k][:greater_than_pm] = false
+            position_obj[k][:fdr] = nil
+          end
+        end
+
+        return_obj[:positions] << position_obj
+      end
+
+      return_obj
+    end # end of nt_variants
+
+
     # align the @dna_hash sequences, return a new ViralSeq::SeqHash object with aligned @dna_hash using MUSCLE
     # @param path_to_muscle [String], path to MUSCLE excutable. if not provided (as default), it will use RubyGem::MuscleBio
     # @return [SeqHash] new SeqHash object of the aligned @dna_hash, the title has "_aligned"
@@ -1214,6 +1300,28 @@ module ViralSeq
       return new_sh
     end
 
+    # QC for each nucleotide sequence comparing with sample consensus for indels
+    # @return [Hash] object containing two SeqHash {no_indel: seq_hash, has_indel: seq_hash}
+
+    def qc_indel
+      con = self.consensus
+      dna_hash = self.dna_hash
+      names_passed = []
+      names_indel = []
+      dna_hash.uniq_hash.each do |seq, names|
+        if seq.compare_with(con) < 4
+          names_passed += names
+        elsif ViralSeq::Muscle.align(con, seq)[0]["-"]
+          names_indel += names
+        else
+          names_passed += names
+        end
+      end
+      return {no_indel: self.sub(names_passed),
+        has_indel: self.sub(names_indel)}
+    end # end of qc_indel
+
+
     # trim dna sequences based on the provided reference coordinates.
     # @param start_nt [Integer,Range,Array] start nt position(s) on the refernce genome, can be single number (Integer) or a range of Integers (Range), or an Array
     # @param end_nt [Integer,Range,Array] end nt position(s) on the refernce genome,can be single number (Integer) or a range of Integers (Range), or an Array

data/lib/viral_seq/tcs_core.rb

@@ -280,6 +280,19 @@ module ViralSeq
         abort infor.red.bold
       end
 
+      # lower detection sensitivity for minority mutations given the number of TCS, calculated based on binomial distribution.
+      # R required.
+      # @param tcs_number [Integer] number of TCS
+      # @return [Float] lower detection limit
+      # @example calculate lower detection limit
+      #   ViralSeq::TcsCore.detection_limit(100)
+      #   => 0.0362
+
+      def detection_limit(tcs_number)
+        dl =  `Rscript -e "library(dplyr); ifelse(#{tcs_number} > 2, (binom.test(0,#{tcs_number})['conf.int'] %>% unlist %>% unname)[2] %>% round(4) %>% cat, 0)" 2>/dev/null`
+        dl.to_f
+      end
+
       private
 
       def unzip_r(indir, f)

data/lib/viral_seq/version.rb

@@ -2,6 +2,6 @@
 # version info and histroy
 
 module ViralSeq
-  VERSION = "1.4.0"
-  TCS_VERSION = "2.3.8"
+  VERSION = "1.5.0"
+  TCS_VERSION = "2.4.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: viral_seq
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.5.0
 platform: ruby
 authors:
 - Shuntai Zhou
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-10-14 00:00:00.000000000 Z
+date: 2022-01-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler