viral_seq 1.6.4 → 1.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 02d26d720fef0501d70b012d9919f932b23a21b1caabbf508a56fffa162c311b
-  data.tar.gz: '0681add2b2fa2ca7dedffeaaf43bd8b0e2b6200dd38633e2eeda58946ced8238'
+  metadata.gz: 8be7a521e58d5335122db011b5f003407cfaab95480062337451377ee2fdfca9
+  data.tar.gz: 5c437afa58d63d0bde9dc6acf6c98904b8a7b364618fb3ebebd2cb36a44daa2c
 SHA512:
-  metadata.gz: 301c188d736c9812006d30db8995fa7df683cc63443c1370de3d487dae77b88cfc60c8b674abc93b35f7457ced536a6e374433e5fbe0f423e4a7993ea4240ebc
-  data.tar.gz: 1118ab7b586da98bb2c3533f81c35a02f0efb1978c0b91e15b56218b05342ad83e73f96bd2df53f75e2e6cdd16c591582ebe864562a02d3dd78997678b706233
+  metadata.gz: 23622009f3f39961e3d2d760bdde3b9f9b831d001aca68b6eee3d44305a77d3e964c48541811fd9dddc26ad9427383716ccdc64436789b01eb11c51f762d2a6b
+  data.tar.gz: c1a1ac49930c24f61bfa0872f518fea8146e701a5a874de45e373d4d3d20eca50d138bd44f9d59ea1102d525b392dd9b6ed053647b1c25d97ad0244eb4fe15ff

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    viral_seq (1.6.2)
+    viral_seq (1.6.5)
       colorize (~> 0.1)
       combine_pdf (~> 1.0, >= 1.0.0)
       muscle_bio (~> 0.5)

data/README.md

@@ -10,6 +10,8 @@ A Ruby Gem containing bioinformatics tools for processing viral NGS data.
 
 Specifically for Primer ID sequencing and HIV drug resistance analysis.
 
+CLI tools `tcs`, `tcs_sdrm`, `tcs_log` and `locator` included in the gem. 
+
 #### tcs web app - https://primer-id.org/
 
 ## Illustration for the Primer ID Sequencing
@@ -22,6 +24,12 @@ Specifically for Primer ID sequencing and HIV drug resistance analysis.
 [Primer ID MiSeq protocol](https://doi.org/10.1128/JVI.00522-15)  
 [Application of Primer ID sequencing in COVID-19 research](https://doi.org/10.1126/scitranslmed.abb5883)
 
+## Requirements
+
+Required Ruby Version: >= 2.5
+
+Required RubyGems version: >= 1.3.6
+
 ## Install
 
 ```bash
@@ -179,6 +187,11 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
 
 ## Updates
 
+### Version-1.7.0-08242022
+
+  1. Add warnings if `tcs` pipeline is excecuting through source instead of installing from `gem`. 
+  2. Optimized `ViralSeq:SeqHash#a3g` hypermut algorithm. Allowing a external reference other than the sample reference. 
+
 ### Version-1.6.4-07182022
 
   1. Included region "P17" in the default `tcs -d` pipeline setting. `tcs` pipeline updated to version 2.5.1. 

data/bin/tcs

@@ -22,20 +22,38 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 # THE SOFTWARE.
 
+# Install using `gem install viral_seq`
 # Use JSON file as the run param
 # run `tcs -j` to generate param json file.
 
-require 'viral_seq'
+def gem_installed?(gem_name)
+  found_gem = false
+  begin
+    found_gem = Gem::Specification.find_by_name(gem_name)
+  rescue Gem::LoadError
+    return false   
+  else
+    return true 
+  end
+end
+
+if gem_installed?('viral_seq')
+  require 'viral_seq'
+else 
+  printf "\n****************************************************\n"
+  printf "**** THIS PACKAGE CANNOT BE RAN FROM SOURCE ********\n"
+  printf "**** PLEASE INSTALL USING `gem install viral_seq` **\n"
+  printf "****************************************************\n\n"
+  exit 1
+end
+
+
 require 'json'
 require 'colorize'
 require 'optparse'
 
 options = {}
 
-# banner = '-'*50 + "\n" +
-#         '| The TCS Pipeline ' + "Version #{ViralSeq::TCS_VERSION}".red.bold + " by " + "Shuntai Zhou".blue.bold + ' |' + "\n" +
-#         '-'*50 + "\n"
-
 banner = "\n" +
 "████████  ██████ ███████     ██████  ██ ██████  ███████ ██      ██ ███    ██ ███████\n".light_red +
 "   ██    ██      ██          ██   ██ ██ ██   ██ ██      ██      ██ ████   ██ ██\n".light_yellow +

data/lib/viral_seq/seq_hash.rb

@@ -450,7 +450,7 @@ module ViralSeq
     # function to determine if the sequences have APOBEC3g/f hypermutation.
     #   # APOBEC3G/F pattern: GRD -> ARD
     #   # control pattern: G[YN|RC] -> A[YN|RC]
-    #   # use the sample consensus to determine potential a3g sites
+    #   # use the sample consensus to determine potential a3g sites (default) or provide external reference sequences as a `String`
     #   # Two criteria to identify hypermutation
     #   # 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
@@ -486,7 +486,7 @@ module ViralSeq
     #   # but it is still called as hypermutation sequence b/c it's Poisson outlier sequence.
     # @see https://www.hiv.lanl.gov/content/sequence/HYPERMUT/hypermut.html LANL Hypermut
 
-    def a3g_hypermut
+    def a3g_hypermut(ref = nil)
       # mut_hash number of apobec3g/f mutations per sequence
       mut_hash = {}
       hm_hash = {}
@@ -495,8 +495,10 @@ module ViralSeq
       # total G->A mutations at apobec3g/f positions.
       total = 0
 
-      # make consensus sequence for the input sequence hash
-      ref = self.consensus
+      unless ref 
+        # make consensus sequence for the input sequence hash
+        ref = self.consensus
+      end
 
       # obtain apobec3g positions and control positions
       apobec = apobec3gf(ref)
@@ -509,7 +511,6 @@ module ViralSeq
         c = 0 # control muts
         d = 0 # potenrial controls
         mut.each do |n|
-          next if v[n] == "-"
           if v[n] == "A"
             a += 1
             b += 1
@@ -521,7 +522,6 @@ module ViralSeq
         total += a
 
         control.each do |n|
-          next if v[n] == "-"
           if v[n] == "A"
             c += 1
             d += 1
@@ -544,7 +544,7 @@ module ViralSeq
         end
       end
 
-      if self.dna_hash.size > 20
+      if self.dna_hash.size > 200
         rate = total.to_f/(self.dna_hash.size)
         count_mut = mut_hash.values.count_freq
         maxi_count = count_mut.values.max
@@ -566,10 +566,12 @@ module ViralSeq
           end
         end
       end
+
       hm_seq_hash = ViralSeq::SeqHash.new
       hm_hash.each do |k,_v|
         hm_seq_hash.dna_hash[k] = self.dna_hash[k]
       end
+    
       hm_seq_hash.title = self.title + "_hypermut"
       hm_seq_hash.file = self.file
       filtered_seq_hash = self.sub(self.dna_hash.keys - hm_hash.keys)
@@ -1356,7 +1358,7 @@ module ViralSeq
     # APOBEC3G/F pattern: GRD -> ARD,
     # control pattern: G[YN|RC] -> A[YN|RC],
     def apobec3gf(seq = '')
-      seq.tr!("-", "")
+      #seq.tr!("-", "")
       seq_length = seq.size
       apobec_position = []
       control_position = []
@@ -1368,6 +1370,7 @@ module ViralSeq
           control_position << n
         end
       end
+
       return [apobec_position,control_position]
     end # end of #apobec3gf
 

data/lib/viral_seq/version.rb

@@ -2,6 +2,6 @@
 # version info and histroy
 
 module ViralSeq
-  VERSION = "1.6.4"
+  VERSION = "1.7.0"
   TCS_VERSION = "2.5.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: viral_seq
 version: !ruby/object:Gem::Version
-  version: 1.6.4
+  version: 1.7.0
 platform: ruby
 authors:
 - Shuntai Zhou
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-07-19 00:00:00.000000000 Z
+date: 2022-08-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -193,7 +193,6 @@ files:
 - lib/viral_seq/tcs_dr.rb
 - lib/viral_seq/tcs_json.rb
 - lib/viral_seq/version.rb
-- rc_swans.svc@longleaf.unc.edu
 - viral_seq.gemspec
 homepage: https://github.com/ViralSeq/viral_seq
 licenses: