snp-search 2.10.0 → 2.10.2

data/VERSION

@@ -1 +1 @@
-2.10.0
+2.10.2

data/bin/snp-search

@@ -1,28 +1,26 @@
 require 'snp-search'
-require 'snp_db_connection.rb'
-require 'snp_db_models.rb'
-require 'snp_db_schema.rb'
-require 'output_information_methods.rb'
+require 'snp_db_connection'
+require 'snp_db_models'
+require 'snp_db_schema'
+require 'output_information_methods'
 require 'activerecord-import'
 require 'slop'
 
+# README file: https://github.com/phe-bioinformatics/snp-search/blob/master/README.rdoc'
+
 opts = Slop.parse do
 
-  banner "\nruby snp-search [-create] [-output] [-n <sqlite3>] [options]*"
+  banner "\nruby snp-search [-create] [-output] [-d <sqlite3>] [options]*"
 
   separator ''
 
   on :C, :create, 'Create database'
   on :O, :output, 'Output a process'
-
-  # separator ''
-  # # separator 'README file: https://github.com/hpa-bioinformatics/snp-search/blob/master/README.rdoc'
-  # # separator 'The following command must be used when using -create, or -query or -out_file'
-  # on :n, :name_of_database=, 'Name of database, Required'
-
+  
   separator ''
   
-  separator '-create -r reference_file.fasta -v vcf_file.vcf -d db.sqlite3'
+  separator '-create -r reference_file.gbk (or .embl) -v vcf_file.vcf -d db.sqlite3'
+  separator 'e.g. snp-search -C -r ecoli.gbk -v ecoli.vcf -d ecoli.sqlite3'
   on :r, :reference_file=, 'Reference genome file, in gbk or embl file format, Required', true
   on :v, :vcf_file=, 'variant call format (vcf) file, Required', true
   on :d, :name_of_database=, 'Name of database, Required'
@@ -30,8 +28,9 @@ opts = Slop.parse do
 
   separator ''
  
-  separator '-output -all_or_filtered_snps -d db.sqlite3 [options]'
-  on :f, :all_or_filtered_snps, 'SNPs from specified features in the database (if you do not want to ignore any SNPs, just use this option with -n -F/T -o)'
+  separator '-output -all_or_filtered_snps -d db.sqlite3 -T|-F [options]'
+  separator 'e.g. snp-search -O -f -F -d ecoli.sqlite3 -R -I phage,insertion,transposon -o ecoli_concatenated_snps_filtered.fasta'
+  on :f, :all_or_filtered_snps, 'ignore SNPs from specified features in the database (if you do not want to ignore any SNPs, just use this option with -F/T -o)'
   on :F, :fasta, 'output fasta file format (default)'
   on :T, :tabular, 'output tabular file format'
   on :c, :cuttoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
@@ -39,13 +38,14 @@ opts = Slop.parse do
   on :R, :remove_non_informative_snps, 'Only output informative SNPs.'
   on :e, :ignore_snps_in_range=, 'A list of position ranges to ignore e.g 10..500,2000..2500.'
   on :a, :ignore_strains=, 'A list of strains to ignore (seperate by comma e.g. S1,S4,S8 ).'
-  on :I, :ignore_snps_on_annotation=, 'The name of the feature(s) to ignore.  Features should be seperated by comma (e.g. phages,inserstion,transposons)'
+  on :I, :ignore_snps_on_annotation=, 'The name of the feature(s) to ignore.  Features should be seperated by comma (e.g. phage,inserstion,transposon)'
   on :o, :out=, 'Name of output file, Required'
   on :t, :tree, 'Generate SNP phylogeny (only used with -fasta option)'
   on :p, :fasttree_path=, 'Full path to the FastTree tool (e.g. /usr/local/bin/FastTree. only used with -tree option)'
   separator ''
 
-  separator '-output -unique_snps -d db.sqlite3 [options]'
+  separator '-output -unique_snps -d db.sqlite3 -s strains.txt -o unique_snps.txt [options]'
+  separator 'e.g. snp-search -O -u -d ecoli.sqlite3 -s strains_list_for_unique_snps.txt -o ecoli_unique_snps_strains.txt'
   on :u, :unique_snps, 'Query for unique snps in the database'  
   on :c, :cuttoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
   on :g, :cuttoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30
@@ -54,7 +54,8 @@ opts = Slop.parse do
 
   separator ''
 
-  separator '-output -info -d db.sqlite3 [options]'
+  separator '-output -info -d db.sqlite3 -o info.txt [options]'
+  separator ''
   on :i, :info, 'Output various information about SNPs'
   on :c, :cuttoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
   on :g, :cuttoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30

data/lib/output_information_methods.rb

@@ -19,7 +19,7 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
       snp.alleles.each do |allele|
         next if snp.alleles.any?{|allele| allele.base.length > 1} # indel
         if allele.id != snp.reference_allele_id
-          
+          snps_counter += 1
           # get annotation (if there is any) for each SNP
           features = Feature.joins(:snps).where("snps.id = ?", snp.id)
           
@@ -37,7 +37,7 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
           ref_base = Bio::Sequence.auto(Allele.find(snp.reference_allele_id).base)
           snp_base = Bio::Sequence.auto(allele.base)
           # count snps now: after you have selected the snps with gqs and snp_qual greater than the threshold.
-          snps_counter += 1
+          
           # If the feature is empty then just output basic information about the snp.
 
           if features.empty?
@@ -114,7 +114,7 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
                       total_number_of_pseudo +=1
                       outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tnon-synonymous\t#{annotation.value}\tYes\t#{diffs[0][0].element}\t#{diffs[0][1].element}\t#{'Yes' if (hydrophobic.include? diffs[0][0].element) == (non_hydrophobic.include? diffs[0][1].element)}#{'No' if (hydrophobic.include? diffs[0][0].element) != (non_hydrophobic.include? diffs[0][1].element)}\t#{'Yes' if (polar.include? diffs[0][0].element) == (non_polar.include? diffs[0][1].element)}#{'No' if (polar.include? diffs[0][0].element) != (non_polar.include? diffs[0][1].element)}\t#{'Yes' if (small.include? diffs[0][0].element) == (non_small.include? diffs[0][1].element)}#{'No' if (small.include? diffs[0][0].element) != (non_small.include? diffs[0][1].element)}\t#{alleles_array.join("\t") if info}"
                     else
-                      outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tnon-synonymous\t#{annotation.value}\tNo\t#{diffs[0][0].element}\t#{diffs[0][1].element}\t#{'Yes' if (hydrophobic.include? diffs[0][0].element) == (non_hydrophobic.include? diffs[0][1].element)}#{'No' if (hydrophobic.include? diffs[0][0].element) != (non_hydrophobic.include? diffs[0][1].element)}\t#{'Yes' if (polar.include? diffs[0][0].element) == (non_polar.include? diffs[0][1].element)}#{'No' if (polar.include? diffs[0][0].element) != (non_polar.include? diffs[0][1].element)}\t#{'Yes' if (small.include? diffs[0][0].element) == (non_small.include? diffs[0][1].element)}#{'No' if (small.include? diffs[0][0].element) != (non_small.include? diffs[0][1].element)}\t#{alleles_array.join("\t") if info}"
+                      outfile.puts "#{snp.ref_pos-1}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tnon-synonymous\t#{annotation.value}\tNo\t#{diffs[0][0].element}\t#{diffs[0][1].element}\t#{'Yes' if (hydrophobic.include? diffs[0][0].element) == (non_hydrophobic.include? diffs[0][1].element)}#{'No' if (hydrophobic.include? diffs[0][0].element) != (non_hydrophobic.include? diffs[0][1].element)}\t#{'Yes' if (polar.include? diffs[0][0].element) == (non_polar.include? diffs[0][1].element)}#{'No' if (polar.include? diffs[0][0].element) != (non_polar.include? diffs[0][1].element)}\t#{'Yes' if (small.include? diffs[0][0].element) == (non_small.include? diffs[0][1].element)}#{'No' if (small.include? diffs[0][0].element) != (non_small.include? diffs[0][1].element)}\t#{alleles_array.join("\t") if info}"
                     end
                   end
                 end

data/snp-search.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "snp-search"
-  s.version = "2.10.0"
+  s.version = "2.10.2"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Ali Al-Shahib", "Anthony Underwood"]
@@ -37,6 +37,7 @@ Gem::Specification.new do |s|
     "lib/snp_db_schema.rb",
     "pkg/snp-search-1.1.0.gem",
     "pkg/snp-search-1.2.0.gem",
+    "pkg/snp-search-2.10.0.gem",
     "pkg/snp-search-2.3.0.gem",
     "pkg/snp-search-2.4.0.gem",
     "pkg/snp-search-2.5.0.gem",

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: snp-search
 version: !ruby/object:Gem::Version
-  version: 2.10.0
+  version: 2.10.2
   prerelease: 
 platform: ruby
 authors:
@@ -201,6 +201,7 @@ files:
 - lib/snp_db_schema.rb
 - pkg/snp-search-1.1.0.gem
 - pkg/snp-search-1.2.0.gem
+- pkg/snp-search-2.10.0.gem
 - pkg/snp-search-2.3.0.gem
 - pkg/snp-search-2.4.0.gem
 - pkg/snp-search-2.5.0.gem
@@ -226,7 +227,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -814863516568107020
+      hash: -4259340875047454544
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: