cheripic 1.1.0 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 458f681424a73ea58acb8aefa73d68019ad0854d
-  data.tar.gz: 23547939b1fead465d06d2f6d8e45ce4172b1cb1
+  metadata.gz: 958b4091f2c95903c3a43a13af7d75cbc7605813
+  data.tar.gz: 18b91af8e68553f4d1700dae921beb7e420f11ac
 SHA512:
-  metadata.gz: 2e3af0df95197769c542b4aab76444a6b14842890b46a97d6be10101f267db5f5df7d1ed8d67083ac8890a866e1cab678a9b23c5dc03b1edb7b8fc2150b35097
-  data.tar.gz: 9aa159df9086102679bd6359d4a5bf94dfe72f52d9c11e66259ffd40754f767001bb2a67e996b958018a009db0a6aa558c7ebe4001c2f6bce9b8993bdfd66091
+  metadata.gz: 7290c13e270aae1a777767179168353c5c55a035bfd6e82025d000414112425e77f59ad7a6fd0c736d2d2775182e17f978ffa6b67153201e9d316458a6360db6
+  data.tar.gz: 595be6e01fdc4e0d6185a86f79f207abb2dc6bf50a8763a67186339e639542294185656b204cde8d86cda2f3519f7ae3341443a978f9f019c51cfef294513694

data/.travis.yml

@@ -1,4 +1,4 @@
 language: ruby
 rvm:
-  - 2.2.1
-before_install: gem install bundler -v 1.10.6
+  - 2.1.5
+before_install: gem install bundler -v 1.7.6

data/Gemfile

@@ -1,4 +1,5 @@
 source 'https://rubygems.org'
+ruby '2.1.5'
 
 # Specify your gem's dependencies in cheripic.gemspec
 gemspec

data/README.md

@@ -15,6 +15,15 @@ Currently this gem is still in development and nearing complete working package.
         
 ## Installation
 
+Cheripic is available both as a command line tool and as a gem.     
+Binaries are available for Linux 64bit and OSX.      
+Best way to use Cheripic is to download appropriate binary arhcive      
+unpack (`tar -xzf`) and add the unpacked directory to your `PATH`       
+
+Latest binaries are available to [download here](https://github.com/shyamrallapalli/cheripic/releases/tag/v1.1.0)       
+
+
+To install gem and use the gem in your development     
 Add this line to your application's Gemfile:
 
 ```ruby
@@ -31,7 +40,72 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+Running `cheripic` without any input at command line interface shows following help options
+
+```
+
+Cheripic v1.1.0
+Authors: Shyam Rallapalli and Dan MacLean
+
+Description: Candidate mutation and closely linked marker selection for non reference genomes
+Uses bulk segregant data from non-reference sequence genomes
+
+Inputs:
+1. Needs a reference fasta file of asssembly use for variant analysis
+2. Pileup files for mutant (phenotype of interest) bulks and background (wildtype phenotype) bulks
+3. If polyploid species, include of pileup from one or both parents
+
+USAGE:
+cheripic <options>
+
+OPTIONS:
+  -f, --assembly=<s>                                 Assembly file in FASTA format
+  -F, --input-format=<s>                             bulk and parent alignment file format types - set either pileup or bam (default: pileup)
+  -a, --mut-bulk=<s>                                 Pileup or sorted BAM file alignments from mutant/trait of interest bulk 1
+  -b, --bg-bulk=<s>                                  Pileup or sorted BAM file alignments from background/wildtype bulk 2
+  --output=<s>                                       Directory to store results, will be created if not existing (default: cheripic_results)
+  --loglevel=<s>                                     Choose any one of "info / warn / debug" level for logs generated (default: debug)
+  --hmes-adjust=<f>                                  factor added to snp count of each contig to adjust for hme score calculations (default: 0.5)
+  --htlow=<f>                                        lower level for categorizing heterozygosity (default: 0.2)
+  --hthigh=<f>                                       high level for categorizing heterozygosity (default: 0.9)
+  --mindepth=<i>                                     minimum read depth to conisder a position for variant calls (default: 6)
+  --min-non-ref-count=<i>                            minimum read depth supporting non reference base at each position (default: 3)
+  --min-indel-count-support=<i>                      minimum read depth supporting an indel at each position (default: 3)
+  --ignore-reference-n, --no-ignore-reference-n      ignore variant calls at N (completely ambigous) bases in the reference (default: true)
+  -q, --mapping-quality=<i>                          minimum mapping quality of read covering the position (default: 20)
+  -Q, --base-quality=<i>                             minimum base quality of bases covering the position (default: 15)
+  --noise=<f>                                        praportion of reads for a variant to conisder as noise (default: 0.1)
+  --cross-type=<s>                                   type of cross used to generated mapping population - back or out (default: back)
+  --only-frag-with-vars, --no-only-frag-with-vars    select only contigs containing variants for analysis (default: true)
+  --filter-out-low-hmes, --no-filter-out-low-hmes    ignore variants from contigs with low hmescore or bfr to list in the final output (default: true)
+  --polyploidy                                       Set if the data input is from polyploids
+  -p, --mut-parent=<s>                               Pileup or sorted BAM file alignments from mutant/trait of interest parent (default: )
+  -r, --bg-parent=<s>                                Pileup or sorted BAM file alignments from background/wildtype parent (default: )
+  --bfr-adjust=<f>                                   factor added to hemi snp frequency of each parent to adjust for bfr calculations (default: 0.05)
+  --examples                                         shows some example commands with explanation
+
+```
+        
+        
+        
+Example Commands
+
+
+```
+EXAMPLE COMMANDS:
+  1. cheripic -f assembly.fa -a mutbulk.pileup -b bgbulk.pileup --output=cheripic_output
+  2. cheripic --assembly assembly.fa --mut-bulk mutbulk.pileup --bg-bulk bgbulk.pileup 
+        --mut-parent mutparent.pileup --bg-parent bgparent.pileup --polyploidy true --output cheripic_results
+  3. cheripic --assembly assembly.fa --mut-bulk mutbulk.pileup --bg-bulk bgbulk.pileup 
+        --mut-parent mutparent.pileup --bg-parent bgparent.pileup --polyploidy true 
+        --no-only-frag-with-vars --no-filter-out-low-hmes --output cheripic_results
+
+```
+
+
+By default contigs with out a variant and thos contigs with lower scores are discarded. 
+      so use options `--no-only-frag-with-vars` and `--no-filter-out-low-hmes` to disable them 
+
 
 ## Development
 

data/Rakefile

@@ -1,10 +1,78 @@
-require "bundler/gem_tasks"
-require "rake/testtask"
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+# For Bundler.with_clean_env
+require 'bundler/setup'
 
 Rake::TestTask.new(:test) do |t|
-  t.libs << "test"
-  t.libs << "lib"
+  t.libs << 'test'
+  t.libs << 'lib'
   t.test_files = FileList['test/**/*_test.rb']
 end
 
 task :default => :test
+
+
+# for packaging
+
+PACKAGE_NAME = 'cheripic'
+VERSION = `bundle exec bin/cheripic -v`.chomp
+TRAVELING_RUBY_VERSION = '20150210-2.1.5'
+
+# pre-downloaded travelling ruby from following links and placed them in 'packaging' dirctory
+# http://d6r77u77i8pq3.cloudfront.net/releases/traveling-ruby-20150210-2.1.5-linux-x86_64.tar.gz
+# http://d6r77u77i8pq3.cloudfront.net/releases/traveling-ruby-20150210-2.1.5-osx.tar.gz
+
+desc 'Package your app'
+task :package => ['package:linux:x86_64', 'package:osx']
+
+namespace :package do
+
+  namespace :linux do
+    desc 'Package your app for Linux x86_64'
+    task :x86_64 => [:bundle_install, "packaging/traveling-ruby-#{TRAVELING_RUBY_VERSION}-linux-x86_64.tar.gz"] do
+      create_package('linux-x86_64')
+    end
+  end
+
+  desc 'Package your app for OS X'
+  task :osx => [:bundle_install, "packaging/traveling-ruby-#{TRAVELING_RUBY_VERSION}-osx.tar.gz"] do
+    create_package('osx')
+  end
+
+  desc 'Install gems to local directory'
+  task :bundle_install do
+    if RUBY_VERSION !~ /^2\.1\./
+      abort "You can only 'bundle install' using Ruby 2.1, because that's what Traveling Ruby uses."
+    end
+    sh 'rm -rf packaging/tmp'
+    sh 'mkdir packaging/tmp'
+    sh 'cp Gemfile.lock packaging/tmp/'
+    sh 'cp packaging/Gemfile packaging/tmp/'
+    Bundler.with_clean_env do
+      sh 'env BUNDLE_IGNORE_CONFIG=1 bundle install --path packaging/vendor --without development'
+    end
+    sh 'rm -rf packaging/tmp'
+    sh 'rm -f packaging/vendor/*/*/cache/*'
+  end
+end
+
+def create_package(target)
+  package_dest = "#{PACKAGE_NAME}-#{VERSION}-#{target}"
+  package_dir = "packaging/#{package_dest}"
+  sh "rm -rf #{package_dir}"
+  sh "mkdir #{package_dir}"
+  sh "mkdir -p #{package_dir}/lib/app"
+  sh "cp -R bin #{package_dir}/lib/app/"
+  sh "cp -R lib #{package_dir}/lib/app/"
+  sh "mkdir #{package_dir}/lib/app/ruby"
+  sh "tar -xzf packaging/traveling-ruby-#{TRAVELING_RUBY_VERSION}-#{target}.tar.gz -C #{package_dir}/lib/app/ruby"
+  sh "cp packaging/wrapper.sh #{package_dir}/cheripic"
+  sh "cp -pR packaging/vendor/ruby/2.1.0 #{package_dir}/lib/app/ruby/"
+  sh "cp packaging/cheripic.gemspec Gemfile Gemfile.lock LICENSE.txt #{package_dir}/lib/app/"
+  sh "mkdir #{package_dir}/lib/app/.bundle"
+  sh "cp packaging/bundler-config #{package_dir}/lib/app/.bundle/config"
+  # if !ENV['DIR_ONLY']
+  #   sh "tar -czf #{package_dir}.tar.gz #{package_dir}"
+  #   sh "rm -rf #{package_dir}"
+  # end
+end

data/lib/cheripic/cmd.rb

@@ -40,6 +40,7 @@ module Cheripic
     def argument_parser
       cmds = self
       Trollop::Parser.new do
+        version Cheripic::VERSION
         banner cmds.help_message
         opt :assembly, 'Assembly file in FASTA format',
             :short => '-f',
@@ -76,9 +77,9 @@ module Cheripic
         opt :min_indel_count_support, 'minimum read depth supporting an indel at each position',
             :type => Integer,
             :default => 3
-        opt :ignore_reference_n, 'ignore variant calls at N (completely ambigous) bases in the reference',
+        opt :ambiguous_ref_bases, 'including variant at completely ambiguous bases in the reference',
             :type => FalseClass,
-            :default => true
+            :default => false
         opt :mapping_quality, 'minimum mapping quality of read covering the position',
             :short => '-q',
             :type => Integer,
@@ -93,12 +94,12 @@ module Cheripic
         opt :cross_type, 'type of cross used to generated mapping population - back or out',
             :type => String,
             :default => 'back'
-        opt :only_frag_with_vars, 'select only contigs containing variants for analysis',
+        opt :use_all_contigs, 'option to select all contigs or only contigs containing variants for analysis',
             :type => FalseClass,
-            :default => true
-        opt :filter_out_low_hmes, 'ignore variants from contigs with low hmescore or bfr to list in the final output',
+            :default => false
+        opt :include_low_hmes, 'option to include or discard variants from contigs with low hme-score or bfr score to list in the final output',
             :type => FalseClass,
-            :default => true
+            :default => false
         opt :polyploidy, 'Set if the data input is from polyploids',
             :type => FalseClass,
             :default => false
@@ -113,6 +114,9 @@ module Cheripic
         opt :bfr_adjust, 'factor added to hemi snp frequency of each parent to adjust for bfr calculations',
             :type => Float,
             :default => 0.05
+        opt :sel_seq_len, 'sequence length to print from either side of selected variants',
+            :type => Integer,
+            :default => 50
         opt :examples, 'shows some example commands with explanation'
       end
     end
@@ -148,7 +152,12 @@ module Cheripic
         Cheripic v#{Cheripic::VERSION.dup}
 
         EXAMPLE COMMANDS:
-
+          1. cheripic -f assembly.fa -a mutbulk.pileup -b bgbulk.pileup --output=cheripic_output
+          2. cheripic --assembly assembly.fa --mut-bulk mutbulk.pileup --bg-bulk bgbulk.pileup
+                --mut-parent mutparent.pileup --bg-parent bgparent.pileup --polyploidy true --output cheripic_results
+          3. cheripic --assembly assembly.fa --mut-bulk mutbulk.pileup --bg-bulk bgbulk.pileup
+                --mut-parent mutparent.pileup --bg-parent bgparent.pileup --polyploidy true
+                --no-only-frag-with-vars --no-filter-out-low-hmes --output cheripic_results
       EOS
       puts msg.split("\n").map{ |line| line.lstrip }.join("\n")
       exit(0)

data/lib/cheripic/contig_pileups.rb

@@ -131,12 +131,14 @@ module Cheripic
     # @return [Symbol] variant mode of the background bulk (:hom or :het) at the position
     def bg_bulk_var(pos)
       bg_base_hash = @bg_bulk[pos].var_base_frac
+      bg_base_hash.delete(:ref)
+      return nil if bg_base_hash.empty?
       if bg_base_hash.length > 1
         # taking only var mode
         var_mode(bg_base_hash.values.max)
       else
         # taking only var mode
-        var_mode(bg_base_hash[0])
+        var_mode(bg_base_hash[bg_base_hash.keys[0]])
       end
     end
 

data/lib/cheripic/implementer.rb

@@ -36,13 +36,13 @@ module Cheripic
                 mindepth
                 min_non_ref_count
                 min_indel_count_support
-                ignore_reference_n
+                ambiguous_ref_bases
                 mapping_quality
                 base_quality
                 noise
                 cross_type
-                only_frag_with_vars
-                filter_out_low_hmes
+                use_all_contigs
+                include_low_hmes
                 polyploidy
                 bfr_adjust}
       settings = inputs.select { |k| set2.include?(k) }

data/lib/cheripic/options.rb

@@ -14,13 +14,13 @@ module Cheripic
         :mindepth => 6,
         :min_non_ref_count => 3,
         :min_indel_count_support => 3,
-        :ignore_reference_n => true,
+        :ambiguous_ref_bases => false,
         :mapping_quality => 20,
         :base_quality => 15,
         :noise => 0.1,
         :cross_type => 'back',
-        :only_frag_with_vars => true,
-        :filter_out_low_hmes => true,
+        :use_all_contigs => false,
+        :include_low_hmes => false,
         :polyploidy => false,
         :bfr_adjust => 0.05,
         :sel_seq_len => 50
@@ -66,9 +66,10 @@ module Cheripic
     end
 
     # Option to whether to ignore or consider the reference positions which are ambiguous
+    # @note switching option name here so Pileup options are same
     # @return [Boolean]
     def self.ignore_reference_n
-      @user_settings[:ignore_reference_n]
+      @user_settings[:ambiguous_ref_bases] ? false : true
     end
 
     # Minimum alignment mapping quality of the read to be used for bam files
@@ -98,14 +99,14 @@ module Cheripic
 
     # Option to whether to ignore or consider the contigs with out any variants
     # @return [Boolean]
-    def self.only_frag_with_vars
-      @user_settings[:only_frag_with_vars]
+    def self.use_all_contigs
+      @user_settings[:use_all_contigs]
     end
 
     # Option to whether to ignore or consider the contigs with low HME score
     # @return [Boolean]
-    def self.filter_out_low_hmes
-      @user_settings[:filter_out_low_hmes]
+    def self.include_low_hmes
+      @user_settings[:include_low_hmes]
     end
 
     # Option to whether to set the input data is from polyploid or not

data/lib/cheripic/variants.rb

@@ -119,15 +119,17 @@ module Cheripic
     end
 
     # Applies selection procedure on assembly contigs based on the ratio_type provided.
-    # If only_frag_with_vars is set to true then contigs without any variant are discarded for :hme_score
+    # If use_all_contigs is set to false then contigs without any variant are discarded for :hme_score
     # while contigs without any hemisnps are discarded for :bfr_score
-    # If filter_out_low_hmes is set to true then contigs are further filtered based on a cut off value of the score
+    # If include_low_hmes is set to false then contigs are further filtered based on a cut off value of the score
     # @param ratio_type [Symbol] ratio_type is either :hme_score or :bfr_score
     def select_contigs(ratio_type)
       selected_contigs ={}
-      only_frag_with_vars = Options.only_frag_with_vars
+      use_all_contigs = Options.use_all_contigs
       @assembly.each_key do | frag |
-        if only_frag_with_vars
+        if use_all_contigs
+          selected_contigs[frag] = @assembly[frag]
+        else
           if ratio_type == :hme_score
             # selecting fragments which have a variant
             if @assembly[frag].hm_num + @assembly[frag].ht_num > 2 * Options.hmes_adjust
@@ -139,15 +141,13 @@ module Cheripic
               selected_contigs[frag] = @assembly[frag]
             end
           end
-        else
-          selected_contigs[frag] = @assembly[frag]
         end
       end
       selected_contigs = filter_contigs(selected_contigs, ratio_type)
-      if only_frag_with_vars
-        logger.info "Selected #{selected_contigs.length} out of #{@assembly.length} fragments with #{ratio_type} score\n"
-      else
+      if use_all_contigs
         logger.info "No filtering was applied to fragments\n"
+      else
+        logger.info "Selected #{selected_contigs.length} out of #{@assembly.length} fragments with #{ratio_type} score\n"
       end
       selected_contigs
     end
@@ -171,11 +171,13 @@ module Cheripic
     # @param ratio_type [Symbol] ratio_type is either :hme_score or :bfr_score
     # @param selected_contigs [Hash] a hash of contigs with selected ratio_type, a subset of assembly hash
     def get_cutoff(selected_contigs, ratio_type)
-      filter_out_low_hmes = Options.filter_out_low_hmes
+      include_low_hmes = Options.include_low_hmes
       # set minimum cut off hme_score or bfr_score to pick fragments with variants
       # calculate min hme score for back or out crossed data or bfr_score for polypoidy data
       # if no filtering applied set cutoff to 1.1
-      if filter_out_low_hmes
+      if include_low_hmes
+        cutoff = 0.0
+      else
         if ratio_type == :hme_score
           adjust = Options.hmes_adjust
           if Options.cross_type == 'back'
@@ -186,8 +188,6 @@ module Cheripic
         else # ratio_type is bfr_score
           cutoff = bfr_cutoff(selected_contigs)
         end
-      else
-        cutoff = 0.0
       end
       cutoff
     end

data/lib/cheripic/version.rb

@@ -2,6 +2,6 @@ module Cheripic
 
   # Sets the semantic version number for this module.
   # Version number will be used in help messages and for generating gem.
-  VERSION = '1.1.0'
+  VERSION = '1.2.0'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cheripic
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Shyam Rallapalli
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-08-08 00:00:00.000000000 Z
+date: 2016-08-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: yell