cheripic 1.2.0 → 1.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 958b4091f2c95903c3a43a13af7d75cbc7605813
-  data.tar.gz: 18b91af8e68553f4d1700dae921beb7e420f11ac
+  metadata.gz: 824a8c68d3707ad02cf0d3b7d567191244d1a5a6
+  data.tar.gz: 6d2b3c7bef04aba06b5206968d1a0d69996a25b0
 SHA512:
-  metadata.gz: 7290c13e270aae1a777767179168353c5c55a035bfd6e82025d000414112425e77f59ad7a6fd0c736d2d2775182e17f978ffa6b67153201e9d316458a6360db6
-  data.tar.gz: 595be6e01fdc4e0d6185a86f79f207abb2dc6bf50a8763a67186339e639542294185656b204cde8d86cda2f3519f7ae3341443a978f9f019c51cfef294513694
+  metadata.gz: 6ae5a85c30a0b1ea19f118409ddec95a6c7c3e11f00663e9769a5642770e90cb2ab5b0200f9d9eaa4ed8c6873492ac7f5f3acd568dc0cc14ddf8ccaac5012435
+  data.tar.gz: efe77b2ccafd0ad7ed4eeb47b497207cacf3dbaee058779b46af7a5ca34597991a3949dbeb0f3807bba69ea7dca0dd7e24fb58c040bf0065fef2ca1e4e3424fc

data/ChangeLog.md

@@ -0,0 +1,21 @@
+### Change Log
+
+All significant changes to this project at each release are documented in this file.
+
+
+#### Future changes to include
+    
+    1. option to take multiple background pileup files
+    2. replace output directory with output file name tag, since we only write to one file
+    3. option to take bam file or pileup file as inputs of bulks
+
+#### [1.2.0] - 2016-08-11
+
+    1. fixed calculation of heterzygosity for background bulks
+    2. changed command line boolean option to be set using only true or false
+    3. included command line option to set length of sequnce to retireve on either side of each variant
+     
+    
+#### [1.1.0] - 2016-07-26
+
+    first release of the binaries for Linux 64 bit and OSX 64bit

data/Gemfile

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

data/README.md

@@ -11,6 +11,7 @@ Computing Homozygosity Enriched Regions In genomes to Prioritize Identification
 is a ruby tools to pick causative mutation from bulks segregant sequencing.     
         
 Currently this gem is still in development and nearing complete working package.
+And software only works with pileup as input files, use of bam and vcf files will be implemented in future
         
         
 ## Installation
@@ -20,7 +21,7 @@ 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)       
+Latest binaries are available to [download here](https://github.com/shyamrallapalli/cheripic/releases/latest)       
 
 
 To install gem and use the gem in your development     
@@ -44,7 +45,7 @@ Running `cheripic` without any input at command line interface shows following h
 
 ```
 
-Cheripic v1.1.0
+Cheripic v1.2.0
 Authors: Shyam Rallapalli and Dan MacLean
 
 Description: Candidate mutation and closely linked marker selection for non reference genomes
@@ -59,30 +60,31 @@ 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
+  -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)
+  --ambiguous-ref-bases            including variant at completely ambiguous bases in the reference
+  -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)
+  --use-all-contigs                option to select all contigs or only contigs containing variants for analysis
+  --include-low-hmes               option to include or discard variants from contigs with low hme-score or bfr score to list in the final output
+  --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)
+  --sel-seq-len=<i>                sequence length to print from either side of selected variants (default: 50)
+  --examples                       shows some example commands with explanation
 
 ```
         
@@ -98,7 +100,7 @@ EXAMPLE COMMANDS:
         --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
+        --use-all-contigs true --include-low-hmes true --output cheripic_results
 
 ```
 

data/Rakefile

@@ -23,7 +23,7 @@ TRAVELING_RUBY_VERSION = '20150210-2.1.5'
 # 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']
+task :package => %w(package:linux:x86_64 package:osx)
 
 namespace :package do
 
@@ -71,8 +71,12 @@ def create_package(target)
   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
+  if target == 'linux-x86_64'
+    sh "cp -p packaging/linux-x86_64_samtools/external/* packaging/cheripic-#{VERSION}-linux-x86_64/lib/app/ruby/2.1.0/gems/bio-samtools-2.4.0/lib/bio/db/sam/external/"
+  end
+  unless ENV['DIR_ONLY']
+    Dir.chdir('packaging') do
+      sh "gtar -czf #{package_dest}.tar.gz #{package_dest}"
+    end
+  end
 end

data/bin/cheripic

@@ -1,4 +1,5 @@
 #!/usr/bin/env ruby
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 require 'cheripic'
 
 # rescue errors to get clean error messages through the logger

data/cheripic.gemspec

@@ -23,8 +23,6 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency 'trollop', '~> 2.1', '>= 2.1.2'
   spec.add_runtime_dependency 'bio', '~> 1.5', '>= 1.5.0'
   spec.add_dependency 'bio-samtools', '~> 2.4.0'
-  spec.add_dependency 'bio-gngm', '~> 0.2.1'
-  spec.add_runtime_dependency 'rinruby', '~> 2.0', '>= 2.0.3'
 
   spec.add_development_dependency 'activesupport', '~> 4.2.6'
   spec.add_development_dependency 'bundler', '~> 1.7.6'

data/galaxy_cheripic_tool.xml

@@ -0,0 +1,196 @@
+<tool id="cheripic" name="CHERIPIC" version="1.2.0">
+
+  <description>CHERIPIC</description>
+
+  <version_command>cheripic -v</version_command>
+
+  <command>
+<![CDATA[
+    cheripic
+    --assembly $assembly
+    --mut-bulk $mut_bulk
+    --bg-bulk $bg_bulk
+    --output $output
+    --loglevel $loglevel
+    --hmes-adjust $hmes_adjust
+    --htlow $ht_low
+    --hthigh $ht_high
+    --mindepth $min_depth
+    --min-non-ref-count $min_non_ref_count
+    --min-indel-count-support $min_indel_count_support
+    --ambiguous-ref-bases $ambiguous_ref_bases
+    --mapping-quality $mapping_quality
+    --base-quality $base_quality
+    --noise $noise
+    --cross-type $cross_type
+    --use-all-contigs $use_all_contigs
+    --include-low-hmes $include_low_hmes
+    --polyploidy $polyploidy
+    --mut-parent $mut_parent
+    --bg-parent $bg_parent
+    --bfr-adjust $bfr_adjust
+    --sel-seq-len $sel_seq_len
+]]>
+  </command>
+
+  <inputs>
+    <param name="assembly" type="data" format="fasta" label="Input Assembly file" help="Select Assembly fasta file" />
+    <param name="mut_bulk" type="data" format="pileup" label="mutant bulk pileup file" help="Select mutant bulk pileup file" />
+    <param name="bg_bulk" type="data" format="pileup" label="background bulk pileup file" min="1" multiple="true" help="Select background bulk pileup file" />
+    <param name="loglevel" type="select" optional="true" label="analysis log level" help="choose between info, warn and debug levels">
+      <option value="info" selected="true">info </option>
+      <option value="warn">warnings</option>
+      <option value="debug">debug</option>
+    </param>
+    <param name="hmes_adjust" size="4" type="float" optional="true" value="0.5" min="0.01" max="1.0"
+           label="hme score adjuster" help="factor added to snp count of each contig to adjust for hme score calculations" />
+    <param name="ht_low" size="4"  type="float" optional="true" value="0.25" min="0.1" max="1.0"
+           label="heterozygosity low limit" help="lower limit to heterozygosity allele fraction" />
+    <param name="ht_high" size="4" type="float" optional="true" value="0.75" min="0.1" max="1.0"
+           label="heterozygosity high limit" help="upper limit to heterozygosity allele fraction" />
+    <param name="min_depth" size="4" type="integer" optional="true" value="6" min="1" max="8000"
+           label="minimum read coverage" help="minimum read depth to conisder a position for variant calls" />
+    <param name="min_non_ref_count" size="4" type="integer" optional="true" value="3" min="1" max="8000"
+           label="minimum alternate read coverage" help="minimum read depth supporting non reference base at each position" />
+    <param name="min_indel_count_support" size="4" type="integer" optional="true" value="3" min="1" max="8000"
+           label="minimum indel read coverage" help="minimum read depth supporting an indel at each position" />
+    <param name="ambiguous_ref_bases" type="boolean" optional="true" checked="false" label="ambiguous reference position"
+            help="including variant at completely ambiguous bases in the reference" truevalue="true" falsevalue="false" />
+    <param name="mapping_quality" size="4" type="integer" optional="true" value="20" min="0" max="255"
+           label="minimum mapping quality" help="minimum mapping quality of read covering the position" />
+    <param name="base_quality" size="4" type="integer" optional="true" value="15" min="0" max="40"
+           label="minimum base quality" help="minimum base quality of nucleotides covering the position" />
+    <param name="noise" size="4" type="float" optional="true" value="0.1" min="0" max="0.2"
+           label="read noise" help="proportion of reads supporting a variant, below which are consider as noise" />
+    <param name="cross_type" type="select" optional="true" label="cross type" help="type of cross used to generated mapping population - back or out" >
+      <option value="back" selected="true">back cross</option>
+      <option value="out">out cross</option>
+    </param>
+
+    <param name="use_all_contigs" type="boolean" optional="true" checked="false" label="use all contigs in analysis"
+           help="option to select all contigs or only contigs containing variants for analysis" truevalue="true" falsevalue="false" />
+    <param name="include_low_hmes" type="boolean" optional="true" checked="false" label="no hme or bfr score cut off"
+           help="option to include or discard variants from contigs with low hme-score or bfr score to list in the final output" truevalue="true" falsevalue="false" />
+    <param name="polyploidy" type="boolean" optional="true" checked="false" label="polyploid data"
+           help="Set if the input data is from polyploids" truevalue="true" falsevalue="false" />
+    <param name="mut-parent" type="data" optional="true" format="pileup" label="mutant parent pileup file" help="Select mutant parent pileup file" />
+    <param name="bg-parent" type="data" optional="true" format="pileup" label="background parent pileup file" help="Select background parent pileup file" />
+
+    <param name="bfr_adjust" size="4" type="float" optional="true" value="0.05" min="0.01" max="1.0"
+           label="bfr score adjuster" help="factor added to hemi snp frequency of each parent to adjust for bfr calculations (default: 0.05)" />
+    <param name="sel_seq_len" size="4" type="integer" optional="true" value="50" min="10" max="250"
+           label="selected variant seq length out" help="sequence length to print from either side of selected variants (default: 50)" />
+
+    <param name="output" type="text" size="30" value="cheripic_results" label="tag for output filename" help="write a tag to include with output filename" />
+  </inputs>
+
+  <outputs>
+    <data name="output_1" format="txt" file="${output}_selected_hme_variants.txt" />
+    <data name="output_2" format="txt" file="${output}_selected_bfr_variants.txt" />
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="assembly" value="picked_fasta.fa" ftype="fasta" />
+      <param name="mut_bulk" value="mut_bulk.pileup" ftype="pileup" />
+      <param name="bg_bulk" value="wt_bulk.pileup" ftype="pileup" />
+      <output name="output" ftype="txt" file="selected_variants.out" />
+    </test>
+  </tests>
+
+  <help>
+
+**Computing Homozygosity Enriched Regions In genomes to Prioritize Identification of Candidate variants (CHERIPIC)**
+
+CHERIPIC is a ruby tool to pick causative mutation from bulk segregant sequencing
+
+------
+
+**What it does**
+
+This tool uses ``cheripic`` tool to analyse bulk segregant sequencing to identify causative muation
+
+
+.. class:: infomark
+
+Provides a list of snps that could either closely linked markers or the causative mutation.
+
+------
+
+**Input formats**
+
+assembly file should be a fasta file used for generating pileups from bulks
+bulk alignment files should be pileup files
+
+------
+
+**Outputs**
+
+The output is a text file, and has the following columns::
+
+  Column              Description
+  -----------------   --------------------------------------------------------
+  1  HME_Score        Homozygosity Enrichment score
+  2  AlleleFreq       Allele frequency
+  3  seq_id           Contig/Scaffold id
+  4  position         1-based index of the position in contig
+  5  ref_base         Reference nucleotide at the position
+  6  coverage         read depth
+  7  bases            read bases
+  8  base_quals       read base qualities
+  9  sequence_left    selected size of reference sequence on the left variant
+  10 Alt_seq          Alternate allele at the position
+  11 sequence_right   selected size of reference sequence on the right variant
+
+------
+
+**cheripic settings**
+
+All of the options have a default value. You can change any of them. All of the options are implemented.
+
+------
+
+**cheripic parameter list**
+
+OPTIONS:
+  -f, --assembly               Assembly file in FASTA format
+  -F, --input-format           bulk and parent alignment file format types - set either pileup or bam (default: pileup)
+  -a, --mut-bulk               Pileup or sorted BAM file alignments from mutant/trait of interest bulk 1
+  -b, --bg-bulk                Pileup or sorted BAM file alignments from background/wildtype bulk 2
+  --output                     Directory to store results, will be created if not existing (default: cheripic_results)
+  --loglevel                   Choose any one of "info / warn / debug" level for logs generated (default: debug)
+  --hmes-adjust                factor added to snp count of each contig to adjust for hme score calculations (default: 0.5)
+  --htlow                      lower level for categorizing heterozygosity (default: 0.2)
+  --hthigh                     high level for categorizing heterozygosity (default: 0.9)
+  --mindepth                   minimum read depth to conisder a position for variant calls (default: 6)
+  --min-non-ref-count          minimum read depth supporting non reference base at each position (default: 3)
+  --min-indel-count-support    minimum read depth supporting an indel at each position (default: 3)
+  --ambiguous-ref-bases        including variant at completely ambiguous bases in the reference
+  -q, --mapping-quality        minimum mapping quality of read covering the position (default: 20)
+  -Q, --base-quality           minimum base quality of bases covering the position (default: 15)
+  --noise                      praportion of reads for a variant to conisder as noise (default: 0.1)
+  --cross-type                 type of cross used to generated mapping population - back or out (default: back)
+  --use-all-contigs            option to select all contigs or only contigs containing variants for analysis
+  --include-low-hmes           option to include or discard variants from contigs with low hme-score or bfr score to list in the final output
+  --polyploidy                 Set if the data input is from polyploids
+  -p, --mut-parent             Pileup or sorted BAM file alignments from mutant/trait of interest parent (default: )
+  -r, --bg-parent              Pileup or sorted BAM file alignments from background/wildtype parent (default: )
+  --bfr-adjust                 factor added to hemi snp frequency of each parent to adjust for bfr calculations (default: 0.05)
+  --sel-seq-len                sequence length to print from either side of selected variants (default: 50)
+
+------
+
+.. class:: infomark
+
+**Tool Author**
+
+Shyam Rallapalli
+
+
+  </help>
+
+  <citations>
+    <citation type="doi">10.1093/bioinformatics/btg1080</citation>
+  </citations>
+
+</tool>

data/lib/cheripic.rb

@@ -38,3 +38,4 @@ require 'cheripic/options'
 require 'cheripic/contig_pileups'
 require 'cheripic/bfr'
 require 'cheripic/regions'
+require 'cheripic/vcf'

data/lib/cheripic/cmd.rb

@@ -52,10 +52,14 @@ module Cheripic
         opt :mut_bulk, 'Pileup or sorted BAM file alignments from mutant/trait of interest bulk 1',
             :short => '-a',
             :type => String
+        opt :mut_bulk_vcf, 'vcf file for variants from mutant/trait of interest bulk 1',
+            :type => String
         opt :bg_bulk, 'Pileup or sorted BAM file alignments from background/wildtype bulk 2',
             :short => '-b',
             :type => String
-        opt :output, 'Directory to store results, will be created if not existing',
+        opt :bg_bulk_vcf, 'vcf file for variants from background/wildtype bulk 2',
+            :type => String
+        opt :output, 'custom name tag to include in the output file name',
             :default => 'cheripic_results'
         opt :loglevel, 'Choose any one of "info / warn / debug" level for logs generated',
             :default => 'debug'
@@ -68,9 +72,17 @@ module Cheripic
         opt :hthigh, 'high level for categorizing heterozygosity',
             :type => Float,
             :default => 0.9
-        opt :mindepth, 'minimum read depth to conisder a position for variant calls',
+        opt :mindepth, 'minimum read depth at a position to consider for variant calls',
             :type => Integer,
             :default => 6
+        opt :max_d_multiple, "multiplication factor for average coverage to calculate maximum read coverage
+if set zero no calculation will be made from bam file.\nsetting this value will override user set max depth",
+            :type => Integer,
+            :default => 5
+        opt :maxdepth, "maximum read depth at a position to consider for variant calls
+if set to zero no user max depth will be used",
+            :type => Integer,
+            :default => 0
         opt :min_non_ref_count, 'minimum read depth supporting non reference base at each position',
             :type => Integer,
             :default => 3
@@ -97,7 +109,8 @@ module Cheripic
         opt :use_all_contigs, 'option to select all contigs or only contigs containing variants for analysis',
             :type => FalseClass,
             :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',
+        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 => false
         opt :polyploidy, 'Set if the data input is from polyploids',
@@ -111,6 +124,10 @@ module Cheripic
             :short => '-r',
             :type => String,
             :default => ''
+        opt :repeats_file, 'repeat masker output file for the assembly ',
+            :short => '-R',
+            :type => String,
+            :default => ''
         opt :bfr_adjust, 'factor added to hemi snp frequency of each parent to adjust for bfr calculations',
             :type => Float,
             :default => 0.05
@@ -133,8 +150,9 @@ module Cheripic
 
       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
+      2. Pileup/Bam files for mutant (phenotype of interest) bulks and background (wildtype phenotype) bulks
+      3. If providing bam files, you have to include vcf files for the respective bulks
+      4. If polyploid species, include pileup/bam files from one or both parents
 
       USAGE:
       cheripic <options>
@@ -149,15 +167,19 @@ module Cheripic
     def print_examples
       msg = <<-EOS
 
-        Cheripic v#{Cheripic::VERSION.dup}
+      Cheripic v#{Cheripic::VERSION.dup}
+      Authors: Shyam Rallapalli and Dan MacLean
+
+      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
+        4. cheripic -h or cheripic --help
+        5. cheripic -v or cheripic --version
 
-        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)
@@ -165,44 +187,66 @@ module Cheripic
 
     # calls other methods to check if command line inputs are valid
     def check_arguments
-      check_output_dir
+      check_output
       check_log_level
-      check_input_files
+      check_input_types
     end
 
-    # TODO: check bulk input types and process associated files
-    # def check_input_types
-    #   if @options[:input_format] == 'vcf'
-    #
-    #   end
-    # end
-
-    # checks if input files are valid
-    def check_input_files
+    # checks input files based on bulk file type
+    def check_input_types
+      inputfiles = {}
+      inputfiles[:required] = %i{assembly mut_bulk}
+      inputfiles[:optional] = %i{bg_bulk}
+      if @options[:input_format] == 'bam'
+        inputfiles[:required] << %i{mut_bulk_vcf}
+        inputfiles[:optional] << %i{bg_bulk_vcf}
+      end
       if @options[:polyploidy]
-        inputfiles = %i{assembly mut_bulk bg_bulk mut_parent bg_parent}
-      else
-        inputfiles = %i{assembly mut_bulk bg_bulk}
+        inputfiles[:either] = %i{mut_parent bg_parent}
       end
-      inputfiles.each do | symbol |
-        if @options[symbol]
-          file = @options[symbol]
-          @options[symbol] = File.expand_path(file)
-          unless File.exist?(file)
-            raise CheripicIOError.new "#{symbol} file, #{file} does not exist: "
+      check_input_files(inputfiles)
+    end
+
+    # checks if input files are valid
+    def check_input_files(inputfiles)
+      check = 0
+      inputfiles.each_key do | type |
+        inputfiles[type].flatten!
+        inputfiles[type].each do | symbol |
+          if @options[symbol]
+            file = @options[symbol]
+            @options[symbol] = File.expand_path(file)
+            next if type == :optional
+            if type == :required and not File.exist?(file)
+              raise CheripicIOError.new "#{symbol} file, #{file} does not exist: "
+            elsif type == :either and File.exist?(file)
+              check = 1
+            end
+          elsif type == :required
+            raise CheripicArgError.new "Options #{inputfiles}, all must be specified. " +
+                                              'Try --help for further help.'
           end
-        else
-          raise CheripicArgError.new "Options #{inputfiles}, all must be specified. " +
-                                            'Try --help for help.'
+        end
+        if type == :either and check == 0
+          raise CheripicArgError.new "One of the options #{inputfiles}, must be specified. " +
+                                       'Try --help for further help.'
         end
       end
     end
 
-    # checks if output directory already exists
-    def check_output_dir
-      if Dir.exist?(@options[:output])
-        raise CheripicArgError.new "#{@options[:output]} directory exists" +
-                                       'please choose a different output directory name'
+    # checks if files with output tag name already exists
+    def check_output
+      if (@options[:output].split('') & %w{# / : * ? ' < > | & $ ,}).any?
+        raise CheripicArgError.new 'please choose a name tag that contains ' +
+                                       'alphanumeric characters, hyphen(-) and underscore(_) only'
+      end
+      @options[:hmes_frags] = "#{@options[:output]}_selected_hme_variants.txt"
+      @options[:bfr_frags] = "#{@options[:output]}_selected_bfr_variants.txt"
+      [@options[:hmes_frags], @options[:bfr_frags]].each do | file |
+        if File.exist?(file)
+          raise CheripicArgError.new "'#{file}' file exists " +
+                                         'please choose a different name tag to be included in the output file name'
+        end
       end
     end
 
@@ -220,7 +264,8 @@ module Cheripic
     # A hash of trollop option names as keys and user or default
     # setting as values is passed to Implementer object
     def run
-      @options[:output] = File.expand_path @options[:output]
+      @options[:hmes_frags] = File.expand_path @options[:hmes_frags]
+      @options[:bfr_frags] = File.expand_path @options[:bfr_frags]
       analysis = Implementer.new(@options)
       analysis.run
     end

data/lib/cheripic/contig.rb

@@ -22,7 +22,7 @@ module Cheripic
   #   @return [Integer] length of contig in bases
   class Contig
 
-    attr_accessor :hm_pos, :ht_pos, :hemi_pos
+    attr_accessor :hm_pos, :ht_pos, :hemi_pos, :mean_depth, :sd_depth
     attr_reader :id, :length
 
     # creates a Contig object using fasta entry
@@ -33,6 +33,8 @@ module Cheripic
       @hm_pos = {}
       @ht_pos = {}
       @hemi_pos = {}
+      @mean_depth = nil
+      @sd_depth = nil
     end
 
     # Number of homozygous variants identified in the contig

data/lib/cheripic/contig_pileups.rb

@@ -32,7 +32,7 @@ module Cheripic
     def_delegators :@mut_parent, :each, :each_key, :each_value, :length, :[], :store
     def_delegators :@bg_parent, :each, :each_key, :each_value, :length, :[], :store
     attr_accessor :id, :parent_hemi
-    attr_accessor :mut_bulk, :bg_bulk, :mut_parent, :bg_parent
+    attr_accessor :mut_bulk, :bg_bulk, :mut_parent, :bg_parent, :masked_regions
 
     # creates a ContigPileup object using fasta entry id
     # @param fasta [String] a contig id from fasta entry
@@ -43,16 +43,27 @@ module Cheripic
       @mut_parent = {}
       @bg_parent = {}
       @parent_hemi = {}
+      @masked_regions = Hash.new { |h,k| h[k] = {} }
+      @hm_pos = {}
+      @ht_pos = {}
+      @hemi_pos = {}
     end
 
     # bulk pileups are compared and variant positions are selected
     # @return [Array<Hash>] variant positions are stored in hashes
     # for homozygous, heterozygous and hemi-variant positions
     def bulks_compared
-      @hm_pos = {}
-      @ht_pos = {}
-      @hemi_pos = {}
       @mut_bulk.each_key do | pos |
+        ignore = 0
+        unless @masked_regions.empty?
+          @masked_regions.each_key do | index |
+            if pos.between?(@masked_regions[index][:begin], @masked_regions[index][:end])
+              ignore = 1
+              logger.info "variant is in the masked region\t#{@mut_bulk[pos].to_s}"
+            end
+          end
+        end
+        next if ignore == 1
         if Options.polyploidy and @parent_hemi.key?(pos)
           bg_bases = ''
           if @bg_bulk.key?(pos)
@@ -74,27 +85,37 @@ module Cheripic
     # @param pos [Integer] position in the contig
     # stores variant type, position and allele fraction to either @hm_pos or @ht_pos hashes
     def compare_pileup(pos)
-      base_hash = @mut_bulk[pos].var_base_frac
-      base_hash.delete(:ref)
-      return nil if base_hash.empty?
-      # we could ignore complex loci or
-      # take the variant type based on predominant base
-      if base_hash.length > 1
-        fraction = base_hash.values.max
-        mut_type = var_mode(fraction)
-      else
-        fraction = base_hash[base_hash.keys[0]]
-        mut_type = var_mode(fraction)
-      end
+      mut_type, fraction = var_mode_fraction(@mut_bulk[pos])
+      return nil if mut_type.nil?
       if @bg_bulk.key?(pos)
-        bg_type = bg_bulk_var(pos)
+        bg_type = var_mode_fraction(@bg_bulk[pos])[0]
         mut_type = compare_var_type(mut_type, bg_type)
       end
-      unless mut_type == nil
+      unless mut_type.nil?
         categorise_pos(mut_type, pos, fraction)
       end
     end
 
+
+    # Method to extract var_mode and allele fraction from pileup information at a position in contig
+    #
+    # @param pileup_info [Pileup] pileup object
+    # @return [Symbol] variant mode from pileup position (:hom or :het) at the position
+    # @return [Float] allele fraction at the position
+    def var_mode_fraction(pileup_info)
+      base_frac_hash = pileup_info.var_base_frac
+      base_frac_hash.delete(:ref)
+      return [nil, nil] if base_frac_hash.empty?
+      # we could ignore complex loci or
+      # take the variant type based on predominant base
+      if base_frac_hash.length > 1
+        fraction = base_frac_hash.values.max
+      else
+        fraction = base_frac_hash[base_frac_hash.keys[0]]
+      end
+      [var_mode(fraction), fraction]
+    end
+
     # Categorizes variant zygosity based on the allele fraction provided.
     # Uses lower and upper limit set for heterozygosity in the options.
     # @note consider increasing the range of heterozygosity limits for RNA-seq data
@@ -125,23 +146,6 @@ module Cheripic
       end
     end
 
-    # Method to extract var_mode from pileup information at a position in contig
-    #
-    # @param pos [Integer] position in the contig
-    # @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[bg_base_hash.keys[0]])
-      end
-    end
-
     # method stores pos as key and allele fraction as value
     # to @hm_pos or @ht_pos hash based on variant type
     # @param var_type [Symbol]  values are either :hom or :het
@@ -156,18 +160,18 @@ module Cheripic
     end
 
     # Compares parental pileups for the contig and identify position
-    # that indicate variants from homelogues called hemi-snps
+    # that indicate variants from homeologues called hemi-snps
     # and calculates bulk frequency ratio (bfr)
     # @return [Hash] parent_hemi hash with position as key and bfr as value
     def hemisnps_in_parent
       # mark all the hemi snp based on both parents
-      self.mut_parent.each_key do |pos|
+      @mut_parent.each_key do |pos|
         mut_parent_frac = @mut_parent[pos].var_base_frac
-        if self.bg_parent.key?(pos)
+        if @bg_parent.key?(pos)
           bg_parent_frac = @bg_parent[pos].var_base_frac
           bfr = Bfr.get_bfr(mut_parent_frac, bg_parent_frac)
           @parent_hemi[pos] = bfr
-          self.bg_parent.delete(pos)
+          @bg_parent.delete(pos)
         else
           bfr = Bfr.get_bfr(mut_parent_frac)
           @parent_hemi[pos] = bfr
@@ -175,7 +179,7 @@ module Cheripic
       end
 
       # now include all hemi snp unique to background parent
-      self.bg_parent.each_key do |pos|
+      @bg_parent.each_key do |pos|
         unless @parent_hemi.key?(pos)
           bg_parent_frac = @bg_parent[pos].var_base_frac
           bfr = Bfr.get_bfr(bg_parent_frac)

data/lib/cheripic/implementer.rb

@@ -25,15 +25,21 @@ module Cheripic
                 input_format
                 mut_bulk
                 bg_bulk
-                output
+                mut_bulk_vcf
+                bg_bulk_vcf
+                hmes_frags
+                bfr_frags
                 mut_parent
-                bg_parent}
+                bg_parent
+                repeats_file}
       @options = OpenStruct.new(inputs.select { |k| set1.include?(k) })
 
       set2 = %i{hmes_adjust
                 htlow
                 hthigh
                 mindepth
+                maxdepth
+                max_d_multiple
                 min_non_ref_count
                 min_indel_count_support
                 ambiguous_ref_bases
@@ -44,10 +50,10 @@ module Cheripic
                 use_all_contigs
                 include_low_hmes
                 polyploidy
-                bfr_adjust}
+                bfr_adjust
+                sel_seq_len}
       settings = inputs.select { |k| set2.include?(k) }
       Options.update(settings)
-      FileUtils.mkdir_p @options.output
       @vars_extracted = false
       @has_run = false
     end
@@ -62,15 +68,21 @@ module Cheripic
 
     # Extracted variants from bulk comparison are re-analysed
     # and selected variants are written to a file
-    def process_variants
-      @variants.verify_bg_bulk_pileup
+    def process_variants(pos_type)
+      if pos_type == :hmes_frags
+        @variants.verify_bg_bulk_pileup
+      end
       # print selected variants that could be potential markers or mutation
-      out_file = File.open("#{@options.output}/selected_variants.txt", 'w')
-      out_file.puts "HME_Score\tAlleleFreq\tseq_id\tposition\tref_base\tcoverage\tbases\tbase_quals\tsequence_left\tAlt_seq\tsequence_right"
+      out_file = File.open(@options[pos_type], 'w')
+      out_file.puts "Score\tAlleleFreq\tseq_id\tposition\tref_base\tcoverage\tbases\tbase_quals\tsequence_left\tAlt_seq\tsequence_right"
       regions = Regions.new(@options.assembly)
-      @variants.hmes_frags.each_key do | frag |
+      @variants.send(pos_type).each_key do | frag |
         contig_obj = @variants.assembly[frag]
-        positions = contig_obj.hm_pos.keys
+        if pos_type == :hmes_frags
+          positions = contig_obj.hm_pos.keys
+        else
+          positions = contig_obj.hemi_pos.keys
+        end
         positions.each do | pos |
           pileup = @variants.pileups[frag].mut_bulk[pos]
           seqs = regions.fetch_seq(frag,pos)
@@ -87,11 +99,9 @@ module Cheripic
       unless @vars_extracted
         self.extract_vars
       end
+      self.process_variants(:hmes_frags)
       if Options.polyploidy
-        self.process_variants
-        @variants.bfr_frags
-      else
-        self.process_variants
+        self.process_variants(:bfr_frags)
       end
       @has_run = true
     end

data/lib/cheripic/options.rb

@@ -12,6 +12,8 @@ module Cheripic
         :htlow => 0.2,
         :hthigh => 0.9,
         :mindepth => 6,
+        :maxdepth => 0,
+        :max_d_multiple => 5,
         :min_non_ref_count => 3,
         :min_indel_count_support => 3,
         :ambiguous_ref_bases => false,
@@ -53,6 +55,26 @@ module Cheripic
       @user_settings[:mindepth]
     end
 
+    # Maximum read coverage at the variant position to be considered for analysis
+    # @return [Integer]
+    def self.maxdepth
+      @user_settings[:maxdepth]
+    end
+
+    # Setting maximum read coverage at the variant position to be considered for analysis
+    # @param value [Integer] provided integer value will be updated as maxdepth
+    # @return [Integer] updated maxdepth value
+    def self.maxdepth=(value)
+      @user_settings[:maxdepth] = value
+    end
+
+    # Multiplication factor to average coverage to calculate maximum read coverage
+    # at the variant position to be considered for analysis
+    # @return [Integer]
+    def self.max_d_multiple
+      @user_settings[:max_d_multiple]
+    end
+
     # Minimum non reference count at the variant position to be considered for analysis
     # @return [Integer]
     def self.min_non_ref_count

data/lib/cheripic/variants.rb

@@ -4,6 +4,36 @@ require 'forwardable'
 
 module Cheripic
 
+  require 'bio-samtools'
+  require 'bio/db/sam'
+  require 'open3'
+
+  # An extension of Bio::DB::Sam object to modify depth method
+  class Bio::DB::Sam
+
+    # A method to retrieve depth information from bam object
+    # @param opts [Hash] a hash of following input options
+    #   b [File] list of positions or regions in BED format
+    #   l [INT] minQLen
+    #   q [INT] base quality threshold
+    #   Q [INT] mapping quality threshold
+    #   r [chr:from-to] region
+    # @returns a block with each line reporting sequence_name, position and depth
+    def depth(opts={})
+      command = form_opt_string(self.samtools, 'depth', opts)
+      # capture returns string output, so careful not to give whole genome or big contigs for depth analysis
+      stdout, stderr, status = Open3.capture3(command)
+      unless status.success?
+        logger.error "resulted in exit code #{status.exitstatus} using #{command}"
+        logger.error "stderr output is: #{stderr}"
+        raise CheripicError
+      end
+      # return stdout
+      stdout
+    end
+
+  end
+
   # Custom error handling for Variants class
   class VariantsError < CheripicError; end
 
@@ -27,10 +57,10 @@ module Cheripic
     include Enumerable
     extend Forwardable
     def_delegators :@assembly, :each, :each_key, :each_value, :size, :length, :[]
-    attr_reader :assembly, :pileups, :hmes_frags, :bfr_frags, :pileups_analyzed
+    attr_reader :assembly, :pileups, :pileups_analyzed
 
     # creates a Variants object using user input files
-    # @param options [Hash] a hash of required input files as keys and file paths as values
+    # @param options [OpenStruct] a hash of required input files as keys and file paths as values
     def initialize(options)
       @params = options
       @assembly = {}
@@ -50,25 +80,76 @@ module Cheripic
         @pileups[contig.id] = ContigPileups.new(contig.id)
       end
       @pileups_analyzed = false
+      unless @params.repeats_file == ''
+        store_repeat_regions
+      end
+    end
+
+    # reads repeat masker output file and stores masked regions to ignore variants in thos regions
+    def store_repeat_regions
+      File.foreach(@params.repeats_file) do |line|
+        line.strip!
+        next if line =~ /^SW/ or line =~ /^score/ or line == ''
+        info = line.split("\s")
+        pileups_obj = @pileups[info[4]]
+        index = pileups_obj.masked_regions.length
+        pileups_obj.masked_regions[index + 1][:begin] = info[5].to_i
+        pileups_obj.masked_regions[index + 1][:end] = info[6].to_i
+      end
     end
 
     # Reads and store pileup data for each of input bulk and parents pileup files
     # And sets pileups_analyzed to true that pileups files are processed
     def analyse_pileups
-      @bg_bulk = @params.bg_bulk
-      @mut_parent = @params.mut_parent
-      @bg_parent = @params.bg_parent
-
+      if @params.input_format == 'bam'
+        @vcf_hash = Vcf.filtering(@params.mut_bulk_vcf, @params.bg_bulk_vcf)
+      end
       %i{mut_bulk bg_bulk mut_parent bg_parent}.each do | input |
         infile = @params[input]
         if infile != ''
-          extract_pileup(infile, input)
+          logger.info "processing #{input} file"
+          if @params.input_format == 'pileup'
+            extract_pileup(infile, input)
+          else
+            extract_bam_pileup(infile, input)
+          end
         end
       end
 
       @pileups_analyzed = true
     end
 
+    # Bam object is read and each contig mean and std deviation of depth calculated
+    # @param bamobject [Bio::DB::Sam]
+    # Open3 capture returns string output, so careful not to give whole genome or big contigs for depth analysis
+    def set_max_depth(bamobject, bamfile)
+      logger.info "processing #{bamfile} file for depth"
+      all_depths = []
+      bq = Options.base_quality
+      mq = Options.mapping_quality
+      @assembly.each_key do | id |
+        contig_obj = @assembly[id]
+        len = contig_obj.length
+        data = bamobject.depth(:r => "#{id}", :Q => bq, :q => mq)
+        depths = []
+        data.split("\n").each do |line|
+          info = line.split("\t")
+          depths << info[2].to_i
+        end
+        variance = 0
+        mean_depth = depths.reduce(0, :+) / len.to_f
+        depths.each do |value|
+          variance += (value.to_f - mean_depth)**2
+        end
+        all_depths << mean_depth
+        contig_obj.sd_depth = Math.sqrt(variance)
+        contig_obj.mean_depth = mean_depth
+      end
+      # setting max depth as 3 times the average depth
+      mean_coverage = all_depths.reduce(0, :+) / @assembly.length.to_f
+      Options.maxdepth = Options.max_d_multiple * mean_coverage
+    end
+
     # Input pileup file is read and positions are selected that pass the thresholds
     # @param pileupfile [String] path to the pileup file to read
     # @param sym [Symbol] Symbol of the pileup file used to write selected variants
@@ -84,6 +165,54 @@ module Cheripic
       end
     end
 
+    # Input bamfile is read and selected positions pileups are stored
+    # @param bamfile [String] path to the bam file to read
+    # @param sym [Symbol] Symbol of the bam file used to write selected variants
+    # pileup information to respective ContigPileups object
+    def extract_bam_pileup(bamfile, sym)
+      bq = Options.base_quality
+      mq = Options.mapping_quality
+      bamobject = Bio::DB::Sam.new(:bam=>bamfile, :fasta=>@params.assembly)
+      bamobject.index unless bamobject.indexed?
+
+      # check if user has set max depth or set to zero to ignore
+      max_d = Options.maxdepth
+      # or calculate from bamfile
+      if Options.max_d_multiple > 0
+        set_max_depth(bamobject, bamfile)
+        max_d = Options.maxdepth
+        logger.info "max depth used for #{sym} file\t#{max_d}"
+      end
+
+      @vcf_hash.each_key do | id |
+        positions = @vcf_hash[id][:het].keys
+        positions << @vcf_hash[id][:hom].keys
+        positions.flatten!
+        next if positions.empty?
+        contig_obj = @pileups[id]
+        positions.each do | pos |
+          command = "#{bamobject.samtools} mpileup -r #{id}:#{pos}-#{pos} -Q #{bq} -q #{mq} -B -f #{@params.assembly} #{bamfile}"
+          stdout, stderr, status = Open3.capture3(command)
+          unless status.success?
+            logger.error "resulted in exit code #{status.exitstatus} using #{command}"
+            logger.error "stderr output is: #{stderr}"
+            raise CheripicError
+          end
+          stdout.chomp!
+          if stdout == '' or stdout.split("\t")[3].to_i == 0 or stdout =~ /^\t0/
+            logger.info "pileup data empty for\t#{id}\t#{pos}"
+          else
+            pileup = Pileup.new(stdout)
+            unless max_d == 0 or pileup.coverage <= max_d
+              logger.info "pileup coverage is higher than max\t#{pileup.to_s}"
+              next
+            end
+            contig_obj.send(sym).store(pos, pileup)
+          end
+        end
+      end
+    end
+
     # Once pileup files are analysed and variants are extracted from each bulk;
     # bulks are compared to identify and isolate variants for downstream analysis.
     # If polyploidy set to trye and mut_parent and bg_parent bulks are provided
@@ -95,8 +224,10 @@ module Cheripic
       @assembly.each_key do | id |
         contig = @assembly[id]
         # extract parental hemi snps for polyploids before bulks are compared
-        if @mut_parent != '' or @bg_parent != ''
-          @pileups[id].hemisnps_in_parent
+        if Options.polyploidy
+          if @params.mut_parent != '' or @params.bg_parent != ''
+            @pileups[id].hemisnps_in_parent
+          end
         end
         contig.hm_pos, contig.ht_pos, contig.hemi_pos = @pileups[id].bulks_compared
       end

data/lib/cheripic/vcf.rb

@@ -0,0 +1,83 @@
+# encoding: utf-8
+
+module Cheripic
+
+  # Custom error handling for Vcf class
+  class VcfError < CheripicError; end
+
+  require 'bio-samtools'
+
+  class Vcf
+
+    def self.get_allele_freq(vcf_obj)
+      # check if the vcf is from samtools (has DP4 and AF1 fields in INFO)
+      if vcf_obj.info.key?('DP4')
+        freq = vcf_obj.info['DP4'].split(',')
+        depth = freq.inject { | sum, n | sum.to_f + n.to_f }
+        alt = freq[2].to_f + freq[3].to_f
+        allele_freq = alt / depth
+        # allele_freq = vcf_obj.non_ref_allele_freq
+      # check if the vcf is from VarScan (has RD, AD and FREQ fields in FORMAT)
+      elsif vcf_obj.samples['1'].key?('RD')
+        alt = vcf_obj.samples['1']['AD'].to_f
+        depth = vcf_obj.samples['1']['RD'].to_f + alt
+        allele_freq = alt / depth
+      # check if the vcf is from GATK (has AD and GT fields in FORMAT)
+      elsif vcf_obj.samples['1'].key?('AD') and vcf_obj.samples['1']['AD'].include?(',')
+        freq = vcf_obj.samples['1']['AD'].split(',')
+        allele_freq = freq[1].to_f / ( freq[0].to_f + freq[1].to_f )
+      # check if the vcf has has AF fields in INFO
+      elsif vcf_obj.info.key?('AF')
+        allele_freq = vcf_obj.info['AF'].to_f
+      else
+        raise VcfError.new 'not a supported vcf format (VarScan, GATK, Bcftools(Samtools), Vcf 4.0, 4.1 and 4.2)' +
+                               " and check that it is one sample vcf\n"
+      end
+      allele_freq
+    end
+
+
+    ##Input: vcf file
+    ##Ouput: lists of hm and ht SNPS and hash of all fragments with variants
+    def self.get_vars(vcf_file)
+      ht_low = Options.htlow
+      ht_high = Options.hthigh
+
+      # hash of :het and :hom with frag ids and respective variant positions
+      var_pos = Hash.new{ |h,k| h[k] = Hash.new(&h.default_proc) }
+      File.foreach(vcf_file) do |line|
+        next if line =~ /^#/
+        v = Bio::DB::Vcf.new(line)
+        unless v.alt == '.'
+          allele_freq = get_allele_freq(v)
+          if allele_freq.between?(ht_low, ht_high)
+            var_pos[v.chrom][:het][v.pos] = allele_freq
+          elsif allele_freq > ht_high
+            var_pos[v.chrom][:hom][v.pos] = allele_freq
+          end
+        end
+      end
+      var_pos
+    end
+
+    def self.filtering(mutant_vcf, bgbulk_vcf)
+      var_pos_mut = get_vars(mutant_vcf)
+      return var_pos_mut if bgbulk_vcf == ''
+      var_pos_bg = get_vars(bgbulk_vcf)
+
+      # if both bulks have homozygous mutations at same positions then deleting them
+      var_pos_mut.each_key do | frag |
+        positions = var_pos_mut[frag][:hom].keys
+        pos_bg_bulk = var_pos_bg[frag][:hom].keys
+        positions.each do |pos|
+          if pos_bg_bulk.include?(pos)
+            var_pos_mut[frag][:hom].delete(pos)
+          end
+        end
+      end
+      var_pos_mut
+    end
+
+  end
+
+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 = '1.2.0'
+  VERSION = '1.2.5'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cheripic
 version: !ruby/object:Gem::Version
-  version: 1.2.0
+  version: 1.2.5
 platform: ruby
 authors:
 - Shyam Rallapalli
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-08-11 00:00:00.000000000 Z
+date: 2016-10-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: yell
@@ -84,40 +84,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 2.4.0
-- !ruby/object:Gem::Dependency
-  name: bio-gngm
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 0.2.1
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 0.2.1
-- !ruby/object:Gem::Dependency
-  name: rinruby
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 2.0.3
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.0'
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 2.0.3
 - !ruby/object:Gem::Dependency
   name: activesupport
   requirement: !ruby/object:Gem::Requirement
@@ -259,6 +225,7 @@ files:
 - ".gitignore"
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
+- ChangeLog.md
 - Gemfile
 - LICENSE.txt
 - README.md
@@ -267,6 +234,7 @@ files:
 - bin/console
 - bin/setup
 - cheripic.gemspec
+- galaxy_cheripic_tool.xml
 - lib/cheripic.rb
 - lib/cheripic/bfr.rb
 - lib/cheripic/cmd.rb
@@ -277,6 +245,7 @@ files:
 - lib/cheripic/pileup.rb
 - lib/cheripic/regions.rb
 - lib/cheripic/variants.rb
+- lib/cheripic/vcf.rb
 - lib/cheripic/version.rb
 homepage: https://github.com/shyamrallapalli/cheripic
 licenses: