dirseq 0.0.2 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 84e91d3823af5395053c2104197b68223d3e4d96
-  data.tar.gz: 7488e7557cd4005dcfc8b6f3c504d4e250434e5b
+  metadata.gz: 7b2362c43bff2a2cd43f0dc727bf8d713e4ab3c4
+  data.tar.gz: 7a56c16b7bfe38543c8d217d9307dc4f18ea5d21
 SHA512:
-  metadata.gz: f21a59e7fc5bf7e9cf77721ed50935a85a3123cb4fcc74a0a556666721d13449de00c93464e3defb8f3552f1872b7c2df49ea2168810354dd89946eaa5035205
-  data.tar.gz: e202cb7e0f00eb15b76cb91ccafb55b00fbe1269b617088f8d601b7f94d55b56fd900ecef578584fbaebacebaffe3c5e999e56a069b9a5c672921435e9bfb7b7
+  metadata.gz: 526abeb2d9b53cc0b0d26b3688d9b01ed44dea5d9b010d575b64922c8b3ae3d7097134db5fe23cff29855aa05f46449563ce7fcc575601a30e901782d90aaf7d
+  data.tar.gz: 8702f8ba681c9e161f97f76cfd763593ad266a77acf813a194ecbc7390ef08d46d6c0a68d6b60bebe46f2b9d86bc6bb0a1dbf51c0f1ae3861d33b27e775b1e59

data/Gemfile

@@ -15,4 +15,5 @@ group :development do
   gem "jeweler", "~> 2.0"
   gem "bundler", "~> 1.6"
   gem "rspec", "~> 2.99"
+  gem 'pry', '~>0.10'
 end

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.1.0

data/bin/dirseq

@@ -4,7 +4,6 @@ require 'optparse'
 require 'bio-logger'
 require 'bio'
 require 'bio-commandeer'
-#require 'pry'
 require 'set'
 require 'tempfile'
 
@@ -95,12 +94,12 @@ end
 # Remove the ##FASTA and afterwards from the GFF file as this makes bedtools <2.25 fail
 # https://github.com/arq5x/bedtools2/issues/235#issuecomment-103776618
 no_fasta_gff = Tempfile.new('dirseq')
-Bio::Commandeer.run "sed '/^##FASTA$/,$d' #{gff_file.inspect} > #{no_fasta_gff.path}"
+Bio::Commandeer.run "sed '/^##FASTA$/,$d' #{gff_file.inspect} > #{no_fasta_gff.path}", :log => log
 gff_file = no_fasta_gff.path
 
 covs_fwd = nil
 if options[:ignore_directions]
-  cmd1 = "bedtools coverage -abam #{bam_file.inspect} -b #{gff_file.inspect} -hist"
+  cmd1 = "bedtools coverage -b #{bam_file.inspect} -a #{gff_file.inspect} -hist"
   cov_lines_fwd = Bio::Commandeer.run cmd1, :log => log
   log.info "Parsing coverage profiles"
   covs_fwd = get_covs.call(cov_lines_fwd)
@@ -109,10 +108,10 @@ else
   # fwd read 1
   read1_flag = '-F128' #account for read1 in pair, as well as single reads mapping
   read2_flag = '-f128'
-  cmdf1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -abam /dev/stdin -b #{gff_file.inspect} -hist -s"
-  cmdf2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -abam /dev/stdin -b #{gff_file.inspect} -hist -s"
-  cmdr1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -abam /dev/stdin -b #{gff_file.inspect} -hist -S"
-  cmdr2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -abam /dev/stdin -b #{gff_file.inspect} -hist -S"
+  cmdf1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -s"
+  cmdf2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -s"
+  cmdr1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -S"
+  cmdr2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -S"
 
   command_to_parsed = lambda do |cmds, name|
     covs_lines_initial = cmds.collect do |cmd|
@@ -122,7 +121,6 @@ else
       log.info "Parsing #{name}"
       get_covs.call(lines)
     end
-    #binding.pry
     covs = covs_initial[0]
     covs_initial[1].each do |cov_key, cov|
       covs[cov_key] += cov

data/spec/data/realer.gff

@@ -0,0 +1,3 @@
+##gff-version 3
+##sequence-region contig_100 1 42207
+contig_100	Prodigal_v2.60	CDS	2	127	0.5	+	0	ID=PROKKA_00001;eC_number=2.1.1.-;gene=ycgJ_1;inference=ab initio prediction:Prodigal:2.60,similar to AA sequence:UniProtKB:O31474;locus_tag=PROKKA_00001;product=putative methyltransferase YcgJ

data/spec/script_spec.rb

@@ -39,4 +39,16 @@ describe 'script' do
 
     found.should == answer
   end
+
+  it 'should print annotation out properly' do
+    answer = %w(
+    contig	type	start	end	strand	forward_average_coverage	reverse_average_coverage	annotation
+    ).join("\t")+"\n"+%w(
+    contig_100	CDS	2	127	+	0.0	1.1428571428571428	putative
+    ).join("\t")+" methyltransferase YcgJ\n"
+
+    found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/realer.gff -q"
+
+    found.should == answer
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dirseq
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.1.0
 platform: ruby
 authors:
 - Ben J. Woodcroft
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-09 00:00:00.000000000 Z
+date: 2016-01-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-commandeer
@@ -142,6 +142,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.99'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.10'
 description: FPKG (gene expression metric) calculator for metatranscriptomics
 email: donttrustben near gmail.com
 executables:
@@ -164,6 +178,7 @@ files:
 - spec/data/eg.bam
 - spec/data/eg.gff
 - spec/data/eg_with_fasta.gff
+- spec/data/realer.gff
 - spec/script_spec.rb
 - spec/spec_helper.rb
 homepage: http://github.com/wwood/dirseq
@@ -186,7 +201,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.4.5.1
 signing_key: 
 specification_version: 4
 summary: FPKG calculator for metatranscriptomics