dirseq 0.0.2 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 84e91d3823af5395053c2104197b68223d3e4d96
-  data.tar.gz: 7488e7557cd4005dcfc8b6f3c504d4e250434e5b
+SHA256:
+  metadata.gz: 9ff1307d262c875afd01391fccb60007735127dda4fa1303c17c246fbcc1262c
+  data.tar.gz: 0e040b3e9688aa214da2d2bffc1480b207f8fdc836c75d5bbd9de9199fb67394
 SHA512:
-  metadata.gz: f21a59e7fc5bf7e9cf77721ed50935a85a3123cb4fcc74a0a556666721d13449de00c93464e3defb8f3552f1872b7c2df49ea2168810354dd89946eaa5035205
-  data.tar.gz: e202cb7e0f00eb15b76cb91ccafb55b00fbe1269b617088f8d601b7f94d55b56fd900ecef578584fbaebacebaffe3c5e999e56a069b9a5c672921435e9bfb7b7
+  metadata.gz: d6ef576145d863fae37da16dbc6e224572a9928bc5293fd471c7fa4c831e5f69ac8a9eeb272d5dd8b531f48c791476e4a514d63de3be4a17a5f48f21017d9a61
+  data.tar.gz: 49bae83cf0ad60ec57b91e51931cb380369c04921296552024620d9a837b77f4875f1b09e4fd5b69871c5e905423b64da0d974400f3953423f9e4eadacabc61d

data/Gemfile

@@ -9,10 +9,10 @@ gem "bio", "~>1.4", ">=1.4.2"
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
 group :development do
-  gem "shoulda", "~> 3.5"
-  gem "rdoc", "~> 3.12"
-  gem "simplecov", "~> 0.8"
-  gem "jeweler", "~> 2.0"
-  gem "bundler", "~> 1.6"
-  gem "rspec", "~> 2.99"
+  #gem "shoulda", "~> 3.5"
+  #gem "simplecov", "~> 0.8"
+  gem "jeweler", "~> 2.3"
+  gem "bundler", "~> 2.1"
+  gem "rspec", "~> 3.0"
+  gem 'pry', '~>0.10'
 end

data/README.md

@@ -13,8 +13,8 @@ Won't work just yet:
 gem install dirseq
 ```
 Requires:
-* samtools (tested with 0.1.19)
-* bedtools (tested with 2.20.1)
+* samtools (tested with 0.1.19 and 1.0+)
+* bedtools (tested with 2.24.0) - old versions won't work.
 * Ruby (tested with 2.1.1)
 
 ## Usage
@@ -32,8 +32,13 @@ $ dirseq -h
 
 Optional parameters:
 
+        --forward-read-only          consider only forward reads (i.e. read1) and ignore reverse reads. [default false]
         --ignore-directions          ignore directionality, give overall coverage [default: false i.e. differentiate between directions]
-
+        --measure-type TYPE          what to count for each gene [options: count, coverage][default: coverage]
+        --accepted-feature-types TYPE
+                                     Print only features of these type(s) [default CDS]
+        --comment-fields             Print elements from the comments in the GFF file [default ID]
+        
 Verbosity:
 
     -q, --quiet                      Run quietly, set logging to ERROR level [default INFO]

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.4.0

data/bin/dirseq

@@ -4,17 +4,31 @@ require 'optparse'
 require 'bio-logger'
 require 'bio'
 require 'bio-commandeer'
-#require 'pry'
 require 'set'
 require 'tempfile'
 
 SCRIPT_NAME = File.basename(__FILE__); LOG_NAME = SCRIPT_NAME.gsub('.rb','')
 
+COVERAGE_COUNT_TYPE = 'coverage'
+COUNT_COUNT_TYPE = 'count'
+COUNT_TYPES = [
+  COUNT_COUNT_TYPE,
+  COVERAGE_COUNT_TYPE
+]
+
 # Parse command line options into the options hash
 options = {
   :ignore_directions => false,
   :logger => 'stderr',
   :log_level => 'info',
+  :count_type => COVERAGE_COUNT_TYPE,
+  :forward_read_only => false,
+  :accepted_feature_types => ['CDS'],
+<<<<<<< HEAD
+  :comment_fields_to_print => ['ID'],
+=======
+  :sam_filter_flags => "-F0x100 -F0x800",
+>>>>>>> d6f450a... dirseq: Filter out non-primary and supplementary aligns.
 }
 o = OptionParser.new do |opts|
   opts.banner = "
@@ -29,9 +43,27 @@ o = OptionParser.new do |opts|
     options[:gff] = arg
   end
   opts.separator "\nOptional parameters:\n\n"
+  opts.on("--forward-read-only", "consider only forward reads (i.e. read1) and ignore reverse reads. [default #{options[:forward_read_only]}]") do
+    options[:forward_ready_only] = true
+  end
   opts.on("--ignore-directions", "ignore directionality, give overall coverage [default: false i.e. differentiate between directions]") do |arg|
     options[:ignore_directions] = true
   end
+  opts.on("--measure-type TYPE", "what to count for each gene [options: #{COUNT_TYPES.join(', ')}][default: #{options[:count_type]}]") do |arg|
+    raise "Unexpected count type detected" if not COUNT_TYPES.include?(arg)
+    options[:count_type] = arg
+  end
+  opts.on("--accepted-feature-types TYPE", Array,
+          "Print only features of these type(s) [default #{options[:accepted_feature_types].join(',')}]") do |arg|
+    options[:accepted_feature_types] = Set.new(arg)
+  end
+  opts.on("--comment-fields", Array,
+          "Print elements from the comments in the GFF file [default #{options[:comment_fields_to_print].join(',')}]") do |arg|
+    options[:comment_fields_to_print] = arg
+  end
+  opts.on("--sam-filter-flags", "Apply these samtools filters [default: #{options[:sam_filter_flags]}]") do |arg|
+    options[:sam_filter_flags] = arg
+  end
 
   # logger options
   opts.separator "\nVerbosity:\n\n"
@@ -48,6 +80,11 @@ Bio::Log::CLI.logger(options[:logger]); Bio::Log::CLI.trace(options[:log_level])
 
 gff_file = options[:gff]
 bam_file = options[:bam]
+accepted_feature_types = options[:accepted_feature_types]
+
+if options[:count_type] != COVERAGE_COUNT_TYPE and options[:ignore_directions]
+  raise "ignore_directions + count_type != coverage is currently unsupported"
+end
 
 
 calculate_cov = lambda do |covs, num_covs|
@@ -77,14 +114,26 @@ get_covs = lambda do |cov_lines|
     #96 #coverage
     #0.0208333
     feat = splits[0..8]
+    feature_type = feat[2]
+    if not accepted_feature_types.include?(feature_type)
+      log.debug "Skipping feature as it is of type #{feature_type}"
+      next
+    end
     if feat != previous_feature
       feature_to_covs[previous_feature] = calculate_cov.call(covs, num_covs) unless previous_feature.nil?
       covs = []
       num_covs = 0
     end
-    num = splits[10].to_i
-    covs.push num*splits[9].to_i
-    num_covs += num
+    if splits.length == 13 # -hist
+      num = splits[10].to_i
+      covs.push num*splits[9].to_i
+      num_covs += num
+    elsif splits.length == 10 # -count
+      covs.push splits[9].to_i
+      num_covs += 1
+    else
+      raise "Unexpected bedtools output line: #{line}"
+    end
     previous_feature = feat
   end
   feature_to_covs[previous_feature] = calculate_cov.call(covs, num_covs)
@@ -94,13 +143,57 @@ 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}"
+no_fasta_gff = Tempfile.new(['dirseq','.gff3'])
+Bio::Commandeer.run "sed '/^##FASTA$/,$d' #{gff_file.inspect} > #{no_fasta_gff.path}", :log => log
 gff_file = no_fasta_gff.path
 
+
+
+
+
+# Find featureless contigs. Need to so that bedtools coverage -sorted does not complain
+if not File.exists?("#{bam_file}.bai")
+  raise "Input bam file must be indexed, but the index file does not exist"
+end
+
+chromosome_file = Tempfile.new('bam_contigs')
+log.info "Listing contigs in sorted order .."
+cmd = "samtools idxstats #{bam_file.inspect} |cut -f1,2 |grep -v '^*' >#{chromosome_file.path.inspect}"
+Bio::Commandeer.run(cmd, :log => log)
+
+log.info "Finding featureless contigs"
+cmd = "grep -v '^#' #{gff_file.inspect} |cut -f1 |sort |uniq |grep -vFw -f /dev/stdin #{chromosome_file.path.inspect} |cut -f1"
+featureless_contigs = Bio::Commandeer.run(cmd, :log => log).lines.map(&:chomp).reject{ |ref| ref=='*' }
+log.info "Found #{featureless_contigs.length} featureless contigs"
+
+# Sort the GFF
+dummy_features = featureless_contigs.collect do |ref|
+  [ref,
+   'dirseq',
+   'misc_RNA',
+   '1',
+   '2',
+   '.',
+   '+',
+   '0',
+   "ID=#{ref}_dummy_feature"].join("\t")
+end
+sorted_gff_file_f = Tempfile.new(['sorted_gff','.gff3'])
+sorted_gff_file = sorted_gff_file_f.path
+Tempfile.open(["extra_features",'.gff']) do |ef|
+  ef.puts dummy_features.join("\n")
+  ef.close
+
+  cmd = "cat #{ef.path} #{gff_file.inspect} |bedtools sort -i /dev/stdin -faidx #{chromosome_file.path.inspect} >#{sorted_gff_file.inspect}"
+  log.info "Running bedtools sort"
+  Bio::Commandeer.run(cmd, :log => log)
+end
+
+
+
 covs_fwd = nil
 if options[:ignore_directions]
-  cmd1 = "bedtools coverage -abam #{bam_file.inspect} -b #{gff_file.inspect} -hist"
+  cmd1 = "samtools view -u #{options[:sam_filter_flags]} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -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 +202,14 @@ 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"
+  bedtools_type_flag = '-hist'
+  if options[:count_type] == COUNT_COUNT_TYPE
+    bedtools_type_flag = '-counts'
+  end
+  cmdf1 = "samtools view #{options[:sam_filter_flags]} -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -sorted -g #{chromosome_file.path.inspect} -b /dev/stdin -a #{sorted_gff_file.inspect} -s #{bedtools_type_flag}"
+  cmdf2 = "samtools view #{options[:sam_filter_flags]} -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -sorted -g #{chromosome_file.path.inspect} -b /dev/stdin -a #{sorted_gff_file.inspect} -s #{bedtools_type_flag}"
+  cmdr1 = "samtools view #{options[:sam_filter_flags]} -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -sorted -g #{chromosome_file.path.inspect} -b /dev/stdin -a #{sorted_gff_file.inspect} -S #{bedtools_type_flag}"
+  cmdr2 = "samtools view #{options[:sam_filter_flags]} -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -sorted -g #{chromosome_file.path.inspect} -b /dev/stdin -a #{sorted_gff_file.inspect} -S #{bedtools_type_flag}"
 
   command_to_parsed = lambda do |cmds, name|
     covs_lines_initial = cmds.collect do |cmd|
@@ -122,17 +219,24 @@ 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
+    if covs_initial.length > 1
+      covs_initial[1].each do |cov_key, cov|
+        covs[cov_key] += cov
+      end
     end
     covs #'return' from lambda
   end
 
   # Agreeing reads (those whose template are fwd along the reference sequence) are either first and fwd, or second and rev
-  covs_fwd = command_to_parsed.call([cmdf1,cmdr2], 'reads with same direction as their reference')
-  covs_rev = command_to_parsed.call([cmdf2,cmdr1], 'reads with opposing direction as their reference')
+  commands_fwd = [cmdf1,cmdr2]
+  commands_rev = [cmdf2,cmdr1]
+  if options[:forward_ready_only]
+    commands_fwd = [cmdf1]
+    commands_rev = [cmdr1]
+  end
+  covs_fwd = command_to_parsed.call(commands_fwd, 'reads with same direction as their reference')
+  covs_rev = command_to_parsed.call(commands_rev, 'reads with opposing direction as their reference')
 end
 
 headers = [
@@ -144,11 +248,19 @@ headers = [
 ]
 if options[:ignore_directions]
   headers.push 'average_coverage'
-else
+elsif options[:count_type] == COVERAGE_COUNT_TYPE
   headers.push 'forward_average_coverage'
   headers.push 'reverse_average_coverage'
+elsif options[:count_type] == COUNT_COUNT_TYPE
+  headers.push 'forward_read_count'
+  headers.push 'reverse_read_count'
+else
+  raise
 end
 headers.push 'annotation'
+options[:comment_fields_to_print].each do |field|
+  headers.push field
+end
 puts headers.join("\t")
 
 covs_fwd.each do |feature, cov_fwd|
@@ -171,5 +283,13 @@ covs_fwd.each do |feature, cov_fwd|
   ]
   to_print.push cov_rev unless options[:ignore_directions]
   to_print.push product
+  options[:comment_fields_to_print].each do |field|
+    answer1 = record.attributes.select{|a| a[0] == field}
+    if answer1.empty?
+      to_print.push ''
+    else
+      to_print.push answer1[0][1]
+    end
+  end
   puts to_print.join("\t")
 end

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

@@ -6,9 +6,9 @@ describe 'script' do
 
   it "should regular mode" do
     answer = %w(
-    contig	type	start	end	strand	forward_average_coverage	reverse_average_coverage	annotation
+    contig	type	start	end	strand	forward_average_coverage	reverse_average_coverage	annotation	ID
     ).join("\t")+"\n"+%w(
-    contig_100	CDS	2	127	+	0.0	1.1428571428571428	unannotated
+    contig_100	CDS	2	127	+	0.0	1.1428571428571428	unannotated	40_1
     ).join("\t")+"\n"
 
     found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/eg.gff -q"
@@ -20,9 +20,9 @@ describe 'script' do
     found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/eg.gff -q --ignore-direction"
 
     answer = %w(
-    contig	type	start	end	strand	average_coverage	annotation
+    contig	type	start	end	strand	average_coverage	annotation	ID
     ).join("\t")+"\n"+%w(
-    contig_100	CDS	2	127	+	1.1428571428571428	unannotated
+    contig_100	CDS	2	127	+	1.1428571428571428	unannotated	40_1
     ).join("\t")+"\n"
 
     found.should == answer
@@ -30,13 +30,49 @@ describe 'script' do
 
   it 'should not fail when the GFF has a FASTA section' do
     answer = %w(
-    contig	type	start	end	strand	forward_average_coverage	reverse_average_coverage	annotation
+    contig	type	start	end	strand	forward_average_coverage	reverse_average_coverage	annotation	ID
     ).join("\t")+"\n"+%w(
-    contig_100	CDS	2	127	+	0.0	1.1428571428571428	unannotated
+    contig_100	CDS	2	127	+	0.0	1.1428571428571428	unannotated	40_1
     ).join("\t")+"\n"
 
     found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/eg_with_fasta.gff -q"
 
     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	ID
+    ).join("\t")+"\n"+%w(
+    contig_100	CDS	2	127	+	0.0	1.1428571428571428	putative
+    ).join("\t")+" methyltransferase YcgJ	PROKKA_00001\n"
+
+    found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/realer.gff -q"
+
+    found.should == answer
+  end
+
+  it 'should print counts correctly' do
+    answer = %w(
+    contig	type	start	end	strand	forward_read_count	reverse_read_count	annotation	ID
+    ).join("\t")+"\n"+%w(
+    contig_100	CDS	2	127	+	0.0	2.0	putative
+    ).join("\t")+" methyltransferase YcgJ	PROKKA_00001\n"
+
+    found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/realer.gff -q --measure-type count"
+
+    found.should == answer
+  end
+
+  it 'should count only the forward read when asked' do
+    answer = %w(
+    contig	type	start	end	strand	forward_read_count	reverse_read_count	annotation	ID
+    ).join("\t")+"\n"+%w(
+    contig_100	CDS	2	127	+	0.0	1.0	putative
+    ).join("\t")+" methyltransferase YcgJ	PROKKA_00001\n"
+
+    found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/realer.gff -q --measure-type count --forward-read-only"
+
+    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: 0.4.0
 platform: ruby
 authors:
 - Ben J. Woodcroft
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2015-06-09 00:00:00.000000000 Z
+date: 2020-12-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-commandeer
@@ -42,106 +42,78 @@ dependencies:
   name: bio
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.4.2
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.4'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: 1.4.2
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.4'
-- !ruby/object:Gem::Dependency
-  name: shoulda
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.5'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
-- !ruby/object:Gem::Dependency
-  name: rdoc
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.12'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
+        version: '1.4'
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3.12'
+        version: 1.4.2
 - !ruby/object:Gem::Dependency
-  name: simplecov
+  name: jeweler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '2.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '2.3'
 - !ruby/object:Gem::Dependency
-  name: jeweler
+  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '2.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '2.1'
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '3.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.99'
+        version: '0.10'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.99'
+        version: '0.10'
 description: FPKG (gene expression metric) calculator for metatranscriptomics
 email: donttrustben near gmail.com
 executables:
@@ -162,15 +134,17 @@ files:
 - lib/bio-rnaseq_transcription_directionality.rb
 - lib/bio-rnaseq_transcription_directionality/rnaseq_transcription_directionality.rb
 - spec/data/eg.bam
+- spec/data/eg.bam.bai
 - 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
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -185,9 +159,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.2.2
-signing_key: 
+rubygems_version: 3.1.2
+signing_key:
 specification_version: 4
 summary: FPKG calculator for metatranscriptomics
 test_files: []