dirseq 0.2.0 → 0.4.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 57eb18eb4e971726d26849e01d3a4dd32597584d
-  data.tar.gz: f38d044727e8163873617fad111d3c244507fe71
+SHA256:
+  metadata.gz: d3d1019d1157dc1d53d0d802027b439d03d8cd0aeacc2670e0e7825be6a14f06
+  data.tar.gz: adc9eda6d50933442e3ee82a66757ce553e2a2aae7e92628c2ed5ed6c8304cc9
 SHA512:
-  metadata.gz: 8842180ae34fa546362dbcd63a0d07e9269b9903cdec1b078c10f5031b848d59b8f4db6d1e9708942beb84b92c639365049e8fd563c59723e861402b92771797
-  data.tar.gz: c2f035c3dba77ee68fd2861d30c4764eb61095dac654e402a47a7213ddfec651bfb401caf2b5fa015c60efa783c7a50f09a7f4573bcfb544c621bbd3e8d6b0e3
+  metadata.gz: 4bd8397bf9a8a6190d3467daf094c1909a71d90d7f0b349990291b5168954663f11ae54f971324bb7cf53663a5f4e48bbaa7722c3343ec0075f0f3634df263d9
+  data.tar.gz: 5e2dedd8e96ad9699fd949fd61a02a81c556285b2f850a268dbc7702a85f5863054da17fff0c208d3bb319139382e1770970294778ac1aaeb57796d25c5fbf2f

data/Gemfile

@@ -11,8 +11,8 @@ gem "bio", "~>1.4", ">=1.4.2"
 group :development do
   #gem "shoulda", "~> 3.5"
   #gem "simplecov", "~> 0.8"
-  gem "jeweler", "~> 2.0"
-  gem "bundler", "~> 1.6"
+  gem "juwelier", "~> 2.4", ">=2.4.9"
+  gem "bundler", "~> 2.1"
   gem "rspec", "~> 3.0"
   gem 'pry', '~>0.10'
 end

data/README.md

@@ -8,18 +8,34 @@ Note: this software is under active development!
 
 ## Installation
 
-Won't work just yet:
+Install some prerequisites via conda, and then dirseq itself:
 ```sh
+conda create -c bioconda -n dirseq -y ruby samtools bedtools'>'2.24
+conda activate dirseq
 gem install dirseq
 ```
-Requires:
+
+The following dependencies are installed above, but for completeness of documentation, dirseq requires these dependencies, on top of the Ruby ones:
 * 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
 
-Only the script is available at the moment
+Example usage:
+
+Download the example data:
+```sh
+git clone https://github.com/wwood/dirseq
+cd dirseq
+```
+
+Then run dirseq:
+```sh
+dirseq --bam spec/data/eg.bam --gff spec/data/eg.gff --measure-type count
+```
+
+Full usage help:
 ```sh
 $ dirseq -h
 
@@ -32,8 +48,14 @@ $ 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]
+        --sam-filter-flags           Apply these samtools filters [default: -F0x100 -F0x800]
+        
 Verbosity:
 
     -q, --quiet                      Run quietly, set logging to ERROR level [default INFO]
@@ -41,6 +63,11 @@ Verbosity:
         --trace options              Set log level [default INFO]. e.g. '--trace debug' to set logging level to DEBUG
 ```
 
+Running on [EnrichM](https://github.com/geronimp/enrichM) output, the output columns are changed relative to [PROKKA](https://github.com/tseemann/prokka)-generated GFF files:
+```sh
+dirseq --bam spec/data/eg.bam --gff spec/data/eg.gff --measure-type count --comment-fields seq_id,annotations
+```
+
 ## Project home page
 
 Information on the source tree, documentation, examples, issues and
@@ -52,16 +79,11 @@ The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
 
 ## Cite
 
-If you use this software, please cite one of
-
-* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
-* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
-
-## Biogems.info
+If you use this software, please cite
 
-This Biogem is published at (http://biogems.info/index.html#bio-rnaseq_transcription_directionality)
+Woodcroft, B.J., Singleton, C.M., Boyd, J.A. et al. Genome-centric view of carbon processing in thawing permafrost. Nature 560, 49–54 (2018). https://doi.org/10.1038/s41586-018-0338-1
 
 ## Copyright
 
-Copyright (c) 2014 Ben J. Woodcroft. See LICENSE.txt for further details.
+Copyright (c) 2014-2021 Ben J. Woodcroft. See LICENSE.txt for further details.
 

data/Rakefile

@@ -11,8 +11,8 @@ rescue Bundler::BundlerError => e
 end
 require 'rake'
 
-require 'jeweler'
-Jeweler::Tasks.new do |gem|
+require 'juwelier'
+Juwelier::Tasks.new do |gem|
   # gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
   gem.name = "dirseq"
   gem.homepage = "http://github.com/wwood/dirseq"
@@ -23,7 +23,7 @@ Jeweler::Tasks.new do |gem|
   gem.authors = ["Ben J. Woodcroft"]
   # dependencies defined in Gemfile
 end
-Jeweler::RubygemsDotOrgTasks.new
+Juwelier::RubygemsDotOrgTasks.new
 
 require 'rspec/core'
 require 'rspec/core/rake_task'

data/VERSION

@@ -1 +1 @@
-0.2.0
+0.4.3

data/bin/dirseq

@@ -24,6 +24,8 @@ options = {
   :count_type => COVERAGE_COUNT_TYPE,
   :forward_read_only => false,
   :accepted_feature_types => ['CDS'],
+  :comment_fields_to_print => ['ID'],
+  :sam_filter_flags => "-F0x100 -F0x800",
 }
 o = OptionParser.new do |opts|
   opts.banner = "
@@ -50,7 +52,14 @@ o = OptionParser.new do |opts|
   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(arg)
+    options[:accepted_feature_types] = Set.new(arg)
+  end
+  opts.on("--comment-fields COMMA_SEPARATED_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
@@ -146,7 +155,7 @@ end
 
 chromosome_file = Tempfile.new('bam_contigs')
 log.info "Listing contigs in sorted order .."
-cmd = "samtools idxstats #{bam_file.inspect} |cut -f1,2 >#{chromosome_file.path.inspect}"
+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"
@@ -181,7 +190,7 @@ end
 
 covs_fwd = nil
 if options[:ignore_directions]
-  cmd1 = "bedtools coverage -b #{bam_file.inspect} -a #{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)
@@ -194,10 +203,10 @@ else
   if options[:count_type] == COUNT_COUNT_TYPE
     bedtools_type_flag = '-counts'
   end
-  cmdf1 = "samtools view -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 -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 -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 -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}"
+  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|
@@ -246,6 +255,9 @@ 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|
@@ -268,5 +280,13 @@ 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/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
@@ -30,9 +30,9 @@ 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"
@@ -42,10 +42,10 @@ describe 'script' do
 
   it 'should print annotation out properly' 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	putative
-    ).join("\t")+" methyltransferase YcgJ\n"
+    ).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"
 
@@ -54,10 +54,10 @@ describe 'script' do
 
   it 'should print counts correctly' do
     answer = %w(
-    contig	type	start	end	strand	forward_read_count	reverse_read_count	annotation
+    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\n"
+    ).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"
 
@@ -66,10 +66,10 @@ describe 'script' do
 
   it 'should count only the forward read when asked' do
     answer = %w(
-    contig	type	start	end	strand	forward_read_count	reverse_read_count	annotation
+    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\n"
+    ).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"
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dirseq
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.4.3
 platform: ruby
 authors:
 - Ben J. Woodcroft
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-02-08 00:00:00.000000000 Z
+date: 2021-03-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-commandeer
@@ -42,50 +42,56 @@ dependencies:
   name: bio
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.4.2
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.4'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.4.2
   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::Version
+        version: 1.4.2
 - !ruby/object:Gem::Dependency
-  name: jeweler
+  name: juwelier
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '2.4'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.4.9
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '2.4'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.4.9
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '2.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '2.1'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -144,7 +150,7 @@ homepage: http://github.com/wwood/dirseq
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -159,9 +165,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.6.13
-signing_key: 
+rubygems_version: 3.1.2
+signing_key:
 specification_version: 4
 summary: FPKG calculator for metatranscriptomics
 test_files: []