dirseq 0.0.2 → 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Gemfile +1 -0
- data/VERSION +1 -1
- data/bin/dirseq +6 -8
- data/spec/data/realer.gff +3 -0
- data/spec/script_spec.rb +12 -0
- metadata +18 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 7b2362c43bff2a2cd43f0dc727bf8d713e4ab3c4
|
4
|
+
data.tar.gz: 7a56c16b7bfe38543c8d217d9307dc4f18ea5d21
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 526abeb2d9b53cc0b0d26b3688d9b01ed44dea5d9b010d575b64922c8b3ae3d7097134db5fe23cff29855aa05f46449563ce7fcc575601a30e901782d90aaf7d
|
7
|
+
data.tar.gz: 8702f8ba681c9e161f97f76cfd763593ad266a77acf813a194ecbc7390ef08d46d6c0a68d6b60bebe46f2b9d86bc6bb0a1dbf51c0f1ae3861d33b27e775b1e59
|
data/Gemfile
CHANGED
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.0
|
1
|
+
0.1.0
|
data/bin/dirseq
CHANGED
@@ -4,7 +4,6 @@ require 'optparse'
|
|
4
4
|
require 'bio-logger'
|
5
5
|
require 'bio'
|
6
6
|
require 'bio-commandeer'
|
7
|
-
#require 'pry'
|
8
7
|
require 'set'
|
9
8
|
require 'tempfile'
|
10
9
|
|
@@ -95,12 +94,12 @@ end
|
|
95
94
|
# Remove the ##FASTA and afterwards from the GFF file as this makes bedtools <2.25 fail
|
96
95
|
# https://github.com/arq5x/bedtools2/issues/235#issuecomment-103776618
|
97
96
|
no_fasta_gff = Tempfile.new('dirseq')
|
98
|
-
Bio::Commandeer.run "sed '/^##FASTA$/,$d' #{gff_file.inspect} > #{no_fasta_gff.path}"
|
97
|
+
Bio::Commandeer.run "sed '/^##FASTA$/,$d' #{gff_file.inspect} > #{no_fasta_gff.path}", :log => log
|
99
98
|
gff_file = no_fasta_gff.path
|
100
99
|
|
101
100
|
covs_fwd = nil
|
102
101
|
if options[:ignore_directions]
|
103
|
-
cmd1 = "bedtools coverage -
|
102
|
+
cmd1 = "bedtools coverage -b #{bam_file.inspect} -a #{gff_file.inspect} -hist"
|
104
103
|
cov_lines_fwd = Bio::Commandeer.run cmd1, :log => log
|
105
104
|
log.info "Parsing coverage profiles"
|
106
105
|
covs_fwd = get_covs.call(cov_lines_fwd)
|
@@ -109,10 +108,10 @@ else
|
|
109
108
|
# fwd read 1
|
110
109
|
read1_flag = '-F128' #account for read1 in pair, as well as single reads mapping
|
111
110
|
read2_flag = '-f128'
|
112
|
-
cmdf1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -
|
113
|
-
cmdf2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -
|
114
|
-
cmdr1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -
|
115
|
-
cmdr2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -
|
111
|
+
cmdf1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -s"
|
112
|
+
cmdf2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -s"
|
113
|
+
cmdr1 = "samtools view -u #{read1_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -S"
|
114
|
+
cmdr2 = "samtools view -u #{read2_flag} #{bam_file.inspect} |bedtools coverage -b /dev/stdin -a #{gff_file.inspect} -hist -S"
|
116
115
|
|
117
116
|
command_to_parsed = lambda do |cmds, name|
|
118
117
|
covs_lines_initial = cmds.collect do |cmd|
|
@@ -122,7 +121,6 @@ else
|
|
122
121
|
log.info "Parsing #{name}"
|
123
122
|
get_covs.call(lines)
|
124
123
|
end
|
125
|
-
#binding.pry
|
126
124
|
covs = covs_initial[0]
|
127
125
|
covs_initial[1].each do |cov_key, cov|
|
128
126
|
covs[cov_key] += cov
|
@@ -0,0 +1,3 @@
|
|
1
|
+
##gff-version 3
|
2
|
+
##sequence-region contig_100 1 42207
|
3
|
+
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
CHANGED
@@ -39,4 +39,16 @@ describe 'script' do
|
|
39
39
|
|
40
40
|
found.should == answer
|
41
41
|
end
|
42
|
+
|
43
|
+
it 'should print annotation out properly' do
|
44
|
+
answer = %w(
|
45
|
+
contig type start end strand forward_average_coverage reverse_average_coverage annotation
|
46
|
+
).join("\t")+"\n"+%w(
|
47
|
+
contig_100 CDS 2 127 + 0.0 1.1428571428571428 putative
|
48
|
+
).join("\t")+" methyltransferase YcgJ\n"
|
49
|
+
|
50
|
+
found = Bio::Commandeer.run "#{path_to_script} --bam #{data_dir}/eg.bam --gff #{data_dir}/realer.gff -q"
|
51
|
+
|
52
|
+
found.should == answer
|
53
|
+
end
|
42
54
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dirseq
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0
|
4
|
+
version: 0.1.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ben J. Woodcroft
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2016-01-08 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bio-commandeer
|
@@ -142,6 +142,20 @@ dependencies:
|
|
142
142
|
- - "~>"
|
143
143
|
- !ruby/object:Gem::Version
|
144
144
|
version: '2.99'
|
145
|
+
- !ruby/object:Gem::Dependency
|
146
|
+
name: pry
|
147
|
+
requirement: !ruby/object:Gem::Requirement
|
148
|
+
requirements:
|
149
|
+
- - "~>"
|
150
|
+
- !ruby/object:Gem::Version
|
151
|
+
version: '0.10'
|
152
|
+
type: :development
|
153
|
+
prerelease: false
|
154
|
+
version_requirements: !ruby/object:Gem::Requirement
|
155
|
+
requirements:
|
156
|
+
- - "~>"
|
157
|
+
- !ruby/object:Gem::Version
|
158
|
+
version: '0.10'
|
145
159
|
description: FPKG (gene expression metric) calculator for metatranscriptomics
|
146
160
|
email: donttrustben near gmail.com
|
147
161
|
executables:
|
@@ -164,6 +178,7 @@ files:
|
|
164
178
|
- spec/data/eg.bam
|
165
179
|
- spec/data/eg.gff
|
166
180
|
- spec/data/eg_with_fasta.gff
|
181
|
+
- spec/data/realer.gff
|
167
182
|
- spec/script_spec.rb
|
168
183
|
- spec/spec_helper.rb
|
169
184
|
homepage: http://github.com/wwood/dirseq
|
@@ -186,7 +201,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
186
201
|
version: '0'
|
187
202
|
requirements: []
|
188
203
|
rubyforge_project:
|
189
|
-
rubygems_version: 2.
|
204
|
+
rubygems_version: 2.4.5.1
|
190
205
|
signing_key:
|
191
206
|
specification_version: 4
|
192
207
|
summary: FPKG calculator for metatranscriptomics
|