bio-rocker 0.2.1beta → 0.2.4
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/bin/ROCker +1 -1
- data/lib/rocker.rb +9 -5
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: d1f7834b90614d13e3b1c8f23b56e282b65066aa
|
4
|
+
data.tar.gz: 80cb0cf8a692ee23421167d5d0e7822124fb51f8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0592a06d98989b18dc7be92243288df57cf01c623e694d3faafd5f800843290b055dba586195a3bac8439d178c9372c77e5a195f47f20fb5142f4e0bae28fc7e
|
7
|
+
data.tar.gz: 88d41e820e038df84995bce99b17551a17181f81e07adf0d1969ff1ece7d53704f25699b44d8748865f00f9dbac77f6c3897b71fec034f04682d1058ed2422c3
|
data/bin/ROCker
CHANGED
@@ -54,7 +54,7 @@ opts = OptionParser.new do |opt|
|
|
54
54
|
opt.on("-v", "--overlap NUMBER", "Minimum overlap with reference gene to tag a read as positive. By default: '#{ROCker.default :minovl}'."){ |v| o[:minovl]=v.to_f }
|
55
55
|
opt.on( "--genome-frx NUMBER", "Fraction to subsample the positive set genomes to generate the metagenome. By default: #{ROCker.default :genomefrx}"){ |v| o[:genomefrx]=v.to_f }
|
56
56
|
opt.on( "--per-taxon RANK", "If selected, only one genome per taxon is used to build the metagenome. Valid ranks include: species, genus, family, order, class, phylum.",
|
57
|
-
"This option replaces --per-genus and --per-species
|
57
|
+
"This option replaces --per-genus and --per-species from v0.1.*."){ |v| o[:pertaxon]=v.downcase }
|
58
58
|
opt.on( "--nometagenome", "Do not create metagenome. Implies --noblast. By default, metagenome is created."){ |v| o[:nomg]=v }
|
59
59
|
opt.on( "--noblast", "Do not execute BLAST. By default, BLAST is executed."){ |v| o[:noblast]=v }
|
60
60
|
opt.on( "--noalignment", "Do not align reference set. By default, references are aligned."){ |v| o[:noaln]=v }
|
data/lib/rocker.rb
CHANGED
@@ -2,7 +2,7 @@
|
|
2
2
|
# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
3
3
|
# @author Luis (Coto) Orellana
|
4
4
|
# @license artistic license 2.0
|
5
|
-
# @update May-
|
5
|
+
# @update May-14-2015
|
6
6
|
#
|
7
7
|
|
8
8
|
require 'rocker/blasthit'
|
@@ -18,7 +18,7 @@ class ROCker
|
|
18
18
|
:positive=>[], :negative=>[], :thr=>2,:genomefrx=>1.0,
|
19
19
|
# ext. software
|
20
20
|
:grinder=>'grinder', :muscle=>'muscle', :blastbins=>'', :seqdepth=>3, :minovl=>0.75,
|
21
|
-
:grindercmd=>'%1$s -reference_file "%2$s" -cf "%3$f" -base_name "%4$s" -dc \'-~*Nn\' -md "
|
21
|
+
:grindercmd=>'%1$s -reference_file "%2$s" -cf "%3$f" -base_name "%4$s" -dc \'-~*Nn\' -md "uniform 0.1" -mr "95 5" -rd "100 uniform 5"',
|
22
22
|
:musclecmd=>'%1$s -in "%2$s" -out "%3$s" -quiet',
|
23
23
|
:blastcmd=>'%1$s%2$s -query "%3$s" -db "%4$s" -out "%5$s" -num_threads %6$d -outfmt 6 -max_target_seqs 1',
|
24
24
|
:makedbcmd=>'%1$smakeblastdb -dbtype %2$s -in "%3$s" -out "%4$s"',
|
@@ -132,8 +132,10 @@ class ROCker
|
|
132
132
|
doc = res.split("\n").grep(/^[^#]/)
|
133
133
|
end
|
134
134
|
doc.each do |ln|
|
135
|
+
next if ln =~ /^#/
|
135
136
|
r = ln.chomp.split /\t/
|
136
|
-
|
137
|
+
next if r.size < 9
|
138
|
+
prots = r[8].split(/;/).grep(/^db_xref=UniProtKB[\/A-Za-z-]*:/){ |xref| xref.split(/:/)[1] }
|
137
139
|
p = prots.select{ |p| @o[:positive].include? p }.first
|
138
140
|
next if p.nil?
|
139
141
|
positive_coords[ r[0] ] ||= []
|
@@ -148,10 +150,12 @@ class ROCker
|
|
148
150
|
print "\n" unless @o[:q]
|
149
151
|
unless @o[:pertaxon].nil?
|
150
152
|
genome_ids[:positive] = genome_org.values
|
151
|
-
puts " Using #{genome_org.size}
|
153
|
+
puts " Using #{genome_org.size} genome(s) after filtering by #{@o[:pertaxon]}." unless @o[:q]
|
152
154
|
end
|
153
155
|
all_genome_ids = genome_ids.values.reduce(:+).uniq
|
154
|
-
|
156
|
+
found = positive_coords.values.map{ |a| a.map{ |b| b[:prot_id] } }.reduce(:+)
|
157
|
+
raise "Cannot find the genomic location of any provided sequence." if found.nil?
|
158
|
+
missing = @o[:positive] - found
|
155
159
|
warn "\nWARNING: Cannot find genomic location of sequence(s) #{missing.join(',')}.\n\n" unless missing.size==0 or @o[:genomefrx]<1.0 or not @o[:pertaxon].nil?
|
156
160
|
|
157
161
|
# Download genomes
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: bio-rocker
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Luis (Coto) Orellana
|
@@ -56,9 +56,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
56
56
|
version: '0'
|
57
57
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - '
|
59
|
+
- - '>='
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version:
|
61
|
+
version: '0'
|
62
62
|
requirements: []
|
63
63
|
rubyforge_project:
|
64
64
|
rubygems_version: 2.0.14
|