lederhosen 0.4.0 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lederhosen.gemspec +1 -2
- data/lib/lederhosen/version.rb +1 -1
- data/spec/cli_spec.rb +0 -5
- metadata +3 -4
- data/lib/lederhosen/tasks/uniquify.rb +0 -61
data/lederhosen.gemspec
CHANGED
@@ -5,7 +5,7 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = "lederhosen"
|
8
|
-
s.version = "0.
|
8
|
+
s.version = "0.5.0"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["Austin G. Davis-Richardson"]
|
@@ -45,7 +45,6 @@ Gem::Specification.new do |s|
|
|
45
45
|
"lib/lederhosen/tasks/trim.rb",
|
46
46
|
"lib/lederhosen/tasks/uc_filter.rb",
|
47
47
|
"lib/lederhosen/tasks/uc_stats.rb",
|
48
|
-
"lib/lederhosen/tasks/uniquify.rb",
|
49
48
|
"lib/lederhosen/tasks/version.rb",
|
50
49
|
"lib/lederhosen/version.rb",
|
51
50
|
"readme.md",
|
data/lib/lederhosen/version.rb
CHANGED
data/spec/cli_spec.rb
CHANGED
@@ -45,11 +45,6 @@ describe Lederhosen::CLI do
|
|
45
45
|
`./bin/lederhosen otu_filter --input=#{$test_dir}/otu_table.csv --output=#{$test_dir}/otu_table.filtered.csv --reads 1 --samples 1`
|
46
46
|
end
|
47
47
|
|
48
|
-
it 'should uniquify reads' do
|
49
|
-
`./bin/lederhosen uniquify --input=#{$test_dir}/sorted.fasta --output=#{$test_dir}/uniqued.fasta --table-out=#{$test_dir}/uniquify.txt`
|
50
|
-
$?.success?.should be_true
|
51
|
-
end
|
52
|
-
|
53
48
|
it 'should split joined.fasta into reads for each cluster' do
|
54
49
|
`./bin/lederhosen split --reads=#{$test_dir}/joined.fasta --clusters=#{$test_dir}/clusters.uc --out-dir=#{$test_dir}/split --min-clst-size=1`
|
55
50
|
end
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: lederhosen
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 11
|
5
5
|
prerelease:
|
6
6
|
segments:
|
7
7
|
- 0
|
8
|
-
-
|
8
|
+
- 5
|
9
9
|
- 0
|
10
|
-
version: 0.
|
10
|
+
version: 0.5.0
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Austin G. Davis-Richardson
|
@@ -141,7 +141,6 @@ files:
|
|
141
141
|
- lib/lederhosen/tasks/trim.rb
|
142
142
|
- lib/lederhosen/tasks/uc_filter.rb
|
143
143
|
- lib/lederhosen/tasks/uc_stats.rb
|
144
|
-
- lib/lederhosen/tasks/uniquify.rb
|
145
144
|
- lib/lederhosen/tasks/version.rb
|
146
145
|
- lib/lederhosen/version.rb
|
147
146
|
- readme.md
|
@@ -1,61 +0,0 @@
|
|
1
|
-
##
|
2
|
-
# uniquify - uniquify a fasta file generating a fasta file of only unique sequences
|
3
|
-
# also output table with sequence_id -> number of reads
|
4
|
-
#
|
5
|
-
|
6
|
-
module Lederhosen
|
7
|
-
class CLI
|
8
|
-
desc 'uniquify',
|
9
|
-
'uniquify a fasta file generating a fasta file of only unique sequences.' +\
|
10
|
-
'also generate a table with sequence_id -> abundance'
|
11
|
-
|
12
|
-
method_option :input, :type => :string, :required => true
|
13
|
-
method_option :output, :type => :string, :required => true
|
14
|
-
method_option :table_out, :type => :string, :required => true
|
15
|
-
|
16
|
-
def uniquify
|
17
|
-
input = options[:input]
|
18
|
-
output = options[:output]
|
19
|
-
table_out = options[:table_out]
|
20
|
-
|
21
|
-
ohai "uniquifying #{input} to #{output} w/ table #{table_out}"
|
22
|
-
|
23
|
-
sequence_counts = Hash.new { |h, k| h[k] = 0 }
|
24
|
-
sequence_to_id = Hash.new
|
25
|
-
|
26
|
-
out = File.open(output, 'w')
|
27
|
-
|
28
|
-
File.open(input) do |handle|
|
29
|
-
pbar = ProgressBar.new 'loading', File.size(input)
|
30
|
-
Dna.new(handle).each do |record|
|
31
|
-
pbar.inc handle.pos
|
32
|
-
unless sequence_counts.has_key? record.sequence
|
33
|
-
# store the sequence and id so we can have ids in the
|
34
|
-
# table. If the file is sorted by length then this
|
35
|
-
# should also be a seed sequence.
|
36
|
-
sequence_to_id[record.sequence] = record.name
|
37
|
-
out.puts record
|
38
|
-
end
|
39
|
-
sequence_counts[record.sequence] += 1
|
40
|
-
end
|
41
|
-
pbar.finish
|
42
|
-
end
|
43
|
-
|
44
|
-
out.close
|
45
|
-
|
46
|
-
# write table
|
47
|
-
pbar = ProgressBar.new 'table', sequence_counts.size
|
48
|
-
File.open(table_out, 'w') do |out|
|
49
|
-
sequence_counts.each_pair do |sequence, count|
|
50
|
-
pbar.inc
|
51
|
-
id = sequence_to_id[sequence]
|
52
|
-
out.puts "#{id}\t#{count}"
|
53
|
-
end
|
54
|
-
end
|
55
|
-
pbar.finish
|
56
|
-
kept = sequence_counts.keys.size
|
57
|
-
total = sequence_counts.values.inject(:+)
|
58
|
-
ohai "kept #{kept} out of #{total} reads (#{100*kept/total.to_f})"
|
59
|
-
end
|
60
|
-
end
|
61
|
-
end
|