lederhosen 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/lederhosen/cli.rb +7 -204
- data/lib/version.rb +1 -1
- metadata +3 -3
data/lib/lederhosen/cli.rb
CHANGED
@@ -1,212 +1,15 @@
|
|
1
1
|
module Lederhosen
|
2
2
|
class CLI < Thor
|
3
|
-
|
4
|
-
##
|
5
|
-
# QUALITY TRIMMING
|
6
|
-
#
|
7
|
-
desc "trim Illumina QSEQ files", "--reads_dir=reads/* --out_dir=trimmed.fasta"
|
8
|
-
method_options :reads_dir => :string, :out_dir => :string
|
9
|
-
def trim
|
10
3
|
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
raw_reads = Helpers.get_grouped_qseq_files raw_reads
|
17
|
-
puts "found #{raw_reads.length} pairs of reads"
|
18
|
-
puts "trimming!"
|
19
|
-
|
20
|
-
pbar = ProgressBar.new "trimming", raw_reads.length
|
21
|
-
|
22
|
-
raw_reads.each do |a|
|
23
|
-
pbar.inc
|
24
|
-
out = File.join(out_dir, "#{File.basename(a[0])}.fasta")
|
25
|
-
# TODO get total and trimmed
|
26
|
-
total, trimmed = Helpers.trim_pairs a[1][0], a[1][1], out, :min_length => 70
|
27
|
-
end
|
28
|
-
|
29
|
-
pbar.finish
|
30
|
-
end
|
31
|
-
|
32
|
-
##
|
33
|
-
# PAIRED-END READ WORK-AROUND (JOIN THEM)
|
34
|
-
#
|
35
|
-
desc "join reads end-to-end", "--trimmed=trimmed/*.fasta --output=joined.fasta"
|
36
|
-
method_options :trimmed => :string, :output => :string
|
37
|
-
def join
|
38
|
-
puts "joining!"
|
39
|
-
|
40
|
-
trimmed = Dir[options[:trimmed] || 'trimmed/*.fasta']
|
41
|
-
output = options[:output] || 'joined.fasta'
|
42
|
-
|
43
|
-
fail "no reads in #{trimmed}" if trimmed.length == 0
|
44
|
-
|
45
|
-
output = File.open(output, 'w')
|
46
|
-
|
47
|
-
pbar = ProgressBar.new "joining", trimmed.length
|
48
|
-
|
49
|
-
trimmed.each do |fasta_file|
|
50
|
-
pbar.inc
|
51
|
-
records = Dna.new File.open(fasta_file)
|
52
|
-
records.each_slice(2) do |r, l|
|
53
|
-
output.puts ">#{r.name}:#{File.basename(fasta_file, '.fasta')}\n#{r.sequence.reverse+l.sequence}"
|
54
|
-
end
|
4
|
+
no_tasks do
|
5
|
+
# just print string to STDERR
|
6
|
+
def ohai(s)
|
7
|
+
$stderr.puts s
|
55
8
|
end
|
56
|
-
pbar.finish
|
57
9
|
end
|
58
10
|
|
59
|
-
|
60
|
-
# SORT JOINED READS BY LENGTH
|
61
|
-
#
|
62
|
-
desc "sort fasta file by length", "--input=joined.fasta --output=sorted.fasta"
|
63
|
-
method_options :input => :string, :output => :string
|
64
|
-
def sort
|
65
|
-
input = options[:input] || 'joined.fasta'
|
66
|
-
output = options[:output] || 'sorted.fasta'
|
67
|
-
`uclust --mergesort #{input} --output #{output}`
|
68
|
-
end
|
69
|
-
|
70
|
-
##
|
71
|
-
# FINALLY, CLUSTER!
|
72
|
-
#
|
73
|
-
desc "cluster fasta file", "--input=sorted.fasta --identity=0.80 --output=clusters.uc"
|
74
|
-
method_options :input => :string, :output => :string, :identity => :float
|
75
|
-
def cluster
|
76
|
-
identity = options[:identity] || 0.8
|
77
|
-
output = options[:output] || 'clusters.uc'
|
78
|
-
input = options[:input] || 'sorted.fasta'
|
79
|
-
|
80
|
-
cmd = [
|
81
|
-
'uclust',
|
82
|
-
"--input #{input}",
|
83
|
-
"--uc #{output}",
|
84
|
-
"--id #{identity}",
|
85
|
-
].join(' ')
|
86
|
-
exec cmd
|
87
|
-
end
|
88
|
-
|
89
|
-
##
|
90
|
-
# MAKE TABLES
|
91
|
-
#
|
92
|
-
desc "otu_tables generates otu tables & representative reads", "--clusters=clusters.uc --output=otu_prefix --joined=joined.fasta"
|
93
|
-
method_options :clusters => :string, :output => :string, :joined => :string
|
94
|
-
def otu_table
|
95
|
-
input = options[:clusters] || 'clusters.uc'
|
96
|
-
output = options[:output] || 'otus'
|
97
|
-
joined_reads = options[:joined] || 'joined.fasta'
|
98
|
-
|
99
|
-
clusters = Hash.new
|
100
|
-
|
101
|
-
# Load cluster table!
|
102
|
-
clusters = Helpers.load_uc_file(input)
|
103
|
-
|
104
|
-
clusters_total = clusters[:count_data].values.collect{ |x| x[:total] }.inject(:+)
|
105
|
-
|
106
|
-
# Get representative sequences!
|
107
|
-
reads_total = 0
|
108
|
-
representatives = {}
|
109
|
-
clusters[:count_data].each{ |k, x| representatives[x[:seed]] = k }
|
110
|
-
|
111
|
-
out_handle = File.open("#{output}.fasta", 'w')
|
112
|
-
|
113
|
-
File.open(joined_reads) do |handle|
|
114
|
-
records = Dna.new handle
|
115
|
-
records.each do |dna|
|
116
|
-
reads_total += 1
|
117
|
-
if !representatives[dna.name].nil?
|
118
|
-
dna.name = "#{dna.name}:cluster_#{representatives[dna.name]}"
|
119
|
-
out_handle.puts dna
|
120
|
-
end
|
121
|
-
end
|
122
|
-
end
|
123
|
-
|
124
|
-
out_handle.close
|
125
|
-
|
126
|
-
# Print some statistics
|
127
|
-
puts "reads in clusters: #{clusters_total}"
|
128
|
-
puts "number of reads: #{reads_total}"
|
129
|
-
puts "unique clusters: #{clusters.keys.length}"
|
130
|
-
|
131
|
-
# print OTU abundancy matrix
|
132
|
-
csv = Helpers.cluster_data_as_csv(clusters)
|
133
|
-
File.open("#{output}.csv", 'w') do |h|
|
134
|
-
h.puts csv
|
135
|
-
end
|
136
|
-
|
137
|
-
end
|
138
|
-
|
139
|
-
##
|
140
|
-
# Create a fasta file with nucleotide sequences for each cluster larger than a cutoff
|
141
|
-
#
|
142
|
-
desc "output separate fasta file containing sequences belonging to each cluster", "--clusters=clusters.uc --reads=joined.fasta --min-clst-size=100"
|
143
|
-
method_options :clusters => :string, :reads=> :string, :buffer_size => :int, :min_clst_size => :int, :out_dir => :string
|
144
|
-
def split
|
145
|
-
clusters = options[:clusters] || 'clusters.uc'
|
146
|
-
reads = options[:reads] || 'joined.fasta'
|
147
|
-
out_dir = options[:out_dir] || 'clusters_split'
|
148
|
-
buffer_size = (options[:buffer_size] || 1000).to_i
|
149
|
-
min_clst_size = (options[:min_clst_size] || 100).to_i
|
150
|
-
finalize_every = 100_000
|
151
|
-
|
152
|
-
`mkdir -p #{out_dir}/`
|
153
|
-
|
154
|
-
puts "loading #{clusters}"
|
155
|
-
|
156
|
-
# Load read id -> cluster
|
157
|
-
read_to_clusterid = Hash.new
|
158
|
-
|
159
|
-
# keep track of cluster sizes
|
160
|
-
cluster_counts = Hash.new { |h, k| h[k] = 0}
|
161
|
-
|
162
|
-
File.open(clusters)do |handle|
|
163
|
-
handle.each do |line|
|
164
|
-
line = line.strip.split
|
165
|
-
cluster_nr = line[1]
|
166
|
-
if line[0] == 'S' || line[0] == 'H'
|
167
|
-
read = line[8]
|
168
|
-
else
|
169
|
-
next
|
170
|
-
end
|
171
|
-
read_to_clusterid[read] = cluster_nr
|
172
|
-
cluster_counts[cluster_nr] += 1
|
173
|
-
end
|
174
|
-
end
|
175
|
-
|
176
|
-
read_to_clusterid.delete_if do |read, cluster_nr|
|
177
|
-
cluster_counts[cluster_nr] < min_clst_size
|
178
|
-
end
|
179
|
-
|
180
|
-
total_reads = read_to_clusterid.length
|
181
|
-
total_clusters = read_to_clusterid.values.uniq.length
|
182
|
-
puts "#{total_reads} reads in #{total_clusters} clusters"
|
183
|
-
|
184
|
-
puts "writing out fasta files"
|
185
|
-
|
186
|
-
pbar = ProgressBar.new "writing", total_reads
|
187
|
-
|
188
|
-
# Write reads to individual fasta files using Buffer
|
189
|
-
buffer = Buffer.new :buffer_max => buffer_size
|
190
|
-
File.open(reads) do |handle|
|
191
|
-
records = Dna.new handle
|
192
|
-
$stderr.puts "reads = #{reads}"
|
193
|
-
records.each_with_index do |record, i|
|
194
|
-
cluster_id = read_to_clusterid[record.name]
|
195
|
-
if cluster_id
|
196
|
-
pbar.inc
|
197
|
-
filename = File.join(out_dir, cluster_id + '.fasta')
|
198
|
-
buffer[filename] << record
|
199
|
-
buffer.finalize if (i%finalize_every == 0)
|
200
|
-
end
|
201
|
-
end
|
202
|
-
end
|
203
|
-
|
204
|
-
pbar.finish
|
205
|
-
puts "finalizing output"
|
206
|
-
buffer.finalize # finish writing out
|
11
|
+
end # class CLI
|
207
12
|
|
208
|
-
|
209
|
-
end
|
13
|
+
end # module
|
210
14
|
|
211
|
-
|
212
|
-
end # module
|
15
|
+
Dir.glob(File.join(File.dirname(__FILE__), 'tasks', '*.rb')).each { |f| require f }
|
data/lib/version.rb
CHANGED
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: 25
|
5
5
|
prerelease:
|
6
6
|
segments:
|
7
7
|
- 0
|
8
8
|
- 0
|
9
|
-
-
|
10
|
-
version: 0.0.
|
9
|
+
- 3
|
10
|
+
version: 0.0.3
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Austin G. Davis-Richardson
|