BioDSL 1.0.0
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 +7 -0
- data/.gitignore +10 -0
- data/BioDSL.gemspec +64 -0
- data/LICENSE +339 -0
- data/README.md +205 -0
- data/Rakefile +94 -0
- data/examples/fastq_to_fasta.rb +8 -0
- data/lib/BioDSL/cary.rb +242 -0
- data/lib/BioDSL/command.rb +133 -0
- data/lib/BioDSL/commands/add_key.rb +110 -0
- data/lib/BioDSL/commands/align_seq_mothur.rb +194 -0
- data/lib/BioDSL/commands/analyze_residue_distribution.rb +222 -0
- data/lib/BioDSL/commands/assemble_pairs.rb +336 -0
- data/lib/BioDSL/commands/assemble_seq_idba.rb +230 -0
- data/lib/BioDSL/commands/assemble_seq_ray.rb +345 -0
- data/lib/BioDSL/commands/assemble_seq_spades.rb +252 -0
- data/lib/BioDSL/commands/classify_seq.rb +217 -0
- data/lib/BioDSL/commands/classify_seq_mothur.rb +226 -0
- data/lib/BioDSL/commands/clip_primer.rb +318 -0
- data/lib/BioDSL/commands/cluster_otus.rb +181 -0
- data/lib/BioDSL/commands/collapse_otus.rb +170 -0
- data/lib/BioDSL/commands/collect_otus.rb +150 -0
- data/lib/BioDSL/commands/complement_seq.rb +117 -0
- data/lib/BioDSL/commands/count.rb +135 -0
- data/lib/BioDSL/commands/count_values.rb +149 -0
- data/lib/BioDSL/commands/degap_seq.rb +253 -0
- data/lib/BioDSL/commands/dereplicate_seq.rb +168 -0
- data/lib/BioDSL/commands/dump.rb +157 -0
- data/lib/BioDSL/commands/filter_rrna.rb +239 -0
- data/lib/BioDSL/commands/genecall.rb +237 -0
- data/lib/BioDSL/commands/grab.rb +535 -0
- data/lib/BioDSL/commands/index_taxonomy.rb +226 -0
- data/lib/BioDSL/commands/mask_seq.rb +175 -0
- data/lib/BioDSL/commands/mean_scores.rb +168 -0
- data/lib/BioDSL/commands/merge_pair_seq.rb +175 -0
- data/lib/BioDSL/commands/merge_table.rb +225 -0
- data/lib/BioDSL/commands/merge_values.rb +113 -0
- data/lib/BioDSL/commands/plot_heatmap.rb +233 -0
- data/lib/BioDSL/commands/plot_histogram.rb +306 -0
- data/lib/BioDSL/commands/plot_matches.rb +282 -0
- data/lib/BioDSL/commands/plot_residue_distribution.rb +278 -0
- data/lib/BioDSL/commands/plot_scores.rb +285 -0
- data/lib/BioDSL/commands/random.rb +153 -0
- data/lib/BioDSL/commands/read_fasta.rb +222 -0
- data/lib/BioDSL/commands/read_fastq.rb +414 -0
- data/lib/BioDSL/commands/read_table.rb +329 -0
- data/lib/BioDSL/commands/reverse_seq.rb +113 -0
- data/lib/BioDSL/commands/slice_align.rb +400 -0
- data/lib/BioDSL/commands/slice_seq.rb +151 -0
- data/lib/BioDSL/commands/sort.rb +223 -0
- data/lib/BioDSL/commands/split_pair_seq.rb +220 -0
- data/lib/BioDSL/commands/split_values.rb +165 -0
- data/lib/BioDSL/commands/trim_primer.rb +314 -0
- data/lib/BioDSL/commands/trim_seq.rb +192 -0
- data/lib/BioDSL/commands/uchime_ref.rb +170 -0
- data/lib/BioDSL/commands/uclust.rb +286 -0
- data/lib/BioDSL/commands/unique_values.rb +145 -0
- data/lib/BioDSL/commands/usearch_global.rb +171 -0
- data/lib/BioDSL/commands/usearch_local.rb +171 -0
- data/lib/BioDSL/commands/write_fasta.rb +207 -0
- data/lib/BioDSL/commands/write_fastq.rb +191 -0
- data/lib/BioDSL/commands/write_table.rb +419 -0
- data/lib/BioDSL/commands/write_tree.rb +167 -0
- data/lib/BioDSL/commands.rb +31 -0
- data/lib/BioDSL/config.rb +55 -0
- data/lib/BioDSL/csv.rb +307 -0
- data/lib/BioDSL/debug.rb +42 -0
- data/lib/BioDSL/fasta.rb +133 -0
- data/lib/BioDSL/fastq.rb +77 -0
- data/lib/BioDSL/filesys.rb +137 -0
- data/lib/BioDSL/fork.rb +145 -0
- data/lib/BioDSL/hamming.rb +128 -0
- data/lib/BioDSL/helpers/aux_helper.rb +44 -0
- data/lib/BioDSL/helpers/email_helper.rb +66 -0
- data/lib/BioDSL/helpers/history_helper.rb +40 -0
- data/lib/BioDSL/helpers/log_helper.rb +55 -0
- data/lib/BioDSL/helpers/options_helper.rb +405 -0
- data/lib/BioDSL/helpers/status_helper.rb +132 -0
- data/lib/BioDSL/helpers.rb +35 -0
- data/lib/BioDSL/html_report.rb +200 -0
- data/lib/BioDSL/math.rb +55 -0
- data/lib/BioDSL/mummer.rb +216 -0
- data/lib/BioDSL/pipeline.rb +354 -0
- data/lib/BioDSL/seq/ambiguity.rb +66 -0
- data/lib/BioDSL/seq/assemble.rb +240 -0
- data/lib/BioDSL/seq/backtrack.rb +252 -0
- data/lib/BioDSL/seq/digest.rb +99 -0
- data/lib/BioDSL/seq/dynamic.rb +263 -0
- data/lib/BioDSL/seq/homopolymer.rb +59 -0
- data/lib/BioDSL/seq/kmer.rb +293 -0
- data/lib/BioDSL/seq/levenshtein.rb +113 -0
- data/lib/BioDSL/seq/translate.rb +109 -0
- data/lib/BioDSL/seq/trim.rb +188 -0
- data/lib/BioDSL/seq.rb +742 -0
- data/lib/BioDSL/serializer.rb +98 -0
- data/lib/BioDSL/stream.rb +113 -0
- data/lib/BioDSL/taxonomy.rb +691 -0
- data/lib/BioDSL/test.rb +42 -0
- data/lib/BioDSL/tmp_dir.rb +68 -0
- data/lib/BioDSL/usearch.rb +301 -0
- data/lib/BioDSL/verbose.rb +42 -0
- data/lib/BioDSL/version.rb +31 -0
- data/lib/BioDSL.rb +81 -0
- data/test/BioDSL/commands/test_add_key.rb +105 -0
- data/test/BioDSL/commands/test_align_seq_mothur.rb +99 -0
- data/test/BioDSL/commands/test_analyze_residue_distribution.rb +134 -0
- data/test/BioDSL/commands/test_assemble_pairs.rb +459 -0
- data/test/BioDSL/commands/test_assemble_seq_idba.rb +50 -0
- data/test/BioDSL/commands/test_assemble_seq_ray.rb +51 -0
- data/test/BioDSL/commands/test_assemble_seq_spades.rb +50 -0
- data/test/BioDSL/commands/test_classify_seq.rb +50 -0
- data/test/BioDSL/commands/test_classify_seq_mothur.rb +59 -0
- data/test/BioDSL/commands/test_clip_primer.rb +377 -0
- data/test/BioDSL/commands/test_cluster_otus.rb +128 -0
- data/test/BioDSL/commands/test_collapse_otus.rb +81 -0
- data/test/BioDSL/commands/test_collect_otus.rb +82 -0
- data/test/BioDSL/commands/test_complement_seq.rb +78 -0
- data/test/BioDSL/commands/test_count.rb +103 -0
- data/test/BioDSL/commands/test_count_values.rb +85 -0
- data/test/BioDSL/commands/test_degap_seq.rb +96 -0
- data/test/BioDSL/commands/test_dereplicate_seq.rb +92 -0
- data/test/BioDSL/commands/test_dump.rb +109 -0
- data/test/BioDSL/commands/test_filter_rrna.rb +128 -0
- data/test/BioDSL/commands/test_genecall.rb +50 -0
- data/test/BioDSL/commands/test_grab.rb +398 -0
- data/test/BioDSL/commands/test_index_taxonomy.rb +62 -0
- data/test/BioDSL/commands/test_mask_seq.rb +98 -0
- data/test/BioDSL/commands/test_mean_scores.rb +111 -0
- data/test/BioDSL/commands/test_merge_pair_seq.rb +115 -0
- data/test/BioDSL/commands/test_merge_table.rb +131 -0
- data/test/BioDSL/commands/test_merge_values.rb +83 -0
- data/test/BioDSL/commands/test_plot_heatmap.rb +185 -0
- data/test/BioDSL/commands/test_plot_histogram.rb +194 -0
- data/test/BioDSL/commands/test_plot_matches.rb +157 -0
- data/test/BioDSL/commands/test_plot_residue_distribution.rb +309 -0
- data/test/BioDSL/commands/test_plot_scores.rb +308 -0
- data/test/BioDSL/commands/test_random.rb +88 -0
- data/test/BioDSL/commands/test_read_fasta.rb +229 -0
- data/test/BioDSL/commands/test_read_fastq.rb +552 -0
- data/test/BioDSL/commands/test_read_table.rb +327 -0
- data/test/BioDSL/commands/test_reverse_seq.rb +79 -0
- data/test/BioDSL/commands/test_slice_align.rb +218 -0
- data/test/BioDSL/commands/test_slice_seq.rb +131 -0
- data/test/BioDSL/commands/test_sort.rb +128 -0
- data/test/BioDSL/commands/test_split_pair_seq.rb +164 -0
- data/test/BioDSL/commands/test_split_values.rb +95 -0
- data/test/BioDSL/commands/test_trim_primer.rb +329 -0
- data/test/BioDSL/commands/test_trim_seq.rb +150 -0
- data/test/BioDSL/commands/test_uchime_ref.rb +113 -0
- data/test/BioDSL/commands/test_uclust.rb +139 -0
- data/test/BioDSL/commands/test_unique_values.rb +98 -0
- data/test/BioDSL/commands/test_usearch_global.rb +123 -0
- data/test/BioDSL/commands/test_usearch_local.rb +125 -0
- data/test/BioDSL/commands/test_write_fasta.rb +159 -0
- data/test/BioDSL/commands/test_write_fastq.rb +166 -0
- data/test/BioDSL/commands/test_write_table.rb +411 -0
- data/test/BioDSL/commands/test_write_tree.rb +122 -0
- data/test/BioDSL/helpers/test_options_helper.rb +272 -0
- data/test/BioDSL/seq/test_assemble.rb +98 -0
- data/test/BioDSL/seq/test_backtrack.rb +176 -0
- data/test/BioDSL/seq/test_digest.rb +71 -0
- data/test/BioDSL/seq/test_dynamic.rb +133 -0
- data/test/BioDSL/seq/test_homopolymer.rb +58 -0
- data/test/BioDSL/seq/test_kmer.rb +134 -0
- data/test/BioDSL/seq/test_translate.rb +75 -0
- data/test/BioDSL/seq/test_trim.rb +101 -0
- data/test/BioDSL/test_cary.rb +176 -0
- data/test/BioDSL/test_command.rb +45 -0
- data/test/BioDSL/test_csv.rb +514 -0
- data/test/BioDSL/test_debug.rb +42 -0
- data/test/BioDSL/test_fasta.rb +154 -0
- data/test/BioDSL/test_fastq.rb +46 -0
- data/test/BioDSL/test_filesys.rb +145 -0
- data/test/BioDSL/test_fork.rb +85 -0
- data/test/BioDSL/test_math.rb +41 -0
- data/test/BioDSL/test_mummer.rb +79 -0
- data/test/BioDSL/test_pipeline.rb +187 -0
- data/test/BioDSL/test_seq.rb +790 -0
- data/test/BioDSL/test_serializer.rb +72 -0
- data/test/BioDSL/test_stream.rb +55 -0
- data/test/BioDSL/test_taxonomy.rb +336 -0
- data/test/BioDSL/test_test.rb +42 -0
- data/test/BioDSL/test_tmp_dir.rb +58 -0
- data/test/BioDSL/test_usearch.rb +33 -0
- data/test/BioDSL/test_verbose.rb +42 -0
- data/test/helper.rb +82 -0
- data/www/command.html.haml +14 -0
- data/www/css.html.haml +55 -0
- data/www/input_files.html.haml +3 -0
- data/www/layout.html.haml +12 -0
- data/www/output_files.html.haml +3 -0
- data/www/overview.html.haml +15 -0
- data/www/pipeline.html.haml +4 -0
- data/www/png.html.haml +2 -0
- data/www/status.html.haml +9 -0
- data/www/time.html.haml +11 -0
- metadata +503 -0
data/test/helper.rb
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
1
|
+
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
|
|
2
|
+
# #
|
|
3
|
+
# Copyright (C) 2007-2015 Martin Asser Hansen (mail@maasha.dk). #
|
|
4
|
+
# #
|
|
5
|
+
# This program is free software; you can redistribute it and/or #
|
|
6
|
+
# modify it under the terms of the GNU General Public License #
|
|
7
|
+
# as published by the Free Software Foundation; either version 2 #
|
|
8
|
+
# of the License, or (at your option) any later version. #
|
|
9
|
+
# #
|
|
10
|
+
# This program is distributed in the hope that it will be useful, #
|
|
11
|
+
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
|
|
12
|
+
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
|
|
13
|
+
# GNU General Public License for more details. #
|
|
14
|
+
# #
|
|
15
|
+
# You should have received a copy of the GNU General Public License #
|
|
16
|
+
# along with this program; if not, write to the Free Software #
|
|
17
|
+
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. #
|
|
18
|
+
# #
|
|
19
|
+
# http://www.gnu.org/copyleft/gpl.html #
|
|
20
|
+
# #
|
|
21
|
+
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
|
|
22
|
+
# #
|
|
23
|
+
# This software is part of the BioDSL framework (www.BioDSL.org). #
|
|
24
|
+
# #
|
|
25
|
+
# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< #
|
|
26
|
+
|
|
27
|
+
require 'simplecov'
|
|
28
|
+
|
|
29
|
+
if ENV['SIMPLECOV']
|
|
30
|
+
SimpleCov.start do
|
|
31
|
+
add_filter "/test/"
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
SimpleCov.command_name 'test:units'
|
|
35
|
+
end
|
|
36
|
+
|
|
37
|
+
require 'pp'
|
|
38
|
+
require 'tempfile'
|
|
39
|
+
require 'fileutils'
|
|
40
|
+
require 'BioDSL'
|
|
41
|
+
require 'test/unit'
|
|
42
|
+
require 'mocha/test_unit'
|
|
43
|
+
|
|
44
|
+
ENV['BP_TEST'] = "true"
|
|
45
|
+
|
|
46
|
+
module Kernel
|
|
47
|
+
def capture_stdout
|
|
48
|
+
out = StringIO.new
|
|
49
|
+
$stdout = out
|
|
50
|
+
yield
|
|
51
|
+
return out.string
|
|
52
|
+
ensure
|
|
53
|
+
$stdout = STDOUT
|
|
54
|
+
end
|
|
55
|
+
|
|
56
|
+
def capture_stderr
|
|
57
|
+
out = StringIO.new
|
|
58
|
+
$stderr = out
|
|
59
|
+
yield
|
|
60
|
+
return out.string
|
|
61
|
+
ensure
|
|
62
|
+
$stderr = STDERR
|
|
63
|
+
end
|
|
64
|
+
end
|
|
65
|
+
|
|
66
|
+
class Test::Unit::TestCase
|
|
67
|
+
# Ruby 2.2 have omit, < 2.2 have skip
|
|
68
|
+
alias :omit :skip if ! self.instance_methods.include? :omit
|
|
69
|
+
|
|
70
|
+
def self.test(desc, &impl)
|
|
71
|
+
define_method("test #{desc}", &impl)
|
|
72
|
+
end
|
|
73
|
+
|
|
74
|
+
def collect_result
|
|
75
|
+
@input2.each_with_object('') { |e, a| a << "#{e}#{$/}" }
|
|
76
|
+
end
|
|
77
|
+
|
|
78
|
+
def collect_sorted_result
|
|
79
|
+
@input2.sort_by { |a| a.to_s }.
|
|
80
|
+
each_with_object('') { |e, a| a << "#{e}#{$/}" }
|
|
81
|
+
end
|
|
82
|
+
end
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
.section
|
|
2
|
+
%a{:name => "#{command.name}#{index}"}
|
|
3
|
+
%h2
|
|
4
|
+
Command: #{command.name}
|
|
5
|
+
%a{:href => help_url(command.name), :title => "Click for help on #{command.name}", :target => "_blank"} ?
|
|
6
|
+
%p.command #{command.to_s}
|
|
7
|
+
= render_status command
|
|
8
|
+
= render_time command.status
|
|
9
|
+
- if input? command.options
|
|
10
|
+
= render_input_files command.options
|
|
11
|
+
- if output? command.options
|
|
12
|
+
= render_output_files command.options
|
|
13
|
+
- if png? command.options
|
|
14
|
+
= render_png command.options
|
data/www/css.html.haml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
:css
|
|
2
|
+
.center {
|
|
3
|
+
text-align: center;
|
|
4
|
+
}
|
|
5
|
+
|
|
6
|
+
.right {
|
|
7
|
+
text-align: right;
|
|
8
|
+
}
|
|
9
|
+
|
|
10
|
+
.left {
|
|
11
|
+
text-align: left;
|
|
12
|
+
}
|
|
13
|
+
|
|
14
|
+
.bold {
|
|
15
|
+
font-weight: bold;
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
img {
|
|
19
|
+
display: block;
|
|
20
|
+
margin-left: auto;
|
|
21
|
+
margin-right: auto;
|
|
22
|
+
}
|
|
23
|
+
|
|
24
|
+
table {
|
|
25
|
+
border-collapse: collapse;
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
th {
|
|
29
|
+
padding-left: 10px;
|
|
30
|
+
padding-right: 10px;
|
|
31
|
+
}
|
|
32
|
+
|
|
33
|
+
td {
|
|
34
|
+
padding-left: 10px;
|
|
35
|
+
padding-right: 10px;
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
body {
|
|
39
|
+
font-family: Arial, Helvetica, Verdana, sans-serif;
|
|
40
|
+
min-width: 1000px;
|
|
41
|
+
margin-left: 10%;
|
|
42
|
+
margin-right: 10%;
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
.section {
|
|
46
|
+
padding-bottom: 1em;
|
|
47
|
+
border-bottom: 2px solid #ccc;
|
|
48
|
+
}
|
|
49
|
+
|
|
50
|
+
.command {
|
|
51
|
+
font-family: Courier, monospace, sans-serif;
|
|
52
|
+
border: 1px solid black;
|
|
53
|
+
padding: 1em;
|
|
54
|
+
white-space: pre;
|
|
55
|
+
}
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
!!!
|
|
2
|
+
%head
|
|
3
|
+
%title BioDSL report
|
|
4
|
+
= render_css
|
|
5
|
+
%body
|
|
6
|
+
%h1.center BioDSL report
|
|
7
|
+
%p.center.bold Version #{BioDSL::VERSION}
|
|
8
|
+
%p.center.bold Generated #{Time.now}
|
|
9
|
+
= render_pipeline pipeline
|
|
10
|
+
= render_overview commands
|
|
11
|
+
- commands.each_with_index do |command, i|
|
|
12
|
+
= render_command command, i
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
.section
|
|
2
|
+
%h2 Overview
|
|
3
|
+
%table
|
|
4
|
+
%tr.left
|
|
5
|
+
%th.bold Command
|
|
6
|
+
%th.bold Records in
|
|
7
|
+
%th.bold Records out
|
|
8
|
+
%th.bold Time elapsed
|
|
9
|
+
- commands.each_with_index do |command, i|
|
|
10
|
+
%tr
|
|
11
|
+
%td
|
|
12
|
+
%a{:href => "##{command.name}#{i}"} #{command.name}
|
|
13
|
+
%td.right #{command.status[:records_in].commify}
|
|
14
|
+
%td.right #{command.status[:records_out].commify}
|
|
15
|
+
%td.right #{command.status[:time_elapsed]}
|
data/www/png.html.haml
ADDED