miga-base 0.3.1.1 → 0.3.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/actions/add_result.rb +6 -7
- data/actions/init.rb +68 -61
- data/actions/stats.rb +31 -19
- data/lib/miga/common.rb +45 -0
- data/lib/miga/dataset.rb +7 -3
- data/lib/miga/project.rb +9 -4
- data/lib/miga/result.rb +13 -8
- data/lib/miga/version.rb +2 -2
- data/scripts/essential_genes.bash +3 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +1 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +1 -0
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +1 -0
- data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +1 -0
- data/utils/enveomics/Scripts/lib/enveomics.R +1 -0
- metadata +161 -160
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl +0 -56
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl +0 -60
- data/utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl +0 -38
- data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl +0 -55
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 787c36c0ff7eb3a77d1b6fd4dd73015b4b49850e
|
4
|
+
data.tar.gz: 2a4ec0d82f8be2bb8e486d3d5410d909b01f3522
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 71bf56e6cbfdeb36d3f19c9a4ea4aaac8160537ca3b7a95c6bff44d83e07298f8df3889fd3719eaaf9beae4adf9024b1f53e7a9ff743aadeb802c29664838fed
|
7
|
+
data.tar.gz: d351e7f4374a7859b3661a554c967f11406dcc696763da6e3b623025412ed9dcfe8bfe46f6125d22ef5ab341df1e978d93b0e54e222462faa55b7746dca931ef
|
data/actions/add_result.rb
CHANGED
@@ -3,10 +3,13 @@
|
|
3
3
|
# @package MiGA
|
4
4
|
# @license Artistic-2.0
|
5
5
|
|
6
|
-
o = {q:true}
|
6
|
+
o = {q:true, force:false}
|
7
7
|
opts = OptionParser.new do |opt|
|
8
8
|
opt_banner(opt)
|
9
9
|
opt_object(opt, o, [:project, :dataset_opt, :result])
|
10
|
+
opt.on("-f", "--force",
|
11
|
+
"Forces re-indexing of the result even if it's already registered."
|
12
|
+
){ |v| o[:force]=v }
|
10
13
|
opt_common(opt, o)
|
11
14
|
end.parse!
|
12
15
|
|
@@ -19,12 +22,8 @@ p = MiGA::Project.load(o[:project])
|
|
19
22
|
raise "Impossible to load project: #{o[:project]}" if p.nil?
|
20
23
|
|
21
24
|
$stderr.puts "Registering result." unless o[:q]
|
22
|
-
|
23
|
-
|
24
|
-
else
|
25
|
-
d = p.dataset(o[:dataset])
|
26
|
-
r = d.add_result o[:name].to_sym
|
27
|
-
end
|
25
|
+
obj = o[:dataset].nil? ? p : p.dataset(o[:dataset])
|
26
|
+
r = obj.add_result(o[:name].to_sym, true, force: o[:force])
|
28
27
|
|
29
28
|
raise "Cannot add result, incomplete expected files." if r.nil?
|
30
29
|
|
data/actions/init.rb
CHANGED
@@ -107,7 +107,11 @@ File.open(File.expand_path("utils/requirements.txt", miga), "r") do |fh|
|
|
107
107
|
$stderr.print "Testing #{r[0]}#{" (#{r[3]})" if r[3]}... "
|
108
108
|
path = nil
|
109
109
|
loop do
|
110
|
-
|
110
|
+
if File.exist? o[:config]
|
111
|
+
d_path = File.dirname(`source "#{o[:config]}" && which "#{r[1]}"`)
|
112
|
+
else
|
113
|
+
d_path = File.dirname(`which "#{r[1]}"`)
|
114
|
+
end
|
111
115
|
if o[:ask] or d_path=="."
|
112
116
|
path = ask_user("Where can I find it?", d_path, nil, true)
|
113
117
|
else
|
@@ -188,67 +192,70 @@ $stderr.puts ""
|
|
188
192
|
|
189
193
|
# Configure daemon
|
190
194
|
$stderr.puts "Default daemon configuration:"
|
191
|
-
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
|
198
|
-
|
199
|
-
|
200
|
-
|
201
|
-
|
202
|
-
"How
|
203
|
-
|
204
|
-
|
205
|
-
|
206
|
-
|
207
|
-
|
208
|
-
|
209
|
-
|
210
|
-
|
211
|
-
|
212
|
-
"
|
213
|
-
|
214
|
-
|
215
|
-
else # [qm]sub
|
216
|
-
queue = ask_user("What queue should I use?", nil, nil, true)
|
217
|
-
v[:latency] = ask_user("How long should I sleep? (in seconds)", "150").to_i
|
218
|
-
v[:maxjobs] = ask_user("How many jobs can I launch at once?", "300").to_i
|
219
|
-
v[:ppn] = ask_user("How many CPUs can I use per job?", "4").to_i
|
220
|
-
$stderr.puts "Setting up internal daemon defaults."
|
221
|
-
$stderr.puts "If you don't understand this just leave default values:"
|
222
|
-
v[:cmd] = ask_user(
|
223
|
-
"How should I launch tasks?\n %1$s: script path, %2$s: variables, " +
|
224
|
-
"%3$d: CPUs, %4$d: log file, %5$s: task name.\n",
|
225
|
-
"#{v[:type]} -q '#{queue}' -v '%2$s' -l nodes=1:ppn=%3$d %1$s " +
|
226
|
-
"-j oe -o '%4$s' -N '%5$s' -l mem=9g -l walltime=12:00:00 | grep .")
|
227
|
-
v[:var] = ask_user(
|
228
|
-
"How should I pass variables?\n %1$s: keys, %2$s: values.\n",
|
229
|
-
"%1$s=%2$s")
|
230
|
-
v[:varsep] = ask_user("What should I use to separate variables?", ",")
|
231
|
-
if v[:type] == "qsub"
|
232
|
-
v[:alive] = ask_user(
|
233
|
-
"How can I know that a process is still alive?\n %1$s: job id, " +
|
195
|
+
daemon_f = File.expand_path(".miga_daemon.json", ENV["HOME"])
|
196
|
+
unless File.exist?(daemon_f) and ask_user(
|
197
|
+
"A template daemon already exists, do you want to preserve it?",
|
198
|
+
"yes", %w(yes no))=="yes"
|
199
|
+
v = {created:Time.now.to_s, updated:Time.now.to_s}
|
200
|
+
v[:type] = ask_user("Please select the type of daemon you want to setup",
|
201
|
+
o[:dtype], %w(bash qsub msub))
|
202
|
+
case v[:type]
|
203
|
+
when "bash"
|
204
|
+
v[:latency] = ask_user("How long should I sleep? (in seconds)","30").to_i
|
205
|
+
v[:maxjobs] = ask_user("How many jobs can I launch at once?", "6").to_i
|
206
|
+
v[:ppn] = ask_user("How many CPUs can I use per job?", "2").to_i
|
207
|
+
$stderr.puts "Setting up internal daemon defaults."
|
208
|
+
$stderr.puts "If you don't understand this just leave default values:"
|
209
|
+
v[:cmd] = ask_user(
|
210
|
+
"How should I launch tasks?\n %1$s: script path, %2$s: variables, " +
|
211
|
+
"%3$d: CPUs, %4$s: log file, %5$s: task name.\n",
|
212
|
+
"%2$s '%1$s' > '%4$s' 2>&1")
|
213
|
+
v[:var] = ask_user(
|
214
|
+
"How should I pass variables?\n %1$s: keys, %2$s: values.\n",
|
215
|
+
"%1$s=%2$s")
|
216
|
+
v[:varsep] = ask_user("What should I use to separate variables?", " ")
|
217
|
+
v[:alive] = ask_user(
|
218
|
+
"How can I know that a process is still alive?\n %1$s: PID, " +
|
234
219
|
"output should be 1 for running and 0 for non-running.\n",
|
235
|
-
"
|
236
|
-
|
237
|
-
|
238
|
-
|
239
|
-
|
240
|
-
v[:
|
241
|
-
|
242
|
-
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
|
250
|
-
|
251
|
-
|
220
|
+
"ps -p '%1$s'|tail -n+2|wc -l")
|
221
|
+
v[:kill] = ask_user(
|
222
|
+
"How should I terminate tasks?\n %s: process ID.", "kill -9 '%s'")
|
223
|
+
else # [qm]sub
|
224
|
+
queue = ask_user("What queue should I use?", nil, nil, true)
|
225
|
+
v[:latency] = ask_user("How long should I sleep? (in seconds)","150").to_i
|
226
|
+
v[:maxjobs] = ask_user("How many jobs can I launch at once?", "300").to_i
|
227
|
+
v[:ppn] = ask_user("How many CPUs can I use per job?", "4").to_i
|
228
|
+
$stderr.puts "Setting up internal daemon defaults."
|
229
|
+
$stderr.puts "If you don't understand this just leave default values:"
|
230
|
+
v[:cmd] = ask_user(
|
231
|
+
"How should I launch tasks?\n %1$s: script path, %2$s: variables, " +
|
232
|
+
"%3$d: CPUs, %4$d: log file, %5$s: task name.\n",
|
233
|
+
"#{v[:type]} -q '#{queue}' -v '%2$s' -l nodes=1:ppn=%3$d %1$s " +
|
234
|
+
"-j oe -o '%4$s' -N '%5$s' -l mem=9g -l walltime=12:00:00 | grep .")
|
235
|
+
v[:var] = ask_user(
|
236
|
+
"How should I pass variables?\n %1$s: keys, %2$s: values.\n",
|
237
|
+
"%1$s=%2$s")
|
238
|
+
v[:varsep] = ask_user("What should I use to separate variables?", ",")
|
239
|
+
if v[:type] == "qsub"
|
240
|
+
v[:alive] = ask_user(
|
241
|
+
"How can I know that a process is still alive?\n %1$s: job id, " +
|
242
|
+
"output should be 1 for running and 0 for non-running.\n",
|
243
|
+
"qstat -f '%1$s'|grep ' job_state ='|perl -pe 's/.*= //'|grep '[^C]'"+
|
244
|
+
"|tail -n1|wc -l|awk '{print $1}'")
|
245
|
+
v[:kill] = ask_user(
|
246
|
+
"How should I terminate tasks?\n %s: process ID.", "qdel '%s'")
|
247
|
+
else
|
248
|
+
v[:alive] = ask_user(
|
249
|
+
"How can I know that a process is still alive?\n %1$s: job id, " +
|
250
|
+
"output should be 1 for running and 0 for non-running.\n",
|
251
|
+
"checkjob '%1$s'|grep '^State:'|perl -pe 's/.*: //'" +
|
252
|
+
"|grep 'Deferred\\|Hold\\|Idle\\|Starting\\|Running\\|Blocked'"+
|
253
|
+
"|tail -n1|wc -l|awk '{print $1}'")
|
254
|
+
v[:kill] = ask_user(
|
255
|
+
"How should I terminate tasks?\n %s: process ID.", "canceljob '%s'")
|
256
|
+
end
|
257
|
+
end
|
258
|
+
File.open(daemon_f, "w"){ |fh| fh.puts JSON.pretty_generate(v) }
|
252
259
|
end
|
253
260
|
$stderr.puts ""
|
254
261
|
|
data/actions/stats.rb
CHANGED
@@ -43,31 +43,43 @@ if o[:compute]
|
|
43
43
|
stats = {}
|
44
44
|
case o[:name]
|
45
45
|
when :raw_reads
|
46
|
-
scr = "awk 'NR%4==2{L+=length($0)} END{print NR/4, L*4/NR}'"
|
47
46
|
if r[:files][:pair1].nil?
|
48
|
-
s =
|
49
|
-
stats = {reads: s[
|
47
|
+
s = MiGA::MiGA.seqs_length(r.file_path(:single), :fastq, gc: true)
|
48
|
+
stats = {reads: s[:n],
|
49
|
+
length_average: [s[:avg], "bp"],
|
50
|
+
length_standard_deviation: [s[:sd], "bp"],
|
51
|
+
g_c_content: [s[:gc], "%"]}
|
50
52
|
else
|
51
|
-
s1 =
|
52
|
-
s2 =
|
53
|
-
stats = {read_pairs: s1[
|
54
|
-
|
55
|
-
|
53
|
+
s1 = MiGA::MiGA.seqs_length(r.file_path(:pair1), :fastq, gc: true)
|
54
|
+
s2 = MiGA::MiGA.seqs_length(r.file_path(:pair2), :fastq, gc: true)
|
55
|
+
stats = {read_pairs: s1[:n],
|
56
|
+
forward_length_average: [s1[:avg], "bp"],
|
57
|
+
forward_length_standard_deviation: [s1[:sd], "bp"],
|
58
|
+
forward_g_c_content: [s1[:gc], "%"],
|
59
|
+
reverse_length_average: [s2[:avg], "bp"],
|
60
|
+
reverse_length_standard_deviation: [s2[:sd], "bp"],
|
61
|
+
reverse_g_c_content: [s2[:gc], "%"]}
|
56
62
|
end
|
57
63
|
when :trimmed_fasta
|
58
|
-
scr = "awk '{L+=$2} END{print NR, L/NR}'"
|
59
64
|
f = r[:files][:coupled].nil? ? r.file_path(:single) : r.file_path(:coupled)
|
60
|
-
s =
|
61
|
-
stats = {reads: s[
|
65
|
+
s = MiGA::MiGA.seqs_length(f, :fasta, gc: true)
|
66
|
+
stats = {reads: s[:n],
|
67
|
+
length_average: [s[:avg], "bp"],
|
68
|
+
length_standard_deviation: [s[:sd], "bp"],
|
69
|
+
g_c_content: [s[:gc], "%"]}
|
62
70
|
when :assembly
|
63
|
-
|
64
|
-
|
65
|
-
stats = {contigs: s[
|
71
|
+
s = MiGA::MiGA.seqs_length(r.file_path(:largecontigs), :fasta,
|
72
|
+
n50:true, gc:true)
|
73
|
+
stats = {contigs: s[:n], n50: [s[:n50], "bp"],
|
74
|
+
total_length: [s[:tot], "bp"], g_c_content: [s[:gc], "%"]}
|
66
75
|
when :cds
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
76
|
+
s = MiGA::MiGA.seqs_length(r.file_path(:proteins), :fasta)
|
77
|
+
stats = {predicted_proteins: s[:n], average_length: [s[:avg], "aa"]}
|
78
|
+
asm = d.add_result(:assembly, false)
|
79
|
+
unless asm.nil? or asm[:stats][:total_length].nil?
|
80
|
+
stats[:coding_density] =
|
81
|
+
[300.0*s[:tot]/asm[:stats][:total_length][0], "%"]
|
82
|
+
end
|
71
83
|
when :essential_genes
|
72
84
|
if d.is_multi?
|
73
85
|
stats = {median_copies:0, mean_copies:0}
|
@@ -118,7 +130,7 @@ end
|
|
118
130
|
|
119
131
|
if o[:key].nil?
|
120
132
|
r[:stats].each do |k,v|
|
121
|
-
puts "#{k.to_s.unmiga_name.capitalize}: #{
|
133
|
+
puts "#{k==:g_c_content ? "G+C content" : k.to_s.unmiga_name.capitalize}: #{
|
122
134
|
v.is_a?(Array) ? v.join(" ") : v}."
|
123
135
|
end
|
124
136
|
else
|
data/lib/miga/common.rb
CHANGED
@@ -4,6 +4,7 @@
|
|
4
4
|
require "miga/version"
|
5
5
|
require "json"
|
6
6
|
require "tempfile"
|
7
|
+
require "zlib"
|
7
8
|
|
8
9
|
##
|
9
10
|
# Generic class used to handle system-wide information and methods, and parent
|
@@ -103,6 +104,50 @@ class MiGA::MiGA
|
|
103
104
|
tmp.unlink
|
104
105
|
end
|
105
106
|
end
|
107
|
+
|
108
|
+
##
|
109
|
+
# Calculates the average and standard deviation of the sequence lengths in
|
110
|
+
# a FastA or FastQ file (supports gzipped files). The +format+ must be a
|
111
|
+
# Symbol, one of +:fasta+ or +:fastq+. Additional estimations can be
|
112
|
+
# controlled via the +opts+ Hash. Supported options include:
|
113
|
+
# - +:n50+: If true, it also returns the N50 and the median (in bp).
|
114
|
+
# - +gc+: If true, it also returns the G+C content (in %).
|
115
|
+
def self.seqs_length(file, format, opts={})
|
116
|
+
fh = (file =~ /\.gz/) ? Zlib::GzipReader.open(file) : File.open(file, "r")
|
117
|
+
l = []
|
118
|
+
gc = 0
|
119
|
+
i = 0 # <- Zlib::GzipReader doesn't set $.
|
120
|
+
fh.each_line do |ln|
|
121
|
+
i += 1
|
122
|
+
if (format==:fasta and ln =~ /^>/) or (format==:fastq and (i % 4)==1)
|
123
|
+
l << 0
|
124
|
+
elsif format==:fasta or (i % 4)==2
|
125
|
+
l[l.size-1] += ln.chomp.size
|
126
|
+
gc += ln.scan(/[GCgc]/).count if opts[:gc]
|
127
|
+
end
|
128
|
+
end
|
129
|
+
fh.close
|
130
|
+
|
131
|
+
o = { n: l.size, tot: l.inject(:+) }
|
132
|
+
o[:avg] = o[:tot].to_f/l.size
|
133
|
+
o[:var] = l.map{ |a| a ** 2 }.inject(:+).to_f/l.size - o[:avg]**2
|
134
|
+
o[:sd] = Math.sqrt o[:var]
|
135
|
+
o[:gc] = 100.0*gc/o[:tot] if opts[:gc]
|
136
|
+
if opts[:n50]
|
137
|
+
l.sort!
|
138
|
+
thr = o[:tot]/2
|
139
|
+
pos = 0
|
140
|
+
l.each do |a|
|
141
|
+
pos += a
|
142
|
+
o[:n50] = a
|
143
|
+
break if pos >= thr
|
144
|
+
end
|
145
|
+
o[:med] = o[:n].even? ?
|
146
|
+
0.5*( l[o[:n]/2-1,2].inject(:+) ) : l[(o[:n]-1)/2]
|
147
|
+
end
|
148
|
+
o
|
149
|
+
end
|
150
|
+
|
106
151
|
|
107
152
|
##
|
108
153
|
# Path to a script to be executed for +task+. Supported +opts+ are:
|
data/lib/miga/dataset.rb
CHANGED
@@ -187,16 +187,20 @@ class MiGA::Dataset < MiGA::MiGA
|
|
187
187
|
##
|
188
188
|
# Look for the result with symbol key +result_type+ and register it in the
|
189
189
|
# dataset. If +save+ is false, it doesn't register the result, but it still
|
190
|
-
# returns a result if the expected files are complete. The +opts+
|
190
|
+
# returns a result if the expected files are complete. The +opts+ hash
|
191
191
|
# controls result creation (if necessary). Supported values include:
|
192
192
|
# - +is_clean+: A Boolean indicating if the input files are clean.
|
193
|
+
# - +force+: A Boolean indicating if the result must be re-indexed. If true, it
|
194
|
+
# implies save=true.
|
193
195
|
# Returns MiGA::Result or nil.
|
194
196
|
def add_result(result_type, save=true, opts={})
|
195
197
|
dir = @@RESULT_DIRS[result_type]
|
196
198
|
return nil if dir.nil?
|
197
199
|
base = File.expand_path("data/#{dir}/#{name}", project.path)
|
198
|
-
|
199
|
-
|
200
|
+
unless opts[:force]
|
201
|
+
r_pre = MiGA::Result.load("#{base}.json")
|
202
|
+
return r_pre if (r_pre.nil? and not save) or not r_pre.nil?
|
203
|
+
end
|
200
204
|
r = File.exist?("#{base}.done") ?
|
201
205
|
self.send("add_result_#{result_type}", base, opts) : nil
|
202
206
|
r.save unless r.nil?
|
data/lib/miga/project.rb
CHANGED
@@ -269,12 +269,17 @@ class MiGA::Project < MiGA::MiGA
|
|
269
269
|
|
270
270
|
##
|
271
271
|
# Add the result identified by Symbol +name+, and return MiGA::Result. Save
|
272
|
-
# the result if +save+.
|
273
|
-
|
272
|
+
# the result if +save+. The +opts+ hash controls result creation (if necessary).
|
273
|
+
# Supported values include:
|
274
|
+
# - +force+: A Boolean indicating if the result must be re-indexed. If true, it
|
275
|
+
# implies save=true.
|
276
|
+
def add_result(name, save=true, opts={})
|
274
277
|
return nil if @@RESULT_DIRS[name].nil?
|
275
278
|
base = "#{path}/data/#{@@RESULT_DIRS[name]}/miga-project"
|
276
|
-
|
277
|
-
|
279
|
+
unless opts[:force]
|
280
|
+
r_pre = MiGA::Result.load("#{base}.json")
|
281
|
+
return r_pre if (r_pre.nil? and not save) or not r_pre.nil?
|
282
|
+
end
|
278
283
|
r = result_files_exist?(base, ".done") ?
|
279
284
|
send("add_result_#{name}", base) : nil
|
280
285
|
r.save unless r.nil?
|
data/lib/miga/result.rb
CHANGED
@@ -133,22 +133,27 @@ class MiGA::Result < MiGA::MiGA
|
|
133
133
|
end
|
134
134
|
|
135
135
|
##
|
136
|
-
# Iterate +blk+ for each registered file.
|
137
|
-
#
|
138
|
-
#
|
139
|
-
#
|
140
|
-
#
|
136
|
+
# Iterate +blk+ for each registered file. Depending on the number of
|
137
|
+
# arguments of +blk+ (arity), it's called as:
|
138
|
+
# - blk[file_rel]
|
139
|
+
# - blk[file_sym, file_rel]
|
140
|
+
# - blk[file_sym, file_rel, file_abs]
|
141
|
+
# Note that multiple files may have the same symbol (file_sym), since
|
142
|
+
# arrays of files are supported.
|
141
143
|
def each_file(&blk)
|
142
144
|
@data[:files] ||= {}
|
143
145
|
self[:files].each do |k,files|
|
144
146
|
files = [files] unless files.kind_of? Array
|
145
147
|
files.each do |file|
|
146
|
-
|
148
|
+
case blk.arity
|
149
|
+
when 1
|
147
150
|
blk.call(file)
|
148
|
-
|
151
|
+
when 2
|
149
152
|
blk.call(k, file)
|
153
|
+
when 3
|
154
|
+
blk.call(k, file, File.expand_path(file, dir))
|
150
155
|
else
|
151
|
-
raise "Wrong number of arguments: #{blk.arity} for
|
156
|
+
raise "Wrong number of arguments: #{blk.arity} for 1..3"
|
152
157
|
end
|
153
158
|
end
|
154
159
|
end
|
data/lib/miga/version.rb
CHANGED
@@ -10,7 +10,7 @@ module MiGA
|
|
10
10
|
# - Float representing the major.minor version.
|
11
11
|
# - Integer representing gem releases of the current version.
|
12
12
|
# - Integer representing minor changes that require new version number.
|
13
|
-
VERSION = [0.3, 1,
|
13
|
+
VERSION = [0.3, 1, 2]
|
14
14
|
|
15
15
|
##
|
16
16
|
# Nickname for the current major.minor version.
|
@@ -18,7 +18,7 @@ module MiGA
|
|
18
18
|
|
19
19
|
##
|
20
20
|
# Date of the current gem release.
|
21
|
-
VERSION_DATE = Date.new(2017,
|
21
|
+
VERSION_DATE = Date.new(2017, 11, 22)
|
22
22
|
|
23
23
|
##
|
24
24
|
# Reference of MiGA.
|
@@ -0,0 +1 @@
|
|
1
|
+
utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.N50.pl
|
@@ -0,0 +1 @@
|
|
1
|
+
utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.filterN.pl
|
@@ -0,0 +1 @@
|
|
1
|
+
utils/enveomics/Pipelines/assembly.pbs/../../Scripts/FastA.length.pl
|
@@ -0,0 +1 @@
|
|
1
|
+
utils/enveomics/Pipelines/blast.pbs/../../Scripts/FastA.split.pl
|
@@ -0,0 +1 @@
|
|
1
|
+
utils/enveomics/Scripts/lib/../../enveomics.R
|
metadata
CHANGED
@@ -1,109 +1,109 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: miga-base
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.1.
|
4
|
+
version: 0.3.1.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Luis M. Rodriguez-R
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-
|
11
|
+
date: 2017-11-22 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rest-client
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - ~>
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '1.7'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - ~>
|
24
|
+
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '1.7'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: daemons
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - ~>
|
31
|
+
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
33
|
version: '1.2'
|
34
|
-
- -
|
34
|
+
- - ">="
|
35
35
|
- !ruby/object:Gem::Version
|
36
36
|
version: 1.2.4
|
37
37
|
type: :runtime
|
38
38
|
prerelease: false
|
39
39
|
version_requirements: !ruby/object:Gem::Requirement
|
40
40
|
requirements:
|
41
|
-
- - ~>
|
41
|
+
- - "~>"
|
42
42
|
- !ruby/object:Gem::Version
|
43
43
|
version: '1.2'
|
44
|
-
- -
|
44
|
+
- - ">="
|
45
45
|
- !ruby/object:Gem::Version
|
46
46
|
version: 1.2.4
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: json
|
49
49
|
requirement: !ruby/object:Gem::Requirement
|
50
50
|
requirements:
|
51
|
-
- -
|
51
|
+
- - ">"
|
52
52
|
- !ruby/object:Gem::Version
|
53
53
|
version: '1.8'
|
54
|
-
- - <
|
54
|
+
- - "<"
|
55
55
|
- !ruby/object:Gem::Version
|
56
56
|
version: '3'
|
57
57
|
type: :runtime
|
58
58
|
prerelease: false
|
59
59
|
version_requirements: !ruby/object:Gem::Requirement
|
60
60
|
requirements:
|
61
|
-
- -
|
61
|
+
- - ">"
|
62
62
|
- !ruby/object:Gem::Version
|
63
63
|
version: '1.8'
|
64
|
-
- - <
|
64
|
+
- - "<"
|
65
65
|
- !ruby/object:Gem::Version
|
66
66
|
version: '3'
|
67
67
|
- !ruby/object:Gem::Dependency
|
68
68
|
name: sqlite3
|
69
69
|
requirement: !ruby/object:Gem::Requirement
|
70
70
|
requirements:
|
71
|
-
- - ~>
|
71
|
+
- - "~>"
|
72
72
|
- !ruby/object:Gem::Version
|
73
73
|
version: '1.3'
|
74
74
|
type: :runtime
|
75
75
|
prerelease: false
|
76
76
|
version_requirements: !ruby/object:Gem::Requirement
|
77
77
|
requirements:
|
78
|
-
- - ~>
|
78
|
+
- - "~>"
|
79
79
|
- !ruby/object:Gem::Version
|
80
80
|
version: '1.3'
|
81
81
|
- !ruby/object:Gem::Dependency
|
82
82
|
name: rake
|
83
83
|
requirement: !ruby/object:Gem::Requirement
|
84
84
|
requirements:
|
85
|
-
- - ~>
|
85
|
+
- - "~>"
|
86
86
|
- !ruby/object:Gem::Version
|
87
87
|
version: '11'
|
88
88
|
type: :development
|
89
89
|
prerelease: false
|
90
90
|
version_requirements: !ruby/object:Gem::Requirement
|
91
91
|
requirements:
|
92
|
-
- - ~>
|
92
|
+
- - "~>"
|
93
93
|
- !ruby/object:Gem::Version
|
94
94
|
version: '11'
|
95
95
|
- !ruby/object:Gem::Dependency
|
96
96
|
name: test-unit
|
97
97
|
requirement: !ruby/object:Gem::Requirement
|
98
98
|
requirements:
|
99
|
-
- - ~>
|
99
|
+
- - "~>"
|
100
100
|
- !ruby/object:Gem::Version
|
101
101
|
version: '3'
|
102
102
|
type: :development
|
103
103
|
prerelease: false
|
104
104
|
version_requirements: !ruby/object:Gem::Requirement
|
105
105
|
requirements:
|
106
|
-
- - ~>
|
106
|
+
- - "~>"
|
107
107
|
- !ruby/object:Gem::Version
|
108
108
|
version: '3'
|
109
109
|
description: Microbial Genomes Atlas
|
@@ -114,6 +114,34 @@ extensions: []
|
|
114
114
|
extra_rdoc_files:
|
115
115
|
- README.md
|
116
116
|
files:
|
117
|
+
- Gemfile
|
118
|
+
- LICENSE
|
119
|
+
- README.md
|
120
|
+
- Rakefile
|
121
|
+
- actions/about.rb
|
122
|
+
- actions/add.rb
|
123
|
+
- actions/add_result.rb
|
124
|
+
- actions/daemon.rb
|
125
|
+
- actions/date.rb
|
126
|
+
- actions/files.rb
|
127
|
+
- actions/find.rb
|
128
|
+
- actions/get.rb
|
129
|
+
- actions/init.rb
|
130
|
+
- actions/ln.rb
|
131
|
+
- actions/ls.rb
|
132
|
+
- actions/new.rb
|
133
|
+
- actions/plugins.rb
|
134
|
+
- actions/rm.rb
|
135
|
+
- actions/run.rb
|
136
|
+
- actions/stats.rb
|
137
|
+
- actions/tax_dist.rb
|
138
|
+
- actions/tax_index.rb
|
139
|
+
- actions/tax_set.rb
|
140
|
+
- actions/tax_test.rb
|
141
|
+
- bin/miga
|
142
|
+
- lib/miga.rb
|
143
|
+
- lib/miga/_data/aai-intax.tsv.gz
|
144
|
+
- lib/miga/_data/aai-novel.tsv.gz
|
117
145
|
- lib/miga/common.rb
|
118
146
|
- lib/miga/daemon.rb
|
119
147
|
- lib/miga/dataset.rb
|
@@ -127,18 +155,6 @@ files:
|
|
127
155
|
- lib/miga/tax_index.rb
|
128
156
|
- lib/miga/taxonomy.rb
|
129
157
|
- lib/miga/version.rb
|
130
|
-
- lib/miga.rb
|
131
|
-
- test/common_test.rb
|
132
|
-
- test/daemon_test.rb
|
133
|
-
- test/dataset_test.rb
|
134
|
-
- test/metadata_test.rb
|
135
|
-
- test/project_test.rb
|
136
|
-
- test/remote_dataset_test.rb
|
137
|
-
- test/tax_index_test.rb
|
138
|
-
- test/taxonomy_test.rb
|
139
|
-
- test/test_helper.rb
|
140
|
-
- lib/miga/_data/aai-intax.tsv.gz
|
141
|
-
- lib/miga/_data/aai-novel.tsv.gz
|
142
158
|
- scripts/_distances_functions.bash
|
143
159
|
- scripts/_distances_noref_nomulti.bash
|
144
160
|
- scripts/_distances_ref_nomulti.bash
|
@@ -163,75 +179,24 @@ files:
|
|
163
179
|
- scripts/taxonomy.bash
|
164
180
|
- scripts/trimmed_fasta.bash
|
165
181
|
- scripts/trimmed_reads.bash
|
182
|
+
- test/common_test.rb
|
183
|
+
- test/daemon_test.rb
|
184
|
+
- test/dataset_test.rb
|
185
|
+
- test/metadata_test.rb
|
186
|
+
- test/project_test.rb
|
187
|
+
- test/remote_dataset_test.rb
|
188
|
+
- test/tax_index_test.rb
|
189
|
+
- test/taxonomy_test.rb
|
190
|
+
- test/test_helper.rb
|
166
191
|
- utils/adapters.fa
|
167
192
|
- utils/arch-ess-genes.rb
|
168
193
|
- utils/core-pan-plot.R
|
169
|
-
- utils/enveomics/build_enveomics_r.bash
|
170
|
-
- utils/enveomics/enveomics.R/data/growth.curves.rda
|
171
|
-
- utils/enveomics/enveomics.R/data/phyla.counts.rda
|
172
|
-
- utils/enveomics/enveomics.R/DESCRIPTION
|
173
|
-
- utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd
|
174
|
-
- utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd
|
175
|
-
- utils/enveomics/enveomics.R/man/enve.__tribs.Rd
|
176
|
-
- utils/enveomics/enveomics.R/man/enve.barplot.Rd
|
177
|
-
- utils/enveomics/enveomics.R/man/enve.cliopts.Rd
|
178
|
-
- utils/enveomics/enveomics.R/man/enve.col.alpha.Rd
|
179
|
-
- utils/enveomics/enveomics.R/man/enve.col2alpha.Rd
|
180
|
-
- utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd
|
181
|
-
- utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd
|
182
|
-
- utils/enveomics/enveomics.R/man/enve.df2dist.Rd
|
183
|
-
- utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd
|
184
|
-
- utils/enveomics/enveomics.R/man/enve.growthcurve.Rd
|
185
|
-
- utils/enveomics/enveomics.R/man/enve.prune.dist.Rd
|
186
|
-
- utils/enveomics/enveomics.R/man/enve.recplot.Rd
|
187
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd
|
188
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd
|
189
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeak.Rd
|
190
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeaks.Rd
|
191
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd
|
192
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd
|
193
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd
|
194
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd
|
195
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd
|
196
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd
|
197
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd
|
198
|
-
- utils/enveomics/enveomics.R/man/enve.recplot2.Rd
|
199
|
-
- utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd
|
200
|
-
- utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd
|
201
|
-
- utils/enveomics/enveomics.R/man/enve.tribs.Rd
|
202
|
-
- utils/enveomics/enveomics.R/man/enve.tribs.test.Rd
|
203
|
-
- utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd
|
204
|
-
- utils/enveomics/enveomics.R/man/enveomics.R-package.Rd
|
205
|
-
- utils/enveomics/enveomics.R/man/growth.curves.Rd
|
206
|
-
- utils/enveomics/enveomics.R/man/phyla.counts.Rd
|
207
|
-
- utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd
|
208
|
-
- utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd
|
209
|
-
- utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd
|
210
|
-
- utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd
|
211
|
-
- utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd
|
212
|
-
- utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd
|
213
|
-
- utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd
|
214
|
-
- utils/enveomics/enveomics.R/man/z$-methods.Rd
|
215
|
-
- utils/enveomics/enveomics.R/NAMESPACE
|
216
|
-
- utils/enveomics/enveomics.R/R/autoprune.R
|
217
|
-
- utils/enveomics/enveomics.R/R/barplot.R
|
218
|
-
- utils/enveomics/enveomics.R/R/cliopts.R
|
219
|
-
- utils/enveomics/enveomics.R/R/df2dist.R
|
220
|
-
- utils/enveomics/enveomics.R/R/growthcurve.R
|
221
|
-
- utils/enveomics/enveomics.R/R/recplot.R
|
222
|
-
- utils/enveomics/enveomics.R/R/recplot2.R
|
223
|
-
- utils/enveomics/enveomics.R/R/tribs.R
|
224
|
-
- utils/enveomics/enveomics.R/R/utils.R
|
225
|
-
- utils/enveomics/enveomics.R/README.md
|
226
194
|
- utils/enveomics/Examples/aai-matrix.bash
|
227
195
|
- utils/enveomics/Examples/ani-matrix.bash
|
228
196
|
- utils/enveomics/Examples/essential-phylogeny.bash
|
229
197
|
- utils/enveomics/Examples/unus-genome-phylogeny.bash
|
230
|
-
- utils/enveomics/globals.mk
|
231
198
|
- utils/enveomics/LICENSE.txt
|
232
199
|
- utils/enveomics/Makefile
|
233
|
-
- utils/enveomics/Manifest/categories.json
|
234
|
-
- utils/enveomics/Manifest/examples.json
|
235
200
|
- utils/enveomics/Manifest/Tasks/aasubs.json
|
236
201
|
- utils/enveomics/Manifest/Tasks/blasttab.json
|
237
202
|
- utils/enveomics/Manifest/Tasks/distances.json
|
@@ -245,20 +210,21 @@ files:
|
|
245
210
|
- utils/enveomics/Manifest/Tasks/tables.json
|
246
211
|
- utils/enveomics/Manifest/Tasks/trees.json
|
247
212
|
- utils/enveomics/Manifest/Tasks/variants.json
|
213
|
+
- utils/enveomics/Manifest/categories.json
|
214
|
+
- utils/enveomics/Manifest/examples.json
|
248
215
|
- utils/enveomics/Manifest/tasks.json
|
249
|
-
- utils/enveomics/manifest.json
|
250
216
|
- utils/enveomics/Pipelines/assembly.pbs/CONFIG.mock.bash
|
217
|
+
- utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl
|
251
218
|
- utils/enveomics/Pipelines/assembly.pbs/FastA.filterN.pl
|
252
219
|
- utils/enveomics/Pipelines/assembly.pbs/FastA.length.pl
|
253
|
-
- utils/enveomics/Pipelines/assembly.pbs/FastA.N50.pl
|
254
|
-
- utils/enveomics/Pipelines/assembly.pbs/kSelector.R
|
255
|
-
- utils/enveomics/Pipelines/assembly.pbs/newbler.pbs
|
256
|
-
- utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl
|
257
220
|
- utils/enveomics/Pipelines/assembly.pbs/README.md
|
258
221
|
- utils/enveomics/Pipelines/assembly.pbs/RUNME-2.bash
|
259
222
|
- utils/enveomics/Pipelines/assembly.pbs/RUNME-3.bash
|
260
223
|
- utils/enveomics/Pipelines/assembly.pbs/RUNME-4.bash
|
261
224
|
- utils/enveomics/Pipelines/assembly.pbs/RUNME.bash
|
225
|
+
- utils/enveomics/Pipelines/assembly.pbs/kSelector.R
|
226
|
+
- utils/enveomics/Pipelines/assembly.pbs/newbler.pbs
|
227
|
+
- utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl
|
262
228
|
- utils/enveomics/Pipelines/assembly.pbs/soap.pbs
|
263
229
|
- utils/enveomics/Pipelines/assembly.pbs/stats.pbs
|
264
230
|
- utils/enveomics/Pipelines/assembly.pbs/velvet.pbs
|
@@ -270,25 +236,23 @@ files:
|
|
270
236
|
- utils/enveomics/Pipelines/blast.pbs/FastA.split.pl
|
271
237
|
- utils/enveomics/Pipelines/blast.pbs/README.md
|
272
238
|
- utils/enveomics/Pipelines/blast.pbs/RUNME.bash
|
273
|
-
- utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash
|
274
239
|
- utils/enveomics/Pipelines/blast.pbs/TASK.check.bash
|
275
240
|
- utils/enveomics/Pipelines/blast.pbs/TASK.dry.bash
|
276
241
|
- utils/enveomics/Pipelines/blast.pbs/TASK.eo.bash
|
277
242
|
- utils/enveomics/Pipelines/blast.pbs/TASK.pause.bash
|
278
243
|
- utils/enveomics/Pipelines/blast.pbs/TASK.run.bash
|
244
|
+
- utils/enveomics/Pipelines/blast.pbs/sentinel.pbs.bash
|
279
245
|
- utils/enveomics/Pipelines/idba.pbs/README.md
|
280
|
-
- utils/enveomics/Pipelines/idba.pbs/run.pbs
|
281
246
|
- utils/enveomics/Pipelines/idba.pbs/RUNME.bash
|
247
|
+
- utils/enveomics/Pipelines/idba.pbs/run.pbs
|
282
248
|
- utils/enveomics/Pipelines/trim.pbs/README.md
|
283
|
-
- utils/enveomics/Pipelines/trim.pbs/run.pbs
|
284
249
|
- utils/enveomics/Pipelines/trim.pbs/RUNME.bash
|
250
|
+
- utils/enveomics/Pipelines/trim.pbs/run.pbs
|
285
251
|
- utils/enveomics/README.md
|
286
|
-
- utils/enveomics/Scripts/aai.rb
|
287
252
|
- utils/enveomics/Scripts/AAsubs.log2ratio.rb
|
288
253
|
- utils/enveomics/Scripts/Aln.cat.rb
|
289
254
|
- utils/enveomics/Scripts/Aln.convert.pl
|
290
255
|
- utils/enveomics/Scripts/AlphaDiversity.pl
|
291
|
-
- utils/enveomics/Scripts/ani.rb
|
292
256
|
- utils/enveomics/Scripts/BlastPairwise.AAsubs.pl
|
293
257
|
- utils/enveomics/Scripts/BlastTab.addlen.rb
|
294
258
|
- utils/enveomics/Scripts/BlastTab.advance.bash
|
@@ -301,8 +265,8 @@ files:
|
|
301
265
|
- utils/enveomics/Scripts/BlastTab.pairedHits.rb
|
302
266
|
- utils/enveomics/Scripts/BlastTab.recplot2.R
|
303
267
|
- utils/enveomics/Scripts/BlastTab.seqdepth.pl
|
304
|
-
- utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl
|
305
268
|
- utils/enveomics/Scripts/BlastTab.seqdepth_ZIP.pl
|
269
|
+
- utils/enveomics/Scripts/BlastTab.seqdepth_nomedian.pl
|
306
270
|
- utils/enveomics/Scripts/BlastTab.subsample.pl
|
307
271
|
- utils/enveomics/Scripts/BlastTab.sumPerHit.pl
|
308
272
|
- utils/enveomics/Scripts/BlastTab.taxid2taxrank.pl
|
@@ -310,6 +274,7 @@ files:
|
|
310
274
|
- utils/enveomics/Scripts/Chao1.pl
|
311
275
|
- utils/enveomics/Scripts/CharTable.classify.rb
|
312
276
|
- utils/enveomics/Scripts/EBIseq2tax.rb
|
277
|
+
- utils/enveomics/Scripts/FastA.N50.pl
|
313
278
|
- utils/enveomics/Scripts/FastA.filter.pl
|
314
279
|
- utils/enveomics/Scripts/FastA.filterLen.pl
|
315
280
|
- utils/enveomics/Scripts/FastA.filterN.pl
|
@@ -317,7 +282,6 @@ files:
|
|
317
282
|
- utils/enveomics/Scripts/FastA.gc.pl
|
318
283
|
- utils/enveomics/Scripts/FastA.interpose.pl
|
319
284
|
- utils/enveomics/Scripts/FastA.length.pl
|
320
|
-
- utils/enveomics/Scripts/FastA.N50.pl
|
321
285
|
- utils/enveomics/Scripts/FastA.per_file.pl
|
322
286
|
- utils/enveomics/Scripts/FastA.qlen.pl
|
323
287
|
- utils/enveomics/Scripts/FastA.rename.pl
|
@@ -334,36 +298,21 @@ files:
|
|
334
298
|
- utils/enveomics/Scripts/FastQ.tag.rb
|
335
299
|
- utils/enveomics/Scripts/FastQ.toFastA.awk
|
336
300
|
- utils/enveomics/Scripts/GenBank.add_fields.rb
|
337
|
-
- utils/enveomics/Scripts/gi2tax.rb
|
338
301
|
- utils/enveomics/Scripts/HMM.essential.rb
|
339
302
|
- utils/enveomics/Scripts/HMMsearch.extractIds.rb
|
340
|
-
- utils/enveomics/Scripts/in_silico_GA_GI.pl
|
341
303
|
- utils/enveomics/Scripts/JPlace.distances.rb
|
342
304
|
- utils/enveomics/Scripts/JPlace.to_iToL.rb
|
343
|
-
- utils/enveomics/Scripts/lib/data/essential.hmm.gz
|
344
|
-
- utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb
|
345
|
-
- utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb
|
346
|
-
- utils/enveomics/Scripts/lib/enveomics_rb/og.rb
|
347
|
-
- utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb
|
348
|
-
- utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb
|
349
|
-
- utils/enveomics/Scripts/lib/enveomics_rb/stat.rb
|
350
|
-
- utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb
|
351
305
|
- utils/enveomics/Scripts/M5nr.getSequences.rb
|
352
306
|
- utils/enveomics/Scripts/MeTaxa.distribution.pl
|
353
307
|
- utils/enveomics/Scripts/MyTaxa.fragsByTax.pl
|
354
308
|
- utils/enveomics/Scripts/MyTaxa.seq-taxrank.rb
|
355
309
|
- utils/enveomics/Scripts/NCBIacc2tax.rb
|
356
310
|
- utils/enveomics/Scripts/Newick.autoprune.R
|
357
|
-
- utils/enveomics/Scripts/ogs.annotate.rb
|
358
|
-
- utils/enveomics/Scripts/ogs.core-pan.rb
|
359
|
-
- utils/enveomics/Scripts/ogs.extract.rb
|
360
|
-
- utils/enveomics/Scripts/ogs.mcl.rb
|
361
|
-
- utils/enveomics/Scripts/ogs.rb
|
362
|
-
- utils/enveomics/Scripts/ogs.stats.rb
|
363
311
|
- utils/enveomics/Scripts/RAxML-EPA.to_iToL.pl
|
364
|
-
- utils/enveomics/Scripts/rbm.rb
|
365
312
|
- utils/enveomics/Scripts/RefSeq.download.bash
|
366
313
|
- utils/enveomics/Scripts/SRA.download.bash
|
314
|
+
- utils/enveomics/Scripts/TRIBS.plot-test.R
|
315
|
+
- utils/enveomics/Scripts/TRIBS.test.R
|
367
316
|
- utils/enveomics/Scripts/Table.barplot.R
|
368
317
|
- utils/enveomics/Scripts/Table.df2dist.R
|
369
318
|
- utils/enveomics/Scripts/Table.filter.pl
|
@@ -372,10 +321,37 @@ files:
|
|
372
321
|
- utils/enveomics/Scripts/Table.round.rb
|
373
322
|
- utils/enveomics/Scripts/Table.split.pl
|
374
323
|
- utils/enveomics/Scripts/Taxonomy.silva2ncbi.rb
|
375
|
-
- utils/enveomics/Scripts/TRIBS.plot-test.R
|
376
|
-
- utils/enveomics/Scripts/TRIBS.test.R
|
377
324
|
- utils/enveomics/Scripts/VCF.KaKs.rb
|
378
325
|
- utils/enveomics/Scripts/VCF.SNPs.rb
|
326
|
+
- utils/enveomics/Scripts/aai.rb
|
327
|
+
- utils/enveomics/Scripts/ani.rb
|
328
|
+
- utils/enveomics/Scripts/gi2tax.rb
|
329
|
+
- utils/enveomics/Scripts/in_silico_GA_GI.pl
|
330
|
+
- utils/enveomics/Scripts/lib/data/essential.hmm.gz
|
331
|
+
- utils/enveomics/Scripts/lib/enveomics.R
|
332
|
+
- utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb
|
333
|
+
- utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb
|
334
|
+
- utils/enveomics/Scripts/lib/enveomics_rb/og.rb
|
335
|
+
- utils/enveomics/Scripts/lib/enveomics_rb/remote_data.rb
|
336
|
+
- utils/enveomics/Scripts/lib/enveomics_rb/seq_range.rb
|
337
|
+
- utils/enveomics/Scripts/lib/enveomics_rb/stat.rb
|
338
|
+
- utils/enveomics/Scripts/lib/enveomics_rb/vcf.rb
|
339
|
+
- utils/enveomics/Scripts/ogs.annotate.rb
|
340
|
+
- utils/enveomics/Scripts/ogs.core-pan.rb
|
341
|
+
- utils/enveomics/Scripts/ogs.extract.rb
|
342
|
+
- utils/enveomics/Scripts/ogs.mcl.rb
|
343
|
+
- utils/enveomics/Scripts/ogs.rb
|
344
|
+
- utils/enveomics/Scripts/ogs.stats.rb
|
345
|
+
- utils/enveomics/Scripts/rbm.rb
|
346
|
+
- utils/enveomics/Tests/Makefile
|
347
|
+
- utils/enveomics/Tests/Mgen_M2288.faa
|
348
|
+
- utils/enveomics/Tests/Mgen_M2288.fna
|
349
|
+
- utils/enveomics/Tests/Mgen_M2321.fna
|
350
|
+
- utils/enveomics/Tests/Nequ_Kin4M.faa
|
351
|
+
- utils/enveomics/Tests/Xanthomonas_oryzae-PilA.tribs.Rdata
|
352
|
+
- utils/enveomics/Tests/Xanthomonas_oryzae-PilA.txt
|
353
|
+
- utils/enveomics/Tests/Xanthomonas_oryzae.aai-mat.tsv
|
354
|
+
- utils/enveomics/Tests/Xanthomonas_oryzae.aai.tsv
|
379
355
|
- utils/enveomics/Tests/a_mg.cds-go.blast.tsv
|
380
356
|
- utils/enveomics/Tests/a_mg.reads-cds.blast.tsv
|
381
357
|
- utils/enveomics/Tests/a_mg.reads-cds.counts.tsv
|
@@ -388,11 +364,6 @@ files:
|
|
388
364
|
- utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv
|
389
365
|
- utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.lim
|
390
366
|
- utils/enveomics/Tests/hiv_mix-hiv1.blast.tsv.rec
|
391
|
-
- utils/enveomics/Tests/Makefile
|
392
|
-
- utils/enveomics/Tests/Mgen_M2288.faa
|
393
|
-
- utils/enveomics/Tests/Mgen_M2288.fna
|
394
|
-
- utils/enveomics/Tests/Mgen_M2321.fna
|
395
|
-
- utils/enveomics/Tests/Nequ_Kin4M.faa
|
396
367
|
- utils/enveomics/Tests/phyla_counts.tsv
|
397
368
|
- utils/enveomics/Tests/primate_lentivirus.ogs
|
398
369
|
- utils/enveomics/Tests/primate_lentivirus.rbm/hiv1-hiv1.rbm
|
@@ -401,10 +372,65 @@ files:
|
|
401
372
|
- utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-hiv2.rbm
|
402
373
|
- utils/enveomics/Tests/primate_lentivirus.rbm/hiv2-siv.rbm
|
403
374
|
- utils/enveomics/Tests/primate_lentivirus.rbm/siv-siv.rbm
|
404
|
-
- utils/enveomics/
|
405
|
-
- utils/enveomics/
|
406
|
-
- utils/enveomics/
|
407
|
-
- utils/enveomics/
|
375
|
+
- utils/enveomics/build_enveomics_r.bash
|
376
|
+
- utils/enveomics/enveomics.R/DESCRIPTION
|
377
|
+
- utils/enveomics/enveomics.R/NAMESPACE
|
378
|
+
- utils/enveomics/enveomics.R/R/autoprune.R
|
379
|
+
- utils/enveomics/enveomics.R/R/barplot.R
|
380
|
+
- utils/enveomics/enveomics.R/R/cliopts.R
|
381
|
+
- utils/enveomics/enveomics.R/R/df2dist.R
|
382
|
+
- utils/enveomics/enveomics.R/R/growthcurve.R
|
383
|
+
- utils/enveomics/enveomics.R/R/recplot.R
|
384
|
+
- utils/enveomics/enveomics.R/R/recplot2.R
|
385
|
+
- utils/enveomics/enveomics.R/R/tribs.R
|
386
|
+
- utils/enveomics/enveomics.R/R/utils.R
|
387
|
+
- utils/enveomics/enveomics.R/README.md
|
388
|
+
- utils/enveomics/enveomics.R/data/growth.curves.rda
|
389
|
+
- utils/enveomics/enveomics.R/data/phyla.counts.rda
|
390
|
+
- utils/enveomics/enveomics.R/man/enve.GrowthCurve-class.Rd
|
391
|
+
- utils/enveomics/enveomics.R/man/enve.TRIBS-class.Rd
|
392
|
+
- utils/enveomics/enveomics.R/man/enve.TRIBS.merge.Rd
|
393
|
+
- utils/enveomics/enveomics.R/man/enve.TRIBStest-class.Rd
|
394
|
+
- utils/enveomics/enveomics.R/man/enve.__prune.iter.Rd
|
395
|
+
- utils/enveomics/enveomics.R/man/enve.__prune.reduce.Rd
|
396
|
+
- utils/enveomics/enveomics.R/man/enve.__tribs.Rd
|
397
|
+
- utils/enveomics/enveomics.R/man/enve.barplot.Rd
|
398
|
+
- utils/enveomics/enveomics.R/man/enve.cliopts.Rd
|
399
|
+
- utils/enveomics/enveomics.R/man/enve.col.alpha.Rd
|
400
|
+
- utils/enveomics/enveomics.R/man/enve.col2alpha.Rd
|
401
|
+
- utils/enveomics/enveomics.R/man/enve.df2dist.Rd
|
402
|
+
- utils/enveomics/enveomics.R/man/enve.df2dist.group.Rd
|
403
|
+
- utils/enveomics/enveomics.R/man/enve.df2dist.list.Rd
|
404
|
+
- utils/enveomics/enveomics.R/man/enve.growthcurve.Rd
|
405
|
+
- utils/enveomics/enveomics.R/man/enve.prune.dist.Rd
|
406
|
+
- utils/enveomics/enveomics.R/man/enve.recplot.Rd
|
407
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2-class.Rd
|
408
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.Rd
|
409
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.__counts.Rd
|
410
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeak.Rd
|
411
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.__findPeaks.Rd
|
412
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.__peakHist.Rd
|
413
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.__whichClosestPeak.Rd
|
414
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.changeCutoff.Rd
|
415
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.corePeak.Rd
|
416
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.extractWindows.Rd
|
417
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.findPeaks.Rd
|
418
|
+
- utils/enveomics/enveomics.R/man/enve.recplot2.peak-class.Rd
|
419
|
+
- utils/enveomics/enveomics.R/man/enve.tribs.Rd
|
420
|
+
- utils/enveomics/enveomics.R/man/enve.tribs.test.Rd
|
421
|
+
- utils/enveomics/enveomics.R/man/enveomics.R-package.Rd
|
422
|
+
- utils/enveomics/enveomics.R/man/growth.curves.Rd
|
423
|
+
- utils/enveomics/enveomics.R/man/phyla.counts.Rd
|
424
|
+
- utils/enveomics/enveomics.R/man/plot.enve.GrowthCurve.Rd
|
425
|
+
- utils/enveomics/enveomics.R/man/plot.enve.TRIBS.Rd
|
426
|
+
- utils/enveomics/enveomics.R/man/plot.enve.TRIBStest.Rd
|
427
|
+
- utils/enveomics/enveomics.R/man/plot.enve.recplot2.Rd
|
428
|
+
- utils/enveomics/enveomics.R/man/summary.enve.GrowthCurve.Rd
|
429
|
+
- utils/enveomics/enveomics.R/man/summary.enve.TRIBS.Rd
|
430
|
+
- utils/enveomics/enveomics.R/man/summary.enve.TRIBStest.Rd
|
431
|
+
- utils/enveomics/enveomics.R/man/z$-methods.Rd
|
432
|
+
- utils/enveomics/globals.mk
|
433
|
+
- utils/enveomics/manifest.json
|
408
434
|
- utils/index_metadata.rb
|
409
435
|
- utils/mytaxa_scan.R
|
410
436
|
- utils/mytaxa_scan.rb
|
@@ -414,31 +440,6 @@ files:
|
|
414
440
|
- utils/subclades-compile.rb
|
415
441
|
- utils/subclades-nj.R
|
416
442
|
- utils/subclades.R
|
417
|
-
- bin/miga
|
418
|
-
- actions/about.rb
|
419
|
-
- actions/add.rb
|
420
|
-
- actions/add_result.rb
|
421
|
-
- actions/daemon.rb
|
422
|
-
- actions/date.rb
|
423
|
-
- actions/files.rb
|
424
|
-
- actions/find.rb
|
425
|
-
- actions/get.rb
|
426
|
-
- actions/init.rb
|
427
|
-
- actions/ln.rb
|
428
|
-
- actions/ls.rb
|
429
|
-
- actions/new.rb
|
430
|
-
- actions/plugins.rb
|
431
|
-
- actions/rm.rb
|
432
|
-
- actions/run.rb
|
433
|
-
- actions/stats.rb
|
434
|
-
- actions/tax_dist.rb
|
435
|
-
- actions/tax_index.rb
|
436
|
-
- actions/tax_set.rb
|
437
|
-
- actions/tax_test.rb
|
438
|
-
- Gemfile
|
439
|
-
- Rakefile
|
440
|
-
- README.md
|
441
|
-
- LICENSE
|
442
443
|
homepage: http://enve-omics.ce.gatech.edu/miga
|
443
444
|
licenses:
|
444
445
|
- Artistic-2.0
|
@@ -447,25 +448,25 @@ post_install_message:
|
|
447
448
|
rdoc_options:
|
448
449
|
- lib
|
449
450
|
- README.md
|
450
|
-
- --main
|
451
|
+
- "--main"
|
451
452
|
- README.md
|
452
|
-
- --title
|
453
|
+
- "--title"
|
453
454
|
- MiGA
|
454
455
|
require_paths:
|
455
456
|
- lib
|
456
457
|
required_ruby_version: !ruby/object:Gem::Requirement
|
457
458
|
requirements:
|
458
|
-
- -
|
459
|
+
- - ">="
|
459
460
|
- !ruby/object:Gem::Version
|
460
461
|
version: '1.9'
|
461
462
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
462
463
|
requirements:
|
463
|
-
- -
|
464
|
+
- - ">="
|
464
465
|
- !ruby/object:Gem::Version
|
465
466
|
version: '0'
|
466
467
|
requirements: []
|
467
468
|
rubyforge_project:
|
468
|
-
rubygems_version: 2.
|
469
|
+
rubygems_version: 2.6.13
|
469
470
|
signing_key:
|
470
471
|
specification_version: 4
|
471
472
|
summary: MiGA
|
@@ -1,56 +0,0 @@
|
|
1
|
-
#!/usr/bin/env perl
|
2
|
-
#
|
3
|
-
# @author: Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
4
|
-
# @update: Oct 07 2015
|
5
|
-
# @license: artistic license 2.0
|
6
|
-
#
|
7
|
-
use strict;
|
8
|
-
use warnings;
|
9
|
-
use List::Util qw/sum min max/;
|
10
|
-
|
11
|
-
my ($seqs, $minlen, $n__) = @ARGV;
|
12
|
-
$seqs or die "
|
13
|
-
Description:
|
14
|
-
Calculates the N50 value of a set of sequences. Alternatively, it
|
15
|
-
can calculate other N** values. It also calculates the total number
|
16
|
-
of sequences and the total added length.
|
17
|
-
|
18
|
-
Usage:
|
19
|
-
$0 seqs.fa[ minlen[ **]]
|
20
|
-
|
21
|
-
seqs.fa A FastA file containing the sequences.
|
22
|
-
minlen (optional) The minimum length to take into consideration.
|
23
|
-
By default: 0.
|
24
|
-
** Value N** to calculate. By default: 50 (N50).
|
25
|
-
";
|
26
|
-
$minlen ||= 0;
|
27
|
-
$n__ ||= 50;
|
28
|
-
|
29
|
-
my @len = ();
|
30
|
-
open SEQ, "<", $seqs or die "Cannot open file: $seqs: $!\n";
|
31
|
-
while(<SEQ>){
|
32
|
-
if(/^>/){
|
33
|
-
push @len, 0;
|
34
|
-
}else{
|
35
|
-
next if /^;/;
|
36
|
-
chomp;
|
37
|
-
s/\W//g;
|
38
|
-
$len[-1]+=length $_;
|
39
|
-
}
|
40
|
-
}
|
41
|
-
close SEQ;
|
42
|
-
@len = sort { $a <=> $b } map { $_>=$minlen?$_:() } @len;
|
43
|
-
my $tot = (sum(@len) || 0);
|
44
|
-
|
45
|
-
my $thr = $n__*$tot/100;
|
46
|
-
my $pos = 0;
|
47
|
-
for(@len){
|
48
|
-
$pos+= $_;
|
49
|
-
if($pos>=$thr){
|
50
|
-
print "N$n__: $_\n";
|
51
|
-
last;
|
52
|
-
}
|
53
|
-
}
|
54
|
-
print "Sequences: ".scalar(@len)."\n";
|
55
|
-
print "Total length: $tot\n";
|
56
|
-
|
@@ -1,60 +0,0 @@
|
|
1
|
-
#!/usr/bin/env perl
|
2
|
-
#
|
3
|
-
# @author Luis M. Rodriguez-R
|
4
|
-
# @update Oct-07-2015
|
5
|
-
# @license artistic license 2.0
|
6
|
-
#
|
7
|
-
|
8
|
-
use warnings;
|
9
|
-
use strict;
|
10
|
-
|
11
|
-
my($file, $content, $stretch) = @ARGV;
|
12
|
-
$file or die <<HELP
|
13
|
-
|
14
|
-
Description:
|
15
|
-
Filter sequences by N-content and presence of long homopolymers.
|
16
|
-
Usage:
|
17
|
-
$0 sequences.fa [content [stretch]] > filtered.fa
|
18
|
-
Where:
|
19
|
-
sequences.fa Input file in FastA format
|
20
|
-
content A number between 0 and 1 indicating the maximum proportion of Ns
|
21
|
-
(1 to turn off, 0.5 by default)
|
22
|
-
stretch A number indicating the maximum number of consecutive identical
|
23
|
-
nucleotides allowed (0 to turn off, 100 by default)
|
24
|
-
filtered.fa Filtered set of sequences.
|
25
|
-
|
26
|
-
HELP
|
27
|
-
;
|
28
|
-
($content ||= 0.5)+=0;
|
29
|
-
($stretch ||= 100)+=0;
|
30
|
-
|
31
|
-
my $good = 0;
|
32
|
-
my $N = 0;
|
33
|
-
|
34
|
-
FASTA: {
|
35
|
-
local $/ = "\n>";
|
36
|
-
open FILE, "<", $file or die "I can not open the file: $file: $!\n";
|
37
|
-
SEQ: while(<FILE>){
|
38
|
-
$N++;
|
39
|
-
s/^;.*//gm;
|
40
|
-
s/>//g;
|
41
|
-
my($n,$s) = split /\n/, $_, 2;
|
42
|
-
(my $clean = $s) =~ s/[^ACTGN]//g;
|
43
|
-
if($content < 1){
|
44
|
-
(my $Ns = $clean) =~ s/[^N]//g;
|
45
|
-
next SEQ if length($Ns)>length($clean)*$content;
|
46
|
-
}
|
47
|
-
if($stretch > 0){
|
48
|
-
for my $nuc (qw(A C T G N)){
|
49
|
-
next SEQ if $clean =~ m/[$nuc]{$stretch}/;
|
50
|
-
}
|
51
|
-
}
|
52
|
-
print ">$n\n$s\n";
|
53
|
-
$good++;
|
54
|
-
}
|
55
|
-
close FILE;
|
56
|
-
print STDERR "Total sequences: $N\nAfter filtering: $good\n";
|
57
|
-
}
|
58
|
-
|
59
|
-
|
60
|
-
|
@@ -1,38 +0,0 @@
|
|
1
|
-
#!/usr/bin/env perl
|
2
|
-
#
|
3
|
-
# @author Luis M Rodriguez-R
|
4
|
-
# @update Oct-07-2015
|
5
|
-
# @license artistic license 2.0
|
6
|
-
#
|
7
|
-
|
8
|
-
use warnings;
|
9
|
-
use strict;
|
10
|
-
|
11
|
-
$#ARGV>=0 or die "
|
12
|
-
Usage:
|
13
|
-
$0 seqs.fa... > length.txt
|
14
|
-
|
15
|
-
seqs.fa One or more FastA files.
|
16
|
-
length.txt A table with the lengths of the sequences.
|
17
|
-
|
18
|
-
";
|
19
|
-
|
20
|
-
for my $fa (@ARGV){
|
21
|
-
open FA, "<", $fa or die "Cannot open file: $fa: $!\n";
|
22
|
-
my $def = '';
|
23
|
-
my $len = 0;
|
24
|
-
while(<FA>){
|
25
|
-
next if /^;/;
|
26
|
-
if(m/^>(\S+)\s?/){
|
27
|
-
print "$def\t$len\n" if $def;
|
28
|
-
$def = $1;
|
29
|
-
$len = 0;
|
30
|
-
}else{
|
31
|
-
s/[^A-Za-z]//g;
|
32
|
-
$len+= length $_;
|
33
|
-
}
|
34
|
-
}
|
35
|
-
print "$def\t$len\n" if $def;
|
36
|
-
close FA;
|
37
|
-
}
|
38
|
-
|
@@ -1,55 +0,0 @@
|
|
1
|
-
#!/usr/bin/env perl
|
2
|
-
#
|
3
|
-
# @author Luis M. Rodriguez-R <lmrodriguezr at gmail dot com>
|
4
|
-
# @update Oct-13-2015
|
5
|
-
# @license artistic license 2.0
|
6
|
-
#
|
7
|
-
|
8
|
-
use warnings;
|
9
|
-
use strict;
|
10
|
-
use Symbol;
|
11
|
-
|
12
|
-
my ($file, $base, $outN) = @ARGV;
|
13
|
-
|
14
|
-
$outN ||= 12;
|
15
|
-
($file and $base) or die "
|
16
|
-
Usage
|
17
|
-
$0 in_file.fa out_base[ no_files]
|
18
|
-
|
19
|
-
in_file.fa Input file in FastA format.
|
20
|
-
out_base Prefix for the name of the output files. It will
|
21
|
-
be appended with .<i>.fa, where <i> is a consecutive
|
22
|
-
number starting in 1.
|
23
|
-
no_files Number of files to generate. By default: 12.
|
24
|
-
|
25
|
-
";
|
26
|
-
|
27
|
-
|
28
|
-
my @outSym = ();
|
29
|
-
for my $i (1 .. $outN){
|
30
|
-
$outSym[$i-1] = gensym;
|
31
|
-
open $outSym[$i-1], ">", "$base.$i.fa" or
|
32
|
-
die "I can not create the file: $base.$i.fa: $!\n";
|
33
|
-
}
|
34
|
-
|
35
|
-
|
36
|
-
my($i, $seq) = (-1, '');
|
37
|
-
open FILE, "<", $file or die "I can not read the file: $file: $!\n";
|
38
|
-
while(my $ln=<FILE>){
|
39
|
-
next if $ln=~/^;/;
|
40
|
-
if($ln =~ m/^>/){
|
41
|
-
print { $outSym[$i % $outN] } $seq if $seq;
|
42
|
-
$i++;
|
43
|
-
$seq = '';
|
44
|
-
}
|
45
|
-
$seq.=$ln;
|
46
|
-
}
|
47
|
-
print { $outSym[$i % $outN] } $seq if $seq;
|
48
|
-
close FILE;
|
49
|
-
|
50
|
-
for(my $j=0; $j<$outN; $j++){
|
51
|
-
close $outSym[$j];
|
52
|
-
}
|
53
|
-
|
54
|
-
print STDERR "Sequences: ".($i+1)."\nFiles: $outN\n";
|
55
|
-
|