miga-base 0.3.1.6 → 0.3.1.7

Sign up to get free protection for your applications and to get access to all the features.
Files changed (38) hide show
  1. checksums.yaml +4 -4
  2. data/actions/ncbi_get.rb +57 -42
  3. data/lib/miga/result/base.rb +7 -0
  4. data/lib/miga/result/dates.rb +42 -0
  5. data/lib/miga/result.rb +4 -0
  6. data/lib/miga/version.rb +1 -1
  7. data/scripts/essential_genes.bash +5 -4
  8. data/utils/enveomics/Makefile +1 -1
  9. data/utils/enveomics/Manifest/Tasks/aasubs.json +75 -75
  10. data/utils/enveomics/Manifest/Tasks/blasttab.json +194 -185
  11. data/utils/enveomics/Manifest/Tasks/distances.json +130 -130
  12. data/utils/enveomics/Manifest/Tasks/fasta.json +51 -3
  13. data/utils/enveomics/Manifest/Tasks/fastq.json +161 -126
  14. data/utils/enveomics/Manifest/Tasks/graphics.json +111 -111
  15. data/utils/enveomics/Manifest/Tasks/mapping.json +30 -0
  16. data/utils/enveomics/Manifest/Tasks/ogs.json +308 -265
  17. data/utils/enveomics/Manifest/Tasks/other.json +451 -449
  18. data/utils/enveomics/Manifest/Tasks/remote.json +1 -1
  19. data/utils/enveomics/Manifest/Tasks/sequence-identity.json +18 -10
  20. data/utils/enveomics/Manifest/Tasks/tables.json +250 -250
  21. data/utils/enveomics/Manifest/Tasks/trees.json +52 -52
  22. data/utils/enveomics/Manifest/Tasks/variants.json +4 -4
  23. data/utils/enveomics/Manifest/categories.json +12 -4
  24. data/utils/enveomics/Manifest/examples.json +1 -1
  25. data/utils/enveomics/Scripts/BedGraph.tad.rb +71 -0
  26. data/utils/enveomics/Scripts/BlastTab.recplot2.R +23 -22
  27. data/utils/enveomics/Scripts/FastA.split.rb +79 -0
  28. data/utils/enveomics/Scripts/FastQ.test-error.rb +81 -0
  29. data/utils/enveomics/Scripts/JPlace.to_iToL.rb +272 -258
  30. data/utils/enveomics/Scripts/aai.rb +13 -6
  31. data/utils/enveomics/Scripts/ani.rb +2 -2
  32. data/utils/enveomics/Scripts/clust.rand.rb +102 -0
  33. data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +12 -14
  34. data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +2 -2
  35. data/utils/enveomics/Scripts/rbm.rb +23 -14
  36. data/utils/enveomics/enveomics.R/DESCRIPTION +1 -1
  37. data/utils/enveomics/enveomics.R/R/barplot.R +2 -2
  38. metadata +9 -2
data/utils/enveomics/Manifest/Tasks/ogs.json CHANGED
@@ -8,41 +8,41 @@
8
8
  "help_arg": "--help",
9
9
  "options": [
10
10
  {
11
- "name": "Input file",
12
- "opt": "--in",
13
- "arg": "in_file",
14
- "mandatory": true,
15
- "description": ["Input file containing the OGs (as generated by",
16
- "ogs.mcl.rb)."]
17
- },
18
- {
19
- "name": "Output file",
20
- "opt": "--out",
21
- "arg": "out_file",
22
- "mandatory": true,
23
- "description": "Output file containing the annotated OGs."
24
- },
25
- {
26
- "name": "Annotations",
27
- "opt": "-a",
28
- "arg": "in_file",
29
- "mandatory": true,
30
- "multiple_sep": ",",
31
- "description": ["Input file(s) containing the annotations. One or",
32
- "more tab-delimited files with the gene names in the first column",
33
- "and the annotation in the second."]
34
- },
35
- {
36
- "opt": "--format",
37
- "arg": "string",
38
- "default": "(\\S+)\\.txt",
39
- "description": ["Format of the filenames for the annotation files,",
40
- "using regex syntax."]
41
- },
42
- {
43
- "opt": "--quiet",
44
- "description": "Run quietly (no STDERR output)."
45
- }
11
+ "name": "Input file",
12
+ "opt": "--in",
13
+ "arg": "in_file",
14
+ "mandatory": true,
15
+ "description": ["Input file containing the OGs (as generated by",
16
+ "ogs.mcl.rb)."]
17
+ },
18
+ {
19
+ "name": "Output file",
20
+ "opt": "--out",
21
+ "arg": "out_file",
22
+ "mandatory": true,
23
+ "description": "Output file containing the annotated OGs."
24
+ },
25
+ {
26
+ "name": "Annotations",
27
+ "opt": "-a",
28
+ "arg": "in_file",
29
+ "mandatory": true,
30
+ "multiple_sep": ",",
31
+ "description": ["Input file(s) containing the annotations. One or",
32
+ "more tab-delimited files with the gene names in the first column",
33
+ "and the annotation in the second."]
34
+ },
35
+ {
36
+ "opt": "--format",
37
+ "arg": "string",
38
+ "default": "(\\S+)\\.txt",
39
+ "description": ["Format of the filenames for the annotation files,",
40
+ "using regex syntax."]
41
+ },
42
+ {
43
+ "opt": "--quiet",
44
+ "description": "Run quietly (no STDERR output)."
45
+ }
46
46
  ]
47
47
  },
48
48
  {
@@ -52,48 +52,48 @@
52
52
  "help_arg": "--help",
53
53
  "requires": [
54
54
  {
55
- "ruby_gem": "json"
56
- }
55
+ "ruby_gem": "json"
56
+ }
57
57
  ],
58
58
  "see_also": ["ogs.mcl.rb"],
59
59
  "options": [
60
60
  {
61
- "opt": "--ogs",
62
- "arg": "in_file",
63
- "mandatory": true,
64
- "description": "Input file containing the precomputed OGs."
65
- },
66
- {
67
- "opt": "--summary",
68
- "arg": "out_file",
69
- "description": ["Output file in tabular format with summary",
70
- "statistics."]
71
- },
72
- {
73
- "opt": "--tab",
74
- "arg": "out_file",
75
- "description": "Output file in tabular format."
76
- },
77
- {
78
- "opt": "--json",
79
- "arg": "out_file",
80
- "description": "Output file in JSON format."
81
- },
82
- {
83
- "opt": "--replicates",
84
- "arg": "integer",
85
- "description": "Number of replicates to estimate.",
86
- "default": 100
87
- },
88
- {
89
- "opt": "--threads",
90
- "arg": "integer",
91
- "description": "Children threads to spawn."
92
- },
93
- {
94
- "opt": "--quiet",
95
- "description": "Run quietly (no STDERR output)."
96
- }
61
+ "opt": "--ogs",
62
+ "arg": "in_file",
63
+ "mandatory": true,
64
+ "description": "Input file containing the precomputed OGs."
65
+ },
66
+ {
67
+ "opt": "--summary",
68
+ "arg": "out_file",
69
+ "description": ["Output file in tabular format with summary",
70
+ "statistics."]
71
+ },
72
+ {
73
+ "opt": "--tab",
74
+ "arg": "out_file",
75
+ "description": "Output file in tabular format."
76
+ },
77
+ {
78
+ "opt": "--json",
79
+ "arg": "out_file",
80
+ "description": "Output file in JSON format."
81
+ },
82
+ {
83
+ "opt": "--replicates",
84
+ "arg": "integer",
85
+ "description": "Number of replicates to estimate.",
86
+ "default": 100
87
+ },
88
+ {
89
+ "opt": "--threads",
90
+ "arg": "integer",
91
+ "description": "Children threads to spawn."
92
+ },
93
+ {
94
+ "opt": "--quiet",
95
+ "description": "Run quietly (no STDERR output)."
96
+ }
97
97
  ]
98
98
  },
99
99
  {
@@ -104,77 +104,77 @@
104
104
  "see_also": ["ogs.mcl.rb"],
105
105
  "options": [
106
106
  {
107
- "name": "Input file",
108
- "opt": "--in",
109
- "arg": "in_file",
110
- "mandatory": true,
111
- "description": ["Input file containing the OGs (as generated by",
112
- "ogs.mcl.rb)."]
113
- },
114
- {
115
- "name": "Output file",
116
- "opt": "--out",
117
- "arg": "out_file",
118
- "mandatory": true,
119
- "description": "Output directory where to place extracted sequences."
120
- },
121
- {
122
- "name": "Sequences",
123
- "opt": "--seqs",
124
- "arg": "in_file",
125
- "mandatory": true,
126
- "description": ["Path to the proteomes in FastA format, using '%s'",
127
- "to denote the genome. For example: /path/to/seqs/%s.faa."]
128
- },
129
- {
130
- "opt": "--core",
131
- "arg": "float",
132
- "description": ["Use only OGs present in at least this fraction of",
133
- "the genomes. To use only the strict core genome*, use --core 1."],
134
- "note": ["* To use only the unus genome (OGs with exactly one gene",
135
- "per genome), use: --core 1 --duplicates 1."]
136
- },
137
- {
138
- "opt": "--duplicates",
139
- "arg": "integer",
140
- "description": ["Use only OGs with less than this number of",
141
- "in-paralogs in a genome. To use only genes without in-paralogs*,",
142
- "use --duplicates 1."],
143
- "note": ["* To use only the unus genome (OGs with exactly one gene",
144
- "per genome), use: --core 1 --duplicates 1."]
145
- },
146
- {
147
- "opt": "--per-genome",
148
- "description": ["If set, the output is generated per genome. By",
149
- "default, the output is per OG."]
150
- },
151
- {
152
- "opt": "--prefix",
153
- "description": ["If set, each sequence is prefixed with the genome",
154
- "name (or OG number, if --per-genome) and a dash."]
155
- },
156
- {
157
- "opt": "--rand",
158
- "description": ["Get only one gene per genome per OG (random)",
159
- "regardless of in-paralogs. By default all genes are extracted."]
160
- },
161
- {
162
- "opt": "--first",
163
- "description": ["Get only one gene per genome per OG (first)",
164
- "regardless of in-paralogs. By default all genes are extracted.",
107
+ "name": "Input file",
108
+ "opt": "--in",
109
+ "arg": "in_file",
110
+ "mandatory": true,
111
+ "description": ["Input file containing the OGs (as generated by",
112
+ "ogs.mcl.rb)."]
113
+ },
114
+ {
115
+ "name": "Output file",
116
+ "opt": "--out",
117
+ "arg": "out_file",
118
+ "mandatory": true,
119
+ "description": "Output directory where to place extracted sequences."
120
+ },
121
+ {
122
+ "name": "Sequences",
123
+ "opt": "--seqs",
124
+ "arg": "in_file",
125
+ "mandatory": true,
126
+ "description": ["Path to the proteomes in FastA format, using '%s'",
127
+ "to denote the genome. For example: /path/to/seqs/%s.faa."]
128
+ },
129
+ {
130
+ "opt": "--core",
131
+ "arg": "float",
132
+ "description": ["Use only OGs present in at least this fraction of",
133
+ "the genomes. To use only the strict core genome*, use --core 1."],
134
+ "note": ["* To use only the unus genome (OGs with exactly one gene",
135
+ "per genome), use: --core 1 --duplicates 1."]
136
+ },
137
+ {
138
+ "opt": "--duplicates",
139
+ "arg": "integer",
140
+ "description": ["Use only OGs with less than this number of",
141
+ "in-paralogs in a genome. To use only genes without in-paralogs*,",
142
+ "use --duplicates 1."],
143
+ "note": ["* To use only the unus genome (OGs with exactly one gene",
144
+ "per genome), use: --core 1 --duplicates 1."]
145
+ },
146
+ {
147
+ "opt": "--per-genome",
148
+ "description": ["If set, the output is generated per genome. By",
149
+ "default, the output is per OG."]
150
+ },
151
+ {
152
+ "opt": "--prefix",
153
+ "description": ["If set, each sequence is prefixed with the genome",
154
+ "name (or OG number, if --per-genome) and a dash."]
155
+ },
156
+ {
157
+ "opt": "--rand",
158
+ "description": ["Get only one gene per genome per OG (random)",
159
+ "regardless of in-paralogs. By default all genes are extracted."]
160
+ },
161
+ {
162
+ "opt": "--first",
163
+ "description": ["Get only one gene per genome per OG (first)",
164
+ "regardless of in-paralogs. By default all genes are extracted.",
165
165
  "Takes precedence over --rand."]
166
- },
167
- {
168
- "opt": "--quiet",
169
- "description": "Run quietly (no STDERR output)."
170
- }
166
+ },
167
+ {
168
+ "opt": "--quiet",
169
+ "description": "Run quietly (no STDERR output)."
170
+ }
171
171
  ]
172
172
  },
173
173
  {
174
174
  "task": "ogs.mcl.rb",
175
175
  "description": ["Identifies Orthology Groups (OGs) in Reciprocal Best",
176
176
  "Matches (RBM) between all pairs in a collection of genomes, using the",
177
- "Markov Cluster Algorithm."],
177
+ "Markov Cluster Algorithm."],
178
178
  "see_also": ["ogs.annotate.rb", "ogs.core-pan.rb", "ogs.extract.rb",
179
179
  "ogs.stats.rb"],
180
180
  "cite": [["Enright et al, 2002, NAR",
@@ -182,72 +182,72 @@
182
182
  "help_arg": "--help",
183
183
  "options": [
184
184
  {
185
- "opt": "--out",
186
- "arg": "out_file",
187
- "mandatory": true,
188
- "description": "Output file containing the detected OGs."
189
- },
190
- {
191
- "opt": "--dir",
192
- "arg": "in_dir",
193
- "description": "Directory containing the RBM files.",
194
- "note": "Mandatory, unless --abc is set to a non-empty file."
195
- },
196
- {
197
- "opt": "--format",
198
- "arg": "string",
199
- "description": ["Format of the filenames for the RBM files (within",
200
- "--dir), using regex syntax."],
201
- "default": "(\\S+)-(\\S+)\\.rbm"
202
- },
203
- {
204
- "opt": "--inflation",
205
- "arg": "float",
206
- "description": "Inflation parameter for MCL clustering.",
207
- "default": 1.5
208
- },
209
- {
210
- "opt": "--blind",
211
- "description": ["If set, computes clusters without taking bitscore",
212
- "into account."]
213
- },
214
- {
215
- "opt": "--evalue",
216
- "description": ["If set, uses the e-value to weight edges, instead",
217
- "of the default Bit-Score."]
218
- },
219
- {
220
- "opt": "--identity",
221
- "description": ["If set, uses the identity to weight edges, instead",
222
- "of the default Bit-Score."]
223
- },
224
- {
225
- "opt": "--best-match",
226
- "description": ["If set, it assumes best-matches instead reciprocal",
227
- "best matches."]
228
- },
229
- {
230
- "opt": "--mcl-bin",
231
- "arg": "in_dir",
232
- "description": ["Path to the directory containing the mcl binaries.",
233
- "By default, assumed to be in the PATH."]
234
- },
235
- {
236
- "name": "abc",
237
- "arg": "out_file",
238
- "opt": "--abc",
239
- "description": "Use this abc file instead of a temporal file."
240
- },
241
- {
242
- "opt": "--threads",
243
- "arg": "integer",
244
- "default": 2,
245
- "description": "Number of threads to use."
246
- },
247
- {
248
- "opt": "--quiet",
249
- "description": "Run quietly (no STDERR output)."
250
- }
185
+ "opt": "--out",
186
+ "arg": "out_file",
187
+ "mandatory": true,
188
+ "description": "Output file containing the detected OGs."
189
+ },
190
+ {
191
+ "opt": "--dir",
192
+ "arg": "in_dir",
193
+ "description": "Directory containing the RBM files.",
194
+ "note": "Mandatory, unless --abc is set to a non-empty file."
195
+ },
196
+ {
197
+ "opt": "--format",
198
+ "arg": "string",
199
+ "description": ["Format of the filenames for the RBM files (within",
200
+ "--dir), using regex syntax."],
201
+ "default": "(\\S+)-(\\S+)\\.rbm"
202
+ },
203
+ {
204
+ "opt": "--inflation",
205
+ "arg": "float",
206
+ "description": "Inflation parameter for MCL clustering.",
207
+ "default": 1.5
208
+ },
209
+ {
210
+ "opt": "--blind",
211
+ "description": ["If set, computes clusters without taking bitscore",
212
+ "into account."]
213
+ },
214
+ {
215
+ "opt": "--evalue",
216
+ "description": ["If set, uses the e-value to weight edges, instead",
217
+ "of the default Bit-Score."]
218
+ },
219
+ {
220
+ "opt": "--identity",
221
+ "description": ["If set, uses the identity to weight edges, instead",
222
+ "of the default Bit-Score."]
223
+ },
224
+ {
225
+ "opt": "--best-match",
226
+ "description": ["If set, it assumes best-matches instead reciprocal",
227
+ "best matches."]
228
+ },
229
+ {
230
+ "opt": "--mcl-bin",
231
+ "arg": "in_dir",
232
+ "description": ["Path to the directory containing the mcl binaries.",
233
+ "By default, assumed to be in the PATH."]
234
+ },
235
+ {
236
+ "name": "abc",
237
+ "arg": "out_file",
238
+ "opt": "--abc",
239
+ "description": "Use this abc file instead of a temporal file."
240
+ },
241
+ {
242
+ "opt": "--threads",
243
+ "arg": "integer",
244
+ "default": 2,
245
+ "description": "Number of threads to use."
246
+ },
247
+ {
248
+ "opt": "--quiet",
249
+ "description": "Run quietly (no STDERR output)."
250
+ }
251
251
  ]
252
252
  },
253
253
  {
@@ -256,44 +256,44 @@
256
256
  "Matches (RBM) between all pairs in a collection of genomes."],
257
257
  "warn": ["This script suffers from chaining effect and is very",
258
258
  "sensitive to spurious connections, because it applies a greedy",
259
- "clustering algorithm. For most practical purposes, the use of this",
260
- "script is discouraged and `ogs.mcl.rb` should be preferred."],
259
+ "clustering algorithm. For most practical purposes, the use of this",
260
+ "script is discouraged and `ogs.mcl.rb` should be preferred."],
261
261
  "help_arg": "--help",
262
262
  "see_also": ["ogs.mcl.rb"],
263
263
  "options": [
264
264
  {
265
- "opt": "--out",
266
- "mandatory": true,
267
- "arg": "out_file",
268
- "description": "Output file containing the detected OGs."
269
- },
270
- {
271
- "opt": "--dir",
272
- "arg": "in_dir",
273
- "description": "Directory containing the RBM files.",
274
- "note": "Required unless --pre-ogs is passed."
275
- },
276
- {
277
- "opt": "--pre-ogs",
278
- "arg": "in_file",
279
- "multiple_sep": ",",
280
- "description": "Pre-computed OGs file(s), separated by commas."
281
- },
282
- {
283
- "opt": "--unchecked",
284
- "description": "Do not check internal redundancy in OGs."
285
- },
286
- {
287
- "opt": "--format",
288
- "arg": "string",
289
- "default": "(\\S+)-(\\S+)\\.rbm",
290
- "description": ["Format of the filenames for the RBM files (within",
291
- "-d), using regex syntax."]
292
- },
293
- {
294
- "opt": "--quiet",
295
- "description": "Run quietly (no STDERR output)."
296
- }
265
+ "opt": "--out",
266
+ "mandatory": true,
267
+ "arg": "out_file",
268
+ "description": "Output file containing the detected OGs."
269
+ },
270
+ {
271
+ "opt": "--dir",
272
+ "arg": "in_dir",
273
+ "description": "Directory containing the RBM files.",
274
+ "note": "Required unless --pre-ogs is passed."
275
+ },
276
+ {
277
+ "opt": "--pre-ogs",
278
+ "arg": "in_file",
279
+ "multiple_sep": ",",
280
+ "description": "Pre-computed OGs file(s), separated by commas."
281
+ },
282
+ {
283
+ "opt": "--unchecked",
284
+ "description": "Do not check internal redundancy in OGs."
285
+ },
286
+ {
287
+ "opt": "--format",
288
+ "arg": "string",
289
+ "default": "(\\S+)-(\\S+)\\.rbm",
290
+ "description": ["Format of the filenames for the RBM files (within",
291
+ "-d), using regex syntax."]
292
+ },
293
+ {
294
+ "opt": "--quiet",
295
+ "description": "Run quietly (no STDERR output)."
296
+ }
297
297
  ]
298
298
  },
299
299
  {
@@ -305,34 +305,77 @@
305
305
  "requires": [ { "ruby_gem": "json" } ],
306
306
  "options": [
307
307
  {
308
- "opt": "--ogs",
309
- "arg": "in_file",
310
- "mandatory": true,
311
- "description": "Input file containing the precomputed OGs."
312
- },
313
- {
314
- "opt": "--json",
315
- "arg": "out_file",
316
- "description": "Output file in JSON format."
317
- },
318
- {
319
- "opt": "--tab",
320
- "arg": "out_file",
321
- "description": "Output file in tabular format."
322
- },
323
- {
324
- "opt": "--transposed-tab",
325
- "arg": "out_file",
326
- "description": "Output file in transposed tabular format."
327
- },
328
- {
329
- "opt": "--auto",
330
- "description": "Run completely quiertly (no STDERR or STDOUT)."
331
- },
332
- {
333
- "opt": "--quiet",
334
- "description": "Run quietly (no STDERR output)."
335
- }
308
+ "opt": "--ogs",
309
+ "arg": "in_file",
310
+ "mandatory": true,
311
+ "description": "Input file containing the precomputed OGs."
312
+ },
313
+ {
314
+ "opt": "--json",
315
+ "arg": "out_file",
316
+ "description": "Output file in JSON format."
317
+ },
318
+ {
319
+ "opt": "--tab",
320
+ "arg": "out_file",
321
+ "description": "Output file in tabular format."
322
+ },
323
+ {
324
+ "opt": "--transposed-tab",
325
+ "arg": "out_file",
326
+ "description": "Output file in transposed tabular format."
327
+ },
328
+ {
329
+ "opt": "--auto",
330
+ "description": "Run completely quiertly (no STDERR or STDOUT)."
331
+ },
332
+ {
333
+ "opt": "--quiet",
334
+ "description": "Run quietly (no STDERR output)."
335
+ }
336
+ ]
337
+ },
338
+ {
339
+ "task": "clust.rand.rb",
340
+ "description": ["Calculates the Rand Index and the Adjusted Rand Index",
341
+ "between two clusterings. The clustering format is a raw text file",
342
+ "with one cluster per line, each defined as comma-delimited members,",
343
+ "and a header line (ignored). Note that this is equivalent to the OGs",
344
+ "format for 1 genome."],
345
+ "see_also": ["ogs.mcl.rb"],
346
+ "help_arg": "--help",
347
+ "cite": [
348
+ ["Rand, 1971, J Am Stat Assoc",
349
+ "https://doi.org/10.2307%2F2284239"],
350
+ ["Hubert & Arabie, 1985, J Classif",
351
+ "https://doi.org/10.1007%2FBF01908075"]
352
+ ],
353
+ "options": [
354
+ {
355
+ "name": "Input file 1",
356
+ "opt": "--clust1",
357
+ "arg": "in_file",
358
+ "mandatory": true,
359
+ "description": "First input file."
360
+ },
361
+ {
362
+ "name": "Input file 2",
363
+ "opt": "--clust2",
364
+ "arg": "in_file",
365
+ "mandatory": true,
366
+ "description": "Second input file."
367
+ },
368
+ {
369
+ "name": "Precision",
370
+ "opt": "--prec",
371
+ "arg": "integer",
372
+ "description": "Precision to report.",
373
+ "default": 6
374
+ },
375
+ {
376
+ "opt": "--quiet",
377
+ "description": "Run quietly (no STDERR output)."
378
+ }
336
379
  ]
337
380
  }
338
381
  ]