miga-base 0.3.1.6 → 0.3.1.7
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 +4 -4
- data/actions/ncbi_get.rb +57 -42
- data/lib/miga/result/base.rb +7 -0
- data/lib/miga/result/dates.rb +42 -0
- data/lib/miga/result.rb +4 -0
- data/lib/miga/version.rb +1 -1
- data/scripts/essential_genes.bash +5 -4
- data/utils/enveomics/Makefile +1 -1
- data/utils/enveomics/Manifest/Tasks/aasubs.json +75 -75
- data/utils/enveomics/Manifest/Tasks/blasttab.json +194 -185
- data/utils/enveomics/Manifest/Tasks/distances.json +130 -130
- data/utils/enveomics/Manifest/Tasks/fasta.json +51 -3
- data/utils/enveomics/Manifest/Tasks/fastq.json +161 -126
- data/utils/enveomics/Manifest/Tasks/graphics.json +111 -111
- data/utils/enveomics/Manifest/Tasks/mapping.json +30 -0
- data/utils/enveomics/Manifest/Tasks/ogs.json +308 -265
- data/utils/enveomics/Manifest/Tasks/other.json +451 -449
- data/utils/enveomics/Manifest/Tasks/remote.json +1 -1
- data/utils/enveomics/Manifest/Tasks/sequence-identity.json +18 -10
- data/utils/enveomics/Manifest/Tasks/tables.json +250 -250
- data/utils/enveomics/Manifest/Tasks/trees.json +52 -52
- data/utils/enveomics/Manifest/Tasks/variants.json +4 -4
- data/utils/enveomics/Manifest/categories.json +12 -4
- data/utils/enveomics/Manifest/examples.json +1 -1
- data/utils/enveomics/Scripts/BedGraph.tad.rb +71 -0
- data/utils/enveomics/Scripts/BlastTab.recplot2.R +23 -22
- data/utils/enveomics/Scripts/FastA.split.rb +79 -0
- data/utils/enveomics/Scripts/FastQ.test-error.rb +81 -0
- data/utils/enveomics/Scripts/JPlace.to_iToL.rb +272 -258
- data/utils/enveomics/Scripts/aai.rb +13 -6
- data/utils/enveomics/Scripts/ani.rb +2 -2
- data/utils/enveomics/Scripts/clust.rand.rb +102 -0
- data/utils/enveomics/Scripts/lib/enveomics_rb/enveomics.rb +12 -14
- data/utils/enveomics/Scripts/lib/enveomics_rb/jplace.rb +2 -2
- data/utils/enveomics/Scripts/rbm.rb +23 -14
- data/utils/enveomics/enveomics.R/DESCRIPTION +1 -1
- data/utils/enveomics/enveomics.R/R/barplot.R +2 -2
- metadata +9 -2
@@ -7,116 +7,116 @@
|
|
7
7
|
"help_arg": "-h",
|
8
8
|
"options": [
|
9
9
|
{
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
10
|
+
"name": "Reverse list",
|
11
|
+
"opt": "-r",
|
12
|
+
"description": "Extracts sequences NOT present in the list."
|
13
|
+
},
|
14
|
+
{
|
15
|
+
"name": "Quiet",
|
16
|
+
"opt": "-q",
|
17
|
+
"description": "Runs quietly."
|
18
|
+
},
|
19
|
+
{
|
20
|
+
"name": "List",
|
21
|
+
"arg": "in_file",
|
22
|
+
"mandatory": true,
|
23
|
+
"description": "List of sequences to extract."
|
24
|
+
},
|
25
|
+
{
|
26
|
+
"name": "Seqs.fq",
|
27
|
+
"arg": "in_file",
|
28
|
+
"mandatory": true,
|
29
|
+
"description": "FastQ file containing the superset of sequences."
|
30
|
+
},
|
31
|
+
">",
|
32
|
+
{
|
33
|
+
"name": "Subset.fq",
|
34
|
+
"arg": "out_file",
|
35
|
+
"mandatory": true,
|
36
|
+
"description": "FastQ file to be created."
|
37
|
+
}
|
38
38
|
]
|
39
39
|
},
|
40
40
|
{
|
41
41
|
"task": "FastQ.interpose.pl",
|
42
42
|
"description": ["Interposes sequences in FastQ format from two files",
|
43
43
|
"into one output file. If more than two files are provided, the script",
|
44
|
-
|
44
|
+
"will interpose all the input files."],
|
45
45
|
"warn": ["Note that this script will check for the consistency of the",
|
46
46
|
"names (assuming a pair of related reads contains the same name",
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
47
|
+
"varying only in a trailing slash (/) followed by a digit. If you want",
|
48
|
+
"to turn this feature off just set the -T option to zero. If you want",
|
49
|
+
"to decrease the sampling period (to speed the script up) or increase",
|
50
|
+
"it (to make it more sensitive to errors) just change -T option",
|
51
|
+
"accordingly."],
|
52
52
|
"see_also": ["FastQ.split.pl","FastA.interpose.pl"],
|
53
53
|
"help_arg": "",
|
54
54
|
"options": [
|
55
55
|
{
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
56
|
+
"name": "Checking period",
|
57
|
+
"opt": "-T",
|
58
|
+
"arg": "integer",
|
59
|
+
"default": 1000,
|
60
|
+
"description": "Sampling period for names evaluation."
|
61
|
+
},
|
62
|
+
{
|
63
|
+
"arg": "out_file",
|
64
|
+
"mandatory": true,
|
65
|
+
"description": "Output FastQ file."
|
66
|
+
},
|
67
|
+
{
|
68
|
+
"arg": "in_file",
|
69
|
+
"mandatory": true,
|
70
|
+
"description": "First input FastQ file."
|
71
|
+
},
|
72
|
+
{
|
73
|
+
"arg": "in_file",
|
74
|
+
"mandatory": true,
|
75
|
+
"description": "Second input FastQ file."
|
76
|
+
},
|
77
|
+
{
|
78
|
+
"arg": "in_file",
|
79
|
+
"multiple_sep": " ",
|
80
|
+
"description": "Any additional input FastQ files."
|
81
|
+
}
|
82
82
|
]
|
83
83
|
},
|
84
84
|
{
|
85
85
|
"task": "FastQ.offset.pl",
|
86
86
|
"description": ["There are several FastQ formats. This script takes a",
|
87
87
|
"FastQ in any of them, identifies the type of FastQ (this is, the",
|
88
|
-
|
88
|
+
"offset), and generates a FastQ with the given offset."],
|
89
89
|
"warn": ["Note that Solexa+64 FastQ can cause problematic values when",
|
90
90
|
"using the offset 33, since there is no equivalent in Phred+33 for",
|
91
|
-
|
91
|
+
"negative values (the range of Solexa+64 is -5 to 40)."],
|
92
92
|
"help_arg": "",
|
93
93
|
"options": [
|
94
94
|
{
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
95
|
+
"arg": "in_file",
|
96
|
+
"mandatory": true,
|
97
|
+
"description": ["Input file in FastQ format (range is automatically",
|
98
|
+
"detected)."]
|
99
|
+
},
|
100
|
+
{
|
101
|
+
"name": "Offset",
|
102
|
+
"arg": "integer",
|
103
|
+
"default": 33,
|
104
|
+
"mandatory": true,
|
105
|
+
"description": ["Offset to use for the output. Use 0 (zero) to",
|
106
|
+
"detect the input format and exit."]
|
107
|
+
},
|
108
|
+
{
|
109
|
+
"opt": "force",
|
110
|
+
"description": ["If set, turns errors into warnings and continues.",
|
111
|
+
"Out-of-range values are set to the closest range limit."]
|
112
|
+
},
|
113
|
+
">",
|
114
|
+
{
|
115
|
+
"arg": "out_file",
|
116
|
+
"mandatory": true,
|
117
|
+
"description": ["Output file in FastQ format with the specified",
|
118
|
+
"offset."]
|
119
|
+
}
|
120
120
|
]
|
121
121
|
},
|
122
122
|
{
|
@@ -156,33 +156,33 @@
|
|
156
156
|
"help_arg": "--help",
|
157
157
|
"options": [
|
158
158
|
{
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
180
|
-
|
181
|
-
|
182
|
-
|
183
|
-
|
184
|
-
|
185
|
-
|
159
|
+
"name": "Input file",
|
160
|
+
"opt": "--in",
|
161
|
+
"arg": "in_file",
|
162
|
+
"mandatory": true,
|
163
|
+
"description": "FastQ file containing the sequences."
|
164
|
+
},
|
165
|
+
{
|
166
|
+
"name": "Output file",
|
167
|
+
"opt": "--out",
|
168
|
+
"arg": "out_file",
|
169
|
+
"mandatory": true,
|
170
|
+
"description": "FastQ to create."
|
171
|
+
},
|
172
|
+
{
|
173
|
+
"opt": "--prefix",
|
174
|
+
"arg": "string",
|
175
|
+
"description": "Prefix to use in all IDs."
|
176
|
+
},
|
177
|
+
{
|
178
|
+
"opt": "--suffix",
|
179
|
+
"arg": "string",
|
180
|
+
"description": "Suffix to use in all IDs."
|
181
|
+
},
|
182
|
+
{
|
183
|
+
"opt": "--quiet",
|
184
|
+
"description": "Run quietly (no STDERR output)."
|
185
|
+
}
|
186
186
|
]
|
187
187
|
},
|
188
188
|
{
|
@@ -190,18 +190,53 @@
|
|
190
190
|
"description": "Translates FastQ files into FastA.",
|
191
191
|
"help_arg": "'' --help",
|
192
192
|
"options": [
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
|
198
|
-
|
199
|
-
|
200
|
-
|
201
|
-
|
202
|
-
|
203
|
-
|
204
|
-
|
193
|
+
"<",
|
194
|
+
{
|
195
|
+
"arg": "in_file",
|
196
|
+
"mandatory": true,
|
197
|
+
"description": "Input FastQ file."
|
198
|
+
},
|
199
|
+
">",
|
200
|
+
{
|
201
|
+
"arg": "out_file",
|
202
|
+
"mandatory": true,
|
203
|
+
"description": "Output FastA file."
|
204
|
+
}
|
205
|
+
]
|
206
|
+
},
|
207
|
+
{
|
208
|
+
"task": "FastQ.test-error.rb",
|
209
|
+
"description": ["Compares the estimated error of sequencing reads",
|
210
|
+
"(Q-score) with observed mismatches (identity against a know",
|
211
|
+
"reference sequence)."],
|
212
|
+
"help_arg": "--help",
|
213
|
+
"options": [
|
214
|
+
{
|
215
|
+
"name": "FastQ",
|
216
|
+
"opt": "--fastq",
|
217
|
+
"arg": "in_file",
|
218
|
+
"mandatory": true,
|
219
|
+
"description": "FastQ file containing the sequences."
|
220
|
+
},
|
221
|
+
{
|
222
|
+
"name": "Tabular BLAST",
|
223
|
+
"opt": "--blast",
|
224
|
+
"arg": "in_file",
|
225
|
+
"mandatory": true,
|
226
|
+
"description": ["Tabular BLAST file mapping reads to reference",
|
227
|
+
"sequences."]
|
228
|
+
},
|
229
|
+
{
|
230
|
+
"name": "Output",
|
231
|
+
"opt": "--out",
|
232
|
+
"arg": "out_file",
|
233
|
+
"mandatory": true,
|
234
|
+
"description": "Output tab-delimited file to create."
|
235
|
+
},
|
236
|
+
{
|
237
|
+
"opt": "--quiet",
|
238
|
+
"description": "Run quietly (no STDERR output)."
|
239
|
+
}
|
205
240
|
]
|
206
241
|
}
|
207
242
|
]
|
@@ -7,119 +7,119 @@
|
|
7
7
|
"help_arg": "--help",
|
8
8
|
"options": [
|
9
9
|
{
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
10
|
+
"name": "Input file",
|
11
|
+
"opt": "--x",
|
12
|
+
"arg": "in_file",
|
13
|
+
"mandatory": true,
|
14
|
+
"description": ["A tab-delimited file containing header (first row)",
|
15
|
+
"and row names (first column)."]
|
16
|
+
},
|
17
|
+
{
|
18
|
+
"opt": "--sizes",
|
19
|
+
"arg": "string",
|
20
|
+
"description": ["A numeric vector containing the real size of the",
|
21
|
+
"samples (columns) in the same order of the input table. If set,",
|
22
|
+
"the values are assumed to be 100%, otherwise the sum of the",
|
23
|
+
"columns is used. Separate values by commas."]
|
24
|
+
},
|
25
|
+
{
|
26
|
+
"opt": "--top",
|
27
|
+
"arg": "integer",
|
28
|
+
"default": 25,
|
29
|
+
"description": ["Maximum number of categories to display. Any",
|
30
|
+
"additional categories will be listed as 'Others'."]
|
31
|
+
},
|
32
|
+
{
|
33
|
+
"opt": "--colors-per-group",
|
34
|
+
"arg": "integer",
|
35
|
+
"default": 9,
|
36
|
+
"description": ["Number of categories in the first two saturation",
|
37
|
+
"groups of colors. The third group contains the remaining",
|
38
|
+
"categories if needed."]
|
39
|
+
},
|
40
|
+
{
|
41
|
+
"opt": "--bars-width",
|
42
|
+
"arg": "integer",
|
43
|
+
"default": 4,
|
44
|
+
"description": "Width of the barplot with respect to the legend."
|
45
|
+
},
|
46
|
+
{
|
47
|
+
"opt": "--legend-ncol",
|
48
|
+
"arg": "integer",
|
49
|
+
"default": 1,
|
50
|
+
"description": "Number of columns in the legend."
|
51
|
+
},
|
52
|
+
{
|
53
|
+
"opt": "--other-col",
|
54
|
+
"arg": "string",
|
55
|
+
"default": "#000000",
|
56
|
+
"description": "Color of the 'Others' category."
|
57
|
+
},
|
58
|
+
{
|
59
|
+
"opt": "--add-trend",
|
60
|
+
"description": ["Controls if semi-transparent areas are to be",
|
61
|
+
"plotted between the bars to connect the regions (trend regions)."]
|
62
|
+
},
|
63
|
+
{
|
64
|
+
"opt": "--organic-trend",
|
65
|
+
"description": ["Controls if the trend regions are to be smoothed",
|
66
|
+
"(curves). By default, trend regions have straight edges. If TRUE,",
|
67
|
+
"forces add.trend=TRUE."]
|
68
|
+
},
|
69
|
+
{
|
70
|
+
"opt": "--sort-by",
|
71
|
+
"arg": "string",
|
72
|
+
"default": "median",
|
73
|
+
"description": ["Any function that takes a numeric vector and",
|
74
|
+
"returns a numeric scalar. This function is applied to each row,",
|
75
|
+
"and the resulting values are used to sort the rows",
|
76
|
+
"(decreasingly). Good options include: sd, min, max, mean, median."]
|
77
|
+
},
|
78
|
+
{
|
79
|
+
"opt": "--min-report",
|
80
|
+
"arg": "integer",
|
81
|
+
"default": 101,
|
82
|
+
"description": ["Minimum percentage to report the value in the plot.",
|
83
|
+
"Any value above 100 indicates that no values are to be reported."]
|
84
|
+
},
|
85
|
+
{
|
86
|
+
"opt": "--order",
|
87
|
+
"arg": "string",
|
88
|
+
"description": ["Controls how the rows should be ordered. If empty",
|
89
|
+
"(default), sort.by is applied per row and the results are sorted",
|
90
|
+
"decreasingly. If NA, no sorting is performed, i.e., the original",
|
91
|
+
"order is respected. If a vector is provided, it is assumed to be",
|
92
|
+
"the custom order to be used (either by numeric index or by row",
|
93
|
+
"names). Separate values by commas."]
|
94
|
+
},
|
95
|
+
{
|
96
|
+
"opt": "--col",
|
97
|
+
"arg": "string",
|
98
|
+
"description": ["Colors to use. If provided, overrides the variables",
|
99
|
+
"`top` and `colors.per.group`, but `other.col` is still used if",
|
100
|
+
"the vector is insufficient for all the rows. Separate values by",
|
101
101
|
"commas. An additional palette is available when using value",
|
102
102
|
"'coto' (palette contributed by Luis (Coto) Orellana)."]
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
|
122
|
-
|
103
|
+
},
|
104
|
+
{
|
105
|
+
"arg": "out_file",
|
106
|
+
"mandatory": true,
|
107
|
+
"description": "Output file in PDF format."
|
108
|
+
},
|
109
|
+
{
|
110
|
+
"name": "width",
|
111
|
+
"arg": "float",
|
112
|
+
"mandatory": true,
|
113
|
+
"default": 7,
|
114
|
+
"description": "Width of the plot (in inches)."
|
115
|
+
},
|
116
|
+
{
|
117
|
+
"name": "height",
|
118
|
+
"arg": "float",
|
119
|
+
"mandatory": true,
|
120
|
+
"default": 7,
|
121
|
+
"description": "Height of the plot (in inches)."
|
122
|
+
}
|
123
123
|
]
|
124
124
|
}
|
125
125
|
]
|
@@ -0,0 +1,30 @@
|
|
1
|
+
{
|
2
|
+
"tasks": [
|
3
|
+
{
|
4
|
+
"task": "BedGraph.tad.rb",
|
5
|
+
"description": ["Estimates the truncated average sequencing depth (TAD)",
|
6
|
+
"from a BedGraph file."],
|
7
|
+
"warn": ["This script doesn't consider zero-coverage positions if",
|
8
|
+
"missing from the file. If you produce your BedGraph file with",
|
9
|
+
"bedtools genomecov and want to consider zero-coverage position, be",
|
10
|
+
"sure to use -bga (not -bg)."],
|
11
|
+
"see_also": ["BlastTab.seqdepth.pl", "BlastTab.seqdepth_ZIP.pl"],
|
12
|
+
"help_arg": "--help",
|
13
|
+
"options": [
|
14
|
+
{
|
15
|
+
"opt": "--input",
|
16
|
+
"arg": "in_file",
|
17
|
+
"mandatory": true,
|
18
|
+
"description": "Input BedGraph file."
|
19
|
+
},
|
20
|
+
{
|
21
|
+
"opt": "--range",
|
22
|
+
"arg": "float",
|
23
|
+
"default": 0.5,
|
24
|
+
"description": ["Central range to consider, between 0 and 1. By",
|
25
|
+
"default: inter-quartile range (0.5)."]
|
26
|
+
}
|
27
|
+
]
|
28
|
+
}
|
29
|
+
]
|
30
|
+
}
|