Mercurial > repos > peterjc > blast_top_hit_species

comparison blast_top_hit_species.ga @ 0:68d65aeb3567 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded v0.0.1
author peterjc
date Mon, 30 Mar 2015 11:25:10 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:68d65aeb3567
1 {
2 "a_galaxy_workflow": "true",
3 "annotation": "",
4 "format-version": "0.1",
5 "name": "Species of top BLAST hits",
6 "steps": {
7 "0": {
8 "annotation": "",
9 "id": 0,
10 "input_connections": {},
11 "inputs": [
12 {
13 "description": "",
14 "name": "Transcriptome FASTA file"
15 }
16 ],
17 "label": null,
18 "name": "Input dataset",
19 "outputs": [],
20 "position": {
21 "left": 242,
22 "top": 119
23 },
24 "tool_errors": null,
25 "tool_id": null,
26 "tool_state": "{\"name\": \"Transcriptome FASTA file\"}",
27 "tool_version": null,
28 "type": "data_input",
29 "user_outputs": [],
30 "uuid": "e445b44b-02a7-4fd1-8944-cd680f967062"
31 },
32 "1": {
33 "annotation": "This workflow is deliberately a simple/crude assessment, and there is no need to run BLASTX on all the sequences - a sample of 1000 should be enough.",
34 "id": 1,
35 "input_connections": {
36 "input_file": {
37 "id": 0,
38 "output_name": "output"
39 }
40 },
41 "inputs": [],
42 "label": null,
43 "name": "Sub-sample sequences files",
44 "outputs": [
45 {
46 "name": "output_file",
47 "type": "input"
48 }
49 ],
50 "position": {
51 "left": 435,
52 "top": 119
53 },
54 "post_job_actions": {
55 "RenameDatasetActionoutput_file": {
56 "action_arguments": {
57 "newname": "1000 sequences from #{input_file}"
58 },
59 "action_type": "RenameDatasetAction",
60 "output_name": "output_file"
61 }
62 },
63 "tool_errors": null,
64 "tool_id": "toolshed.g2.bx.psu.edu/repos/peterjc/sample_seqs/sample_seqs/0.2.1",
65 "tool_state": "{\"__page__\": 0, \"input_file\": \"null\", \"__rerun_remap_job_id__\": null, \"sampling\": \"{\\\"count\\\": \\\"1000\\\", \\\"type\\\": \\\"desired_count\\\", \\\"__current_case__\\\": 2}\", \"chromInfo\": \"\\\"/mnt/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"interleaved\": \"\\\"False\\\"\"}",
66 "tool_version": "0.2.1",
67 "type": "tool",
68 "user_outputs": [],
69 "uuid": "87ce69ef-5fb0-41b0-9575-d3b96544f8be"
70 },
71 "2": {
72 "annotation": "We only want one line per query, so limit this to the best scoring target sequence. Assumes current NCBI nr database is available locally as \"nr\".",
73 "id": 2,
74 "input_connections": {
75 "query": {
76 "id": 1,
77 "output_name": "output_file"
78 }
79 },
80 "inputs": [],
81 "label": null,
82 "name": "NCBI BLAST+ blastx",
83 "outputs": [
84 {
85 "name": "output1",
86 "type": "tabular"
87 }
88 ],
89 "position": {
90 "left": 489,
91 "top": 263
92 },
93 "post_job_actions": {
94 "RenameDatasetActionoutput1": {
95 "action_arguments": {
96 "newname": "Top BLAST match"
97 },
98 "action_type": "RenameDatasetAction",
99 "output_name": "output1"
100 }
101 },
102 "tool_errors": null,
103 "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastx_wrapper/0.1.01",
104 "tool_state": "{\"evalue_cutoff\": \"\\\"0.001\\\"\", \"__page__\": 0, \"adv_opts\": \"{\\\"adv_optional_id_files_opts\\\": {\\\"adv_optional_id_files_opts_selector\\\": \\\"none\\\", \\\"__current_case__\\\": 0}, \\\"matrix\\\": \\\"BLOSUM62\\\", \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"ungapped\\\": \\\"False\\\", \\\"filter_query\\\": \\\"True\\\", \\\"word_size\\\": \\\"0\\\", \\\"__current_case__\\\": 1, \\\"parse_deflines\\\": \\\"False\\\", \\\"strand\\\": \\\"-strand both\\\", \\\"max_hits\\\": \\\"1\\\"}\", \"__rerun_remap_job_id__\": null, \"db_opts\": \"{\\\"db_opts_selector\\\": \\\"db\\\", \\\"subject\\\": \\\"\\\", \\\"histdb\\\": \\\"\\\", \\\"__current_case__\\\": 0, \\\"database\\\": \\\"nr\\\"}\", \"query_gencode\": \"\\\"1\\\"\", \"query\": \"null\", \"output\": \"{\\\"out_format\\\": \\\"cols\\\", \\\"std_cols\\\": [\\\"qseqid\\\", \\\"sseqid\\\", \\\"pident\\\", \\\"length\\\", \\\"mismatch\\\", \\\"gapopen\\\", \\\"qstart\\\", \\\"qend\\\", \\\"sstart\\\", \\\"send\\\", \\\"evalue\\\", \\\"bitscore\\\"], \\\"ids_cols\\\": null, \\\"tax_cols\\\": [\\\"staxids\\\", \\\"sscinames\\\", \\\"scomnames\\\", \\\"sblastnames\\\", \\\"sskingdoms\\\"], \\\"__current_case__\\\": 2, \\\"misc_cols\\\": null, \\\"ext_cols\\\": null}\", \"chromInfo\": \"\\\"/mnt/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}",
105 "tool_version": "0.1.01",
106 "type": "tool",
107 "user_outputs": [],
108 "uuid": "1559a0b0-0b66-40f9-b777-2f062fcda4cc"
109 },
110 "3": {
111 "annotation": "Having a tabular file of all 1000 sequences is used in the \"join\" step to count the sequences giving no BLAST hit.",
112 "id": 3,
113 "input_connections": {
114 "input": {
115 "id": 1,
116 "output_name": "output_file"
117 }
118 },
119 "inputs": [],
120 "label": null,
121 "name": "FASTA-to-Tabular",
122 "outputs": [
123 {
124 "name": "output",
125 "type": "tabular"
126 }
127 ],
128 "position": {
129 "left": 696,
130 "top": 139
131 },
132 "post_job_actions": {
133 "HideDatasetActionoutput": {
134 "action_arguments": {},
135 "action_type": "HideDatasetAction",
136 "output_name": "output"
137 },
138 "RenameDatasetActionoutput": {
139 "action_arguments": {
140 "newname": "1000 sequences as tabular"
141 },
142 "action_type": "RenameDatasetAction",
143 "output_name": "output"
144 }
145 },
146 "tool_errors": null,
147 "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/fasta_to_tabular/fasta2tab/1.1.0",
148 "tool_state": "{\"__page__\": 0, \"keep_first\": \"\\\"0\\\"\", \"descr_columns\": \"\\\"2\\\"\", \"input\": \"null\", \"chromInfo\": \"\\\"/mnt/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"__rerun_remap_job_id__\": null}",
149 "tool_version": "1.1.0",
150 "type": "tool",
151 "user_outputs": [],
152 "uuid": "31f11208-b2bd-4d9d-9745-dc1a6ed7ccf9"
153 },
154 "4": {
155 "annotation": "Some BLAST matches will give multiple HSPs, and thus multiple lines in the tabular output. We only want one line per query.",
156 "id": 4,
157 "input_connections": {
158 "input": {
159 "id": 2,
160 "output_name": "output1"
161 }
162 },
163 "inputs": [],
164 "label": null,
165 "name": "Unique",
166 "outputs": [
167 {
168 "name": "outfile",
169 "type": "input"
170 }
171 ],
172 "position": {
173 "left": 665,
174 "top": 376
175 },
176 "post_job_actions": {
177 "HideDatasetActionoutfile": {
178 "action_arguments": {},
179 "action_type": "HideDatasetAction",
180 "output_name": "outfile"
181 },
182 "RenameDatasetActionoutfile": {
183 "action_arguments": {
184 "newname": "One HSP per BLAST hit"
185 },
186 "action_type": "RenameDatasetAction",
187 "output_name": "outfile"
188 }
189 },
190 "tool_errors": null,
191 "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/unique/bg_uniq/0.3",
192 "tool_state": "{\"__page__\": 0, \"ignore_case\": \"\\\"False\\\"\", \"adv_opts\": \"{\\\"column_end\\\": {\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"2\\\"}, \\\"column_start\\\": {\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"1\\\"}, \\\"adv_opts_selector\\\": \\\"advanced\\\", \\\"__current_case__\\\": 1}\", \"__rerun_remap_job_id__\": null, \"is_numeric\": \"\\\"False\\\"\", \"input\": \"null\", \"chromInfo\": \"\\\"/mnt/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}",
193 "tool_version": "0.3",
194 "type": "tool",
195 "user_outputs": [],
196 "uuid": "acf948e3-71dc-4f35-8357-3998bd0abdd8"
197 },
198 "5": {
199 "annotation": "We don't need all the columns in this join, but the key is to assign \"None\" to the sequences with no BLAST hits.",
200 "id": 5,
201 "input_connections": {
202 "input1": {
203 "id": 3,
204 "output_name": "output"
205 },
206 "input2": {
207 "id": 4,
208 "output_name": "outfile"
209 }
210 },
211 "inputs": [],
212 "label": null,
213 "name": "Join two Datasets",
214 "outputs": [
215 {
216 "name": "out_file1",
217 "type": "input"
218 }
219 ],
220 "position": {
221 "left": 827,
222 "top": 263
223 },
224 "post_job_actions": {
225 "HideDatasetActionout_file1": {
226 "action_arguments": {},
227 "action_type": "HideDatasetAction",
228 "output_name": "out_file1"
229 },
230 "RenameDatasetActionout_file1": {
231 "action_arguments": {
232 "newname": "Top BLAST hits or None"
233 },
234 "action_type": "RenameDatasetAction",
235 "output_name": "out_file1"
236 }
237 },
238 "tool_errors": null,
239 "tool_id": "join1",
240 "tool_state": "{\"input2\": \"null\", \"__page__\": 0, \"field1\": \"{\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"1\\\"}\", \"partial\": \"\\\"\\\"\", \"field2\": \"{\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"1\\\"}\", \"__rerun_remap_job_id__\": null, \"fill_empty_columns\": \"{\\\"fill_empty_columns_switch\\\": \\\"fill_empty\\\", \\\"do_fill_empty_columns\\\": {\\\"column_fill_type\\\": \\\"single_fill_value\\\", \\\"fill_value\\\": \\\"None\\\", \\\"__current_case__\\\": 0}, \\\"fill_columns_by\\\": \\\"fill_unjoined_only\\\", \\\"__current_case__\\\": 1}\", \"unmatched\": \"\\\"-u\\\"\", \"input1\": \"null\", \"chromInfo\": \"\\\"/mnt/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}",
241 "tool_version": "2.0.2",
242 "type": "tool",
243 "user_outputs": [],
244 "uuid": "4c280b0e-b4a6-4ae4-8a81-d6e93932ef71"
245 },
246 "6": {
247 "annotation": "Here we make a tally table of the BLAST species name column",
248 "id": 6,
249 "input_connections": {
250 "input": {
251 "id": 5,
252 "output_name": "out_file1"
253 }
254 },
255 "inputs": [],
256 "label": null,
257 "name": "Count",
258 "outputs": [
259 {
260 "name": "out_file1",
261 "type": "tabular"
262 }
263 ],
264 "position": {
265 "left": 952,
266 "top": 398
267 },
268 "post_job_actions": {
269 "HideDatasetActionout_file1": {
270 "action_arguments": {},
271 "action_type": "HideDatasetAction",
272 "output_name": "out_file1"
273 },
274 "RenameDatasetActionout_file1": {
275 "action_arguments": {
276 "newname": "Top BLAST hit species counts (unsorted)"
277 },
278 "action_type": "RenameDatasetAction",
279 "output_name": "out_file1"
280 }
281 },
282 "tool_errors": null,
283 "tool_id": "Count1",
284 "tool_state": "{\"__page__\": 0, \"column\": \"{\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": [\\\"19\\\"]}\", \"__rerun_remap_job_id__\": null, \"delim\": \"\\\"T\\\"\", \"input\": \"null\", \"chromInfo\": \"\\\"/mnt/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\"}",
285 "tool_version": "1.0.0",
286 "type": "tool",
287 "user_outputs": [],
288 "uuid": "d3322137-1911-426d-87a7-c82b5fc16825"
289 },
290 "7": {
291 "annotation": "Sorting the counts makes the results easier to interpret directly.",
292 "id": 7,
293 "input_connections": {
294 "input": {
295 "id": 6,
296 "output_name": "out_file1"
297 }
298 },
299 "inputs": [],
300 "label": null,
301 "name": "Sort",
302 "outputs": [
303 {
304 "name": "out_file1",
305 "type": "input"
306 }
307 ],
308 "position": {
309 "left": 1056,
310 "top": 506
311 },
312 "post_job_actions": {
313 "RenameDatasetActionout_file1": {
314 "action_arguments": {
315 "newname": "Top BLAST hit species counts"
316 },
317 "action_type": "RenameDatasetAction",
318 "output_name": "out_file1"
319 }
320 },
321 "tool_errors": null,
322 "tool_id": "sort1",
323 "tool_state": "{\"__page__\": 0, \"style\": \"\\\"num\\\"\", \"column\": \"{\\\"__class__\\\": \\\"UnvalidatedValue\\\", \\\"value\\\": \\\"1\\\"}\", \"__rerun_remap_job_id__\": null, \"column_set\": \"[]\", \"input\": \"null\", \"chromInfo\": \"\\\"/mnt/galaxy/galaxy-dist/tool-data/shared/ucsc/chrom/?.len\\\"\", \"order\": \"\\\"DESC\\\"\"}",
324 "tool_version": "1.0.3",
325 "type": "tool",
326 "user_outputs": [],
327 "uuid": "c81cc61d-52a3-44ee-b646-b23e0e004c38"
328 }
329 },
330 "uuid": "9fe8754a-3a87-4f6a-89a2-141b02b4793e"
331 }