Mercurial > repos > peterjc > blast_top_hit_species
diff blast_top_hit_species.ga @ 0:68d65aeb3567 draft
Uploaded v0.0.1
author | peterjc |
---|---|
date | Mon, 30 Mar 2015 11:25:10 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/blast_top_hit_species.ga Mon Mar 30 11:25:10 2015 -0400 @@ -0,0 +1,331 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "format-version": "0.1", + "name": "Species of top BLAST hits", + "steps": { + "0": { + "annotation": "", + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "Transcriptome FASTA file" + } + ], + "label": null, + "name": "Input dataset", + "outputs": [], + "position": { + "left": 242, + "top": 119 + }, + "tool_errors": null, + "tool_id": null, + "tool_state": "{\"name\": \"Transcriptome FASTA file\"}", + "tool_version": null, + "type": "data_input", + "user_outputs": [], + "uuid": "e445b44b-02a7-4fd1-8944-cd680f967062" + }, + "1": { + "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.", + "id": 1, + "input_connections": { + "input_file": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Sub-sample sequences files", + "outputs": [ + { + "name": "output_file", + "type": "input" + } + ], + "position": { + "left": 435, + "top": 119 + }, + "post_job_actions": { + "RenameDatasetActionoutput_file": { + "action_arguments": { + "newname": "1000 sequences from #{input_file}" + }, + "action_type": "RenameDatasetAction", + "output_name": "output_file" + } + }, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/peterjc/sample_seqs/sample_seqs/0.2.1", + "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\\\"\"}", + "tool_version": "0.2.1", + "type": "tool", + "user_outputs": [], + "uuid": "87ce69ef-5fb0-41b0-9575-d3b96544f8be" + }, + "2": { + "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\".", + "id": 2, + "input_connections": { + "query": { + "id": 1, + "output_name": "output_file" + } + }, + "inputs": [], + "label": null, + "name": "NCBI BLAST+ blastx", + "outputs": [ + { + "name": "output1", + "type": "tabular" + } + ], + "position": { + "left": 489, + "top": 263 + }, + "post_job_actions": { + "RenameDatasetActionoutput1": { + "action_arguments": { + "newname": "Top BLAST match" + }, + "action_type": "RenameDatasetAction", + "output_name": "output1" + } + }, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/ncbi_blast_plus/ncbi_blastx_wrapper/0.1.01", + "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\\\"\"}", + "tool_version": "0.1.01", + "type": "tool", + "user_outputs": [], + "uuid": "1559a0b0-0b66-40f9-b777-2f062fcda4cc" + }, + "3": { + "annotation": "Having a tabular file of all 1000 sequences is used in the \"join\" step to count the sequences giving no BLAST hit.", + "id": 3, + "input_connections": { + "input": { + "id": 1, + "output_name": "output_file" + } + }, + "inputs": [], + "label": null, + "name": "FASTA-to-Tabular", + "outputs": [ + { + "name": "output", + "type": "tabular" + } + ], + "position": { + "left": 696, + "top": 139 + }, + "post_job_actions": { + "HideDatasetActionoutput": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "output" + }, + "RenameDatasetActionoutput": { + "action_arguments": { + "newname": "1000 sequences as tabular" + }, + "action_type": "RenameDatasetAction", + "output_name": "output" + } + }, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/devteam/fasta_to_tabular/fasta2tab/1.1.0", + "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}", + "tool_version": "1.1.0", + "type": "tool", + "user_outputs": [], + "uuid": "31f11208-b2bd-4d9d-9745-dc1a6ed7ccf9" + }, + "4": { + "annotation": "Some BLAST matches will give multiple HSPs, and thus multiple lines in the tabular output. We only want one line per query.", + "id": 4, + "input_connections": { + "input": { + "id": 2, + "output_name": "output1" + } + }, + "inputs": [], + "label": null, + "name": "Unique", + "outputs": [ + { + "name": "outfile", + "type": "input" + } + ], + "position": { + "left": 665, + "top": 376 + }, + "post_job_actions": { + "HideDatasetActionoutfile": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "outfile" + }, + "RenameDatasetActionoutfile": { + "action_arguments": { + "newname": "One HSP per BLAST hit" + }, + "action_type": "RenameDatasetAction", + "output_name": "outfile" + } + }, + "tool_errors": null, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/unique/bg_uniq/0.3", + "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\\\"\"}", + "tool_version": "0.3", + "type": "tool", + "user_outputs": [], + "uuid": "acf948e3-71dc-4f35-8357-3998bd0abdd8" + }, + "5": { + "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.", + "id": 5, + "input_connections": { + "input1": { + "id": 3, + "output_name": "output" + }, + "input2": { + "id": 4, + "output_name": "outfile" + } + }, + "inputs": [], + "label": null, + "name": "Join two Datasets", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 827, + "top": 263 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + }, + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Top BLAST hits or None" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_errors": null, + "tool_id": "join1", + "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\\\"\"}", + "tool_version": "2.0.2", + "type": "tool", + "user_outputs": [], + "uuid": "4c280b0e-b4a6-4ae4-8a81-d6e93932ef71" + }, + "6": { + "annotation": "Here we make a tally table of the BLAST species name column", + "id": 6, + "input_connections": { + "input": { + "id": 5, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": null, + "name": "Count", + "outputs": [ + { + "name": "out_file1", + "type": "tabular" + } + ], + "position": { + "left": 952, + "top": 398 + }, + "post_job_actions": { + "HideDatasetActionout_file1": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "out_file1" + }, + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Top BLAST hit species counts (unsorted)" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_errors": null, + "tool_id": "Count1", + "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\\\"\"}", + "tool_version": "1.0.0", + "type": "tool", + "user_outputs": [], + "uuid": "d3322137-1911-426d-87a7-c82b5fc16825" + }, + "7": { + "annotation": "Sorting the counts makes the results easier to interpret directly.", + "id": 7, + "input_connections": { + "input": { + "id": 6, + "output_name": "out_file1" + } + }, + "inputs": [], + "label": null, + "name": "Sort", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1056, + "top": 506 + }, + "post_job_actions": { + "RenameDatasetActionout_file1": { + "action_arguments": { + "newname": "Top BLAST hit species counts" + }, + "action_type": "RenameDatasetAction", + "output_name": "out_file1" + } + }, + "tool_errors": null, + "tool_id": "sort1", + "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\\\"\"}", + "tool_version": "1.0.3", + "type": "tool", + "user_outputs": [], + "uuid": "c81cc61d-52a3-44ee-b646-b23e0e004c38" + } + }, + "uuid": "9fe8754a-3a87-4f6a-89a2-141b02b4793e" +} \ No newline at end of file